CN116012681A - Method and system for diagnosing motor faults of pipeline robot based on sound vibration signal fusion - Google Patents
Method and system for diagnosing motor faults of pipeline robot based on sound vibration signal fusion Download PDFInfo
- Publication number
- CN116012681A CN116012681A CN202211622619.7A CN202211622619A CN116012681A CN 116012681 A CN116012681 A CN 116012681A CN 202211622619 A CN202211622619 A CN 202211622619A CN 116012681 A CN116012681 A CN 116012681A
- Authority
- CN
- China
- Prior art keywords
- sound
- vibration
- frequency image
- time
- fault diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of motor fault diagnosis, and provides a method and a system for diagnosing motor faults of a pipeline robot based on sound vibration signal fusion, wherein the method comprises the following steps: acquiring a sound time-frequency image and a vibration time-frequency image of the pipeline robot; the method comprises the steps that a sound time-frequency image and a vibration time-frequency image are input into a fault diagnosis model, the fault diagnosis model comprises two parallel convolutional neural networks, a full connection layer and an output layer, one convolutional neural network processes the sound time-frequency image to obtain a sound feature vector, the other convolutional neural network processes the vibration time-frequency image to obtain a vibration feature vector, and after the feature vector and the vibration feature vector are subjected to data fusion operation, the full connection layer and the output layer are sequentially input to obtain a fault diagnosis result. Through the fusion of the sound vibration signals, the reliability of the fault detection of the motor of the pipeline robot is enhanced.
Description
Technical Field
The invention belongs to the technical field of motor fault diagnosis, and particularly relates to a method and a system for diagnosing motor faults of a pipeline robot based on sound vibration signal fusion.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The three-foot pipeline robot is a crawler-type pipeline robot with robots and pipeline supporting feet distributed in a central symmetry mode, and is a machine, electricity and instrument integrated system capable of automatically walking along the inside or the outside of a large pipeline and carrying one or more sensors and operating machinery, and performing a series of pipeline operations under the remote control of staff or the automatic control of a computer. The motor is critical to the pipeline robot, and the motor is inevitably aged and the like due to the influence of environmental factors such as temperature, humidity and the like and other factors such as looseness, poor contact and the like. How to accurately identify the fault type in time at the initial stage of occurrence of the micro fault is significant to the evolution and propagation of the cut-off fault, and the research of the accurate fault self-diagnosis method of the motor can effectively reduce the probability of serious faults such as shutdown and out-of-control of the robot in the pipeline, so that the situation that the robot cannot exit the pipeline due to the serious faults is avoided, and the method is a key problem for improving the reliability of the robot.
The motor condition of the robot is analyzed from only a single type of measurement signal, which in some cases may lead to insufficient analysis.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides the pipeline robot motor fault diagnosis method and system based on the sound vibration signal fusion, and the reliability of detecting the pipeline robot motor fault is enhanced through the sound vibration signal fusion.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a first aspect of the present invention provides a method for diagnosing a motor failure of a pipe robot based on acoustic-vibration signal fusion, comprising:
acquiring a sound time-frequency image and a vibration time-frequency image of the pipeline robot;
the method comprises the steps that a sound time-frequency image and a vibration time-frequency image are input into a fault diagnosis model, the fault diagnosis model comprises two parallel convolutional neural networks, a full connection layer and an output layer, one convolutional neural network processes the sound time-frequency image to obtain a sound feature vector, the other convolutional neural network processes the vibration time-frequency image to obtain a vibration feature vector, and after the feature vector and the vibration feature vector are subjected to data fusion operation, the full connection layer and the output layer are sequentially input to obtain a fault diagnosis result.
Further, the method for acquiring the sound time-frequency image and the vibration time-frequency image comprises the following steps: and respectively processing the sound signal and the vibration signal through short-time Fourier transformation to obtain a sound time-frequency image and a vibration time-frequency image.
Further, the data fusion operation specifically includes concatenating the acoustic signal feature vector and the vibration signal feature vector into one acoustic vibration feature vector.
Further, in the training process of the fault diagnosis model, after the output layers of the two pre-trained convolutional neural networks are removed, a common full-connection layer is connected behind the two convolutional neural networks, and an output layer is connected behind the full-connection layer, so that the fault diagnosis model is obtained, and after the weights of the full-connection layer and the output layer are randomly initialized, fine adjustment is carried out on the fault diagnosis model.
Further, the convolutional neural network employs ResNet50.
Further, the fine tuning method specifically comprises the following steps: and setting the last residual block, the full connection layer and the output layer in the ResNet50 in the fault diagnosis model as a trainable layer, freezing the first four residual blocks in the ResNet50, and updating the weight of the trainable layer by minimizing the error between the predictive label and the real label based on a training set.
A second aspect of the present invention provides a system for diagnosing a motor failure of a pipe robot based on a fusion of acoustic vibration signals, comprising:
a data acquisition module configured to: acquiring a sound time-frequency image and a vibration time-frequency image of the pipeline robot;
a fault diagnosis module configured to: the method comprises the steps that a sound time-frequency image and a vibration time-frequency image are input into a fault diagnosis model, the fault diagnosis model comprises two parallel convolutional neural networks, a full connection layer and an output layer, one convolutional neural network processes the sound time-frequency image to obtain a sound feature vector, the other convolutional neural network processes the vibration time-frequency image to obtain a vibration feature vector, and after the feature vector and the vibration feature vector are subjected to data fusion operation, the full connection layer and the output layer are sequentially input to obtain a fault diagnosis result.
Further, a model training module is also included that is configured to: after the output layers of the two pre-trained convolutional neural networks are removed, a common full-connection layer is connected to the rear of the two convolutional neural networks, and an output layer is connected to the rear of the full-connection layer, so that the fault diagnosis model is obtained, and after the weights of the full-connection layer and the output layer are randomly initialized, fine tuning is carried out on the fault diagnosis model.
A third aspect of the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps in a method for diagnosing a motor failure of a pipe robot based on fusion of acoustic vibration signals as described above.
A fourth aspect of the present invention provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in a method for diagnosing a motor failure of a pipe robot based on fusion of acoustic vibration signals as described above when executing the program.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a pipeline robot motor fault diagnosis method based on sound vibration signal fusion, which enhances the reliability of detecting the pipeline robot motor fault through the sound vibration signal fusion.
The invention provides a pipeline robot motor fault diagnosis method based on sound vibration signal fusion, which reduces the number of parameters to be trained through transfer learning and solves the problem that a small data set cannot be trained in a deep learning model.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a method for diagnosing motor faults of a pipeline robot based on sound vibration signal fusion according to the first embodiment of the invention;
FIG. 2 is a diagram showing a structure of a fault diagnosis model according to the first embodiment of the present invention;
fig. 3 is a block diagram of a res net50 according to a first embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
The embodiment provides a pipeline robot motor fault diagnosis method based on sound vibration signal fusion, which collects sound signals and vibration signals when a pipeline robot motor runs through a sound sensor and an accelerometer, analyzes running data of the robot motor based on a convolutional neural network, and gives a diagnosis result so as to achieve the purpose of early warning of faults. As shown in fig. 1, the method specifically comprises the following steps:
and step 1, acquiring sound signals and vibration signals of the pipeline robot.
And after the sound signals and the vibration signals of the pipeline robot are acquired by the signal acquisition device, uploading the sound signals and the vibration signals to the upper computer. The signal acquisition device comprises a sound sensor, a vibration sensor (accelerometer) and a synchronous acquisition card connected with the sound sensor and the vibration sensor, and the signal output end of the synchronous acquisition card is connected with the upper computer.
The state of the motor is monitored in real time by installing the sound sensor and the accelerometer beside the pipeline robot to collect sound and vibration signals, so that the probability of serious faults such as shutdown and out-of-control of the robot in the pipeline can be effectively reduced under the condition that the normal operation of the pipeline robot is not influenced, the situation that the robot cannot exit the pipeline due to the serious faults is avoided, and the method is a key problem for improving the reliability of the robot.
The audio event refers to a signal containing a certain piece of information, the operation process of the pipeline robot can generate sound containing rich information, and the sound can be changed along with the change of the operation state. The sound signal is an important information source for reflecting the running state of the equipment, and has the advantages of convenient collection, non-contact measurement, low cost and the like, and the sound signal analysis becomes an effective monitoring method. Audio event classification is the computer aided judgment of the content delivered in a segment of audio signal, helping people to make better decisions.
And 2, respectively processing the sound signal and the vibration signal through short-time Fourier transform (STFT) to obtain a sound time-frequency image and a vibration time-frequency image.
The time-frequency image contains much more information than just the time-domain or frequency-domain representation. The time series sensor data can be better utilized by converting the measurement signals between different domains such as time, frequency or time frequency by adopting a signal processing technology.
And step 3, inputting the sound time-frequency image and the vibration time-frequency image into a fault diagnosis model to obtain a fault diagnosis result, namely the fault category of the motor of the pipeline robot.
As shown in fig. 2, the fault diagnosis model includes two parallel convolutional neural networks, a full connection layer, and an output layer (classification layer).
Processing the sound time-frequency image by a convolutional neural network to obtain a sound feature vector; the other convolution neural network processes the vibration time-frequency image to obtain a vibration characteristic vector; and after the data fusion operation is carried out on the sound characteristic vector and the vibration characteristic vector, sequentially inputting the sound characteristic vector and the vibration characteristic vector into the full-connection layer and the output layer to obtain a fault diagnosis result.
The data fusion operation is specifically to concatenate the sound signal eigenvector and the vibration signal eigenvector into one sound vibration eigenvector.
The output of each convolutional neural network is combined with the fully connected operation and connected to the same classification layer for final prediction, the Softmax function is used as the classification function of the output layer to convert all output values into probabilities, all probability values are added up to be equal to 1, and the category with the highest probability value is the predicted category.
The STFT provides time and frequency information of the measurement signal. The convolutional neural network extracts features from the time-frequency representation and solves the degradation problem through a residual network. The data fusion operation increases the number of features used to diagnose the condition of the robot motor. Each sensor has certain advantages, and can reflect the condition of the machine from different angles.
The convolutional neural network adopts the ResNet50, potential mapping between the input x and the output H (x) is not simply and directly learned any more, and gradient disappearance and degradation caused by deepening the network layer number can be effectively avoided by introducing residual error learning by the ResNet50. ResNet50 has two basic blocks, named Conv Block and Identity Block, respectively, divided into five parts, each consisting of several stacked Conv Block and Identity Block. The dimensions (channel number and size) of Conv Block input and output are different, its role is to change the dimensions of the network; conv Block (C, W, C1, S), parameter C refers to the number of channels input, parameter W refers to the size of the input, parameter C1 refers to the number of channels of the 1x1 convolution layer, and parameter S refers to the step size; the Identity Block has the same input dimension and output dimension (channel number and size) and is used for deepening the network; identity Block (C, W), parameter C refers to the number of channels input, and parameter W refers to the size of the input; the first part (cov 1) contains one convolutional layer CONV (Convolution) (the size of the convolutional kernel is 7×7, the number of convolutional kernels (i.e. the number of channels output by the convolutional layer) is 64, the step size is 2), one BN (Batch Normalization) layer, the RELU activation function and one MAXPOOL layer (the size of the convolutional kernel is 7×7, the step size is 2), the second part (cov 2_x) contains one Conv Block (64, 56, 64, 1) and two Identity blocks (256, 56), the third part (cov 3_x) contains one Conv Block (256, 56, 128,2) and three Identity blocks (512, 28), the fourth part (cov 4_x) contains one Conv Block (512, 28, 256, 2) and five Identity blocks (1024, 14), the fifth part contains one Conv Block (1024, 14, 512,2) and two Identity blocks (256, 56), and the total layers of two Identity blocks (2048,7) are connected completely. Details of the structure of ResNet50 are shown in FIG. 3.
ResNet50 is a deep learning network that has great potential in helping to simplify complex feature extraction, elimination and selection processes when processing large quantities of historical time series sensor data due to its robustness to noise in the data and its ability to automatically learn features from measured data.
The fault diagnosis model is trained through a transfer learning method.
The transfer learning can help train the target model by transferring weights, keeping the weights of the model starting layer unchanged, and fine-tuning higher layers of the neural network through the target dataset. The method provides ideas for solving the defect of fault data and accelerating the training of the neural network.
The lower convolution layers extract low-level features, such as edges and curves, that are suitable for common image classification tasks, and operations in subsequent layers can learn more abstract representations for different application domains. Thus, the weights of the starting layers can be migrated and only the weights of the higher layers need to be learned from the new dataset, the process of updating the weights of the following layers being called fine-tuning. This approach trains faster than from scratch because it essentially reduces the number of parameters that need to be trained and solves the problem that small datasets cannot be trained in deep learning models.
It is difficult to distinguish corresponding fault types according to the original signals, but the difference between the time-frequency images can distinguish each fault type, and the time-frequency images are suitable for further inputting the time-frequency images into a convolutional neural network for feature extraction. Firstly, converting an original signal into a time-frequency image through short-time Fourier transform, and taking the time-frequency image as an input of a convolutional neural network. The time-frequency diagram is a very common time-frequency analysis method and a useful tool for analyzing sensor signals to perform fault diagnosis, and the processed data signals are divided into a training set and a testing set. The training set is used to train the pre-trained model and fine tune its weights, while the test dataset is used to verify the performance of the fine tuned model, not used during the training process.
The pre-trained ResNet50 is adjusted, the output layer is removed from the pre-trained ResNet50, each ResNet50 takes as input a time-frequency representation of a single type of measurement signal, extracts feature vectors of the signal, concatenates the sound signal feature vector and the vibration signal feature vector into one sound vibration feature vector before classification, adds a new fully connected layer and output layer, and connects the concatenated sound vibration feature vectors to the same fully connected layer and output layer for final prediction.
The size of the output layer is determined by the number of pipeline robot working conditions, and the weights of the newly added full-connection layer and the output layer are randomly initialized. The last residual block in the ResNet50 and the full connection layer are set to be trainable, during which the first four residual blocks in the ResNet50 are frozen and the weight of the trainable layer is updated to minimize the error between the predicted and real labels. After enough periods, the fault diagnosis model after fine tuning is stored.
Compared with a single signal, the provided sound vibration signal fusion method has better classification effect and combines the advantages of two measurement signals. The motor condition is analyzed from only a single type of measurement signal, which in some cases may lead to insufficient analysis. The multi-sensor fusion method can strengthen the reliability of fault detection. Multi-sensor data fusion in smart diagnostic applications is considered a very promising technique, and therefore the use of multiple measurement signals helps to develop a more efficient and robust fault diagnosis method.
Example two
The embodiment provides a pipeline robot motor fault diagnosis system based on sound vibration signal fusion, which specifically comprises the following modules:
a data acquisition module configured to: acquiring a sound time-frequency image and a vibration time-frequency image of the pipeline robot;
a fault diagnosis module configured to: the method comprises the steps that a sound time-frequency image and a vibration time-frequency image are input into a fault diagnosis model, the fault diagnosis model comprises two parallel convolutional neural networks, a full connection layer and an output layer, one convolutional neural network processes the sound time-frequency image to obtain a sound feature vector, the other convolutional neural network processes the vibration time-frequency image to obtain a vibration feature vector, and after the feature vector and the vibration feature vector are subjected to data fusion operation, the full connection layer and the output layer are sequentially input to obtain a fault diagnosis result.
A model training module configured to: after the output layers of the two pre-trained convolutional neural networks are removed, a common full-connection layer is connected to the rear of the two convolutional neural networks, and an output layer is connected to the rear of the full-connection layer, so that the fault diagnosis model is obtained, and after the weights of the full-connection layer and the output layer are randomly initialized, fine tuning is carried out on the fault diagnosis model.
It should be noted that, each module in the embodiment corresponds to each step in the first embodiment one to one, and the implementation process is the same, which is not described here.
Example III
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the method for diagnosing a motor failure of a pipe robot based on the fusion of acoustic vibration signals as described in the above embodiment.
Example IV
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps in the method for diagnosing the motor faults of the pipeline robot based on the fusion of sound vibration signals according to the embodiment.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The method for diagnosing the motor faults of the pipeline robot based on the sound vibration signal fusion is characterized by comprising the following steps of:
acquiring a sound time-frequency image and a vibration time-frequency image of the pipeline robot;
the method comprises the steps that a sound time-frequency image and a vibration time-frequency image are input into a fault diagnosis model, the fault diagnosis model comprises two parallel convolutional neural networks, a full connection layer and an output layer, one convolutional neural network processes the sound time-frequency image to obtain a sound feature vector, the other convolutional neural network processes the vibration time-frequency image to obtain a vibration feature vector, and after the feature vector and the vibration feature vector are subjected to data fusion operation, the full connection layer and the output layer are sequentially input to obtain a fault diagnosis result.
2. The method for diagnosing a motor failure of a pipeline robot based on sound and vibration signal fusion as claimed in claim 1, wherein the method for acquiring the sound time-frequency image and the vibration time-frequency image is as follows: and respectively processing the sound signal and the vibration signal through short-time Fourier transformation to obtain a sound time-frequency image and a vibration time-frequency image.
3. The method for diagnosing a motor failure of a pipeline robot based on sound and vibration signal fusion according to claim 1, wherein the data fusion operation is specifically to serially connect a sound signal feature vector and a vibration signal feature vector into a sound and vibration feature vector.
4. The method for diagnosing the motor faults of the pipeline robot based on the sound vibration signal fusion according to claim 1, wherein in the process of training, after the output layers of two pre-trained convolutional neural networks are removed, a common full-connection layer is connected behind the two convolutional neural networks, and after the full-connection layer, an output layer is connected, so that the fault diagnosis model is obtained, and after weights of the full-connection layer and the output layer are randomly initialized, the fault diagnosis model is finely tuned.
5. The method for diagnosing motor faults of a pipeline robot based on sound vibration signal fusion as claimed in claim 4, wherein the convolutional neural network adopts ResNet50.
6. The method for diagnosing a motor failure of a pipeline robot based on sound vibration signal fusion according to claim 5, wherein the fine tuning method is as follows: and setting the last residual block, the full connection layer and the output layer in the ResNet50 in the fault diagnosis model as a trainable layer, freezing the first four residual blocks in the ResNet50, and updating the weight of the trainable layer by minimizing the error between the predictive label and the real label based on a training set.
7. Pipeline robot motor fault diagnosis system based on sound shake signal fuses, its characterized in that includes:
a data acquisition module configured to: acquiring a sound time-frequency image and a vibration time-frequency image of the pipeline robot;
a fault diagnosis module configured to: the method comprises the steps that a sound time-frequency image and a vibration time-frequency image are input into a fault diagnosis model, the fault diagnosis model comprises two parallel convolutional neural networks, a full connection layer and an output layer, one convolutional neural network processes the sound time-frequency image to obtain a sound feature vector, the other convolutional neural network processes the vibration time-frequency image to obtain a vibration feature vector, and after the feature vector and the vibration feature vector are subjected to data fusion operation, the full connection layer and the output layer are sequentially input to obtain a fault diagnosis result.
8. The system for diagnosing a motor failure of a pipe robot based on the fusion of acoustic signals according to claim 7, further comprising a model training module configured to: after the output layers of the two pre-trained convolutional neural networks are removed, a common full-connection layer is connected to the rear of the two convolutional neural networks, and an output layer is connected to the rear of the full-connection layer, so that the fault diagnosis model is obtained, and after the weights of the full-connection layer and the output layer are randomly initialized, fine tuning is carried out on the fault diagnosis model.
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps in the method for diagnosing a motor failure of a pipe robot based on fusion of acoustic vibration signals according to any one of claims 1-6.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method for diagnosing a motor failure of a pipe robot based on fusion of acoustic vibration signals according to any of claims 1-6 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211622619.7A CN116012681A (en) | 2022-12-16 | 2022-12-16 | Method and system for diagnosing motor faults of pipeline robot based on sound vibration signal fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211622619.7A CN116012681A (en) | 2022-12-16 | 2022-12-16 | Method and system for diagnosing motor faults of pipeline robot based on sound vibration signal fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116012681A true CN116012681A (en) | 2023-04-25 |
Family
ID=86024021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211622619.7A Pending CN116012681A (en) | 2022-12-16 | 2022-12-16 | Method and system for diagnosing motor faults of pipeline robot based on sound vibration signal fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116012681A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204821A (en) * | 2023-04-27 | 2023-06-02 | 昆明轨道交通四号线土建项目建设管理有限公司 | Vibration evaluation method and system for rail transit vehicle |
| CN116842418A (en) * | 2023-05-31 | 2023-10-03 | 浙江中屹纺织机械科技有限公司 | Intelligent water-jet loom and control system thereof |
-
2022
- 2022-12-16 CN CN202211622619.7A patent/CN116012681A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116204821A (en) * | 2023-04-27 | 2023-06-02 | 昆明轨道交通四号线土建项目建设管理有限公司 | Vibration evaluation method and system for rail transit vehicle |
| CN116204821B (en) * | 2023-04-27 | 2023-08-11 | 昆明轨道交通四号线土建项目建设管理有限公司 | Vibration evaluation method and system for rail transit vehicle |
| CN116842418A (en) * | 2023-05-31 | 2023-10-03 | 浙江中屹纺织机械科技有限公司 | Intelligent water-jet loom and control system thereof |
| CN116842418B (en) * | 2023-05-31 | 2024-01-05 | 浙江中屹纺织机械科技有限公司 | Intelligent water-jet loom and control system thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059601B (en) | Intelligent fault diagnosis method for multi-feature extraction and fusion | |
| CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
| CN116012681A (en) | Method and system for diagnosing motor faults of pipeline robot based on sound vibration signal fusion | |
| CN107657250B (en) | Bearing fault detection and positioning method and detection and positioning model implementation system and method | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| US7577548B1 (en) | Integrated framework for diagnosis and prognosis of components | |
| Pan et al. | A deep learning network via shunt-wound restricted Boltzmann machines using raw data for fault detection | |
| Sony et al. | Multiclass damage identification in a full-scale bridge using optimally tuned one-dimensional convolutional neural network | |
| CN113837000A (en) | Small sample fault diagnosis method based on task sequencing meta-learning | |
| US20240069539A1 (en) | Sensor-agnostic mechanical machine fault identification | |
| KR102416474B1 (en) | Fault diagnosis apparatus and method based on machine-learning | |
| Ma et al. | Deep recurrent convolutional neural network for remaining useful life prediction | |
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| CN117076955A (en) | Fault detection method and system for high-voltage frequency converter | |
| Hong et al. | Supervised-learning-based intelligent fault diagnosis for mechanical equipment | |
| CN114331214A (en) | Domain-adaptive bearing voiceprint fault diagnosis method and system based on reinforcement learning | |
| CN116108367A (en) | Rotary mechanical system fault diagnosis method, system, electronic equipment and storage medium | |
| CN113095364B (en) | High-speed rail seismic event extraction method, medium and equipment using convolutional neural network | |
| CN115758237A (en) | Bearing fault classification method and system based on intelligent inspection robot | |
| Hao et al. | New fusion features convolutional neural network with high generalization ability on rolling bearing fault diagnosis | |
| Wolf et al. | Unsupervised data-driven automotive diagnostics with improved deep temporal clustering | |
| CN114841196A (en) | Mechanical equipment intelligent fault detection method and system based on supervised learning | |
| CN114676717A (en) | Bearing residual life prediction method, device and medium | |
| Mayaki et al. | Machinery Anomaly Detection using artificial neural networks and signature feature extraction | |
| CN117723782B (en) | Sensor fault identification positioning method and system for bridge structure health monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |