Prediction Method of Equipment Remaining Life Based on Self-Attention Long Short-Term Memory Neural Network

Aiming at the problem of insufficient consideration of the correlation between components in the prediction of the remaining life of mechanical equipment,the method of remaining life prediction that combines the self-attention mechanism with the long short-term memory neural network(LSTM-NN)is proposed,called Self-Attention-LSTM.First,the auto-encoder is used to obtain the component-level state information;second,the state information of each component is input into the self-attention mechanism to learn the correlation between components;then,the multi-component correlation matrix is added to the LSTM input gate,and the LSTM-NN is used for life prediction.Finally,combined with the commercial modular aero-propulsion system simulation data set(C-MAPSS),the experiment was carried out and compared with the existing methods.Research results show that the proposed method can achieve better prediction accuracy and verify the feasibility of the method.

DEVELOPMENT OF A MATERIALS RISK INFORMATION PLATFORM FOR A SAFE SOCIETY

A Materials Risk Information Platform is being developed under the cooperation of companies and academic societies with NIMS as project core. To combine safety and economy, which are sometimes contrary to each other, it is important to find an optimal solution using a new concept: risk based engineering. A 5-year project, the Materials Risk Information Platform, was started in 2001 in NIMS on the boilers of thermal power plants and the objectives of this project, research areas and its present state were outlined.

Comparison on End-of-Life strategies of WEEE in China based on LCA

As the Electrical and Electronic Equipment （EEE） are upgraded more frequently in China, a large quantity of Waste Electrical and Electronic Equipment （WEEE） was and will be generated. It becomes an urgent issue to develop and adopt an effective End-of-Life （EoL） strategy for EEE in order to balance the resource recovery and environmental impacts. In an EoL strategy hierarchy for EEE, reuse strategy is usually deemed to be prior to materials recovery and other strategies. But in practice, the advantages and disadvantages of different strategies are always context-dependent. Therefore, main EoL strategies for EEE in China need to be evaluated in environment and resources aspects from the life cycle perspective. In this study, the obsolete refrigerator and Power Supply Unit （PSU） ofdesktop PC are both taken as the target products. Life Cycle Assessment （LCA） is applied to assess the environmental impacts of different EoL scenarios in China： Unit Reuse Scenario （URS）, Component Reuse Scenario （CRS） and Materials Recovery Scenario （MRS）. The LCA results show that the EoL strategies hierarchy is reasonable for the part＇of computer, bui not necessarily suitable for obsolete refrigerators. When the policy makers promote or demote one EoL strategy especially reuse, it is necessary to take subsequent impacts into consideration.