Analysis of hydraulic pump bearing failure

Hydraulic pump is the power source of the hydraulic system, so the status of the hydraulic pump monitoring and fault diagnosis is particularly important. Bearing failure is one of the common failure modes of hydraulic pumps. Since the additional vibration caused by the bearing failure is weaker than the inherent vibration of the hydraulic pump, it is very difficult to separate the fault information from the signal. Up to now, the diagnosis of hydraulic pump bearing failure is still not very effective method. A feature extraction failure will inevitably lead to additional vibration of the system. The vibration signal is a dynamic signal, it contains a wealth of information, it is suitable for fault diagnosis. However, if the additional vibration signals are submerged due to the interference of the inherent signals or outside interference to the fault signals, how to extract the useful signals from the vibration signals is very crucial. According to tribology theory, when the bearing inner surface of the flow surface, the outer ring raceway and roller there is a damage, the smooth surface of the raceway is damaged, whenever the roller rolls over the injury point, there will be a vibration. Assuming that the bearing part is a rigid body and does not consider the influence of contact deformation, the roller is purely rolled along the raceway, then the following damage vibration frequency: When the inner raceway has a damage, the characteristic frequency of the vibration pulse is: fI = frZ + dcosα / D) / 2 (1) When the outer raceway has a damage, the vibration pulse frequency is: fo = frZ (1-dcosα / D) / 2 (2) When there is a damage on the roller, The characteristic frequency of the vibration pulse is: fR = frD (1 - d2cosα / D2) / d where: fr - speed of inner ring revolution; pitch circle diameter of D- bearing; d - diameter of roller; Z-roller number. In order to overcome the difficulty that bearing fault signal is weak and easily submerged by inherent vibration of hydraulic pump, the following characteristics with strong anti-interference ability are selected as fault diagnosis characteristic parameters. The average energy characteristic of the vibration The vibration acceleration signal measured on the pump body of the hydraulic pump is: a (t) = {a1 (t), a2 (t), ..., an (t)} which is a fault signal Pump after the signal transmission. According to statistical theory, the root mean square of vibration reflects the time domain information of vibration: the characteristic parameter has its effective value representing the vibration signal and reflects the average energy of vibration. Peak characteristic of vibration signal Pp = max {a (t)} (5) This is a characteristic quantity that reflects the periodic pulsation in the vibration signal. The cepstrum envelope feature Let f (t) be the fault excitation signal and h (t) be the impulse response of the transmission channel. Their corresponding Fourier transforms have the following relations: Transform (6) as follows: In the type, τ is called the frequency inversion; (τ) is cepstrum. It can be seen from the above equation that the characteristics of the fault excitation signal and the transmission channel are separated from each other. In general, the fault excitation signal and the transmission channel signal occupy different back-off sections, which can highlight the characteristics of the faulty vibration signal. The Hilbert transform is used to find the envelope of the time-domain signal in signal analysis, in order to smooth the power spectrum and highlight the fault information. Definition signal: the best envelope. Cepstral envelope model is the essence of the signal obtained from the sensor cepstrum analysis, and then its cepstrum signal envelope extraction, which dual highlighted the fault information for the signal to noise ratio of small fault feature extraction provided in accordance with. BP neural network fault diagnosis Due to the complexity of the fault diagnosis system, the application of neural network to fault diagnosis system design will be large-scale neural network organization and learning problems. In order to reduce the complexity of the work and reduce the learning time of the network, this dissertation decomposes the fault diagnosis knowledge set into several logically independent sub-sets, each sub-set is subdivided into a number of rule subsets, and then the network is organized according to the rule subsets. Each rule subset is a logically independent mapping of subnetworks, the relations between the subsets of rules, represented by the matrix of rights of the subnetworks. Each sub-network independently uses BP learning algorithm to study and train respectively. Since the decomposed sub-network is much smaller than the original network and the problem is localized, the training time is greatly reduced. The information processing capability of fault diagnosis of hydraulic pump using integrated BP neural network stems from the nonlinear mechanism characteristics and BP algorithm of neuron. Each sub-network is a BP network. Each sub-network is learned by BP algorithm and the result of learning Integrated by the control network. BP network learning algorithm such as the selection of each feature parameters (including energy features, amplitude features and cepstrum envelope characteristics) x value mapped to a single node in the input and output layer of the neural network, and its regular processing: xi = 0.8 (x-xmin) / (xmax-xmin) +0.1 (8) The purpose of regularity of the eigenparameters to (0.1,0.9) is to avoid the learning curve from converging due to the extreme output of the Sigmoid function The problem. For the regular value obtained from (8), the following operation is performed to obtain the weighted value of each neuron and the threshold: where j represents the current layer, i represents the previous layer, wij represents the connection weight, cj represents the current node threshold ; Fj on behalf of the output. Triple Robustness It is well-known that the human brain has a fault-tolerant property that damage to individual neurons in the brain does not severely degrade its overall performance because each concept in the brain does not exist in only one neuron but rather Spread over many neurons and their connections. By learning again, the brain can re-express knowledge forgotten due to the damage of a part of neurons in the remaining neurons. As the neural network is a simulation of the biological neural network, the most important feature of the neural network is the function of "associative memory". That is to say, the neural network can be composed of the past knowledge, and under the condition of partial information loss or partial information uncertainty, The remaining feature information to make the correct diagnosis. The success rate of correctly diagnosing and recognizing some of the six characteristic information of bearing is given if it is incorrect or uncertain. Neural network Robustness Statistical input feature Uncertainty element Diagnostic success rate One characteristic parameter Uncertainty 100% Two characteristic parameters Uncertainty 94% Three characteristic parameters Uncertainty 76% Four characteristic parameters Uncertainty 70% Five characteristic parameters No Determining 20% ​​of the uncertainty of the six characteristic parameters 8% It can be seen that fault diagnosis using an integrated neural network can have a fairly high success rate in the event that a large amount of information is lost (nearly half the uncertainty of the characteristic parameters) can still be correctly judged 76% ~ 100%) Therefore integrated neural network has strong ability. Conclusion: Since neural network has many functions such as self-learning, self-organizing and associative memory, the neural network method is very suitable for fault diagnosis research. In this paper, the vibration signals in the frequency domain and the scrambling frequency domain are taken as the characteristic parameters, and the multi-fault diagnosis and identification of the hydraulic pump bearing is realized by the integrated BP network. Experimental results show that this method has high success rate and robustness.