Evolutionary Virtual Expert System

Lead Research Organisation: University of Lincoln
Department Name: Lincoln School of Engineering


UK industries are facing a growing problem - a lack of experts! Multiple sectors of the UK's economy, especially in Engineering, are increasingly dependent on older workers, leaving employers exposed to a massive need for skilled staff when they retire. While the UK attempts to provide more quality vocational training to young people so they can replace skilled older workers when they retire, there remains years of knowledge gap to be filled. Hence, a technological solution becomes increasingly attractive - i.e. assisting humans with "Virtual Expert" (VE) systems and complementing them while they acquire experience. Many UK companies in industry have a range of automation and digitalisation challenges, such as automatic remote condition monitoring tools and engine test automation, which this project seeks to address. The main concept behind this new project is to build and train an Evolutionary Virtual Expert System (EVES) to assist current and future industrial fault diagnostic engineers. These "virtual apprentices" (diagnostic agents, including knowledge-based rules, signal processing algorithms and model-based approaches) will be trained by human experts, through coaching, examining and refining processes. After a number of subject matter tests, the successful "virtual apprentices" are promoted to become VEs and their weightings (rankings) will be updated using a genetic algorithm. Over generations of evolution, EVES will be able to find a suitable population of VEs (rules/algorithms/models), and produce a heuristically best decision through a weighted voting process, with reasoning mechanisms and possible solutions made transparent to users. EVES integrates the strengths of precision, learning ability, adaptability and knowledge representation from all the VEs that conform to the population, aiming to provide an automated and digitalised fault diagnostic system, to match or possibly outperform human experts working without such support.

The EVES project will have a big impact on areas of industrial application. This proposal is timely, as the proportion of experts in UK industries are getting older, while at the same time more modern technologies involve longer learning curves for young people. To be ready for the industries of the future, these VEs, when fully trained, will provide critical support for existing experts, and also act as good trainers for the younger workers. As the future generation is based on high technologies, good virtual assistants and virtual trainers will become increasingly important. The proposal is important, as the structure of EVES is widely applicable to all industrial sectors, for example, from fault diagnostics of machines and plants, to remote condition monitoring for railway applications, agriculture precision, water quality monitoring, and even to diagnostics for human health.

Planned Impact

Impact to Knowledge:
The EVES project will establish a new paradigm on fault diagnostic strategies in the academic field, which focuses more on the integration and automation of the diagnostic system rather than the development of individual algorithms. The EVES concepts are widely applicable to all fault diagnostics related projects, ranging from the close disciplines, such as in mechanical engineering, electrical engineering and civil engineering, to the more diverse disciplines, such as in agriculture and healthcare, which also have a direct impact on the population. The researchers within and across disciplines can associate the EVES project with their own research experiences and the existing algorithms/models for their specific projects, to devise methodologies for further applications. The system is flexible regarding to the selection of techniques, and so the EVES concepts can provide a powerful tool in solving a wide range of problems.

Impact to People:
The UoL will benefit from this project, with its contribution to the university's growth and filling a knowledge gap in the Lincolnshire County. With the success of EVES and many ongoing industrial projects, we will be able to retain and attract the best researchers in this area, ranging from PhD students to researchers in academia and industry. We believe the success of EVES will contribute significantly to the overall health of the pipeline in the university, by attracting industry and government funded projects and by training the researchers to have an overall view of the research to suit industry's needs. On the other hand, SITL's support engineers will benefit from this project, as the implemented EVES will assist their daily job by identifying potential problems, which will complement their intensive labour work in the Remote Diagnostic Centre, allowing them to perform more engaging tasks with a higher repercussion to their company and to the industry.

Impact to Economy:
While the profits this project can generate directly apply to SITL and UoL in the short term, the impact to UK's economy will be much wider in the long run. SITL: This project will generate an automated fault diagnostic tool on Siemens data platform. This product can assist service engineers for maintenance scheduling, thereby improving the quality of SITL's operational transactions. It can be transferred to other sectors in SITL, e.g. the engine test facilities. UoL: More support from Siemens, e.g. scholarships, innovation investments and further funded projects, can be attracted. It will also attract more funds outside Siemens, e.g. from Germany and Chinese investors and other companies who are interested in the fault diagnostic topic. Not to forget that, any improvement in the energy industry leads to a reduction on energy prices and emissions, which does have a great impact on the economy, helping in having a healthy energy balance of payments to developing economies, reducing the risk of conflicts.

Impact to Society:
UK industries are facing several issues: an increasing average age of the engineers, the lack of quality vocational training for young people, forthcoming restrictions on immigrant workers. The successful demonstration of EVES will help the society and policy makers to agree on a transformation to the industry of the future through the "virtual expert system" paradigm. The EVES project tackles both Energy and Digital Economy challenges. It aims to provide the product service system to improve performance and reliability of its whole lifecycle, and therefore make the production of energy more efficient, so as to contribute to a more productive nation. On the other hand, with the advance of high technologies, the future society will be a data-driven society. EVES' objective is to add value to the data by generating "smart data", and therefore to add value to the society, with the aim of improving the quality of life throughout our highly connected society.


10 25 50
Description The research fellow (RA) and I have developed relevant models for remote condition monitoring of gas turbines, validated with real industrial data provided by Siemens Industrial Turbomachinery Ltd. (SITL). SITL has supported the RA to attend two Siemens training courses on gas turbine Maintenance (Oct. 18, 4 days) and Control (Feb. 19, 8 days) separately, in which the RA has gained more knowledge on the gas turbine systems. Two conference papers (INDIN 19 and IEEE ARM 19) and one journal paper (IEEE Transactions on Industrial Informatics) have been drafted based on the existing validation results - the research output will be returned in the next submission, with potentially more publications on the EVES project at a later stage.
Exploitation Route The developed models will be presented in the conference and journal papers, which will be made public to the academic and industrial audiences who may be interested. These models are generic, and are applicable to many complex systems in industrial or bio-medical domains, which can be trained and validated with their specific data.
Sectors Aerospace, Defence and Marine,Agriculture, Food and Drink,Construction,Digital/Communication/Information Technologies (including Software),Electronics,Energy,Environment,Healthcare,Manufacturing, including Industrial Biotechology,Transport,Other