{"id":9389,"date":"2026-02-24T12:30:21","date_gmt":"2026-02-24T04:30:21","guid":{"rendered":"https:\/\/ascendas-asia.com\/?page_id=9389"},"modified":"2026-03-06T15:04:48","modified_gmt":"2026-03-06T07:04:48","slug":"ai-with-model-based-design","status":"publish","type":"page","link":"https:\/\/ascendas-asia.com\/th\/resources\/ai-with-model-based-design\/","title":{"rendered":"AI with Model-Based Design"},"content":{"rendered":"

\n\n\n\n
\n

Apply artificial intelligence (AI) techniques to the design of engineered systems<\/p>\n

\u201cEven though we are not specialists in deep learning, using MATLAB and Deep Learning Toolbox we were able to create and train a network that predicts NOX emissions with almost 90% accuracy.\u201d<\/p>\n

\u00a0– Nicoleta-Alexandra Stroe and Vincent Talon, Renault<\/em><\/p>\n

\n\n\n\n\n
\"Virtual<\/td>\n\"System<\/td>\n\"Reinforcement<\/td>\nTry for free<\/span><\/strong><\/a><\/td>\n<\/tr>\n
Virtual Sensor Modeling<\/strong><\/span><\/td>\nSystem Identification and<\/strong><\/span>
\nReduced Order Modeling (ROM)<\/strong><\/span><\/td>\n		Reinforcement Learning<\/strong><\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n\n\n\n
\n

Virtual Sensor Modeling<\/strong><\/h2>\n

Estimate signals of interest that a physical sensor cannot directly measure, or when a physical sensor adds too much cost and complexity to the design.<\/p>\n

    \n
  • Create and compare virtual sensor models using different deep learning and machine learning architectures such as fully connected layers, long short-term memory (LSTM) layers, and support vector machines<\/li>\n
  • Import AI models created in TensorFlow\u2122 or PyTorch\u00ae for simulation and deployment with Simulink<\/li>\n
  • Integrate, simulate, and test AI-based virtual sensors with the rest of the system<\/li>\n
  • Compress AI-based virtual sensor models and deploy them to microcontrollers and ECUs using library-free C code generation<\/li>\n
  • Adapt virtual sensor models to process data in real-time using incremental learning<\/li>\n<\/ul>\n<\/td>\n

<\/td>\n\n

\"Virtual<\/span><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n\n\n\n\n
Customer Stories and Case Studies<\/strong><\/td>\nVideos<\/strong><\/td>\nExamples<\/strong><\/td>\n<\/tr>\n
\n
    \n
  • Coca-Cola Develops Virtual Pressure Sensor with Machine Learning to Improve Beverage Dispenser Diagnostics<\/li>\n
  • Mercedes-Benz Simulates Hardware Sensors with Deep Neural Networks<\/li>\n
  • Poclain Hydraulics Develops Soft Sensors to Measure Motor Temperature in Real Time Using Deep Learning and Kalman Filters<\/li>\n<\/ul>\n<\/td>\n
\n
    \n
  • Developing and Embedding AI-Based SOC Estimation for BMS Using MATLAB (7:52)<\/li>\n
  • AI with Model-Based Design: Virtual Sensor Modeling (35:53)<\/li>\n
  • Integrate TensorFlow Model into Simulink for Simulation and Code Generation (5:47)<\/li>\n<\/ul>\n<\/td>\n
\n