A reinforcement learning tri-state combination long-short-term memory neural network system and a training and prediction method thereof

Abstract

The invention relates to a reinforcement learning tri-state combination long-short-term memory neural network system. The system comprises a long-short-term memory neural network, a reinforcement learning unit and a monotone trend recognizer. The monotonous trend recognizer judges a trend state of the input time sequence, the reinforcement learning unit, according to a trend state according to theinput time sequence, selects the number of hidden layers, the number of hidden layer nodes and the long-short-term memory neural network adaptive to the change rule of the number of the hidden layersand the number of the hidden layer nodes, wherein the trend state of the input time sequence comprises three states, and each trend state corresponds to one hidden layer, the number of hidden layer nodes and the long-short-term memory neural network adaptive to the change rule of the number of the hidden layers and the number of the hidden layer nodes. According to the method, the trend of the input time sequence is judged, the optimal action is selected to be executed according to the updated Q value set, the network generalization capability is enhanced, and the relatively higher predictionprecision is achieved on the degradation trend of the rotary machine; and by outputting an error calculation reward, the convergence speed of the network is improved, and the calculation efficiency of the system is improved.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a three-state combined long-short-term memory neural network system for reinforcement learning and a training and prediction method. Background technique [0002] Rotating machinery is one of the most widely used components in civil and national defense mechanical equipment. During long-term operation, rotating machinery will gradually degrade, and the remaining life will gradually decrease. The occurrence of failures often brings catastrophic accidents, resulting in major economic loss and serious social impact. At present, industrial enterprises generally adopt a time-based maintenance system for the maintenance of rotating machinery, that is, regardless of whether the equipment fails or not, it is regularly overhauled. Although such an overhaul system is highly planned, it takes up a lot of time and space, and requires a large number of spare parts. , It consumes a lo...

AI Technical Summary

Problems solved by technology

However, these methods still have shortcomings. For example, for PF, the resampling stage will cause the loss of sample validity and diversity, resulting in sample depletion.

Since the kernel function type and kernel parameters of SVR are still difficult to set accurately, the prediction results are also uncertain

There is no mature theoretical guidance for the selection of the number of hidden layers and the number of nodes of the artificial neural network. Generally, the selection is based on experience, which leads to unsatisfactory prediction accuracy and calculation efficiency of the model.

Images