{"id":2794,"date":"2019-12-18T19:15:47","date_gmt":"2019-12-18T13:45:47","guid":{"rendered":"http:\/\/navveenbalani.dev\/?p=2794"},"modified":"2019-12-18T19:31:24","modified_gmt":"2019-12-18T14:01:24","slug":"internet-of-things-application-of-iot-in-manufacturing","status":"publish","type":"post","link":"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/","title":{"rendered":"Internet of Things &#8211; Application of IoT in Manufacturing"},"content":{"rendered":"\n<p>This article is part of IoT Architecture Series &#8211; <a href=\"https:\/\/navveenbalani.dev\/index.php\/articles\/internet-of-things-architecture-components-and-stack-view\/\">https:\/\/navveenbalani.dev\/index.php\/articles\/internet-of-things-architecture-components-and-stack-view\/<\/a><\/p>\n\n\n\n<p>Large manufacturers have been using some automation and smart technology to streamline and optimize their processes and improve their operation and production efficiency. However, as manufacturers start moving towards the next industrial revolution (Industry 4.0 or Industrial Internet of Things(IIoT)) and technologies available today that can analyze massive volume, variety, and velocity of data generated by various machines and sensors, there arises an opportunity to streamline this information to further improve the manufacturing process and most importantly start designing and developing connected products that can enhance customer satisfaction and services and open up avenues for new financial business models.<\/p>\n\n\n\n<p><em>Note\n\u2013 The term Industry 4.0 and Industrial Internet of Things are usually used interchangeably, but they have\ndifferent context and reference. Industry 4.0 is a term coined by the German government,\nit marks the fourth&nbsp;<\/em><a href=\"https:\/\/en.wikipedia.org\/wiki\/Industrial_revolution\"><em>industrial\nrevolution<\/em><\/a><em> and can be described as the digitalization of industrial\nsector, especially for manufacturing. Industrial Internet of Things is about\nenabling and applying IoT across industries. Also check out Industrial Internet\nConsortium (<\/em><a href=\"http:\/\/www.industrialinternetconsortium.org\/\">http:\/\/www.industrialinternetconsortium.org\/<\/a><em>) a non-profit\norganization, founded by AT&amp;T, Cisco, GE, IBM and Intel&nbsp;to collaborate\nand set the architectural framework and direction for the Industrial Internet\nof Things <\/em><\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p>Let\u2019s take an example of a leading elevator\nmanufacturing company which supplies elevators across the globe. The elevators\nalready have some instrumentation built in, like door sensor, a weight sensor\nwhich triggers an alert like beep in case of overload,\netc., but the elevator company has no\nvisibility on how the elevators are being used across the globe and therefore,\nraises the following important questions:<\/p>\n\n\n\n<p>Are these elevators working as expected and\nutilized as per the specification? <\/p>\n\n\n\n<p>Is there a failure condition?<\/p>\n\n\n\n<p>What kind of failure has occurred?<\/p>\n\n\n\n<p>How are failures to be handled?<\/p>\n\n\n\n<p>What is the typical\nacceptable downtime?<\/p>\n\n\n\n<p>Which agency is handling the failure\ncondition?<\/p>\n\n\n\n<p>How effective is the after-sales service in\nthat region? <\/p>\n\n\n\n<p>Is there a competent expertise available to\nhandle a given failure condition?<\/p>\n\n\n\n<p>Are the spare parts available to quickly\nstart the restoration process?<\/p>\n\n\n\n<p>Proper application of IoT can address the\nabove questions by designing a connected solution that will help capture and\nanalyze the product usage, operational and failure data and ultimately improve\nthe customer satisfaction and services.<\/p>\n\n\n\n<p>IoT can not only transform the end products\nbut the entire manufacturing process right from the start where the elevators are manufactured. The supply chain process and\nlogistics can also be streamlined to enhance operational efficiency and\nproductivity and deliver better financial gains.<\/p>\n\n\n\n<p>IoT is an incremental journey; it\u2019s an\nevolution, and any manufacturing IoT realization can be broken down into\nthe following five phases:<\/p>\n\n\n\n<ul><li>Monitoring &amp; Utilization <\/li><li>Condition based maintenance<\/li><li>Predictive Maintenance <\/li><li>Optimization<\/li><li>Connecting \u2018connected solutions.&#8217;<\/li><\/ul>\n\n\n\n<p><\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" width=\"1024\" height=\"360\" src=\"https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/iot-manufactirung-1024x360.jpg\" alt=\"\" class=\"wp-image-2797\" srcset=\"https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/iot-manufactirung-1024x360.jpg 1024w, https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/iot-manufactirung-300x105.jpg 300w, https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/iot-manufactirung-768x270.jpg 768w, https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/iot-manufactirung.jpg 1752w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<h3><a>Monitoring &amp; Utilization<\/a><\/h3>\n\n\n\n<p>Monitoring and utilization are the first\nsteps of an IoT journey. This is an\numbrella phase which itself consists of\nmany requirements.&nbsp; <\/p>\n\n\n\n<p>For the large scale manufacturer, to enable\nseamless monitoring and utilization of their systems, the step usually\ncomprises of:<\/p>\n\n\n\n<ol><li>Asset Management<\/li><li>Identifying assets that need to\nbe monitored<\/li><\/ol>\n\n\n\n<ul><li>Instrumentation<\/li><li>Leveraging existing\ninstrumentation investments (if any)<\/li><li>Adding\nnew hardware capability (new sensors\/actuators\/microcontrollers) based on the\ndesign and requirements of the connected solution.<\/li><\/ul>\n\n\n\n<ul><li>Handle Connectivity<\/li><li>Adding connectivity to devices\nas per above points (1) and (2). We would talk about various patterns, the device\ndirectly connected to the core platform; intercommunication between devices or\na device gateway connected to the core platform which communicates with\nexisting devices using a low level or existing proprietary protocols.<\/li><\/ul>\n\n\n\n<ul><li>Perform Monitoring<\/li><\/ul>\n\n\n\n<h4><a>Asset Management<\/a><\/h4>\n\n\n\n<p>To start with you need to identify the set\nof physical assets that needs to be monitored.\nFor example, for an elevator manufacturing company an elevator is an asset,\nwhich contains various sub-assets like doors, input control buttons (open,\nclose, call, alarm, etc.), elevator telephone, etc. Similarly, for a connected car\nmanufacturer, the car is an asset that contains various sub-assets like engine,\nbrakes, tires, etc. and for any\nmanufacturing plant, machinery equipment, conveyor systems, etc. are examples of assets that needs to be monitored. An asset contains a set of\nmetadata, for example, a car engine can have a manufacturer&#8217;s name, capacity,\nyear of manufacturing, etc. Asset\nmanagement is perceived through asset\nmetadata and its dependencies with other assets. Manufacturers typically have a\nsoftware platform or an application to manage the lifecycle of its assets.\nWhile moving towards implementing IoT, the existing asset management design or\napplication may not be sufficient or good enough for building next generation\nconnected solution. Right from requirements, design to simulation, creating\nconnected products and its lifecycle management, will require a completely new\napproach and a set of next generation software products to realize a connected\nsolution.&nbsp; We envision a set of new\nemerging software products to tackle requirements for designing connected\nsolution. For instance, understanding a dependency between a car engine, engine\noil, led indicators and brakes through the system\u2019s metadata and making use of\nanalytics platform to perform analysis on the actual sensor data in a connected\ncar solution, could help derive correlations easily and suggest measures to\ntackle failure condition. The design of connected products is a separate topic\nin itself and outside the scope of this book.<\/p>\n\n\n\n<h4><a>Instrumentation<\/a><\/h4>\n\n\n\n<p>In the manufacturing world, some kind of instrumentation is already employed,\nlike the use case of the elevator, which we talked about earlier. The elevators\nalready have built-in sensors, but these sensors are not connected to any platform, (the platform here maps to core\nplatform in our architecture diagram &#8211; Refer Chapter 1) so as to enable\ntransfer and analysis of the data. Moreover,\nthe protocol and connectivity (maps to communication layer in our architecture\ndiagram&#8211; Refer Chapter 1) for the various hardware components (or devices) in\nthe elevator and their interactions would be very proprietary in nature. <\/p>\n\n\n\n<p>Based on the requirements of the connected\nproduct, new hardware components (devices, microcontroller, sensors, etc.) might also be required.&nbsp; For instance, in a connected elevator design,\nthe elevators now have new requirements to maintain an optimum temperature for\nsmooth functioning, taking into account surrounding external factors (external\nfactors may vary in different regions). Now the new design could also break\ndown an operating ambient temperature into multiple levels of degradations,\nmonitor this remotely or via notification and use this information to schedule\nservices. For instance, take the following example where X is the optimum\ntemperature that needs to be maintained\nand if X is greater than Threshold value, the degradations process starts.\nLastly, if no action is taken from the start of degradation beyond Y days, a critical\nfailure alert message is sent to the elevator company.<\/p>\n\n\n\n<p>X being optimum temperature, <\/p>\n\n\n\n<p>X &gt; Threshold Value -&gt; Needs\nattention within 5 days. The elevator is\nstill functional but with limited load.\nThe load is cut down from 300 kg to 150 kg.<\/p>\n\n\n\n<p>At this stage, details about the suggestive\nspare part changes, the location of the\nspare part, suggested service vendor nearest to the current location is also made available by the system. It\u2019s easier\nfor the system to detect the GPS\ncoordinates of the connected system, look at the inventory and service vendors\nbased on the region and scheduled\nmaintenance services. At this stage, the elevator\nis operational but with reduced load and have controlled the movement of people using the elevator. <\/p>\n\n\n\n<p>X &gt; Threshold Value (Date) \u2013 Y Days\n\u2013&gt; Critical Failure alert. This is\nfinal alert to repair the defective part, along with a good time to repair the\nelevator based on people movement during that week and projections to ensure\nminimum downtime and least impact on passengers. The above is only one\nsuch example. A manufacturer could employ many such requirements, which would\nrequire design changes right from microcontrollers to adding new hardware\ncomponents. Again, this is an incremental effort;\none can take gradual steps by identifying and adding new hardware\ncomponent and then connecting along the way to the core platform for data\ntransmission. The data is then used to correlate and perform analysis at the core platform layer to understand failure\nconditions and patterns. <\/p>\n\n\n\n<h4><a>Handle Connectivity<\/a><\/h4>\n\n\n\n<p>There are three\ngeneral connectivity patterns, which allow\ndevices to communicate to the core platform<\/p>\n\n\n\n<ul><li>Connecting device directly to\ncore platform<\/li><li>Connecting devices to an\nintelligent system and\/or device gateway.<\/li><li>Intercommunication with devices.<\/li><\/ul>\n\n\n\n<p>Based on the use cases, the connectivity\noption would differ. If there is a requirement to process the data locally and\ntake action and\/or a requirement to map\ndifferent proprietary protocols to a standardized protocol, a device gateway is\ngenerally used which will translate the\nincoming protocol instructions to that of the target platform. The requirement\nalso depends on the power consumption capacity of the device, and it may not make sense for all devices to connect directly to the core platform.<\/p>\n\n\n\n<p>For the elevator manufacturing use case,\nthe devices (doors, motor temperature, shaft alignment,\netc.) is already instrumented and connected to a central device (microcontroller).\nThe central device can be IoT-enabled, or\na new device gateway can be installed which\ntalks to the central device. It can be done\nby installing the required platform libraries and code that connect to the core platform, understands and\nmap the data from the controller into a\npayload object (like JSON) and submits the payload to the core platform.&nbsp; <\/p>\n\n\n\n<p>Libraries are available which supports\nmaking a device IoT-enabled, like the Eclipse-based Paho\nlibrary (http:\/\/www.eclipse.org\/paho\/) which is an open-source client\nimplementation of MQTT that can be installed\non devices supporting C, Java, Android, Python, C++, JavaScript and NET programming model. This is of course with the assumption that the\ncore platform supports the MQTT protocol.<\/p>\n\n\n\n<p>The choice of library depends on the device being IoT-enabled,\nthe programming language supported by the device (C, C++, JavaScript, etc.),\nthe protocols supported by the core platform (MQTT, AMQP, REST, etc.) and the client library available\nfor the device. One can also use REST style invocations to connect to the core platform. Core platform can provide SDKs\nfor various devices that provide APIs to\nconvert the device data into required payload supported by the core platform.\nFor example, open source projects like Connect-The-Dots\n(https:\/\/github.com\/Azure\/connectthedots) allow devices to connect to Microsoft\nIoT services.<\/p>\n\n\n\n<p>Not all data from the IoT-enabled device need to be transferred to the core platform. The IoT-enabled device gateway can employ local\nstorage to filter out the data (like start and stop activity on each floor in case of elevators) and\ntransfer only relevant data to the platform. We don\u2019t want to clog the network\nand the platform with data that is not relevant and at the same time make sure\nenough data is transmitted from the systems to analyze important indicators,\noperational activities of various sensors, identify failures and use the\nhistorical events and data for future prediction of machines. Identifying and\nunderstanding the critical aspect of the data and prioritizing the same should be\na key decision factor for building IoT applications.<\/p>\n\n\n\n<p>Edge gateways can also be used which is\ngeographically located closer to the devices or the device gateways,\nwhich can normalize the data before moving it to the core platform. For\ninstance, to a global connected car manufacturer, it would make sense to have\nedge gateways at respective locations which can then streamline data movement\nto the core platform. We would see a lot\nof such patterns evolving in future that would enable scalability and connectivity\nof billion of devices.<\/p>\n\n\n\n<p>As new production ready devices are manufactured for IoT, we envision the\nrequired firmware and connectivity code would be part of the device design and\nshipped with some standardized protocol support. In an ideal world, we should\nhave converged on one standardized protocol for IoT (like the AllJoyn protocol\nwhich is gaining momentum) to make connectivity seamless, but in reality, many\nsuch standardized protocols would exist, and there would be an integration\napproach required to make them work seamlessly. <\/p>\n\n\n\n<p>Another example is of water and waste water\nmanufacturing plant which uses SCADA network to gather, monitor and process\ndata. The manufacturing plant already employs sensors and proprietary protocols\nthat monitor temperature, relative humidity, pH, barometric pressure, and\nvarious other environmental parameters. To be\nagile and scalable, traditional manufacturing systems need to adopt\ntechnologies to store and aggregate volumes of data from sensors, monitor\nsystems in real-time, analyze the data and give out insights which were not\npossible earlier and eventually create predictive models to predict equipment\nfailure or a possible outcome. <\/p>\n\n\n\n<p>This is especially true for manufacturing companies, which might have\nalready employed a wide variety of protocols. The ideal approach or pattern\nwould be to install an intelligent system of gateways to convert these\nprotocols and make them communicate securely with the core platform.\nManufacturers can incrementally move their legacy devices into the realm of IoT\necosystem by connecting them to the outside world through intelligent gateways.\nFor instance, BACnet is the widely used protocol for smart building and\nproducts like Microsoft AllJoyn Device System Bridge, allows existing devices\nthat use BACnet to connect to an AllJoyn\nnetwork, thereby enabling existing devices to connect with IoT core platform\nand also with new AllJoyn devices. <\/p>\n\n\n\n<p>In future, we would see the connected\nproduct design being a key requirement as part of the manufacturing process.<\/p>\n\n\n\n<h4><a>Perform Monitoring<\/a><\/h4>\n\n\n\n<p>Once the devices are connected and data\nfrom the devices is made available to the core platform, the monitoring part kicks in. The device data is usually stored in a database (possibly a\ntime series database) for further analysis and predictions and at the same time\ncan be acted upon by the system for real-time analysis. The monitoring phase\ntypically involves providing a dashboard to track the devices remotely across\nthe globe and how each device is being utilized\nas per the specification. The specifications are available as part of the metadata\nwe talked about it earlier in Asset Management section. <\/p>\n\n\n\n<p>For instance, in the case of the r elevator use case, the optimum\nmotor temperature should not be more than\n40 degree Celsius or the air condition temperature inside the elevator should\nbe at least 18 degree Celsius at peak load.<\/p>\n\n\n\n<p>Monitoring can also be used to detect if the elevators are installed and functioning as per the specification. For instance, every manufacturer provides a checklist for regular maintenance activity that can be tracked through remote monitoring. The following is a sample checklist, which is provided by the City of Chicago \u2013 Department of Buildings for compliance purpose. As you see, most of the test requirements can be handled by adding sensors and monitoring it remotely.<\/p>\n\n\n\n<figure class=\"wp-block-image is-resized\"><img loading=\"lazy\" src=\"https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/image-74.png\" alt=\"\" class=\"wp-image-2798\" width=\"500\" height=\"400\"\/><\/figure>\n\n\n\n<p>In the future, environmental requirements\nlike energy efficiency, passenger safety,\nand control compliance can be met through the remote monitoring and used for\nauditing and inspection eventually.<\/p>\n\n\n\n<p>As the manufacturers start embracing IoT\nwith the concept of connected products in mind, we would see a new class of\nproducts in future that will change the complete dynamics of manufacturing\nprocess. Imagine a self-test on the elevator which automatically evaluates the\ncompliance parameters and publishes a report as part of the audit and quality\nprocedures in a connected environment. (In short, an elevator would be\ncompliant and secured 24 * 7).<\/p>\n\n\n\n<p>Once the systems and devices are being monitored, next step is to use the\ninformation to provide timely maintenance of the assets based on the\nspecification and its operating condition. We refer to it as condition-based maintenance.<\/p>\n\n\n\n<h3><a>Condition based maintenance<\/a><\/h3>\n\n\n\n<p>Condition-based Maintenance (CBM) is about using the actual data gathered from the\ndevices to decide what maintenance activity needs to be performed on the physical assets being\nmonitored.<\/p>\n\n\n\n<p>The connected device provides a set of\ncontinuous measurements (temperature, vibrations, air pressure, heat, etc.) for the physical asset. This data\nalong with the required operating specification of the physical assets can be\nused to create rules for maintenance activities and taking corrective action. <\/p>\n\n\n\n<p>For the elevator use case, we talked about\noperating temperature requirement earlier as part of the instrumentation\ndesign. With the device data being available, the maintenance service can be\nscheduled whenever the degradation of asset starts.<\/p>\n\n\n\n<p>For example,&nbsp; <\/p>\n\n\n\n<p>X being optimum temperature, <\/p>\n\n\n\n<p>X &gt; Threshold Value \u2013&gt; Alert the\nservice professional. The service professional can inspect the elevator\nremotely and approve the spare part suggested by the system. The elevators can\ncontinue to be functional under limited load,\nand the load sensor rule now triggers at 150 kg instead of 300 kg. This ensures at any given point; the load does not increase beyond the expected value in case of\ndegradation. <\/p>\n\n\n\n<p>Take another example of a scheduled\nmaintenance service for your automobile. The service schedule is usually specified as part of the\nmanufacturer&#8217;s operation manual based on the average operating condition rather\nthan the actual usage and condition of the automobile. Using condition-based\nmaintenance, the service and maintenance activity, like the oil change in your\nvehicle should be triggered when the service and replacement is needed based on actual, rather than a\npredetermined schedule. <\/p>\n\n\n\n<p>There are two approaches to arrive at condition-based\nmaintenance: <\/p>\n\n\n\n<p>The first approach is by creating predetermined rules based on the actual value provided by the devices and\nexecuting the required action. For example, if the optimum temperature of an elevator is &gt; 40 and load &gt; 150 kg,\nexecute load alert\/beep rule and start the elevator only when the load falls below 150 kg.<\/p>\n\n\n\n<p>The rule can be a simple rule or a\ncombination of rules. The rules can be visually modeled\nusing a programming language or a tool supported by the core platform. The\nrules are created using the parameters or fields of the device payload. In the\nabove example, optimum temperature, elevator load are the fields defined as\npart of the payload.<\/p>\n\n\n\n<p>The second approach is monitoring the\nvalues and detecting an anomaly. The\nanomaly detection is about identifying the data and events, which do not conform to the expected pattern as\ncompared to other items in the data set. For\nexample, assume you haven\u2019t defined any rules for optimum temperature\nfunctionality and data from the devices is being collected every second, say\n15, 15, 17, 18 and on the third day you see this pattern 29,.30, 30, 29&#8230;,\nclearly the values read on the first day are less than half of the values read\non the third day. This signifies\nan anomaly in the system, which can trigger an alert for someone to inspect the\nsystem. Another example would be in the case\nof fire, where this might be detected as\nan anomaly by the system indicating the dramatic rise in the temperature. There\ncould be another case where fire sensors itself could be tracking fire events.\nThese two cases could be combined to derive a correlation and thereby enabling\nyou to make a more precise observation.<\/p>\n\n\n\n<p>All anomalies might not necessarily be real\nproblems, but detecting anomaly should be a key requirement to ensure any susceptive exceptions are being caught by the\nsystem. <\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p><em>Tip &#8211;\nAnomalies can be detected using unsupervised machine learning algorithms like\nK-means. Libraries such as Spark MLlib provide first class support for many\nmachine learning algorithms. <\/em><\/p>\n\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<p>In future, we\ncould see pre-built templates available for industry verticals which provide\nthe domain model, rules, process flows, machine learning models, anomaly detectors\nand the job of the system integrator would be to map the device data into the\ndomain model, extend the data model and customize the flow based on the client\nrequirements. <\/p>\n\n\n\n<p>There may be hundreds or thousands of such\nrules in a complex manufacturing system,\nand it becomes very imperative to capture such requirements as part of your\nconnected design. The connected design phase is yet to catch on, and most of the noise is around IoT\nplatforms and implementations. The futuristic software products will provide end-to-end\nIoT implementations from a connected design perspective and also provide large-scale\nsimulations to simulate the design and the end product.<\/p>\n\n\n\n<h3><a>Predictive Maintenance<\/a><\/h3>\n\n\n\n<p>Predictive maintenance is the ability of\nthe system to predict a machine failure. Predictive maintenance phase comprises\nof 2 parts &#8211; one is the ability to predict when the machine\/asset failure would\nhappen and secondly to perform maintenance activity before the malfunction\nhappens. Predictive maintenance is one of the most widely discussed topics in\nthe IoT ecosystem.<\/p>\n\n\n\n<p>The first two phases of the manufacturing\nIoT involved monitoring and condition-based maintenance. These phases can\nprovide us with enough historical data, learnings,\nthe correlation between the data, type of\nfailures and corrective action taken and\nenabled to predict possible failures and what actions needs to be performed on the concerned asset.<\/p>\n\n\n\n<p>In many places, you would read that\npredictive maintenance is same or a part of condition-based maintenance. We\nchose to call it out separately as the scope and implementations are quite\ndifferent. Both deals with ensuring the maintenance are carried out before\nfailure. The condition based maintenance primarily use monitoring, rules, and\nanomaly detection techniques; while predictive maintenance takes a step further\nto analyze volumes of historical or trend data, correlations, and machine\nspecifications to predict an outcome. Predicting an outcome is very complex and\nan ongoing task, which requires being handled\nseparately. <\/p>\n\n\n\n<p>A simple use case is using the information\nof the assets and its lifecycle and actual &#8216;wear and tear&#8217; data of the parts\nprovided through the connected devices; one\ncan possibly predict the remaining life\ncycle of an asset and when should the maintenance be required.&nbsp; Imagine a dashboard, which lists the assets\nand its metadata, like manufacturing date, installed date, type, etc. along with its actual usage and maintenance\nactivity carried out during condition based maintenance phase. It also depicts\nexternal factors and predictions on remaining life cycle of the asset and a\nmaintenance date. These factors can be used to plan a minimum maintenance downtime,\nschedule spare parts delivery and ensure maintenance is executed with least impact. <\/p>\n\n\n\n<p>Secondly, every manufacturer typically has historical maintenance records of\nthe systems and usage data in some form, which needs to be converted into\nrequired format and can be a valuable input to predict the maintenance\nactivity. <\/p>\n\n\n\n<p>Going back to the elevator use case, take\nthe example of the elevator lift cables. Can a system predict when the elevator\nlift cables need to be changed?\nManufacturing innovations are happening in elevator cables, like using super\nlight carbon fiber ropes that increase\nthe lifespan of the cables, but still changing the lift cables is a costly\nmaintenance activity and at the same time its failure can have a considerable downtime.\nEnsuring availability of new lift cables, specialized technicians availability,\ncompliance check and all these factors can impact the business operations\nconsiderably. <\/p>\n\n\n\n<p>In order to carry out any predictive maintenance for elevator lift cables, the\nmanufacturer needs to look at what data points would be required to predict the\nfailure. As part of its Connect product\ndesign, the manufacturer had probably installed a sensor to track the running\ntime or distance served by the cable, a sensor to detect if the elevator is\ndescending faster than its designated speed and to monitor the start and stop\ninstances of the elevator. Sensor input together with the cable\u2019s specified\nlife expectancy can be used to predict when the lift cables need to be replaced. In an actual scenario, many more such data sets need to be provided to\npredict outcomes.<\/p>\n\n\n\n<p>Predictive maintenance involves building\nout machine learning models based on volumes of data. Developing machine\nlearning models require considerable time and effort. It\u2019s virtually impossible\nto expect a system to devise a predictive model which is always 100% accurate\n(not even human operate with that level of accuracy:)),\nbut should be considerable enough to suggest a cause of possible failure with\nreasonable accuracy. <\/p>\n\n\n\n<p>Open source scalable machine learning\nmodels like Spark MLlib or commercial offerings like SPSS from IBM or Azure ML\nfor Microsoft can aid in building predictive models. The real challenge is\nbuilding feature sets (attributes) and using algorithms like Support Vector\nMachines, Logistic Regression, and Decision Trees or an ensemble model using\nmultiple machine learning algorithms to\npredict an outcome.<\/p>\n\n\n\n<p>The model once developed can be integrated\ninto your IoT platform (as part of the Analytics Platform layer \u2013refer Chapter\n1) to predict outcomes in real-time. We would talk about this in detail in our\nnext chapter as part of the services offered by various IoT platforms.<\/p>\n\n\n\n<p>In future, we should see specialized\npre-shipped predictive maintenance services targeted for various\nindustries\/verticals like connected car, elevator maintenance, wind turbines, etc. These services would provide a\ngeneralized machine learning model developed using various factors we talked\nabout earlier. System Integrators would play a key role in building the new machine\nlearning model or use existing machine learning models and integrate with the\nIoT platform. For instance, take an example of a\nconnected car, using the OBD device (actual diagnostic data at runtime) + GPS\nlocation, along with asset metadata (like type and make of car, manufacturing\ndate of various parts and its specifications), a generalized machine learning model\ncan be developed which can help predict maintenance activities and failures for\nany car type. This assumes that you\nshould be able to look up the metadata for the car and its specifications, for instance,\nthe AUDI car type, model, maintenance service requirements would be different\nas compared to BMW or an AUDI of a different model. The generalized data\nmodel (a connected car would have different input\/output parameters as compared\nto a connected elevator) used by the machine learning model would also be a key\ncomponent in helping to build predictive\nmodels effectively. <\/p>\n\n\n\n<p>Many manufacturers are taking a step in this direction but building predictive\nmodels with a good amount of accuracy is\nnot an easy task and this space would see a lot\nof competition, partnership and innovations from manufacturers to software\nplatform provider to system integrators. <\/p>\n\n\n\n<h3><a>Optimization<\/a><\/h3>\n\n\n\n<p>Optimization phase is all about identifying\nnew insights based on the existing data that can further help refine the\nmanufacturing process. A large volume of\ndata generated by the devices, together with events generated by the system and\nvarious insights from predictive and condition based maintenance opens up the\ndoor for identifying and realizing new requirements, which further enriches\nconnected solution design to derive\nbetter outcomes. <\/p>\n\n\n\n<p>Optimization can happen during every phase\nviz- monitoring, condition, and predictive-based maintenance. We called this out\nas a separate phase as this is an important activity to track on how applying IoT\noptimizes the current process and the connected products. For instance, using the\noutcome of predictive maintenance, one can understand failure patterns better\nand look at corrective ways to schedule services across the globe and order\nspare parts effectively and in turn optimize the supply chain process.<\/p>\n\n\n\n<p>Going back to the elevator use case, if the\nelevator is fully occupied and it stops\nat multiple floors due to passengers wanting to enter, only to find that there\nis no room to enter. This can annoy\npassengers who are inside and outside of the elevator. These kinds of pattern (which are not failure conditions) can be detected\nas part of monitoring phase and therefore it can be optimized by creating a\nrule not to stop at floors when load is full other than the floors selected by\nthe passengers inside the elevator and notifying passengers waiting for the elevator\nwith the appropriate status. To inspect\nthe user has already taken another elevator, sensors can be applied to\ntrack the movement and presence of persons on each floor and share the status at runtime, which is picked up by the\nincoming elevator and not to stop at the corresponding floor.<\/p>\n\n\n\n<p>Take another example of various 100 storey buildings (in future tall skyscrapers would be quite common), how would a\nsystem optimize elevators to ensure maximum passenger satisfaction and least\nwaiting time for passengers taking the elevators, fewer stops per trip and an\norganized traffic flow to prevent crowding of passengers. These are the cases\nwhere optimization and innovation can play an important part, and that would mean looking at the elevator IoT solution\nholistically and not just relying only on data provided by the elevators. It\nwould mean determining connected dots like passenger movements, crowd density\nat each floor, or even devising smarter\nalgorithms to utilize the data available and suggest optimized steps\/routes to\nthe elevator system. <\/p>\n\n\n\n<p>As we move into the future of a connected\nworld, we would see various such use cases which primarily focuses on customer\nsatisfaction and employing new innovations\nto solve existing problem using the connected information.<\/p>\n\n\n\n<h3><a>Connecting \u2018connected solutions<\/a>&#8216;<\/h3>\n\n\n\n<p>In a connected world, the real innovation\nwould happen on how the data from one connected\nsystem would be used by other connected systems and come up with new\nbusiness models that we haven\u2019t thought of so far.<\/p>\n\n\n\n<p>For example, let&#8217;s assume the elevator\nmanufacturing company relies on a third-party vendor for their logistics and\nshipment of machinery and spare parts. Getting real-time visibility into the\nmoving parts across the globe along with\nthe external factors could help plan the contingency better. For instance, if\nit takes X amount of additional time to get spare parts from Y location as\ncompared to Z location, but due to real-time weather insight integrated system,\nreporting extreme weather conditions at Y location for next three days, it\u2019s better to order spare parts\nfrom Z location to reach on time. The distance from Z location can be further\noptimized based on real-time notifications from traffic systems that can\nprovide an alternate route to the manufacturing plant. Here insights from the\nlogistics aggregation company are offered as the value added services to\nmanufacturing systems. <\/p>\n\n\n\n<p>Take another example of passengers waiting\nfor an elevator, what is the best way to keep the passengers engaged and\nsatisfied and not grumble about the delay. A\ncustomer after checking-in to the smart connected hotel and waiting for the\nelevator for few minutes and later having too many stops to reach at his 90th\nfloor, in one way can be engaged by providing complimentary vouchers for the\ndelay on his Smartphone (through beacons and hotel smart apps on mobile) or\nthrough his hotel room card (which is digitized and provide various\ninformation) or a call as soon as he reaches his room. In that way, the\ncustomer would get the sense of being instantly connected and feel that the\nhotel acknowledged the delay and cared about it.<\/p>\n\n\n\n<p>Take another\nexample of how data from the connected car solution can be used to derive real\nvalues like, traffic management, public safety, fleet management, after sales\nservice and industries like insurance that would tap into the data and devise\n&#8216;pay per use&#8217; model based on actual usage of the car and based on driving\/behaviour\npattern of the driver. The insurance underwriting\nprocess would be changed to take into account these various connected\nparameters to quote the insurance premium. Insurance companies might also\nprovide various value added services like tying up with service vendors for\nafter sales services or providing just in time insurance for a second person\ndriving the car. Privacy and security can pose a challenge, but they can be effectively handled through service level\nagreements between car broker\/owner and insurance companies. <\/p>\n\n\n\n<p>The current generation does not hesitate to\nshare information on social media. Sometimes sharing information can be tricky\nbut often times you would want to do that\nto improve your experience with the connected world as every smart business\nthen will be able to provide personalized service based on your personal\npreference or characteristic. It will bring out positive outcomes and benefit\nat large and will be appreciated by the\nsame people thereby creating a framework of\nconnected people and business. <\/p>\n\n\n\n<p>In the next article, we will talk about a couple of use cases. We call this as start-up use cases, where start-ups and small organizations are tapping into IoT to create new innovative products from scratch. We would cover two such use cases \u2013 <a href=\"https:\/\/navveenbalani.dev\/index.php\/articles\/internet-of-things-connected-car-use-case\/\">connected car<\/a> and <a href=\"https:\/\/navveenbalani.dev\/index.php\/articles\/internet-of-things-connected-home-application\/\">connected home<\/a>. <\/p>\n","protected":false},"excerpt":{"rendered":"<p>This article is part of IoT Architecture Series &#8211; https:\/\/navveenbalani.dev\/index.php\/articles\/internet-of-things-architecture-components-and-stack-view\/ Large manufacturers have been using some automation and smart technology to streamline and optimize their processes and improve their operation and production efficiency. However, as manufacturers start moving towards the next industrial revolution (Industry 4.0 or Industrial Internet of Things(IIoT)) and technologies available today that [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2797,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[180,3,156],"tags":[287],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v16.0.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Internet of Things - Application of IoT in Manufacturing - Current and Future Technology Trends by Navveen Balani<\/title>\n<meta name=\"description\" content=\"Internet of Things - Application of IoT in Manufacturing - Applications\" \/>\n<link rel=\"canonical\" href=\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Internet of Things - Application of IoT in Manufacturing - Current and Future Technology Trends by Navveen Balani\" \/>\n<meta property=\"og:description\" content=\"Internet of Things - Application of IoT in Manufacturing - Applications\" \/>\n<meta property=\"og:url\" content=\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/\" \/>\n<meta property=\"og:site_name\" content=\"Current and Future Technology Trends by Navveen Balani\" \/>\n<meta property=\"article:published_time\" content=\"2019-12-18T13:45:47+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2019-12-18T14:01:24+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/iot-manufactirung.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1752\" \/>\n\t<meta property=\"og:image:height\" content=\"616\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\">\n\t<meta name=\"twitter:data1\" content=\"27 minutes\">\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebSite\",\"@id\":\"https:\/\/navveenbalani.dev\/#website\",\"url\":\"https:\/\/navveenbalani.dev\/\",\"name\":\"Current and Future Technology Trends by Navveen Balani\",\"description\":\"Current and Future Technology Trends by Navveen Balani\",\"publisher\":{\"@id\":\"https:\/\/navveenbalani.dev\/#\/schema\/person\/51f7ab14b20611d95e3c7fd4ea0950bf\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":\"https:\/\/navveenbalani.dev\/?s={search_term_string}\",\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#primaryimage\",\"inLanguage\":\"en-US\",\"url\":\"https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/12\/iot-manufactirung.jpg\",\"width\":1752,\"height\":616},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#webpage\",\"url\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/\",\"name\":\"Internet of Things - Application of IoT in Manufacturing - Current and Future Technology Trends by Navveen Balani\",\"isPartOf\":{\"@id\":\"https:\/\/navveenbalani.dev\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#primaryimage\"},\"datePublished\":\"2019-12-18T13:45:47+00:00\",\"dateModified\":\"2019-12-18T14:01:24+00:00\",\"description\":\"Internet of Things - Application of IoT in Manufacturing - Applications\",\"breadcrumb\":{\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"item\":{\"@type\":\"WebPage\",\"@id\":\"https:\/\/navveenbalani.dev\/\",\"url\":\"https:\/\/navveenbalani.dev\/\",\"name\":\"Home\"}},{\"@type\":\"ListItem\",\"position\":2,\"item\":{\"@type\":\"WebPage\",\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/\",\"url\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/\",\"name\":\"Internet of Things &#8211; Application of IoT in Manufacturing\"}}]},{\"@type\":\"Article\",\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#webpage\"},\"author\":{\"@id\":\"https:\/\/navveenbalani.dev\/#\/schema\/person\/51f7ab14b20611d95e3c7fd4ea0950bf\"},\"headline\":\"Internet of Things &#8211; Application of IoT in Manufacturing\",\"datePublished\":\"2019-12-18T13:45:47+00:00\",\"dateModified\":\"2019-12-18T14:01:24+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#webpage\"},\"publisher\":{\"@id\":\"https:\/\/navveenbalani.dev\/#\/schema\/person\/51f7ab14b20611d95e3c7fd4ea0950bf\"},\"image\":{\"@id\":\"https:\/\/navveenbalani.dev\/index.php\/applications\/internet-of-things-application-of-iot-in-manufacturing\/#primaryimage\"},\"keywords\":\"iot-guide\",\"articleSection\":\"Applications,Articles,IOT\",\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\/\/navveenbalani.dev\/#\/schema\/person\/51f7ab14b20611d95e3c7fd4ea0950bf\",\"name\":\"Navveen\",\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/navveenbalani.dev\/#personlogo\",\"inLanguage\":\"en-US\",\"url\":\"https:\/\/navveenbalani.dev\/wp-content\/uploads\/2019\/07\/navveen_balani.jpeg\",\"width\":200,\"height\":200,\"caption\":\"Navveen\"},\"logo\":{\"@id\":\"https:\/\/navveenbalani.dev\/#personlogo\"},\"sameAs\":[\"http:\/\/naveenbalani.com\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","_links":{"self":[{"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/posts\/2794"}],"collection":[{"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/comments?post=2794"}],"version-history":[{"count":5,"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/posts\/2794\/revisions"}],"predecessor-version":[{"id":2816,"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/posts\/2794\/revisions\/2816"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/media\/2797"}],"wp:attachment":[{"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/media?parent=2794"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/categories?post=2794"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/navveenbalani.dev\/index.php\/wp-json\/wp\/v2\/tags?post=2794"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}