CAiRS Lecture – Reliability and Safety Analysis using Digital Twins

 The Centre for Advances in Reliability and Safety (CAiRS) organized a webinar named “Reliability and Safety Analysis using Digital Twins” on 9^th March 2022.  The speaker were Mr. Varun Khemani and Dr. Michael H. Azarian.

In the beginning, Dr. Michael H. Azarian introduced what is Digital Twins. He said digital twins approach could help in asset management and maintenance optimization through fault diagnosis and fault prognosis of the various faults of the asset to ensure its safety and reliability.

Mr. Varun Khemani continued to discuss the digital twin for rotating machinery, batteries, and circuits including their failure modes and mechanisms. 

After demonstrated some cases, he mentioned traditional digital twin depended on simulations to approximate the system, but it is not possible to simulate complex system. So he proposed the Deep Digital Twins (DDT) and gave new definitions below.

1.    An implicit physics model of an asset learned from healthy asset data, requiring no explicit physics knowledge.

2.    A digital representation from which sensor values can be sampled under both stationary and non-stationary operational settings such as rotational speed, throttle and load.

3.    A data driven model which does not require any asset specific feature engineering

4.    A probabilistic model which is able to automatically produce a health indicator which is a metric of the deviation from the healthy asset data.

Deep Digital Twins (DDT) framework was proposed afterward.

Finally, he showed some application of DDT such as gearbox and Commercial Modular Aero-Propulsion System Simulation (CMAPSS).  Lastly, Mr. Khemani concluded that digital twins demonstrated for the prediction of remaining useful life, reliability and functional safety for different products. Concept of deep digital twins (DDT) worked with scenarios where digital twin modeling was infeasible.  Reinforcement learning was introduced to digital twin evolving within the system lifetime.

Reference:

CAiRS - https://www.cairs.hk/view/index.php

CAiRS Lecture - Digital twins for reducing testing and qualification needed for safety assurance

The webinar named “Digital twins for reducing testing and qualification needed for safety assurance: Is the Microelectronics Industry Ready?” was organized by Centre for Advances in Reliability and Safety (CAiRS) on 16^th Feb 2022.  The speaker was Prof. Abhijit Dasgupta (University of Maryland). 

In the beginning, he briefed digital twin for developing reliable products.

And he also mentioned the background of microelectronics industry and its development history.  Traditional electronic packaging hierarchy was also discussed including wire bonding, ball grid array and flip chip, 3D IC, etc.

Hybrid Integration (HI) concept such as Intel’s Embedde Multi-Die Interconnect Bridge (EMID) was described and HI digital twins on complex multi-physics multi-scale systems was discussed. And then raised “Reliable/Safe HI system approach”.

After that Prof. Dasgupta mentioned the reliability/safety methodology for HI system using both Top-Down Big Data Approach and Bottom-Up Physics Approach to establish “Reliability Digitals Twins” for fusion prognostics.

Finally, a holistic approach on microelectronics reliability was introduced and discussed the convergence of reliability-physics and AI.

Lastly, different digital twins’ applications were discussed such as In-Situ Service Load Monitoring for automotive life-cycles (driving Digital Twins), Multi-Physics Degradation in Electronics (e.g. Capacitor, Batteries, Printed Hybrid Electronics (PHEs), etc). So that digital twins would improve the whole supply chain.

At the end, Prof. Abhijit Dasgupta briefed grad challenges for digital twins on reliable/Safe microelectronics that were timely development, deployment, and sustainment of reliable, safe, repairable, and affordable systems.

Reference:

CAiRS - https://www.cairs.hk/view/index.php

CAiRS webinar - System Safety Verification and Validation for AI Systems

The webinar named “System Safety Verification and Validation for AI Systems” was organized by Centre for Advances in Reliability and Safety (CAiRS) on 4^th Aug 2021.  System Safety is a complex process because it involves an integration system of different systems to integrate their behaviors and misbehaviors. Therefore, System Verification and Validation of AI systems become the major challenge.  Dr Dev Raheja (Adjunct Professor (Reliability Engineering) at the University of Maryland, Mechanical Engineering Department) was the guest speaker.

Firstly, he gave an overview that system safety is a specialty within system engineering that supports program risk management. Its goal is to optimize safety by the identification of safety related risks, eliminating or controlling them by design, etc. Then he explained traditional verification and validation model.

Then Dr. Dev Raheja briefed risk definition, risk management and big risks as well as high level safety.  Big risks related to the Time-To-Market but danger if unknown hazard in the product. (That let me remember Samsung Note 7 case!)

After that Dr. Raheja said system reliability is the most important component of system safety for AI system and almost all accidents result from poor reliability. He introduced four types of AI and they are Reactive Machines, Limited Memory, Theory of Mind and Self-Aware.

Reactive Machines perform basic operations. This is the first stage of any AI system. A machine learning that takes a human face as input and outputs a box around the face to identify it as a face is simple, reactive machine. (No Input, No Learning!)

Limited memory types refer to an AI’s ability to store previous data and/or predictions, using that data to make better prediction. Every machine learning model requires limited memory to be created, but the model can get deployed as a reactive machine type.

Theory of Mind AI is only beginning phases such as self-driving cars. In this type of AI, it begins to interact with the thoughts and emotions of humans.

Self-aware AI exists only in story that beyond the human has an independent intelligence.

Finally, Dr. Raheja said we need robust specification but at least 60% requirements missed in most specifications. He also said we need several Hazard Analysis tools and Accelerated Life Test (e.g. HALT, S-N diagram).

Lastly he pointed out the secret of success that is to make top management responsible safety and reliability, conducting frequent training and workshop as well as involved in audits with them. He also suggested to get independent consultants and auditors in evaluating the effectiveness of the system of systems.

Reference:

CAiRS - https://www.cairs.hk/view/index.php

20210115: CAiRS webinar - System Reliability and Maintenance - Key Success Factors for your business - https://qualityalchemist.blogspot.com/2021/01/cairs-webinar-system-reliability-and.html

20201126: CAiRS webinar - How Products Reliability and Systems Safety help Local Industry - https://qualityalchemist.blogspot.com/2020/11/cairs-webinar-how-products-reliability.html

20201029: Breakfast with Prof. Winco Yung and meet with Mr. Ben Tsang in Science Park - https://qualityalchemist.blogspot.com/2020/10/breakfast-with-prof-winco-yung-and-meet.html

CAiRS webinar - System Reliability and Maintenance - Key Success Factors for your business

The webinar named “System Reliability and Maintenance - Key Success Factors for your business” was organized by Centre for Advances in Reliability and Safety (CAiRS) and supported by HKSTP on 15^th Jan 2021.  Local and overseas professional experts and renowned industrialist were invited to share their industrial and research experiences on Reliability Prediction, Prognostics and Health Management, and System Maintenance and Management etc. 

Dr. Diganta Das (CALCE) was the first speaker and his topic entitled “Is Your Reliability Prediction Reliable?” Firstly, Dr. Das introduced Reliability and Predicted Reliability.  Reliability is the probability that an item will perform its intended function for a specified interval under stated conditions.  Predicted Reliability is for the stated conditions of use, and taking into account the design of an item, the reliability computed from the observed, assessed, or extrapolated reliabilities of its parts, interconnects and interfaces.

Then Dr. Das explained the reasons to perform reliability prediction that could understand the risks and take different actions.  However, such prediction usually only consider as a contractual requirement or regulatory obligation.  He also briefed different method for prediction including reliability prediction handbooks, reliability testing, use of field data and physics of failure, etc.

After that he briefed a timeline for MIL-HDBK-217 since 1940s.  And then he described the change of transistors number and features from 1970s to 2010s. MIL-HDBK-217F, Notice 2 was issued in 1995.

However, most prediction form various handbook and different methodologies had large deviation.  Problems included incorrectly assume constant failure rates, no information on potential failure modes, mechanisms and sites. Finally, Dr. Diganta Das introduced IEEE Standards 1413 and 1413.1 which provides a framework for reliability prediction of hardware that is a tools for evaluation of reliability predictions.

Dr. Michael H. Azarian (CALCE) was the second speaker and his presentation named “Prognostics and Health Management enabled Maintenance”. Firstly, he introduced health progress timeline from “Start of product life cycle” to “Early incipient fault” to “Component or sub-system failure” and to “System failure”.

And then Dr. Azarian introduced four maintenance strategies and they were “Corrective Maintenance”, “Scheduled Maintenance”, “Condition-based Maintenance” and “Predictive Maintenance”. Then he explained it using automotive health monitoring sample.

After that he briefed Prognostics and Health Management (PHM) that permits the evaluation of system’s reliability in its actual life-cycle conditions. Then PHM process cycle was mentioned.  He raised different possible PHM application levels and they were Level 0 – die, Level 1 – component, Level 2 – assembly, Level 3 – module, Level 4 – system, and Level 5 – system of systems. 

Finally, Dr. Azarian discussed two Prognostic Approaches that were Physics-of-Failure (PoF) Approach and Data-Driven Approach.  The PoF-Based PHM methodology was showed in the following diagram.

Data Driven PHM was discussed.  Machine learning based on statistical methods is well-suited for PHM because it is capable of actively learning about the system and its dynamics, faults, and failures.  Lastly, Dr. Azarian concluded that both approaches are used to evaluate the health of a system, to predict its remaining useful life, and to implement risk-mitigating actions such as preventative maintenance.

The third speaker was Ir. Wilson Kwok (Head of Technical Services, The Hongkong Electric Co., Ltd.) and his presentation topic was “Application of AI in the Reliability and Security of Power Grids”. In the beginning, Ir. Kwok said the meaning of smart cities is to use of connected technologies to improve efficiency and quality of life in a sustainable way.

Then Ir. Kwok compared smart cities and human body that both key elements included brain (decision making), senses (CCTV) and body (ICT). He also shared some application such as hot spot on apparatus, water dripping and flooding.

And then he introduced their Intelligent Volt-VAR Regulation (IVAR) System Architecture and Software Design

After that he briefed the history of medium voltage (MV) cable diagnostic assessment since 1980.

At the end, Ir. Wilson Kwok introduced that they adopt AI methodology to process and analyze data and review the causes of faults for cable life assessment.

The last speaker was Dr Siqi Bu (Associate Professor, PolyU) and his title named “Data-Driven Techniques in enhancing Reliability and Security of Power Networks”. Firstly Dr. Bu briefed the background of power industry transformation as 4D including Decarbonization, Digitization, Decentralization and Deregulation.

Then Dr. Bu briefed the predictive maintenance of power equipment.  The future predictive maintenance (PdM) would be AI-based, Data-driven approach.

After that Dr. Bu mentioned tools of Situation Awareness (SA) that modern power systems were being treated as comprehensive cyber physical systems (CPS). He proposed an Enhanced Situation Awareness Based on Random Matrix and Deep Learning.

Finally, Dr. Siqi Bu discussed CNN-LSTM model to achieve the collaboratively spatiotemporal data mining.  Technically, CNN module is to extract and learn spatially correlated features and LSTM module is to handle temporal correlation of the extracted feature. Lastly he concluded that the very fast post-fault actions (PFAs) could be implemented by the system operators to avoid any unstable operational status of the electric power system.

Q&A Session

At the end, Prof. Winco Yung (Centre Director, CAiRS) gave closing remark.  He said we needed data and knowledge domains from different industries for employing AI in reliability modeling to enhance safety level and CAiRS had different experts and partners to achieve this goal.

Reference:

CAiRS - https://www.cairs.hk/view/index.php

20201126: CAiRS webinar - How Products Reliability and Systems Safety help Local Industry - https://qualityalchemist.blogspot.com/2020/11/cairs-webinar-how-products-reliability.html

20201029: Breakfast with Prof. Winco Yung and meet with Mr. Ben Tsang in Science Park - https://qualityalchemist.blogspot.com/2020/10/breakfast-with-prof-winco-yung-and-meet.html

CAiRS webinar - How Products Reliability and Systems Safety help Local Industry

 The webinar named “How Products Reliability and Systems Safety help Local Industry to address market needs and promote business opportunities” was organized by Centre for Advan es in Reliability and Safety (CAiRS) and supported by HKSTP on 26^th Nov 2020.  It aimed to share industrial and research experiences on products reliability and systems safety and how the industry needs could be addressed and business opportunities could be promoted. 

Prof. Winco Yung (Centre Director, CAiRS) was the first speaker and his topic entitled “Introduction of Reliability and Safety Research in CAiRS”.  Firstly, Prof. Yung mentioned the vision of CAiRS that aimed to be world leading and regional hub for research in reliability and safety innovation.

And then he introduced CAiRS approach in which focused on AI based methods for system health assessment so as to ensure reliability and safety. It aimed to develop a real-time and predictive solution for system safety.  

After that Prof. Yung introduced five key research programs for achieving their objectives below.

l   Identification and acquisition of useful data relating to reliability and safety.

l   Development of different AI technologies in bridging the above knowledge gaps and formation industry big data

l   Integration of Data-driven Model and Physics of Failures approaches on data set in various industry sectors

l   Development of algorithm for Predictive Failure of critical components and systems

l   Formulation of practical modelling on product’s life prediction and process quality forecast

Finally, Prof. Wu stated their testing laboratory capabilities included AI supercomputing, Temperature & Environment Testing, Failure Analysis Equipment and Life Cycle Assessment Equipment. Moreover, he also introduced their team member in different departments in PolyU with different supporting organizations such as HKEIA, HKEIC, ASM, Compass, nVidia, HAECO, CLP, GP, Defond, … etc.

Lastly, Prof. Wu emphasized several benefits to collaborate between Industry and CAiRS such as failure prevention and cost saving.  Until now, there were five application sectors in the program and they were Transportation, Public Utility, Products, Parts & Components, and Data Integrity & Software Trustworth.

Dr. Brian Li (Executive VP, Gold Peak Industries (Holdings) Limited) was the second speaker and his presentation named “Marketing Needs and Challenges of Products Reliability and Systems Safety”.  In the beginning, Dr. Li briefed the background of Gold Peak Group.

Then Dr. Li mentioned the product quality and reliability that was the livelihood of a manufacturer.  He said that the integral cost of supplying products to customers included customer service costs and warranty costs, which could be higher than the manufacturer’s Free On Board (FOB) cost in terms of brand.  Therefore, high quality and high reliability is a most important qualification to establish the brand.  After that he briefed their group’s batteries was working with CAiRS on new approaches for assessing product reliability using Big Data analysis and AI techniques.

Finally, Dr. Li briefed their GP batteries service and requirements.  He expected the best quality and reliability were achieved before new product launch through new technology and research employed from the program with CAiRS.

The last speaker was Dr. Steven Boles (Associate Professor, PolyU) and his presentation title was “Reliability and Safety Research Methodology with Industrial Applications”. Firstly, he briefed the demand trend for energy.  Electricity increasing daily was observed that Natural Gas and Renewables were growing.

Then Dr. Boles said we needed for energy storage using electrochemical energy storage device.  It was observed that Lithium-ion Battery (LIB) was growing in recently years. 

After that Dr. Boles briefed the principles of LIBs and said more energy stored, the higher risk was.  Therefore, safety and reliability of LIBs were concerned especially travelling in fight (e.g. spare lithium batteries never go in a checked bag).  

Finally, Dr. Boles briefed some cases about “Physics of Failure” in LIB such as Li-metal plating, Overcharging, Manufacturing issues, thermal runaway, etc.  Therefore, he suggested to add sensing in batteries like “canary” device so as to improve safety, reliability and health in the future.

Reference:

CAiRS - https://www.cairs.hk/view/index.php