An Anomaly Detection Algorithm for the Power Industrial Terminal Security Monitoring

Power industrial terminal is a complex system with high reliability and security. Traditional methods for detecting data anomalies of power industrial terminal fail to fully mine the data characteristics. And it has shortcomings such as complex calculation, poor flexibility and low accuracy. In order to solve the problem that it is difficult to predict the operational status of power industrial terminal accurately, a prediction method based on long-term memory (LSTM) neural network is proposed. Considering the variety of data reflecting the operating status of power industrial terminal, choose the ambient temperature system related to the operating status of power industrial terminal as a experiment object. Through experiments, the algorithm has higher prediction effect for the operating status of power industrial terminal.