Modern fault diagnosis method for electrical equipment
Coconut Shell Pyrolysis Plant turns coconut shell into mostly charcoal, some biomass, and little bio-oil, which is totally an environmental friendly project.
Coconut Shell Pyrolysis Plant Coconut Shell Pyrolysis Plant,Coconut Shell Carbonization Plant,Coconut Shell Carbonization Machine,Activated Carbon From Coconut Shell Henan Lanning Technology Co., Ltd , https://www.lanningrecycling.com
With the development of economic construction and the improvement of electrification, electrical equipment has been widely used in various fields of industrial production. It is an important measure to ensure the safe operation of production in a timely and accurate manner. Therefore, studying the theory and technology of fault diagnosis of electrical equipment in different occasions and different operating conditions is the guarantee for the reliable operation of equipment. The motor equipment is the basic component that constitutes the power supply and power supply system. During operation, it is affected by various factors such as electricity, thermomechanical and surrounding environment, and its performance is gradually degraded, eventually leading to failure; in case of failure, even if it stops working Extremely short, it also causes a lot of damage. Generally, these faults are always manifested in various signs, and the types of faults are also diverse: both slow and sudden faults, electrical faults and mechanical faults; There are linear system faults and nonlinear system faults, and the relationship is complicated. This brings certain difficulties to the effective and rapid diagnosis of motor equipment faults. This paper describes the basic principles of fault diagnosis of electrical equipment and the domestic and international Modern fault diagnosis methods, and analysis of various diagnostic methods, pointed out the development trend of motor equipment fault diagnosis technology 2 motor equipment fault diagnosis principle The operation of motor equipment is affected by many factors, such as grid voltage, load nature, installation environment, product Quality, etc., harsh environments and super-technical range operations are causing malfunctions The main reason for the production of electrical equipment is based on electromagnetic theory, which is mainly composed of two parts: circuit (winding) and magnetic circuit (core). The transformer is a stationary device, and the motor is a rotating device, and their fault formation process and The form of expression has the same in many respects: the winding overheating of the equipment, the aging of the insulation, the deformation of the core and the eccentricity of the rotor of the motor. These signs are gradually deteriorating and losing the original performance. Effectively and timely through various detection techniques and signal analysis theory. Separating abnormal state information and diagnosing hidden troubles are important measures to achieve reliable operation, reduce maintenance rate, and improve production efficiency. The basic principles of motor equipment fault diagnosis are as follows: 1) Current analysis method uses signal analysis methods such as spectrum to load current The waveform is detected to diagnose the cause and extent of the fault of the motor equipment; 2) The insulation diagnostic method uses various electrical test devices and diagnostic techniques to judge whether the insulation performance of the electrical equipment is defective, and predicts the insulation life. ; 3) Temperature detection method using various temperatures The method of measuring the temperature rise of each part of the motor equipment, the temperature rise of the motor is related to various fault phenomena; 4) The vibration and noise diagnosis method detects the vibration and noise of the motor equipment, and processes the acquired signal to diagnose The cause and location of the motor failure, especially for the diagnosis of mechanical damage. 3 Modern fault diagnosis method for motor equipment 3.1 Diagnosis method based on signal transformation Many fault information of motor equipment exists in the form of modulation in the monitored Among the electrical signals and vibration signals, if the signals are demodulated by some transformation, the fault characteristic information can be easily obtained to determine the type of faults occurring in the motor equipment. The commonly used signal transformation method has the Hilbert transform. And wavelet transform> 9. Hilbert transform specific definition can be seen, using Hilbert transform to achieve motor bearing and induction motor rotor fault diagnosis. Wavelet transform is both time-scale analysis and time-frequency analysis. It has multi-resolution characteristics and has the ability to characterize local features of signals in both time-frequency domains. It uses singular points of wavelet transform (such as zero-crossing and extreme points). The comprehensive performance at multiple scales is used to detect local abrupt points of the signal for fault diagnosis. By pre-processing the stator current and performing the second wavelet transform, the fault characteristics of the stator winding of the motor are effectively extracted, and the diagnosis result of the stator current change caused by the sudden change of the external load and the external current asymmetry is almost unaffected by the load. Effective and reliable online diagnosis of motor faults. The fault diagnosis method of wavelet transform is used to accurately diagnose the single-phase short-circuit fault of synchronous motor. The fault diagnosis of the motor bearing of the shearer of the shearer is realized by wavelet transform. The online fault diagnosis of the transformer is realized by wavelet transform. The fault diagnosis method based on signal transformation has achieved many results in the practical application of motor equipment fault diagnosis; especially the wavelet transform, which is very suitable for detecting transient anomalies entrained in normal signal analysis and showing its composition, mechanical failure in electrical equipment Diagnostics occupies an important position. However, the diagnostic method based on signal transformation lacks the learning function. 3.2 The diagnostic method based on the expert system The diagnostic method based on the expert system is based on the previous experience of the experts of the system being diagnosed, and is classified into rules, and the rule of reason is used to diagnose the fault by using empirical rules. . This method is used to establish a camera fault diagnosis expert system, set the camera fault cause set rotor imbalance, oil film oscillation, shaft misalignment, shaft crack, frequency doubling resonance, frequency division resonance, stator voltage too high, stator current If the temperature is too high, the fault symptom signal uses a noise signal. By spectrum analysis of the noise signal, the characteristic spectrum is extracted. When a certain fault occurs, it must be reflected on the spectrum map, but the correspondence is from the book and It is difficult to find the scene, for this reason, through the previous "experience" of the camera diagnostics experts and troubleshooting. The system also adopts a self-learning control strategy, improves the knowledge base, and increases the system's self-diagnosis capability, thereby greatly improving the rapidity and accuracy of diagnosis. The diagnostic method based on the expert system has the advantages of simple and rapid diagnosis process, but also has limitations. The method based on expert system belongs to inversion reasoning, so it is not a reasoning method to ensure uniqueness. This method has the bottleneck of acquiring knowledge. The connection between the symptoms observed by complex systems and the corresponding faults is quite complicated. Expert experience is often not a single rule and is quite difficult. Therefore, this method is not suitable for fault diagnosis of complex electrical equipment or new and unexperienced electrical equipment. In addition, rule-based methods are used in addition to repeated rules for diagnosis. No further explanation can be made, usually only a single fault can be diagnosed, it is difficult to diagnose multiple scams. 3.3 Based on the fuzzy theory of diagnostic methods In the field of fault diagnosis, fuzzy attributes often appear, such as the description of the symptoms: temperature "high", vibration " "very powerful" and so on have fuzzy characteristics; faults and signs Fuzzy theory is the best tool for dealing with such problems. There are two methods for fuzzy fault diagnosis. One is to establish the causal relationship matrix R between the symptom and the fault type, and then establish the fuzzy relation equation of fault and symptom, ie F= At this time, F is a fuzzy fault vector; S is a fuzzy symptom vector: "." is a fuzzy synthetic operator, which is a diagnostic method based on fuzzy relation and synthetic algorithm. Another method first establishes the fuzzy rule base of faults and symptoms, and then performs the fuzzy logic reasoning diagnosis process. This is a kind of diagnosis method based on knowledge processing. Method 1 is used to realize the fault diagnosis of the squirrel cage induction motor bearing; The fuzzy rule base of motor stator current and stator winding fault is established by method 2. The online diagnosis of stator winding fault is realized by fuzzy reasoning. The fuzzy linguistic variable is close to natural language, the knowledge representation is readable, and the fuzzy reasoning logic is strict. The human thinking process is easy to explain. However, it is difficult to obtain fuzzy diagnostic knowledge, especially the fuzzy relationship between faults and signs. The diagnostic ability of the system depends on the fuzzy knowledge base, and the learning ability is poor, which is prone to missed diagnosis and misdiagnosis. In addition, since fuzzy linguistic variables are represented by fuzzy numbers (ie membership degree), how to realize the transformation between linguistic variables and fuzzy numbers is a difficult point in implementation. However, it is a kind of introduction of fuzzy theory into the field of fault diagnosis. Inevitable trend in line with the nature of things.
3.4 Artificial Neural Network-Based Diagnostic Method Artificial neural network (ANN) is a complex nonlinear system that is widely connected by a large number of simple processing units. It has learning ability, adaptive ability, and nonlinear approximation ability. The task of fault diagnosis is the mapping from symptom to fault type from the perspective of mapping. Using ANN technology to deal with fault diagnosis problems can not only identify complex fault diagnosis modes, but also perform fault severity assessment and so that the system continuously acquires new knowledge during the operation process. Modify the rules: Obstacle prediction Because lANgN can automatically acquire diagnostic knowledge The Ml system has adaptive capabilities.
Applying ANN to motor equipment fault diagnosis is one of the hotspots of current motor equipment fault diagnosis. The basic idea of ​​using BP network to diagnose the fault of motor equipment is to use the sensor to obtain the characteristic signal characterizing the fault of the motor equipment. The rotor current is used as the characteristic signal, and the electrical fault diagnosis of the motor equipment is mainly used, and the noise of the motor equipment is taken as the characteristic signal. The mechanical fault diagnosis of the electrical equipment is mainly used; then the FFT transform is performed on the acquired characteristic signals, and the magnitude and proportional relationship of the feature quantities in the characteristic frequency bands in the frequency can reflect the corresponding fault types, thus utilizing several peak energy in the characteristic signal spectrum. The value is used as the input sample of the neural network, and the corresponding fault type is used as the output sample of the neural network. The network is learned by the BI algorithm to obtain the mapping relationship between the input sample (feature signal) and the output sample (fault type). The use of neural network's associative memory and distributed processing functions to diagnose motor equipment faults BP network has strong nonlinear approximation ability, can identify fault patterns, and can also assess and predict the severity of faults, so it is widely used. However, because the BP algorithm uses the gradient descent method in iteration, there are problems such as slow convergence, oscillation and local minimum. In addition, a prominent problem of BP algorithm for fault diagnosis is that it has low processing ability for abnormal faults and no increment. The learning function can be mainly because the BP algorithm is interpolated in mathematics in nature, and its ability to solve problems is extremely dependent on the sample; when a new fault type with a large difference from the sample occurs, it is often attributed to one. Known types of faults or judged as normal, resulting in misdiagnosis or missed diagnosis, affecting the reliability of diagnosis. Therefore, the BP network is currently used to diagnose motor equipment faults using various BP improved algorithms. 3.5 Based on integrated intelligent system diagnosis Methods With the increasing complexity of electrical equipment systems, it is difficult to meet the fault diagnosis requirements of complex electrical equipment by relying on a single fault diagnosis technology. Therefore, the integrated intelligent diagnostic system formed by the integration of the above various diagnostic technologies has become the current fault diagnosis research of electrical equipment. Hot spot. The main integration technologies are: the combination of rule-based expert system and ANN, the combination of fuzzy logic and ANN, the combination of chaos theory and ANN, and the combination of fuzzy neural network and expert system. The combination of expert systems and neural networks can make full use of the expert experience of expert systems and the powerful nonlinear mapping capabilities of neural networks.
The computer's reasoning ability and the causal relationship within the system, while considering the existence of a large number of unknown situations and the influence of knowledge inaccuracy, combined, successfully applied to the camera fault diagnosis fuzzy neural network technology is to digitize human experience and knowledge. Fuzzy processing, transforming rules and inference into neural network mapping processing and extracting empirical rules directly from data samples, and then combining these two transformations for intelligent information processing technology makes full use of the characteristics of neural network processing digital knowledge and Fuzzy logic is applied to the knowledge of structured knowledge. The fuzzy neural network is applied to the fault diagnosis of brushless DC motor. The structure and learning algorithm of fuzzy neural network are given. A threshold vector fault diagnosis method is proposed. The simulation results show that the method The effectiveness of a neural network composed of chaotic neural network neurons, through the study of its nonlinear dynamic characteristics, chaotic attractor trajectory and sensitivity to initial conditions, to achieve dynamic associative memory of chaotic neural networks, here On the basis of success
4 The development trend of motor equipment fault diagnosis technology is due to the accurate and timely diagnosis of motor equipment faults to ensure the safety and stability of production, to avoid the huge loss of personnel and property. The fault diagnosis technology is a cross-disciplinary science, since the 1960s, In the traditional method, the rapid development, new theory and modern fault diagnosis methods have emerged: wavelet transform expert system, fuzzy system, neural network, etc. have been successfully diagnosed in the field of fault diagnosis due to motor equipment fault signs and fault characteristics The complex nonlinear characteristics make the fault diagnosis and identification more complicated. It is impossible to accurately and timely diagnose the fault of the motor equipment in a complex environment by a theory or a method. Therefore, the integrated intelligent fault diagnosis system is bound to be New Trends in Motor Equipment Fault Diagnosis Technology In addition, no matter what diagnostic method, the acquisition of real signals is the prerequisite for successful fault diagnosis. Multi-sensor data fusion theory will play an important role in fault diagnosis. Research and achieve corresponding results
The charcoal from it could be widely used for barbecue charcoal, Shisha charcoal or Hookah charcoal etc.
The charcoal pyrolysised directly from pyrolysis plant could last for a long time without any chemicals or adhesive inisde. when used as barbecue charcoal directly, it is quite goodto our human health.
While the boioil could be used as food for animals, which is also quite healthy and nourishing; also could be used as a kind of industry cleanser.
Then the gas generated from system could be used as fuel for pyrolysis plant, which saves lots of outside energy(only required at the first several hours).
At the the end, all the smoking from system could be drawn into dedusting system by Draft Fan, before discharging it is completely environmental.
