Today, one challenge of a manufacturer is to maintain with the consumer, the expected service of the supplied product during the whole product life cycle, no matter where the product and the consumer are located. The combination of modern information processing and communication tools, commonly referred to as Tele-service, offers the technical support required to implement this remote service maintenance. However, this technical support is insufficient to face new remote maintenance decision-makings which requires not only informational exchanges between customers and suppliers but also cooperation and negotiation based on the sharing of different complementary and/or contradictory knowledge. It requires an evolution from Tele-service to E-service and e-Maintenance in particular where the maintenance decision-making results from collaboration of maintenance processes and experts to form a DAI environment. For this purpose, a Problem-Oriented Multi-Agent-Based E-Service System (POMAESS) is introduced in this paper. The protocol of negotiation for multi agents and the CBR-based decision support function within this system are discussed, emphasised at the service maintenance problem solving. A prototype system based on these methodologies is developed to demonstrate the feasibility.

The nuclear power plant systems are coupled with each other, and their operation conditions are changeable and complex. In the case of an operation fault in these systems, there will be a large number of alarm parameters, which can cause humans to be hurt in the accidents under great pressure. Therefore, it is necessary to predict the values of the key parameters of a device system. The prediction of the key parameters’ values can help operators determine the changing trends of system parameters in advance, which can effectively improve system safety. In this paper, a deep learning long short-term memory (LSTM) neural network model is developed to predict the key parameters of a nuclear power plant. The proposed network is verified by simulations and compared with the traditional grey theory. The simulation and comparison results show that the proposed LSTM neural network is effective and accurate in predicting the key parameters of the nuclear power plant.

Nuclear power plant operating data are characterized by a large variety, strong coupling, and low data value density. When using machine learning techniques for fault diagnosis and other related research, feature selection enables dimensionality reduction while maintaining the physical meaning of the original features, thus improving the computational efficiency and generalization ability of the learning model. In this paper, a correlation-based feature selection algorithm is developed to implement feature selection of nuclear power plant operating data. The proposed algorithm is verified by experiments and compared with traditional correlation-based feature selection algorithms. The experiments and comparison results show that the proposed algorithm is effective in realizing the dimensionality reduction of nuclear power plant operating data.

By analyzing the recorded operation data of a nuclear power plant (NPP), its results can serve the fault detection or operation experience feedback. Data missing exists in the recorded operation data. It may lower the data quality and affect the accuracy of the analysis results. In order to improve the data quality, two parts of researches are carried on. Firstly, to locate the missing data accurately the detecting algorithm for missing data of the NPP operation parameters based on wavelet analysis. Different judging basis is proposed for discrete and continuous missing respectively. Then, the filling method based on the hot deck algorithm are studied. As the dynamic properties of the parameters are closely related to the operating state of NPP, the similarity of the operation parameter vectors are formed to express the similarity of the operating states, so as to fulfill the requirements of the hot deck algorithm. To improve the accuracy of the measuring results, taken the differences between the characteristics of the analog parameters and the switch parameters into consideration, the similarity measurements using Mahalanobis distance for the analog parameter vectors and the matching measure for the switch parameter vectors are studied respectively. Finally, the operation data is taken to build the experiment data set for the algorithm verification. The results shows that the designed algorithm performs much better than the mean interpolation method and LSTM.

No abstract