Reciprocating compressors play a vital role in oil, natural gas, and general industrial processes. Their safe and stable operation directly affects the healthy development of the enterprise economy. Since the valve failure accounts for 60% of the total failures when the reciprocating compressor fails, it is of great significance to quickly find and diagnose the failure type of the valve for the fault diagnosis of the reciprocating compressor. At present, reciprocating compressor valve fault diagnosis based on deep neural networks requires sufficient labeled data for training, but valve in real-case reciprocating compressor (VRRC) does not have enough labeled data to train a reliable model. Fortunately, the data of valve in laboratory reciprocating compressor (VLRC) contains relevant fault diagnosis knowledge. Therefore, inspired by the idea of transfer learning, a fault diagnosis method for reciprocating compressor valves based on transfer learning convolutional neural network (TCNN) is proposed. This method uses convolutional neural network (CNN) to extract the transferable features of gas temperature and pressure data from VLRC and VRRC and establish pseudolabels for VRRC unlabeled data. Three regularization terms, the maximum mean discrepancy (MMD) of the transferable features of VLRC and VRRC data, the error between the VLRC sample label prediction and the actual label, and the error between the VRRC sample label prediction and the pseudolabel, are proposed. Their weighted sum is used as an objective function to train the model, thereby reducing the distribution difference of domain feature transfer and increasing the distance between learning feature classes. Experimental results show that this method uses VLRC data to identify the health status of VRRC, and the fault recognition rate can reach 98.32%. Compared with existing methods, this method has higher diagnostic accuracy, which proves the effectiveness of this method.

Reciprocating compressors are important equipment in oil and gas industries which closely relate with the healthy development of the enterprise. It is essential to detect the valve fault because valve failures account for 60% in total failures. For this field, an artificial neural network (ANN) is widely used, but a complex network is not suitable for its low accuracy and easy overfitting. This paper proposes a fault diagnosis model of a reciprocating compressor valve based on a one-dimensional convolutional neural network (1DCNN). This method takes the differential pressure and differential temperature of each compressor stage as the input of 1DCNN, using the characteristics of the CNN to extract the features and finally using Softmax to classify the fault. In order to verify this method, it is compared with LM-BP, RBF, and BP neural networks. The results show that the fault recognition rate of 1DCNN reaches 100%, which proves the effectiveness and feasibility of the proposed method.

As the widely use of electronic equipment and the limitation of distribution lines, power quality issues have been more and more critical, and quantifying the power quality, monitoring the power disturbances are getting more and more attention. It crucial for the electric compensation and the improvement of electrical safety to analyze the power quality issues and locate the disturbances. Because of the limitation that most time-frequency algorithms cannot take both time and frequency resolution into account, an improved S transform based on sigmoid function which is used to adjust window width factor is proposed to obtain the characteristics of electrical disturbances, such as occurrence time, magnitude, duration, harmonics and so on. By introducing evaluation index, to measure the effect of different methods on signal analysis. Through the simulation of different kinds of power quality disturbances, and comparing with the S transform, the improved S transform based on sigmoid has the advantages of high accuracy for the extraction of characteristics. Meanwhile, it meets the requirements of most power quality disturbances and the parameters setting are simple, hence the algorithm is convenient for applications. In practice, the effect of noise on power quality disturbance signal is effectively reduced by the improved S transform.