{"id":6296,"date":"2023-05-18T16:33:22","date_gmt":"2023-05-18T16:33:22","guid":{"rendered":"https:\/\/www.quadrical.ai\/?p=6296"},"modified":"2023-05-18T16:44:52","modified_gmt":"2023-05-18T16:44:52","slug":"optimize-solar-asset-performance-with-digital-twin-ai","status":"publish","type":"post","link":"https:\/\/www.quadrical.ai\/optimize-solar-asset-performance-with-digital-twin-ai\/","title":{"rendered":"Optimize Solar Asset Performance with Digital Twin AI"},"content":{"rendered":"
Scientists and engineers have been constructing equation-based models to predict the output\/performance of physical systems since accessible computing became commonplace about 50 years ago.<\/p>\n
Fundamental traits of\u00a0static\u00a0<\/em>models:<\/p>\n Advantages:<\/p>\n With the proliferation of AI (artificial intelligence) over the last fifteen years, models have been designed based on the technology, using data.<\/p>\n With inputs based on substantial data, and outputs measured by sensors, creates a new design of these machine learning models, also known as adaptive models or Digital Twins. Provided both inputs and desired outputs are known, the designer does not require deep technical knowledge of the principles behind the physical system that is being modelled. But having expert level insight into the physical counterpart\u2019s principles does help with input selection, model architecture selection, and optimization of performance of the digital twin model.<\/p>\n Digital Twin models broadly have these characteristics:<\/p>\n Key challenges:<\/p>\n For solar PV plants with a large number of very similar physical systems, individual models can be trained for each of the systems. These unique models are trained to recognize the fact that, given the same inputs, the performance of their corresponding physical systems vary due to their tolerances and operational history.<\/p>\n Digital Twins are at the core of our asset management solutions \u2013 CMMS, Snap-On Advanced Analytics, and Plant Audits.<\/p>\n We can leverage Digital Twins to create individual models for each sub-system making up your plant.<\/p>\n They allow us to:<\/p>\n Using Time-Series models, Classification models and combining with weather forecasts, we can also:<\/p>\n Most Digital Twin models (models based on ML technology) are based on boosted decision tree or neural network models. After sensible initial architectural choices have been made, accuracy of the models depends on the accuracy data used for training and the quality of the practitioners.<\/p>\n At Quadrical, we are using a combination memory models, forecasting models, and model ensembles to improve the accuracy of error reporting, and of forecasts, by adjusting weights associated with input data, and weights associated with output estimates based on confidence and accuracy predictions associated with input data and the analysis process.<\/p>\n Anomaly models can help weight training data so data that has high confidence is weighted significantly, while more problematic data can be represented and used for training exotic events, but does not degrade the models owing to using low weights.<\/p>\n Quadrical is also investigating using more powerful models (e.g., LMUs and GANs) that provide more insight into the nature of the faults that our Digital Twin models are reporting. \u00a0For example, GANs are capable of distinguishing between normally occurring outlier performance, and the abnormal measurements resulting from a fault or failure.<\/p>\n Our technology compares four measures of performance<\/p>\n We also use Digital Twins to monitor reliability of panel cleaning data used to train Digital Twins in (2) and (3) above. Specifically, classification models can be trained to identify the occurrence of a panel cleaning event (planned, or unplanned like rain).<\/p>\n Finally, we use degradation models to predict the average soiling degradation occurring in sectors of the solar plant for those customers who want a regular cleaning schedule, which does not clean all parts of the plant at the same frequency.<\/p>\n Model Structure:<\/p>\n Data Fidelity:<\/p>\n Uses:<\/p>\n Modeling dangerous behaviours (energy storage systems)<\/p>\n I would like to acknowledge help from Shreyasi Halder and Kitty Chachra in creating this post.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":" What is the difference between a Data + AI Digital Twin and a Static, Equation based model? Static, equation-based model Scientists and engineers have been constructing equation-based models to predict the output\/performance of physical systems since accessible computing became commonplace about 50 years ago. Fundamental traits of\u00a0static\u00a0models: Designed by expert with deep technical knowledge of…<\/p>\n","protected":false},"author":2,"featured_media":6306,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/posts\/6296"}],"collection":[{"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/comments?post=6296"}],"version-history":[{"count":1,"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/posts\/6296\/revisions"}],"predecessor-version":[{"id":6297,"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/posts\/6296\/revisions\/6297"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/media\/6306"}],"wp:attachment":[{"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/media?parent=6296"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/categories?post=6296"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.quadrical.ai\/wp-json\/wp\/v2\/tags?post=6296"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}\n
\n
Digital Twin Machine Learning Model<\/h3>\n
\n
\n
Advantages of Machine Learning based Digital Twin Models<\/h2>\n
\n
Why are Digital Twins important for Solar Asset Owners and Managers?<\/h2>\n
\n
Quadrical Ai\u2019s Digital Twin Technology<\/h2>\n
\n
\n
Our Differentiation<\/h3>\n
\n
Purpose-Specific \u2013 How is a Digital Twin designed to specifically look for particular loss types?<\/h3>\n
\n
Future Outlook for Digital Twin Technology<\/h2>\n
\n
\n
\n