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.

Underground vibration signal detection and processing system based on LabWindows/CVI

In order to detect and process underground vibration signal, this paper presents a system with the combination of software and hardware. The hardware part consists of sensor, memory chips, USB, etc. , which is responsible for capturing original signals from sensors. The software part is a virtual oscilloscope based on LabWindows/CVI （C vitual instrument）, which not only has the functions of traditional oscilloscope but also can analyze and process vibration signals in special ways. The experimental results show that the designed system is stable, reliable and easy to be operated, which can meet practical requirements.

APPLICATION OF IMPROVED EMD IN VIBRATION SIGNAL FEATURE EXTRACTION OF VEHICLE

In order to truly obtain the feature extraction of vibration signals under the strong background noise, the analysis and improvement of empirical mode decomposition （EMD） is carried on. After that, the improved EMD is applied to the feature extraction of vehicle vibration signals. First, the multi-autocorrelation method is adopted in each input signal,so the noise is reduced effectively. Then, EMD is used to deal with these signals,and the intrinsic mode functions （IMFs） are obtained. Finally, for obtaining the feature information of these signals, the Hilbert transformation and the spectrum analysis are performed in some IMFs. Theoretical analysis and ex- periment verify the effectiveness of the method, which are valuable reference for the same engineering problems.

Theoretical analysis of adaptive harmonic window and its application in frequency extraction of vibration signal

The goal of this paper is to find an excellent adaptive window function for extracting the weak vibration signal and high frequency vibration signal under strong noise.The relationship between windowing transform andfiltering is analyzed first in the paper.The advantage of adjustable time-frequency window of wavelet transform is introduced.Secondly the relationship between harmonic wavelet and multiple analytic band-pass filter is analyzed.The coherence of the multiple analytic band-pass filter and harmonic wavelet base function is discussed,and the characteristic that multiple analytic band-pass filter included in the harmonic wavelet transform is founded.Thirdly,by extending the harmonic wavelet transform,the concept of the adaptive harmonic window and its theoretical equation without decomposition are put forward in this paper.Then comparing with the Hanning window,the good performance of restraining side-lobe leakage possessed by adaptive harmonic window is shown,and the adaptive characteristics of window width changing and analytical center moving of the adaptive harmonic window are presented.Finally,the proposed adaptive harmonic window is applied to weak signal extraction and high frequency orbit extraction of high speed rotor under strong noise,and the satisfactory results are achieved.The application results show that the adaptive harmonic window function can be successfully applied to the actual engineering signal processing.

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.

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.

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.

Compression techniques of mechanical vibration signals based on optimal sparse representations

This paper presents the result of an experimental study on the compression of mechanical vibration signals. The signals are collected from both rotating and reciprocating machineries by the accelerometers and a data acquisition （DAQ） system. Four optimal sparse representation methods for compression have been considered including the method of frames （ MOF）, best orthogonal basis （ BOB）, matching pursuit （MP） and basis pursuit （BP）. Furthermore, several indicators including compression ratio （CR）, mean square error （MSE）, energy retained （ER） and Kurtosis are taken to evaluate the performance of the above methods. Experimental results show that MP outperforms other three methods.

A method to compress vibration signals using wavelet packet transformation combined with sub-band vector quantization

A novel compression method for mechanical vibrating signals,binding with sub-band vector quantization(SVQ) by wavelet packet transformation(WPT) and discrete cosine transformation(DCT) is proposed.Firstly,the vibrating signal is decomposed into sub-bands by WPT.Then DCT and adaptive bit allocation are done per sub-band and SVQ is performed in each sub-band.It is noted that,after DCT,we only need to code the first components whose numbers are determined by the bits allocated to that sub-band.Through an actual signal,our algorithm is proven to improve the signal-to-noise ratio(SNR) of the reconstructed signal effectively,especially in the situation of lowrate transmission.

Wavelet basis construction method based on separation blast vibration signal

As wavelet basis in wavelet analysis is neither arbitrary nor unique,the same signal dealing with different wavelet bases will generate different results.Therefore,how to construct a wavelet basis suitable for the characteristics of the analyzed signal and solve its algorithm and realization is a fundamental problem which perplexed many researchers.To solve these problems,in accordance with the basic features of the measured millisecond blast vibration signal,a new wavelet basis construction method based on the separation blast vibration signal is proposed,and the feasibility of this method is verified by comparing the practical effect of the newly constructed wavelet with other known wavelets in signal processing.

Damage Diagnosis of Bleacher Based on an Enhanced Convolutional Neural Network with Training Interference

Bleachers play a crucial role in practical engineering applications, and any damage incurred during their operationposes a significant threat to the safety of both life and property. Consequently, it becomes imperative to conductdamage diagnosis and health monitoring of bleachers. The intricate structure of bleachers, the varied types ofpotential damage, and the presence of similar vibration data in adjacent locations make it challenging to achievesatisfactory diagnosis accuracy through traditional time-frequency analysis methods. Furthermore, field environmentalnoise can adversely impact the accuracy of bleacher damage diagnosis. To enhance the accuracy and antinoisecapabilities of bleacher damage diagnosis, this paper proposes improvements to the existing ConvolutionalNeural Network with Training Interference (TICNN). The result is an advanced Convolutional Neural Networkmodel with superior accuracy and robust anti-noise capabilities, referred to as Enhanced TICNN (ETICNN).ETICNN autonomously extracts optimal damage-sensitive features from the original vibration data. To validatethe superiority of the proposed ETICNN, experiments are conducted using the bleacher model from Qatar Universityas the subject. Comparative studies under identical experimental conditions involve TICNN, Deep ConvolutionalNeural Networks with wide first-layer kernels (WDCNN), and One-Dimensional ConvolutionalNeural Network (1DCNN). The experimental findings demonstrate that the ETICNN model achieves the highestaccuracy, approximately 99%, and exhibits robust classification abilities in both Phases I and II of the damagediagnosis experiments. Simultaneously, the ETICNN model demonstrates strong anti-noise capabilities, outperformingTICNN by 3% to 4% and surpassing other models in performance.

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.

Combined optical fiber interferometric sensors for the detection of acoustic emission

A type of combined optical fiber interferometric acoustic emission sensor is proposed. The sensor can be independent on the laser source and make light interference by matching the lengths of two arms,so it can be used to monitor the health of large structure. Theoretical analyses indicate that the system can be equivalent to the Michelson interferometer with two optical fiber loop reflectors,and its sensitivity has been remarkably increased because of the decrease of the losses of light energy. PZT is powered by DC regulator to control the operating point of the system,so the system can accurately detect feeble vibration which is generated by ultrasonic waves propagating on the surface of solid. The amplitude and the frequency of feeble vibration signal are obtained by detecting the output light intensity of interferometer and using Fourier transform technique. The results indicate that the system can be used to detect the acoustic emission signals by the frequency characteristics.

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.