Fault isolation in manufacturing systems based on learning algorithm and fuzzy rule selection

Fault diagnosis is becoming an important issue in industrial environment, and the accurate diagnosis is the most significant part in fault handling. This article discusses a fault detection and diagnosis problem for manufacturing systems taking into account rapid detection and speed performances of fault isolation with minimum ambiguity. However, in many complex real plants, it may not be possible to discover accurately the causes of probable faults. The accuracy of fault or fault detection by the traditional approaches is not adequate. Considering the quality effect of the learning algorithm, a new hybrid neural network approach is developed using the integration of a regression task for classification accuracy. Two models of neural networks: gradient descent and momentum & adaptive learning rate and Levenberg–Marquardt are investigated and compared. The performance of the proposed approach is evaluated using mean square error, convergence speed, and classification accuracy. The case study and experimental results are presented and discussed. A comparison with the Levenberg–Marquardt regression approach shows the importance of considering the proposed learning algorithm quality in the fault detection and diagnosis problem compared with those reported in the literature.

Download Full-text

A FILTER PROPOSAL FOR INCLUDING FEATURE CONSTRUCTION IN A GENETIC LEARNING ALGORITHM

International Journal of Uncertainty Fuzziness and Knowledge-Based Systems ◽

10.1142/s0218488512400144 ◽

2012 ◽

Vol 20 (supp02) ◽

pp. 31-49 ◽

Cited By ~ 2

Author(s):

DAVID GARCIA ◽

ANTONIO GONZALEZ ◽

RAUL PEREZ

Keyword(s):

Learning Algorithm ◽

A Priori ◽

Fuzzy Rule ◽

Feature Construction ◽

Rule Based ◽

Filter Model ◽

Information Measures ◽

Construction Techniques ◽

Basic Learning ◽

Current Proposal

In system identification process often a predetermined set of features is used. However, in many cases it is difficult to know a priori whether the selected features were really the more appropriate ones. This is the reason why the feature construction techniques have been very interesting in many applications. Thus, the current proposal introduces the use of these techniques in order to improve the description of fuzzy rule-based systems. In particular, the idea is to include feature construction in a genetic learning algorithm. The construction of attributes in this study will be restricted to the inclusion of functions defined on the initial attributes of the system. Since the number of functions and the number of attributes can be very large, a filter model, based on the use of information measures, is introduced. In this way, the genetic algorithm only needs to explore the particular new features that may be of greater interest to the final identification of the system. In order to manage the knowledge provided by the new attributes based on the use of functions we propose a new model of rule by extending a basic learning fuzzy rule-based model. Finally, we show the experimental study associated with this work.

Download Full-text

KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/317 ◽

2020 ◽

Cited By ~ 1

Author(s):

Peng Zhang ◽

Jianye Hao ◽

Weixun Wang ◽

Hongyao Tang ◽

Yi Ma ◽

...

Keyword(s):

Reinforcement Learning ◽

Prior Knowledge ◽

Learning Process ◽

Learning Algorithm ◽

Fuzzy Rule ◽

Policy Network ◽

Human Knowledge ◽

Learning Agents ◽

The Common ◽

Low Performance

Reinforcement learning agents usually learn from scratch, which requires a large number of interactions with the environment. This is quite different from the learning process of human. When faced with a new task, human naturally have the common sense and use the prior knowledge to derive an initial policy and guide the learning process afterwards. Although the prior knowledge may be not fully applicable to the new task, the learning process is significantly sped up since the initial policy ensures a quick-start of learning and intermediate guidance allows to avoid unnecessary exploration. Taking this inspiration, we propose knowledge guided policy network (KoGuN), a novel framework that combines human prior suboptimal knowledge with reinforcement learning. Our framework consists of a fuzzy rule controller to represent human knowledge and a refine module to finetune suboptimal prior knowledge. The proposed framework is end-to-end and can be combined with existing policy-based reinforcement learning algorithm. We conduct experiments on several control tasks. The empirical results show that our approach, which combines suboptimal human knowledge and RL, achieves significant improvement on learning efficiency of flat RL algorithms, even with very low-performance human prior knowledge.

Download Full-text