Research on fault diagnosis method of piston rod based on harmonic wavelet and manifold learning

As the core part of reciprocating compressor,piston rod is easy to cause a serious accident when abrasion and breakage fault occur to it. Therefore,it is very important to monitor its running state. At present,a small number of reciprocating compressors have been installed on-line monitoring and diagnosis system,most of which can only monitor a single vertical subsidence of piston rod and it can't fully represent the running state of piston rod. Therefore,a method of monitoring the vertical and horizontal displacement of piston rod axis orbit is simultaneously used. In view of the characteristics that the piston rod axis orbit is disordered and difficult to extract features,purification of the axis orbit is carried out based on harmonic wavelet and then features are extracted such as vibration energy,natural frequency and the axis orbit envelope area. After that,a nonlinear local tangent space manifold learning algorithm is used to reduce the dimension of the features and obtain sensitive features. By analyzing the practical cases,the effectiveness of the method for fault monitoring and diagnosis of reciprocating compressor piston rod assembly has been verified. Finally,as BP neural network has the characteristics of solving complex nonlinear problems,the validity of the fault diagnosis method of reciprocating compressor piston rod based on harmonic wavelet and manifold learning is proved by actual case data analysis based on BP neural network.

Theoretical investigation on self-recovery regulation method for diesel engine misalignment through co-simulation

Misalignment is one of the most common faults for the diesel engine.In order to eliminate the misalignment fault of the diesel engine in the process of operation,a targeting self-recovery regulation system is constructed by using a movable base and displacement sensors.Misalignment is monitored and detected in real time,the value of misalignment is calculated rapidly and accurately,andintelligent decision is made.Then,the base is moved reversely with a definite target to drive the shaft to translate or rotate,so that the shafts can be recovered to alignment online.A co-simulation model for the self-recovery system is established which consists of a dynamic model of the crankshaft system and control model.The self-recovery regulation process of misalignment is simulated.The simulation results show that the system can accurately calculate the misalignment values,with an error of less than 5%,and can automatically eliminate the misalignment fault of the diesel engine online.The research results provide theoretical support for the self-recovery regulation of misalignment fault,and due to the universality of structure and principle,the self-recovery system is not only suitable for diesel engine,but also for other rotating machineries.

Study on effect analysis and parameter optimizing of stepless capacity control system on reciprocating compressors

An improved model of reciprocating compressor operation cycle with a stepless capacity control system is presented and influence of the key parameters of the system is evaluated. In the stepless capacity control system of a reciprocating compressor,mechanical unloaders are used to partially hold suction valves open for a certain time during the compression stroke. The typical working process of the reciprocating compressor is changed by capacity regulation apparatus. However,some critical parameters like the hydraulic force acting at the unloader have not been rigorously studied in previous researches. Here an improved numerical model of a double acting reciprocating compressor under the control stepless capacity is proposed and verified by experimental trials. Numerical simulations are carried out to select and evaluate the acting force which definitely has an influence on indicator diagrams of compressors. It is observed that the optimized range of 350 N to 380 N is preferable for the unloader force such that the intensity of opening and closing impacts are minimized.