57 results about "Bearing vibration" patented technology

The present application relates to the field of bearing test, in particular to bearing raceway surface quality and grease matching characteristic test device. The device comprises a workbench, the workbench is provided with a driving shaft, the driving shaft is provided with a sleeving section for sleeving the bearing on the driving shaft and synchronously rotating the inner ring of the bearing and the driving shaft, the workbench is provided with a fixing structure outside the radial direction of the driving shaft for fixing the outer ring of the bearing at the sleeving position of the bearing, the workbench is provided with a vibration sensor for monitoring the vibration signal of the bearing, a noise sensor for monitoring the noise signal of the bearing, and a stick-slip signal sensor for monitoring the stick-slip signal of the bearing, and the sensors collect signals when the driving shaft drives the inner ring of the bearing to rotate. The collected signals are used to establish a mathematical model to provide theoretical support for the manufacturing process of the bearing and the selection of the grease, so as to ensure the mutual matching of the surface quality of the bearing and the grease, and further reduce the vibration and noise generated by the bearing under high-speed working condition.

The application belongs to the technical field of rotating machinery condition monitoring and fault diagnosis. A bearing failure evaluation method and system are provided. The bearing vibration signal is obtained and processed by mean removal and absolute value to obtain a to-be-processed signal. Then, the lower threshold of the tail part is determined, and the tail sample set with an amplitude greater than the threshold is screened out. Then, a soft-truncated power-law distribution model is constructed based on the tail sample set, and the distribution parameters including the power-law tail index, the truncated scale parameter and the truncated smooth index are solved by maximum likelihood estimation. Then, the analytical expression of the improved Gini index is constructed according to the distribution parameters, and the bearing degradation degree index is calculated. Finally, the bearing degradation curve is constructed according to the degradation degree index of different time periods. The application accurately describes the impact characteristics of the tail part of the vibration signal by the soft-truncated power-law model, and quantifies the degradation degree by the improved Gini index, which can effectively evaluate the health status and failure trend of the rolling bearing.

This invention relates to a method for modeling the vibration of rolling bearings considering non-ideal Hertzian contact, belonging to the field of bearing vibration modeling technology, and includes the following steps: S1: Obtaining the basic geometric and material parameters of the rolling bearing; S2: Calculating the angular range of the load zone of the rolling bearing; S3: Calculating the geometric parameters of the contact between the rolling elements and the healthy raceway; S4: Calculating the mechanical parameters of the contact between the rolling elements and the healthy raceway; S5: Calculating the cage angular velocity parameters; S6: Calculating the angular position and angular velocity parameters of the rolling element's circumferential motion; S7: Calculating the deformation and contact force generated by all rolling elements in contact with the healthy raceway of the bearing; S8: Calculating the time-varying mechanical parameters implied by the contact between the rolling elements and the defect; S9: Dynamic modeling of the vibration excitation mechanism of the rolling bearing defect.

The application provides a lifting pump main motor bearing vibration lightweight intelligent prediction method, realizes accurate prediction of future state of lifting pump main motor bearing vibration, collects power consumption, power, current, temperature and water flow of the lifting pump main motor bearing as model input variables through a sensor, establishes a lifting pump main motor bearing vibration lightweight intelligent prediction model, constructs a multi-layer convolution module stacking structure to extract deep features of input data, relieves influence of insufficient generalization on model prediction performance, realizes accurate prediction of lifting pump main motor bearing vibration, designs a convolution module self-organizing reconstruction mechanism, groups similar convolution kernels by using spectral clustering, self-organizes a low-rank similar convolution kernel result matrix, and assigns the low-rank similar convolution kernel result matrix to a weight vector of a newly-built convolution kernel in each lightweight convolution module, so that the number of parameters of the prediction model is reduced.

The application discloses a kind of fusion attention mechanism and the industrial bearing vibration time series signal fault prediction method and system of LSTM.This method includes: collecting bearing vibration signal and carrying out filtering, noise reduction and normalization preprocessing;BiLSTM and coordinate attention mechanism combined deep learning model is constructed to extract bidirectional time series features and enhance key fault features;Multi-objective composite loss function and Adam optimizer are used for model training, and early stopping mechanism is introduced to prevent overfitting;Real-time vibration signal is used to identify fault type and degree evaluation using the trained model, and multi-scale spectral kurtosis features and nonlinear dynamics parameters are used for quantitative analysis;Finally, output fault diagnosis report, and trigger multi-level early warning based on adaptive threshold value.The application can realize high-precision, high-reliability bearing fault prediction and health state evaluation, and is suitable for industrial equipment intelligent operation and maintenance.

The utility model relates to a gear assembling equipment, including work head, be provided with the conveying mechanism for conveying a plurality of first fixture on work head, along conveying mechanism is provided with first bearing assembling mechanism, gear assembling mechanism, second bearing assembling mechanism and material moving mechanism in proper order, second bearing assembling mechanism includes second bearing vibration disk feeding mechanism, second bearing positioning mechanism and second bearing press -fitting mechanism, and second bearing positioning mechanism and second bearing press -fitting mechanism are located the top of conveying mechanism, and the discharge port of second bearing vibration disk feeding mechanism is butt -joint with the feed port of second bearing positioning mechanism, and second bearing press -fitting mechanism is used for guiding and press -fitting to the second bearing on second bearing positioning mechanism. The assembling equipment not only has realized gear and two bearings's high -efficient, accurate assembling, has also improved product quality and production efficiency.

This invention discloses a method for detecting and analyzing vibration and noise in miniature bearings, relating to the field of noise detection technology. The invention constructs a detection position consistent with the target assembly scenario and collects vibration and acoustic response data under conditions such as gradually changing speed, pulsating speed, axial preload, directional off-center loading, and start-stop transition. It further calculates disturbance-sensitive trajectory data, energy redistribution trajectory data, and repetitive visible trajectory data, thereby enabling the differentiation and analysis of raceway anomalies, cage anomalies, lubrication anomalies, and assembly eccentricity anomalies. Compared to existing technologies, this invention can more realistically reflect the abnormal noise performance of miniature bearings after installation, improve the early identification capability of weak anomalies and the accuracy of anomaly source analysis, and can output conclusions regarding the risk of abnormal noise during installation.

This invention discloses a bearing fault diagnosis method and related device for new operating conditions with limited data, belonging to the field of bearing diagnosis technology. Addressing the challenges of scarce fault data and variable operating conditions in industrial settings, the proposed bearing fault diagnosis method employs a two-layer fractional-order differential enhancement mechanism: at the input layer, multi-order fractional-order differential operators are used to capture subtle temporal fluctuations in bearing vibration signals; at the feature layer, an adaptive distributed fractional-order feature extraction mechanism is designed, utilizing the nonlocal correlation of fractional-order calculus to characterize the dynamic evolution of deep features. The overall framework relies on a meta-learning paradigm, enabling the model to acquire efficient initialization priors through meta-training on a known set of operating conditions. This invention significantly improves diagnostic accuracy and robustness under conditions with very few samples, effectively solving the problem of rapid diagnostic deployment for rotating machinery under complex and variable operating conditions.

The utility model discloses a bearing convexity measuring device, wherein bearing vibration detector is provided with the chassis on, one side center position fixed connection screw rod no.

This invention belongs to the field of rotating machinery condition monitoring and fault diagnosis technology. It proposes a bearing failure assessment method and system. The method involves acquiring bearing vibration signals and performing mean and absolute value removal processing to obtain the signal to be processed. Next, a lower threshold for the tail is determined, and a set of tail samples with amplitudes greater than this threshold is selected. Then, a soft-truncated power-law distribution model is constructed based on the tail sample set, and the distribution parameters, including the power-law tail exponent, truncation scale parameter, and truncation smoothing exponent, are solved using maximum likelihood estimation. Furthermore, an analytical expression for the improved Gini index is constructed based on the distribution parameters, and the bearing degradation degree index is calculated. Finally, a bearing degradation curve is constructed based on the degradation degree index for different time periods. This invention accurately characterizes the tail impact features of vibration signals using a soft-truncated power-law model and quantifies the degradation degree using an improved Gini index, effectively assessing the health status and failure trend of rolling bearings.

This invention relates to the field of motor bearing vibration detection technology. Specifically, it relates to a motor bearing vibration detection method based on PMH (Property Management Hygiene). The method includes the following steps: S1, collecting the vibration state of the motor bearing, work records, and motor operating tasks, while simultaneously acquiring motor parameters and bearing parameters; S2, screening historical vibration states according to operating tasks. This invention overcomes the limitations of traditional detection methods that focus heavily on vibration data and neglect related information, constructing a comprehensive data acquisition and management system to provide high-quality data support for subsequent analysis. It also abandons the traditional fixed-threshold detection mode, constructing a deviation judgment standard that better conforms to the actual operating laws of motor bearings through dynamic adjustment and multi-dimensional correction, significantly reducing false alarms and missed alarms. Furthermore, by upgrading historical data analysis to future state prediction and dynamic risk assessment, multi-dimensional collaborative judgment enables early identification and graded warning of fault risks, buying time for maintenance personnel to handle the situation.

This application relates to the field of industrial equipment fault diagnosis and signal processing technology. It provides a method for generating rolling bearing vibration signals based on a diffusion model. This method includes: standardizing a signal subsequence to generate a preprocessed signal subsequence; constructing a denoising network based on the LS-UNet architecture, where LS-UNet includes an encoder, decoder, skip connections, and LSBlock units; adding forward noise to the preprocessed signal subsequence based on a denoising diffusion probability model framework to obtain a noisy signal; training the denoising network using the noisy signal to enable the denoising network to learn noise prediction capabilities; sampling initial noise from a standard normal distribution, and performing inverse denoising on the initial noise using the trained denoising network to generate a synthetic vibration signal of the target fault category. This method aims to improve the diversity and realism of the generated signal, enhance the model's ability to model multi-scale features of vibration signals, and achieve the technical effect of controllable generation of fault categories.

The utility model belongs to bearing testing machine damping technical field mainly relates to a kind of wind power bearing testing machine is with loaded damping device, including the bottom plate being arranged in bottom;The bottom plate whole is a rectangular plate, and the guide groove being arranged in axial is provided in its top surface front end, and the fixed seat being arranged in vertical is provided in its top surface rear end;The fixed seat is close to the direction of guide groove and is provided with the main shaft of horizontal arrangement on it;The outer circumference of the main shaft is equipped with bearing seat, and the bearing inner ring is provided at the connecting end of main shaft;The bearing outer ring connected with it is provided on the bearing seat;The lower part of the bearing seat is provided with damping component.The utility model can guarantee bearing loading precision, effectively reduce bearing vibration, avoid bearing seat to appear skidding phenomenon, guarantee production quality, and the device installation and dismounting difficulty are low, damping component is connected by bolt, can be conveniently disassembled and replaced Simplified maintenance process, reduce maintenance cost and time.

The utility model provides a kind of steam turbine monitoring instrument monitoring device, it is related to steam turbine monitoring technical field, comprising: wide temperature sensor, the wide temperature sensor is used to monitor steam turbine bearing vibration, tile vibration, axial displacement, expansion difference parameter;The redundant power module is connected with the wide temperature sensor, provides stable power supply;Monitor module has analog output and switch output function, and is connected with the wide temperature sensor signal;Cabinet is used to install wide temperature sensor, redundant power module and monitor module.According to the utility model, wide temperature sensor is used to monitor steam turbine bearing vibration, tile vibration, axial displacement, expansion difference and other key parameters, it is stably arranged on bracket, with good shock resistance, to ensure that wide temperature sensor maintains stable installation state under the vibration environment generated by steam turbine operation, to ensure the accuracy of monitoring data.

This invention relates to the field of bearing vibration measurement technology, and proposes a vibration measurement fixture for the axial loading of the inner ring of an NUP structure cylindrical roller bearing. The fixture includes a base shaft, a pressure cap, a first bearing, a second bearing, a locking washer, a vibration measurement base, an outer ring limiting component, and an adjusting component. In this invention, during vibration testing of the inner ring of the NUP structure cylindrical roller bearing, the inner ring top sleeve of the fixture can be tightly fitted against the inner ring of the NUP structure cylindrical roller bearing, and the outer ring of the NUP structure cylindrical roller bearing can be limited by the outer ring top sleeve. This prevents misalignment between the outer and inner rings while the NUP structure cylindrical roller bearing rotates at high speed with the drive shaft. Simultaneously, by fixing the inner ring of the NUP structure cylindrical roller bearing, the machining dimensions of the inner ring flange can be tested to ensure they are within the standard range. This effectively solves the problems of misalignment between the outer and inner rings and the inability to identify incomplete machining dimensions of the inner ring flange during testing of cylindrical roller bearings in the prior art.

The utility model discloses a kind of low vibration bearing with optimized retainer structure belong to bearing technical field, including inner ring and outer ring, evenly be provided with rolling element between inner ring and outer ring, rolling element outside is provided with retainer, retainer includes first side plate and second side plate, there is array distribution in between first side plate and second side plate pocket, pocket and first side plate and second side plate between fixed connection, pocket and pocket between fixed connection there is pocket crossbeam.The utility model uses above-mentioned a kind of low vibration bearing with optimized retainer structure, reduce the collision of rolling element and retainer, inner ring and outer ring, enhance the overall rigidity of retainer, avoid rolling element position deviation, inhibit bearing vibration;Oil reservoir can store lubricating oil, reduce the friction and abrasion of rolling element and pocket, raceway, prolong the service life of bearing;Retainer uses aluminium alloy material, reduce centrifugal force when high speed operation, reduce the additional load to bearing overall, indirectly reduce vibration.

The application relates to a bearing fault diagnosis method based on working condition decoupling, and belongs to the fault diagnosis technology, and solves the problem that in the prior art, working condition information and fault data are not combined during bearing fault diagnosis, so that the diagnosis precision and reliability are not high. The method comprises the following steps: acquiring bearing vibration signal data; wherein the bearing vibration signal data comprises bearing working condition attributes and bearing vibration data; inputting the bearing vibration signal data into a trained bearing fault diagnosis model to obtain a bearing fault category; wherein the bearing fault diagnosis model comprises a data input layer, a feature extraction layer and a fault classifier tail. The working condition data and the fault data are combined, the relationship between the working condition parameters and the faults is analyzed, and the accuracy and reliability of the diagnosis are further improved.

This invention discloses a reinforcement learning-based bearing fault transfer diagnosis method and system in the field of intelligent operation and maintenance and fault diagnosis technology for high-speed trains. The method includes: preprocessing acquired bearing vibration data to obtain preprocessed bearing vibration data; extracting multidimensional features from the preprocessed bearing vibration data to construct a bearing vibration feature vector; reducing and discretizing the bearing vibration feature vector to obtain the bearing vibration state; and inputting the bearing vibration state into a trained target domain diagnostic model to obtain a diagnostic action. This invention can maintain the effectiveness and stability of bearing fault diagnosis even under label-missing conditions, achieves adaptive transfer of knowledge from the source domain to the target domain, and has advantages such as convergence stability and efficient decision-making. It can be widely applied to online monitoring and intelligent operation and maintenance of bearing faults in high-speed trains.

This invention discloses a bearing fault diagnosis method and system based on a multi-level judgment mechanism. The method involves acquiring bearing vibration signals and preprocessing the signals; calculating the kurtosis index and peak-to-peak value of the preprocessed signal, and determining whether both exceed set values. If both exceed the set values, a fault determination is recorded. The preprocessed signal is then processed using FFT to obtain a spectrum, and the presence of abnormal frequency bands is assessed. If abnormal bands are found, another fault determination is recorded. The number of preliminary fault determinations is accumulated (N). If N ≥ 2, the bearing is determined to be faulty. If N < 2, the preprocessed signal is subjected to algorithm detection. The results of the preliminary diagnosis and algorithm detection are combined to determine whether the bearing is faulty. The introduction of a multi-level judgment mechanism effectively reduces the false alarm rate and significantly improves the accuracy and reliability of fault diagnosis.

The application discloses a bearing vibration abnormality monitoring method in motor load testing, and relates to the technical field of motor testing, comprising the following steps: obtaining a plurality of structure sampling positions having a mechanical connection relationship with a bearing installation position, determining a structure sampling position corresponding to the bearing installation position as a target bearing sampling position, and forming an incoming position sequence and a bearing outgoing position sequence; taking a target load switching time as a unified response starting point, dividing time sampling windows for vibration response data of each structure sampling position, setting window numbers and extracting window peak values. The application can position and compare vibration peak value changes at the target bearing sampling position in a mechanical connection path by obtaining a plurality of structure sampling positions having a mechanical connection relationship with the bearing installation position and forming the incoming position sequence and the bearing outgoing position sequence, and can investigate vibration responses transmitted in a mechanical connection direction of a load end and a mechanical connection direction of a mounting base.

The invention discloses a high-speed train bearing cross-domain fault diagnosis method based on transfer learning, and relates to the technical field of train bearing fault diagnosis, and the method comprises the steps: carrying out the secondary combined noise reduction of a bearing vibration acceleration original signal; extracting time domain statistical features, frequency domain statistical features and associated time-frequency domain features, and constructing a high-dimensional feature set; carrying out dimension reduction processing on the high-dimensional feature set; constructing a multi-task neural network reference model for pre-training; constructing a CDAN migration diagnosis model based on feature adaptation; carrying out adversarial training and pseudo-label iterative optimization to obtain a trained migration diagnosis model; and carrying out actual diagnosis. According to the method, through two-stage combined noise reduction, multi-dimensional multi-domain feature extraction, dimension reduction processing, a multi-task neural network reference model and a feature adaptation-based CDAN migration diagnosis model, the accuracy and robustness of cross-domain fault diagnosis of the high-speed train bearing are improved by combining adversarial training and pseudo-tag iterative optimization.

The application relates to the technical field of fault prediction, in particular to a bearing fault prediction method and system for a pulping and papermaking device, which comprises the following steps: acquiring real-time bearing vibration signals and surface temperature data of each bearing component; determining abnormal characteristic data in at least one of the real-time bearing vibration signals and the multiple surface temperature data; determining vibration amplitude mutation data and temperature rise rate data according to the abnormal characteristic data, and controlling the pulping and papermaking device to reduce the running speed based on the temperature rise rate data; after the pulping and papermaking device reduces the running speed, acquiring bearing acoustic signals and bearing rotating speed information, and determining the position of a first key monitoring point according to the bearing acoustic signals, the bearing rotating speed information and preset historical load data. Through the analysis of the temperature rise rate, oil film pressure and equipment load, the generated maintenance instruction can adjust the lubrication state or operation parameter in a targeted manner, so that the equipment life is prolonged, and the maintenance cost is reduced.

The utility model discloses a kind of nano modified GPS flexible heat preservation sound insulation mat structures, it includes the sound insulation mat with upper surface being plane and the pressure-bearing vibration-reducing structure specially designed lower surface, and the flexible heat-reflecting film covered on upper surface.Pressure-bearing vibration-reducing structure is automatically adapted to ground flatness, dynamic vibration reduction and load capacity optimization by a, b, c three parts different height design, flexible heat-reflecting film is attached using hot melt adhesive coating process, with corrosion resistance, puncture resistance and high efficient heat-reflecting function.This application can significantly improve the paving flatness of sound insulation mat, sound insulation and pressure-bearing compatibility, while enhancing the heat-reflecting efficiency of floor heating system, reducing energy consumption, meeting the needs of building energy saving and sustainable development.

The application discloses a motor rolling bearing residual life prediction method based on optimized feature extraction in the technical field of rolling bearing life prediction. The method comprises the following steps: establishing a bearing vibration signal sample set, denoising and smoothing the X-axis vibration signal and fusing the original signal; extracting the time domain, frequency domain and time-frequency domain features of the processed signal to form an initial degradation feature set, wherein the time-frequency domain feature extraction is obtained through optimized VMD decomposition; dimension reduction and aggregation are performed on the initial feature set to obtain a plurality of HI features; the RIME algorithm is used to optimize the CNN-BiLSTM model parameters, a multi-head attention mechanism is added, and a prediction model is trained; and the residual life is predicted after the test bearing signal is processed and input into the model. Through multi-stage signal processing and model optimization, the bearing degradation features are accurately extracted under the condition of only relying on the vibration signal, and the accuracy and reliability of the residual life prediction are improved.

This invention discloses a bearing vibration detection device, relating to the field of bearing vibration detection technology. It includes a detection component that attaches to multiple different bearings and detects their vibration. The detection component includes a lifting plate and a lifting frame. The lifting plate and lifting frame remove bearings exhibiting abnormal vibration, thus classifying the bearings. A placement component is slidably mounted on the detection component, holding multiple bearings. The placement component moves multiple bearings to the detection position. A drive component is located at the lower end of the detection component to rotate the bearings. After the placement component moves the bearings to the working position, the drive component drives the bearings to rotate. Multiple locking blocks within the drive component rotate bearings at different positions. This invention enables continuous bearing vibration detection, increasing detection efficiency, and allows for rapid removal of bearings exhibiting abnormal vibration.

The application discloses a rolling bearing RUL prediction method based on deep learning, obtains kurtosis and peak factor from a bearing vibration signal, is used for health monitoring of a rolling bearing, judges a first prediction time of the bearing; uses wavelet transform to perform time-frequency analysis on an original vibration signal of the rolling bearing, obtains a wavelet power spectrum diagram; uses the obtained wavelet power spectrum diagram data set to represent a degradation state of the rolling bearing. A convolutional neural network model based on a Transform structure is trained and used to complete prediction of the remaining useful life of the rolling bearing. The application gives play to the advantage of the Transform in extracting long-distance information, solves the problem of actual application of a model in prediction of the remaining useful life of the rolling bearing, and makes the prediction of the remaining useful life of the rolling bearing more accurate.

This invention discloses a method for predicting the remaining service life of bearings based on inverse Gaussian process constraints, belonging to the field of mechanical equipment fault prediction and health management technology. This invention collects bearing vibration signals and constructs a temporal convolutional network to extract degradation features. Simultaneously, it introduces an inverse Gaussian process to probabilistically model the degradation increment, constructing a joint physical information loss function that integrates data fitting loss, inverse Gaussian negative log-likelihood loss, and monotonicity constraint loss. Through joint optimization training, the model extracts complex nonlinear degradation features while strictly adhering to the inverse Gaussian distribution characteristics and monotonic degradation physical laws. This invention maintains high accuracy and high stability in remaining service life prediction even with few samples and complex operating conditions, enhancing the physical consistency and reliability of the model. It is applicable to health monitoring and predictive maintenance of bearings in rotating machinery such as hydropower, wind power, and rail transportation.

The application discloses a resonance control method and device of a rotating machinery vibration measurement system, and relates to the technical field of rotating machinery vibration measurement and control. The method comprises the following steps: acquiring the corresponding rotating speed and vibration amplitude of each bearing of the rotating machinery in real time; after judging that the vibration amplitude of a bearing suddenly exceeds the sum of the amplitude threshold and the amplitude threshold tolerance under the corresponding rotating speed, analyzing the amplitude of each frequency multiplication component of the vibration, and if the 0.5 times frequency and / or 1 times frequency amplitude proportion is lower than a preset proportion, sending a resonance elimination signal to the stiffness adjustment structure of the corresponding bearing vibration measurement system to perform stiffness adjustment until the vibration amplitude drops into the amplitude threshold. The application can effectively analyze and identify the resonance of the rotating machinery vibration measurement system, and can avoid the resonance by optimizing and adjusting the pre-tightening force of the vibration probe installation fixing rod, changing the installation stiffness of the vibration measurement system, changing the inherent frequency of the vibration measurement system, and ensuring the authenticity of the vibration measurement data.