Publication
Diagnosis in an Intelligent Supervision System
| Summary: | In the Automotive industry there is an integration of various systems present in different contexts, such us: production line, logistics spaces, among others. There are also other processes, some performed by machines, and some performed by human intervention, that are prone to failures and errors, whose diagnosis is a difficult task, causing some productivity breaks and slow recovery, which in the end, will present negative results for the business. To address this, the development of an Intelligent Supervision System is proposed. This system, which will integrate monitoring, diagnosis, and failure recovery modules, has the objective of optimizing the entire process including the production line, logistics spaces and quality control stations. By implementing an Intelligent Supervision System, a preventive and reactive system is expected, capable of predicting issues using machine learning techniques. This approach is expected to boost productivity, reduce production line’s stop-time caused by errors, enhancing resource usage efficiency and overall improvement of product quality. These modules are based on real-time data extraction and analysis. Failure detection will be based on comparing the gathered data with the system’s normal functioning information. Once a failure is detected, the system's objective is to discover its origin and type and, whenever possible, implement recovery solutions automatically or, otherwise, report the detected error. The diagnosis and failure recovery processes will be supported by a Decision Support System which will be implemented by an Artificial Neural Network or by Artificial intelligence. |
|---|---|
| Main Authors: | Gonçalves, Luís Miguel Martins |
| Subject: | Intelligent supervision system Neural Network Artificial Intelligence Diagnosis Decision Support System |
| Year: | 2025 |
| Country: | Portugal |
| Document type: | master thesis |
| Access type: | open access |
| Associated institution: | Universidade Nova de Lisboa |
| Language: | English |
| Origin: | Repositório Institucional da UNL |
| Summary: | In the Automotive industry there is an integration of various systems present in different contexts, such us: production line, logistics spaces, among others. There are also other processes, some performed by machines, and some performed by human intervention, that are prone to failures and errors, whose diagnosis is a difficult task, causing some productivity breaks and slow recovery, which in the end, will present negative results for the business. To address this, the development of an Intelligent Supervision System is proposed. This system, which will integrate monitoring, diagnosis, and failure recovery modules, has the objective of optimizing the entire process including the production line, logistics spaces and quality control stations. By implementing an Intelligent Supervision System, a preventive and reactive system is expected, capable of predicting issues using machine learning techniques. This approach is expected to boost productivity, reduce production line’s stop-time caused by errors, enhancing resource usage efficiency and overall improvement of product quality. These modules are based on real-time data extraction and analysis. Failure detection will be based on comparing the gathered data with the system’s normal functioning information. Once a failure is detected, the system's objective is to discover its origin and type and, whenever possible, implement recovery solutions automatically or, otherwise, report the detected error. The diagnosis and failure recovery processes will be supported by a Decision Support System which will be implemented by an Artificial Neural Network or by Artificial intelligence. |
|---|
Funded activities
No funded projects found.