Application of the CatBoost Model for Stirred Reactor State Monitoring Based on Vibration Signals

Stirred reactors are key equipment in production,and unpredictable failures will result in significant economic losses and safety issues.Therefore,it is necessary to monitor its health state.To achieve this goal,in this study,five states of the stirred reactor were firstly preset:normal,shaft bending,blade eccentricity,bearing wear,and bolt looseness.Vibration signals along x,y and z axes were collected and analyzed in both the time domain and frequency domain.Secondly,93 statistical features were extracted and evaluated by ReliefF,Maximal Information Coefficient(MIC)and XGBoost.The above evaluation results were then fused by D-S evidence theory to extract the final 16 features that are most relevant to the state of the stirred reactor.Finally,the CatBoost algorithm was introduced to establish the stirred reactor health monitoring model.The validation results showed that the model achieves 100%accuracy in detecting the fault/normal state of the stirred reactor and 98%accuracy in diagnosing the type of fault.

FEATURE EXTRACTION OF VIBRATION SIGNALS BASED ON WAVELET PACKET TRANSFORM

A method is proposed for the analysis of vibration signals from components ofrotating machines, based on the wavelet packet transformation (WPT) and the underlying physicalconcepts of modulation mechanism. The method provides a finer analysis and better time-frequencylocalization capabilities than any other analysis methods. Both details and approximations are splitinto finer components and result in better-localized frequency ranges corresponding to each node ofa wavelet packet tree. For the punpose of feature extraction, a hard threshold is given and theenergy of the coefficients above the threshold is used, as a criterion for the selection of the bestvector. The feature extraction of a vibration signal is accomplished by computing thereconstruction signal and its spectrum. When applied to a rolling bear vibration signal featureextraction, the proposed method can lead to be very effective.

An algorithm to remove noise from locomotive bearing vibration signal based on self-adaptive EEMD filter

An improved ensemble empirical mode decomposition(EEMD) algorithm is described in this work, in which the sifting and ensemble number are self-adaptive. In particular, the new algorithm can effectively avoid the mode mixing problem. The algorithm has been validated with a simulation signal and locomotive bearing vibration signal. The results show that the proposed self-adaptive EEMD algorithm has a better filtering performance compared with the conventional EEMD. The filter results further show that the feature of the signal can be distinguished clearly with the proposed algorithm, which implies that the fault characteristics of the locomotive bearing can be detected successfully.

Analysis and Simulation for Planetary Gear Fault of Helicopter Based on Vibration Signal

Fault diagnosis for helicopter's main gearbox based on vibration signals by experiments always requires high costs. To solve this problem,a helicopter's planetary gear system is taken as an example. Firstly,a simulation model is established by McFadden,and analyzed under ideal condition. Then this model is developed and improved as the delay-time model of the vibration signal which determines the phase-change of sidebands when the system is running. The cause and change-rules of planetary gear system's vibration signal are analyzed to establish the fault diagnosis model.At the same time,the vibration signal of fault condition is simulated and analyzed. This simulation method can provide a reference for fault monitoring and diagnosis for planetary gear system.

New Method to Measure the Fill Level of the Ball Mill Ⅱ-Analysis of the Vibration Signals

The exact measurement of the fill level is the key and basic problem for automatic control and optimized operation of the coal pulverizing system. Because the ball mill pulverizing system is non-linearity, long time delay and time-varying, the reliable and effective method for measuring the fill level was lacked at present. In order to reduce the influence by various factors on measuring the fill level and improve the measuring accuracy of the fill level, a novel characteristic variable is proposed. A set of wireless transmission device was designed to record vibration signals, and an accelerometer with high accuracy and large measuring range was mounted directly on the mill shell to pick up the vibration signals from the mill shell. A series of data acquisition experiments under various ball load and water content of coal conditions were conducted in an industrial mill to investigate the relationship between the fill level and the angular position of the maximum vibration point of the mill shell through the analysis of the vibration signals. The analytical result of test data clearly show that the angular position of the maximum vibration point on the mill shell decreases as the fill level increases. At the same time, comparing with the traditional characteristic variable, the feature variable of the fill level proposed in this paper is not subject to the effect of the ball load and water content of coal, which provides a new solution and reliable basis for the accurate measurement of the fill level.

Weighted Multi-sensor Data Level Fusion Method of Vibration Signal Based on Correlation Function

As the differences of sensor＇s precision and some random factors are difficult to control,the actual measurement signals are far from the target signals that affect the reliability and precision of rotating machinery fault diagnosis.The traditional signal processing methods,such as classical inference and weighted averaging algorithm usually lack dynamic adaptability that is easy for trends to cause the faults to be misjudged or left out.To enhance the measuring veracity and precision of vibration signal in rotary machine multi-sensor vibration signal fault diagnosis,a novel data level fusion approach is presented on the basis of correlation function analysis to fast determine the weighted value of multi-sensor vibration signals.The approach doesn＇t require knowing the prior information about sensors,and the weighted value of sensors can be confirmed depending on the correlation measure of real-time data tested in the data level fusion process.It gives greater weighted value to the greater correlation measure of sensor signals,and vice versa.The approach can effectively suppress large errors and even can still fuse data in the case of sensor failures because it takes full advantage of sensor＇s own-information to determine the weighted value.Moreover,it has good performance of anti-jamming due to the correlation measures between noise and effective signals are usually small.Through the simulation of typical signal collected from multi-sensors,the comparative analysis of dynamic adaptability and fault tolerance between the proposed approach and traditional weighted averaging approach is taken.Finally,the rotor dynamics and integrated fault simulator is taken as an example to verify the feasibility and advantages of the proposed approach,it is shown that the multi-sensor data level fusion based on correlation function weighted approach is better than the traditional weighted average approach with respect to fusion precision and dynamic adaptability.Meantime,the approach is adaptable and easy to use,can be applied to other areas of vibration measurement.

PARAMETER IDENTIFICATION IN OFFSHORE PLATFORM USING ARMA MODEL AND TECHNOLOGY OF EXTRACTING FREE VIBRATION SIGNAL

A procedure for identifying the dynamic parameter of offshore platform is presented. The present procedure consists of two key features. First uses random decrement (RD) technology to extract free vibration signal in strong noise environment in which it may not white noise. Second technology which called autoregressive moving average (ARMA) was used to model the data treated by the random decrement method. In order to get rid of the color noise in the output signal response from the offshore platform an imaginary system is added in RD system and make the course of extracting performed under the state of color input by choosing the breakover condition and lead time. For eliminating multi_values of parameters identified, an updating moving average method is used. The dynamic parameters of structure under arbitrary input are identified. Example of the method as applied to a scale_model offshore platform was used to evaluate the technology of efficiency and the value of on_line.

A Comparative Study of Bayes Classifiers for Blade Fault Diagnosis in Wind Turbines through Vibration Signals

Renewable energy sources are considered much in energy fields because of thecontemporary energy calamities. Among the important alternatives being considered, windenergy is a durable competitor because of its dependability due to the development of theinnovations, comparative cost effectiveness and great framework. To yield wind energymore proficiently, the structure of wind turbines has turned out to be substantially bigger,creating conservation and renovation works troublesome. Due to various ecologicalconditions, wind turbine blades are subjected to vibration and it leads to failure. If thefailure is not diagnosed early, it will lead to catastrophic damage to the framework. In orderto increase safety observations, to reduce down time, to bring down the recurrence ofunexpected breakdowns and related enormous maintenance, logistic expenditures and tocontribute steady power generation, the wind turbine blade must be monitored now andthen to assure that they are in good condition. In this paper, a three bladed wind turbinewas preferred and using vibration source, the condition of a wind turbine blade is examined.The faults like blade crack, erosion, hub-blade loose connection, pitch angle twist and bladebend faults were considered and these faults are classified using Bayes Net (BN),Discriminative Multinomial Naïve Bayes (DMNB), Naïve Bayes (NB), Simple NaïveBayes (SNB), and Updateable Naïve Bayes (UNB) classifiers. These classifiers arecompared and better classifier is suggested for condition monitoring of wind turbine blades.

A Fault Feature Extraction Model in Synchronous Generator under Stator Inter-Turn Short Circuit Based on ACMD and DEO3S

This paper proposed a new diagnosis model for the stator inter-turn short circuit fault in synchronous generators.Different from the past methods focused on the current or voltage signals to diagnose the electrical fault,the sta-tor vibration signal analysis based on ACMD(adaptive chirp mode decomposition)and DEO3S(demodulation energy operator of symmetrical differencing)was adopted to extract the fault feature.Firstly,FT(Fourier trans-form)is applied to the vibration signal to obtain the instantaneous frequency,and PE(permutation entropy)is calculated to select the proper weighting coefficients.Then,the signal is decomposed by ACMD,with the instan-taneous frequency and weighting coefficient acquired in the former step to obtain the optimal mode.Finally,DEO3S is operated to get the envelope spectrum which is able to strengthen the characteristic frequencies of the stator inter-turn short circuit fault.The study on the simulating signal and the real experiment data indicates the effectiveness of the proposed method for the stator inter-turn short circuit fault in synchronous generators.In addition,the comparison with other methods shows the superiority of the proposed model.

Adaptive Variational Mode Decomposition for Bearing Fault Detection

Rolling element bearings are commonly used in rotary mechanical and electrical equipment. According to investigation, more than half of rotating machinery defects are related to bearing faults. However, reliable bearing fault detection still remains a challenging task, especially in industrial applications. The objective of this work is to propose an adaptive variational mode decomposition (AVMD) technique for non-stationary signal analysis and bearing fault detection. The AVMD includes several steps in processing: 1) Signal characteristics are analyzed to determine the signal center frequency and the related parameters. 2) The ensemble-kurtosis index is suggested to decompose the target signal and select the most representative intrinsic mode functions (IMFs). 3) The envelope spectrum analysis is performed using the selected IMFs to identify the characteristic features for bearing fault detection. The effectiveness of the proposed AVMD technique is examined by experimental tests under different bearing conditions, with the comparison of other related bearing fault techniques.

Intelligent Fault Diagnosis of Rotary Machinery Based on Unsupervised Multiscale Representation Learning

The performance of traditional vibration based fault diagnosis methods greatly depends on those hand- crafted features extracted using signal processing algo- rithms, which require significant amounts of domain knowledge and human labor, and do not generalize well to new diagnosis domains. Recently, unsupervised represen- tation learning provides an alternative promising solution to feature extraction in traditional fault diagnosis due to its superior learning ability from unlabeled data. Given that vibration signals usually contain multiple temporal struc- tures, this paper proposes a multiscale representation learning （MSRL） framework to learn useful features directly from raw vibration signals, with the aim to capture rich and complementary fault pattern information at dif- ferent scales. In our proposed approach, a coarse-grained procedure is first employed to obtain multiple scale signals from an original vibration signal. Then, sparse filtering, a newly developed unsupervised learning algorithm, is applied to automatically learn useful features from each scale signal, respectively, and then the learned features at each scale to be concatenated one by one to obtain multi- scale representations. Finally, the multiscale representa- tions are fed into a supervised classifier to achieve diagnosis results. Our proposed approach is evaluated using two different case studies： motor bearing and wind turbine gearbox fault diagnosis. Experimental results show that the proposed MSRL approach can take full advantages of the availability of unlabeled data to learn discriminative features and achieved better performance with higher accuracy and stability compared to the traditional approaches.

Blast-induced rock damage control in Fangchenggang nuclear power station, China

In the process of blasting excavation, stress wave propagation and gas expansion can basically induce damage to surrounding rocks, which is detrimental to rock mass integrity and engineering safety. In this case, evaluation and control of blast-induced effects are essential to the safety of nearby buildings and integrity of bedrock in blasting field. In Fangchenggang nuclear power station of China, the drill-and- blast method was employed for bedrock excavation. In order to reduce the blast-induced damage zone, the wave propagation and associated damage to rock mass should be carefully investigated. In this paper, the wave propagation regressively obtained from field monitoring data was presented based on empirical formula （e.g. Sadovsloj formula）. The relationship between the peak particle velocity （PPV） at a distance of 30 m away from the charge hole and charge per delay in blast design was derived. Meanwhile, the acoustic tests before and after blasting were conducted to determine the damage depth of rock mass. The charge per delay in blast design was then calibrated based on the blast-induced wave propagation regularity. The results showed that a satisfactory effect was achieved on blast-induced damage control of rock mass. This could be helpful to rock damage control in similar blasting projects.

Aero-Engine Surge Fault Diagnosis Using Deep Neural Network

Deep learning techniques have outstanding performance in feature extraction and modelfitting.In thefield of aero-engine fault diagnosis,the intro-duction of deep learning technology is of great significance.The aero-engine is the heart of the aircraft,and its stable operation is the primary guarantee of the aircraft.In order to ensure the normal operation of the aircraft,it is necessary to study and diagnose the faults of the aero-engine.Among the many engine fail-ures,the one that occurs more frequently and is more hazardous is the wheeze,which often poses a great threat toflight safety.On the basis of analyzing the mechanism of aero-engine surge,an aero-engine surge fault diagnosis method based on deep learning technology is proposed.In this paper,key sensor data are obtained by analyzing different engine sensor data.An aero-engine surge data-set acquisition algorithm(ASDA)is proposed to sample the fault and normal points to generate the training set,validation set and test set.Based on neural net-work models such as one-dimensional convolutional neural network(1D-CNN),convolutional neural network(RNN),and long-short memory neural network(LSTM),different neural network optimization algorithms are selected to achieve fault diagnosis and classification.The experimental results show that the deep learning technique has good effect in aero-engine surge fault diagnosis.The aero-engine surge fault diagnosis network(ASFDN)proposed in this paper achieves better results.Through training,the network achieves more than 99%classification accuracy for the test set.

Wavelet Transform and Neural Networks in Fault Diagnosis of a Motor Rotor

In the motor fault diagnosis technique, vibration and stator current frequency components of detection are two main means. This article will discuss the signal detection method based on vibration fault. Because the motor vibration signal is a non-stationary random signal, fault signals often contain a lot of time-varying, burst proper- ties of ingredients. The traditional Fourier signal analysis can not effectively extract the motor fault characteristics, but are also likely to be rich in failure information but a weak signal as noise. Therefore, we introduce wavelet packet transforms to extract the fault characteristics of the signal information. Obtained was the result as the neural network input signal, using the L-M neural network optimization method for training, and then used the BP net- work for fault recognition. This paper uses Matlab software to simulate and confirmed the method of motor fault di- agnosis validity and accuracy

A Correlation Coefficient Approach for Evaluation of Stiffness Degradation of Beams Under Moving Load

This paper presents a new approach using correlation and cross-correlation coefficients to evaluate the stiffness degradation of beams under moving load.The theoretical study of identifying defects by vibration methods showed that the traditional methods derived from the vibration measurement data have not met the needs of the actual issues.We show that the correlation coefficients allow us to evaluate the degree and the effectiveness of the defects on beams.At the same time,the cross-correlation model is the basis for determining the relative position of defects.The results of this study are experimentally conducted to confirm the relationship between the correlation coefficients and the existence of the defects.In particular,the manuscript shows that the sensitivity of the correlation coefficients and cross-correlation is much higher than the parameters such as changes in stiffness(EJ)and natural frequency values(Δf).This study suggests using the above parameters to evaluate the stiffness degradation of beams by vibration measurement data in practice.

Feature-Based Vibration Monitoring of a Hydraulic Brake System Using Machine Learning

Hydraulic brakes in automobiles are an important control component used not only for the safety of the passenger but also for others moving on the road.Therefore,monitoring the condition of the brake components is inevitable.The brake elements can be monitored by studying the vibration characteristics obtained from the brake system using a proper signal processing technique through machine learning approaches.The vibration signals were captured using an accelerometer sensor under a various fault condition.The acquired vibration signals were processed for extracting meaningful information as features.The condition of the brake system can be predicted using a feature based machine learning approach through the extracted features.This study focuses on a mechatronics system for data acquisitions and a signal processing technique for extracting features such as statistical,histogram and wavelets.Comparative results have been carried out using an experimental study for finding the effectiveness of the suggested signal processing techniques for monitoring the condition of the brake system.

Research on full-period acquisition method for diesel engine based on self-adaptive correlation analysis

Full-period signal acquisition of vibration signal plays a vital role in the health monitoring and fault diagnosis of modern industrial equipment group. The traditional full-period signal acquisition methods usually need not only a reference signal generated from special key phase device but also a reserved position, which is only suitable for a small number of particular equipment. A novel full-period signal acquisition method without key phase is proposed to construct the time-frequency method with strong energy concentration called the synchrosqueezing generalized S-Transform(SGST), combining together the Teager energy operator(TEO) and self-adaptive correlation analysis(SACA) based on the vibration signals of both gear and cylinder head. Actual vibration signals of diesel engine are employed to verify the feasibility and effectiveness of the proposed method by comparing with traditional method with special key phase device. By comparisons, the results show that full-period signal acquisition method without key phase has approximate accuracy for diesel engine under different working conditions.

New Method for Building Vector of Diagnostic Signs to Classify Technical States of Marine Diesel Engine by Torsional Vibrations on Shaft-Line

Vector of diagnostic signs(VDS)using torsional vibration(TV)signal on the main propulsion plant(MPP)is the vector of z maxima(or minima)values of the TV signal in accordance with the cylinder firing orders.The technical states of the marine diesel engine(MDE)include R=z+1 classes and are presented in z-dimensional space coordinate of VDS.The presentation of Dk,k=1÷R using z diagnostic signs(Vi,i=1÷z)is nonfigurative and quite complicated.This paper aims to develop a new method for converting VDS from z-dimensional to 2-dimensional space(two-axes)based on the firing orders of the diesel cylinders,as an equivalent geometrical sign of the all diagnostic signs.The proposed model is useful for presenting a technical state Dk in two-dimensional space(x,y)for better visualization.The paper verifies the simulation of the classification illustration of the 7–state classes for the MDE 6S46-MCC,installed on the motor vessel(MV)34000DWT,using the new above mentioned method.The seven technical state classes(for 6-cylinder MDE,z=6)are drawn separately and visually in the Descartes.The received results are valuable to improve smart diagnostic system for analyzing normal/misfire states of cylinders in operation regimes.

Deep-learning-assisted online surface roughness monitoring in ultraprecision fly cutting

Surface roughness is one of the most critical attributes of machined components,especially those used in high-performance systems.Online surface roughness monitoring offers advancements comparable to post-process inspection methods,reducing inspection time and costs and concurrently reducing the likelihood of defects.Currently,online monitoring approaches for surface roughness are constrained by several limitations,including the reliance on handcrafted feature extraction,which necessitates the involvement of human experts and entails time-consuming processes.Moreover,the prediction models trained under one set of cutting conditions exhibit poor performance when applied to different experimental settings.To address these challenges,this work presents a novel deep-learning-assisted online surface roughness monitoring method for ultraprecision fly cutting of copper workpieces under different cutting conditions.Tooltip acceleration signals were acquired during each cutting experiment to develop two datasets,and no handcrafted features were extracted.Five deep learning models were developed and evaluated using standard performance metrics.A convolutional neural network stacked on a long short-term memory network outperformed all other network models,yielding exceptional results,including a mean absolute percentage error as low as 1.51%and an R2value of 96.6%.Furthermore,the robustness of the proposed model was assessed via a validation cohort analysis using experimental data obtained using cutting parameters different from those previously employed.The performance of the model remained consistent and commendable under varied conditions,asserting its applicability in real-world scenarios.

Comparison of different techniques for time-frequency analysis of internal combustion engine vibration signals

In this study,we report an analysis of cylinder head vibration signals at a steady engine speed using short-time Fourier transform(STFT).Three popular time-frequency analysis techniques,i.e.,STFT,analytic wavelet transform(AWT) and S transform(ST),have been examined.AWT and ST are often applied in engine signal analyses.In particular,an AWT expression in terms of the quality factor Q and an analytical relationship between ST and AWT have been derived.The time-frequency resolution of a Gaussian function windowed STFT was studied via numerical simulation.Based on the simulation,the empirical limits for the lowest distinguishable frequency as well as the time and frequency resolutions were determined.These can provide insights for window width selection,spectrogram interpretation and artifact identification.Gaussian function windowed STFTs were applied to some cylinder head vibration signals.The spectrograms of the same signals from ST and AWT were also determined for comparison.The results indicate that the uniform resolution feature of STFT is not necessarily a disadvantage for time-frequency analysis of vibration signals when the engine is in stationary state because it can more accurately localize the frequency components excited by transient excitations without much loss of time resolution.