A fault prediction method of refrigeration equipment based on neural network

The invention provides a fault prediction method of refrigeration equipment based on a neural network, comprising the following steps: acquiring a time series data set collected by N sensors sensitiveto the fault in the refrigeration equipment; The long-term and short-term neural network model is constructed according to the time series data set, and the actual forecasting results of the time series data set are obtained according to the long-term and short-term neural network model. Determining a fault discrimination model f (x) according to the time series data set; Acquiring a real data set of a part of the known fault conditions of the refrigeration equipment, and determining a fault threshold value according to the fault discrimination model f (x) and the real data set; The probability density of the actual predicted results is determined according to the fault discrimination model, and the health status of the refrigeration equipment is judged by comparing the probability density of the actual predicted