Photovoltaic array fault detection method based on a partial least squares method and an extreme learning machine

Abstract

The invention relates to a photovoltaic array fault detection method based on a partial least squares method and an extreme learning machine. The method comprises the following steps: firstly, carrying out real-time acquisition and filtering preprocessing on data of a photovoltaic array under various working conditions to obtain original monitoring data, and then extracting and normalizing the original monitoring data to generate a seven-dimensional fault sample data set; And carrying out dimension reduction on the obtained seven-dimensional fault sample data set by adopting a partial least square method to generate a three-dimensional fault sample data set, and randomly dividing the fault sample data set into a training set and a test set. Secondly, the training set generates a training subset and a verification subset through K-fold intersection, and an extreme learning machine fault diagnosis model is trained and verified to select an optimal hidden layer neuron number; And finally,training the extreme learning machine by using the training set and the optimal hidden layer number of the extreme learning machine, and detecting by using the test set to obtain the test precision of the fault diagnosis model so as to verify the generalization performance of the model. The technology provided by the invention can accurately and reliably diagnose and classify common faults of thephotovoltaic array.

Description

technical field [0001] The invention relates to the field of photovoltaic array fault detection and classification, in particular to a photovoltaic array fault detection method based on a partial least square method and an extreme learning machine. Background technique [0002] Global environmental pollution is becoming more and more serious, and environmental problems need to be solved urgently. The application of new energy can effectively alleviate the problem of aggravated environmental pollution. Solar energy is one of the new energy sources that has attracted much attention. According to the report of the National Energy Administration, in the first three quarters of 2018, my country's newly installed photovoltaic power generation capacity was 34.544 million kilowatts, a year-on-year decrease of 19.7%. Among them, photovoltaic power stations were 17.401 million kilowatts, a year-on-year decrease of 37.2%; %. my country attaches great importance to the development of so...

AI Technical Summary

Problems solved by technology

It is worth noting that in the current photovoltaic fault diagnosis based on machine learning and intelligent algorithms, the input features of the algorithm are multi-dimensional data calculated between the parameters of current, voltage, temperature and irradiance, and few of them use dimensionality reduction for simple calculation. The calculation simplifies the input features of the algorithm

Images