Summary:<\/em><\/strong>\u00a0 Digital Twins is a concept based in IoT but requiring the skills of machine learning and potentially AI.\u00a0 It\u2019s not completely new but it is integral to Gartner\u2019s vision of the digital enterprise and makes the Hype Cycle for 2017.\u00a0 It\u2019s a major enabler of event processing as opposed to traditional request processing.<\/em><\/p>\n \u00a0 If the concept of Digital Twins is new to you, you need to be looking way over to the left on Gartner\u2019s 2017 Hype Cycles of Emerging Technologies.\u00a0 There between Quantum Computing and Serverless PaaS you\u2019ll find Digital Twins with a time to acceptance of 5 to 10 years, or more specifically that by 2021, one-half of companies will be using Digital Twins.\u00a0 In fact Digital Twins is one of Gartner\u2019s Top Ten Strategic Technology Trends for 2017.<\/p>\n \u00a0 In many respects this is old wine in new bottles.\u00a0 One of those exercises in renaming an existing practice to draw attention, much like separating out prescriptive analytics from predictive analytics<\/u><\/em><\/a> a few years back.\u00a0 I also think Gartner is way off on their time line, but first things first with some definitions.<\/p>\n A digital twin is intended to be a digital replica of physical assets, processes, or systems, in other words, a model. It is most often referenced as an outcome of IoT (internet of things) where the exponentially expanding world of devices with sensors provides us with an equally fast expanding body of data about those devices that can be analyzed and assessed for efficiency, design, maintenance, and many other factors.<\/p>\n Since the data continues to flow, the model can be continuously updated and \u2018learn\u2019 in near real time any change that may occur.<\/p>\n While the definition mentions the ability to model or digitally twin processes and systems, the folks who have most enthusiastically embraced DT are the IIoT community (Industrial Internet of Things) with their focus on large, complex, and capital intensive machines.<\/p>\n \u00a0<\/p>\n A Little History<\/strong><\/span><\/p>\n Michael Grieves at the University of Michigan is credited with first formulating the terminology of digital twins in 2002. \u00a0However, as many of you will immediately observe, data scientists and engineers were buiding computer models of complex machines and even manufacturing processes well before this date.\u00a0 NASA particularly is credited with pioneering this field in the 80s as a way of managing and monitoring spacecraft with which they had no physical connection.<\/p>\n Nor was it only NASA with its large teams of engineers that labored at these problems.\u00a0 Large and complex industrial processes were equipped with SCADA systems that were the precursors of IoT.\u00a0 There was and continues to be great demand for adaptive real time control for these machines and processes.\u00a0 But before MPP and NoSQL we were challenged by both available algorithms and compute power.<\/p>\n To illustrate how far back this goes, I studied a project completed in 2000 to model and subsequently optimize the operation of a very large scale nuclear waste incinerator run by the government in South Carolina.\u00a0 The project was a collaboration between a data scientist friend, Frank Francone and engineers at SAIC.\u00a0 The problem had failed to yield to any number of algorithms including neural nets but was finally solved using Francone\u2019s proprietary genetic algorith achieving an R^2 of .96 but required over 600 CPU hours to compute.\u00a0 Things are easier now.<\/p>\n What was far sighted in 2002 was that Grieves was foretelling the volume of applications that would be possible once stream processing of NoSQL data became possible and morphed into the rapid growth of IoT.<\/p>\n \u00a0<\/p>\n Economic Importance<\/strong><\/span><\/p>\n Modeling to predict preventive mainenance or to optimize output of complex machines or industrial processes may not be new but the news of its economic importance is catching everyone\u2019s attention.<\/p>\n GE is a leader in IIoT and the use of that data to improve performance.\u00a0 Their goal for the digital twin they have created for their wind farms is to generate 20% increases in efficiency.\u00a0 This includes real time maintenance and configuration changes during operation but also extends to new product design, configuration, and the construction of new wind farms.<\/p>\n Passenger jets and Formula 1 racers are just two other examples of complex mechanical systems that have extremely large numbers of sensors gathering and transmitting data in real time to their digital twins where increased performance, efficiency, safety, and reduced unscheduled maintenance are the goal.<\/p>\n IDC forecasts that by this year, 2018, companies investing in digital twins will see improvements of 30% in cycle times of critical processes.<\/p>\n \u00a0<\/p>\n Machine Learning and AI in Digital Twins<\/strong><\/span><\/p>\n The fact is that digital twins can produce value without machine learning and AI if the system is simple.\u00a0 If for example there are limited variables and an easily discoverable linear relation between inputs and outputs then no data science may be required.<\/p>\n However, the vast majority of target systems have multiple variables and multiple streams of data and do require the talents of data science to make sense of what\u2019s going on.<\/p>\n Unfortunately the popular press tends to equate all this with AI.\u00a0 Actually the great majority of the benefit of modeling can be achieved with traditional machine learning algorithms.\u00a0 Let me be clear that I am using \u2018machine learning\u2019 in the traditional sense<\/u><\/em><\/a> of any computer enabled algorithm applied to a body of data to discover a pattern.<\/p>\n It is possible though to see that the AI represented by deep learning, specifically image and video processing and text and speech processing (with CNNs and RNNs respectively) can also be incorporated as input into models alongside traditional numerical sensor readings.\u00a0<\/p>\n For example, video feeds of components during manufacture can already be used to detect defective items and reject them.\u00a0 Similarly audio inputs of large generators can carry signals of impending malfunctions like vibration even before traditional sensors can detect the problem.<\/p>\n \u00a0<\/p>\n Mind the Cost<\/strong><\/span><\/p>\n If you already operate with IoT, especially those connected to industrial machines and processes you are probably in the sweet spot for Digital Twins.\u00a0 However, mind the cost.\u00a0 Any predictive model is potentially subject to drift over time and needs to be maintained.\u00a0 IoT sensors for example are notoriously noisey and as you upgrade sensors or even the mathematical techniques you use to isolate signal from noise your models will undoubtedly need to be updated.\u00a0<\/p>\n The business message here is simple.\u00a0 Be sure to do your cost benefit analysis before launching into DTs, where cost is the incremental cost of the data science staff needed to maintain these models.<\/p>\n \u00a0<\/p>\n What About Business Processes<\/strong><\/span><\/p>\n Although the definition of digital twins often includes specific referenece to \u2018processes\u2019, examples of processes modeled with digital twins other than mechanical factory processes are difficult to find.\u00a0 Since not many of us have complex or capital intensive machinery and industrial processes, what is the role of digital twins in ordinary business processes like order-to-cash, or order-to-inventory-to-fullfillment, or even from first-sales-contact-to-completed-order.<\/p>\n Where you have to look for these types of examples is outside of the digital twin literature, in business process automation (BPA) or business process management (BPM).\u00a0 Although certainly valuable, both these overlapping fields have been slow to find opportunities to incorporate machine learning or AI.\u00a0 But the time may be close if it\u2019s not here already.<\/p>\n Not all the data that streams is IoT.\u00a0 Technically IoT is about data streamed from sensors but there are plenty of other types of data that stream that do not originate from sensors, for example data captured in web logs such as ecommerce applications.<\/p>\n There are not many current examples but one is the case of Rocket Mortgage.\u00a0 The mortgage originator seeks to interface with the borrower exclusively on-line.\u00a0 The efficiency of each step from initial application through funding is closely monitored for both cycle time (efficiency) and accuracy.\u00a0 There are BPA applications available today that can automatically detect the beginning and end points of each step in the transaction from web logs thus providing the same sort of data stream for mortgage origination as sensors might for a wind turbine.\u00a0 Rocket has time and accuracy goals for each of these steps that constitute a digital twin of the process.<\/p>\n This may not be common today but it\u2019s a natural extension of the digital twin concept into human-initiated processes.<\/p>\n \u00a0<\/p>\n Mind the Error Rate<\/strong><\/span><\/p>\n Here\u2019s a fundamental rule of data science.\u00a0 The more that human activity is included in the data of what is being modeled, the less accurate the model will be.\u00a0 So for those of us who have modeled machine-based or factory-process based data where very little human intervention occurs we can regularly achieve accuracy in the high 9s.<\/p>\n However if we are modeling a business process such as customer-views-to-order in ecommerce, or something as mundane as order-to-cash, then the complexity of human action will mean that our best models may be limited to accuracy in the 7s and 8s.<\/p>\n But even with industrial applications the error rate still exists.\u00a0 Models have error rates.\u00a0 So for example, when we use Digital Twin models to predict preventive maintenance or equipment failure, in some percentage of cases we will perform the maintenance too early and in some we will fail to forsee an unexpected failure.\u00a0 We may continue to improve the model as new data and techniques are available but it will always be a model, not a one-to-one identity with reality.<\/p>\n Another major use of Digital Twins is in optimization.\u00a0 The same impact of error rate will be true except that if some of our solutions based on DT modeling involve significant capital spending, then some of those decisions may be wrong.<\/p>\n The third and perhaps most concerning area is where Digital Twins are used as a representation of current reality and new machines, processes, or components are designed and built up from scratch using those assumptions about operating reality.\u00a0 There particular care must be exercised to understand how the error rate in the underlying model might mislead designers into serious errors about how the newly designed machine or process might perform in the current reality.<\/p>\n \u00a0<\/p>\n Stand by for the Event Driven Future<\/strong><\/span><\/p>\n The great majority of our interaction with digital systems is still request driven, that is, once a condition is observed we instruct or request the system to take action.\u00a0 This is being rapidly supplanted by event driven processing.<\/p>\n What used to be called prescriptive analytics, the machine learning extension from the model to the decision of what should happen next is being rebranded as \u2018Event Driven Digital Business\u2019.\u00a0 The modeling of machines, systems, and processes is a precondition for the optimization work that determines when specific actions and decisions are needed.\u00a0 As the digital twin movement expands, more streaming applications will be enabled with automated event driven decision making.<\/p>\n \u00a0<\/p>\n \u00a0<\/p>\n About the author:\u00a0 Bill Vorhies is Editorial Director for Data Science Central and has practiced as a data scientist since 2001.\u00a0 He can be reached at:<\/p>\n Bill@DataScienceCentral.com<\/a><\/p>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"![](\"http:\/\/api.ning.com\/files\/QLR0zZ9SE8t0qgqVpvYymW*GakHkIn1PLpnGioYjablHs3hGtDn*xeefPXvWbQuV4g2nDpiZNoh*TJOEsOiN70PydfNiy2im\/digitaltwins.jpg\")
<\/a><\/p>\n<\/a><\/p>\n<\/a>Tesla is the poster child for using real time IoT data directly from customer\u2019s cars and their driving experiences to enhance the performance of not only its existing fleet but also future models.\u00a0 Reportedly this can be as discrete as resolving a customer\u2019s rattling door by updating on board software to adjust hydraulic pressure in that specific door.<\/p>\n