CN116934304B - Intelligent power distribution room equipment operation maintenance management system and method thereof - Google Patents
Intelligent power distribution room equipment operation maintenance management system and method thereof Download PDFInfo
- Publication number
- CN116934304B CN116934304B CN202310971741.3A CN202310971741A CN116934304B CN 116934304 B CN116934304 B CN 116934304B CN 202310971741 A CN202310971741 A CN 202310971741A CN 116934304 B CN116934304 B CN 116934304B
- Authority
- CN
- China
- Prior art keywords
- vector
- feature vector
- feature
- fusion
- temperature
- 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.)
- Active
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000010219 correlation analysis Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 168
- 230000004927 fusion Effects 0.000 claims description 89
- 239000011159 matrix material Substances 0.000 claims description 64
- 238000007726 management method Methods 0.000 claims description 43
- 230000004044 response Effects 0.000 claims description 35
- 238000010586 diagram Methods 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 15
- 238000012098 association analyses Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 230000002035 prolonged effect Effects 0.000 abstract description 3
- 238000013527 convolutional neural network Methods 0.000 description 26
- 230000006870 function Effects 0.000 description 16
- 238000011176 pooling Methods 0.000 description 15
- 230000008859 change Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 7
- 230000004913 activation Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009022 nonlinear effect Effects 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
An intelligent power distribution room equipment operation maintenance management system and a method thereof are disclosed. Firstly, acquiring vibration signals of monitored equipment in a preset time period, and a plurality of preset time points in the preset time period, then, carrying out time sequence collaborative correlation analysis on the temperature values and the current values of the preset time points, and the vibration signals in the preset time period to obtain equipment state characteristics, and then, determining whether the monitored equipment has faults or not based on the equipment state characteristics. Therefore, the automatic operation maintenance management of the power distribution room equipment can be realized, the problems of low efficiency and low accuracy caused by manual fault detection are avoided, the reliability of the equipment is improved, the maintenance cost is reduced, the service life of the equipment is prolonged, and the stability and the reliability of power supply are ensured.
Description
Technical Field
The present disclosure relates to the field of maintenance management, and more particularly, to an intelligent power distribution room equipment operation maintenance management system and a method thereof.
Background
The power distribution room equipment is a core component of an electric power system and is responsible for conveying and distributing electric energy. The intelligent power distribution room equipment operation maintenance management system is an intelligent system developed for improving the operation efficiency and reliability of the power distribution room equipment and reducing the maintenance cost and the downtime.
However, the conventional management system predicts and judges the occurrence time and type of the fault of the power distribution room equipment based on the service life of the equipment or experience of maintenance personnel, and the scheme is easily affected by subjective factors, and does not consider factors such as actual working environment, load change and the like of the equipment, so that the accuracy of fault prediction is low, and the fault may be missed or misreported.
In addition, conventional management systems typically employ a fixed maintenance period for equipment inspection and maintenance, and are unable to monitor the operational status and failure conditions of the equipment in real time. Once the equipment fails, maintenance personnel may take longer to detect and take corresponding action, resulting in longer downtime and greater economic loss.
Accordingly, an optimized intelligent power distribution room equipment operation maintenance management system is desired.
Disclosure of Invention
In view of this, the disclosure provides an operation maintenance management system and method for intelligent power distribution room equipment, which can realize automatic operation maintenance management for the power distribution room equipment, avoid the problems of low efficiency and low accuracy caused by manual fault detection, thereby improving the reliability of the equipment, reducing the maintenance cost, prolonging the service life of the equipment, and guaranteeing the stability and reliability of power supply.
According to an aspect of the present disclosure, there is provided an intelligent power distribution room equipment operation maintenance management system, including:
the data acquisition module is used for acquiring vibration signals of the monitored equipment in a preset time period, and temperature values and current values of a plurality of preset time points in the preset time period;
The device data time sequence association analysis module is used for performing time sequence collaborative association analysis on the temperature values and the current values of the plurality of preset time points and vibration signals of the preset time period to obtain device state characteristics; and
And the equipment fault detection module is used for determining whether the monitored equipment has faults or not based on the equipment state characteristics.
According to another aspect of the present disclosure, there is provided an intelligent power distribution room equipment operation maintenance management method, including:
Acquiring vibration signals of monitored equipment in a preset time period, and acquiring temperature values and current values of a plurality of preset time points in the preset time period;
performing time sequence collaborative correlation analysis on the temperature values and the current values of the plurality of preset time points and vibration signals of the preset time period to obtain equipment state characteristics; and
And determining whether the monitored equipment has faults or not based on the equipment state characteristics.
According to the embodiment of the disclosure, firstly, a vibration signal of a monitored device in a preset time period is acquired, temperature values and current values of a plurality of preset time points in the preset time period are acquired, then, time sequence collaborative correlation analysis is carried out on the temperature values and the current values of the preset time points, and the vibration signal in the preset time period is analyzed to obtain a device state characteristic, and then, whether the monitored device has faults or not is determined based on the device state characteristic. Therefore, the automatic operation maintenance management of the power distribution room equipment can be realized, the problems of low efficiency and low accuracy caused by manual fault detection are avoided, the reliability of the equipment is improved, the maintenance cost is reduced, the service life of the equipment is prolonged, and the stability and the reliability of power supply are ensured.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 illustrates a block diagram of an intelligent power distribution room equipment operation maintenance management system, according to an embodiment of the present disclosure.
Fig. 2 shows a block diagram of the device data timing correlation analysis module in the intelligent electrical distribution room device operation maintenance management system according to an embodiment of the present disclosure.
Fig. 3 shows a block diagram of the temperature-current timing correlation unit in the intelligent electrical room equipment operation maintenance management system according to an embodiment of the present disclosure.
Fig. 4 shows a block diagram of the device status feature extraction unit in the intelligent power distribution room device operation maintenance management system according to an embodiment of the present disclosure.
Fig. 5 illustrates a flowchart of an intelligent power distribution room equipment operation maintenance management method according to an embodiment of the present disclosure.
Fig. 6 illustrates an architectural diagram of an intelligent power distribution room equipment operation maintenance management method according to an embodiment of the present disclosure.
Fig. 7 illustrates an application scenario diagram of an intelligent power distribution room equipment operation maintenance management system according to an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the disclosure. All other embodiments, which can be made by one of ordinary skill in the art without undue burden based on the embodiments of the present disclosure, are also within the scope of the present disclosure.
As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
Aiming at the technical problems, the technical concept of the present disclosure is to collect vibration signals, temperature and current data of the power distribution room equipment in a preset time period through a sensor, introduce data and an analysis algorithm at the rear end to perform time sequence collaborative analysis of various parameter data of the power distribution room equipment, so as to automatically monitor the running state of the equipment, and timely give an alarm when detecting that the power distribution room equipment has faults, so that maintenance personnel can timely take corresponding measures. Through the mode, the automatic operation maintenance management of the power distribution room equipment can be realized, the problems of low efficiency and low accuracy caused by manual fault detection are avoided, the reliability of the equipment is improved, the maintenance cost is reduced, the service life of the equipment is prolonged, and the stability and the reliability of power supply are ensured.
Specifically, fig. 1 shows a block diagram schematic of an intelligent power distribution room equipment operation maintenance management system according to an embodiment of the present disclosure. As shown in fig. 1, an intelligent power distribution room equipment operation maintenance management system 100 according to an embodiment of the present disclosure includes: a data acquisition module 110, configured to acquire vibration signals of a monitored device in a predetermined time period, and temperature values and current values at a plurality of predetermined time points in the predetermined time period; the device data timing sequence association analysis module 120 is configured to perform timing sequence collaborative association analysis on the temperature values and the current values at the plurality of predetermined time points, and the vibration signals in the predetermined time period to obtain a device state feature; and an equipment fault detection module 130, configured to determine whether a monitored equipment has a fault based on the equipment status feature.
Accordingly, in the technical scheme of the disclosure, firstly, vibration signals of monitored equipment in a preset time period are acquired through a vibration sensor, and temperature values and current values of a plurality of preset time points in the preset time period are acquired. In particular, here, the vibration signal is used to reflect the operation state of the monitored device, and by performing monitoring analysis on the vibration signal, it is possible to determine whether there is abnormal vibration or malfunction of the device. The change in current may reflect a load change, fault condition, or other abnormal condition of the device. And, since heat is generated when current passes through the device, a change in temperature may be associated with a change in current of the device to reflect the operating state of the device and the heat generation.
Then, considering the dynamic change rule of the time sequence in the time dimension due to the temperature value and the current value, and the time sequence cooperative association relationship is also provided between the temperature value and the current value, that is, when the current of the monitored equipment changes, the internal temperature of the monitored equipment correspondingly changes due to heat generated by the current. Therefore, in order to better characterize the working state of the device by using the time sequence cooperative correlation characteristics of the temperature value and the current value, in the technical scheme of the disclosure, the temperature value and the current value at the plurality of preset time points need to be arranged into a temperature time sequence input vector and a current time sequence input vector according to a time dimension, so as to integrate the distribution information of the temperature value and the current value in time sequence respectively.
Then, the position-wise point division between the temperature time sequence input vector and the current time sequence input vector is further calculated to obtain a temperature-current position-by-position response time sequence input vector. It should be understood that during operation of the power distribution room device, the temperature is caused to fluctuate correspondingly by the change of the current, so that the relative change situation between the temperature and the current, namely the proportional relation between the change of the temperature and the change of the current at each time point, can be captured by dividing the temperature time sequence input vector and the current time sequence input vector according to the position points, so that the correlation and the potential causal relation between the temperature and the current can be found, and the capturing of the temperature fluctuation characteristic caused by the change of the current is facilitated. In this way, it is helpful to determine whether the operating condition of the device is normal, such as whether there is overheating, overload, or other abnormal conditions.
Then, feature mining of the waveform pattern of the vibration signal is performed using a convolutional neural network model having excellent performance in implicit feature extraction of an image to extract vibration timing implicit feature distribution information of the monitored device. And processing the temperature-current position-by-position response time sequence input vector through a one-dimensional convolutional neural network model to extract time sequence response associated characteristic information between the temperature value and the current value. Since both the characteristic information can reflect the operating state characteristics of the monitored equipment. Therefore, in order to be able to further improve the accuracy of the operation state and fault detection for the monitored apparatus, in the technical scheme of the present disclosure, it is desirable to optimize the expression of the timing distribution feature of the vibration signal based on the timing cooperative correlation feature of the temperature-current using a CLIP model including a sequence encoder and an image encoder.
Specifically, the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal are passed through a CLIP model comprising a sequence encoder and an image encoder to obtain an initial multi-modal fusion feature matrix. In particular, here, the image encoder is an image feature extractor based on a convolutional neural network model, and the sequence encoder is a sequence encoder based on a one-dimensional convolutional neural network model. Therefore, the time sequence characteristic distribution of the vibration signal can be subjected to characteristic optimization expression based on the time sequence cooperative correlation characteristic distribution of the temperature and the current, so that the accuracy of subsequent classification is improved.
Accordingly, as shown in fig. 2, the device data timing relationship analysis module 120 includes: a temperature-current timing correlation unit 121 for performing position-dependent encoding on the temperature values and the current values at the plurality of predetermined time points to obtain a temperature-current position-by-position response timing input vector; the device state feature extraction unit 122 is configured to perform multi-modal associated feature extraction on the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal to obtain an initial multi-modal fusion feature matrix; and an optimizing unit 123, configured to optimize the initial multi-mode fusion feature matrix to obtain a multi-mode fusion feature matrix as the device state feature.
More specifically, as shown in fig. 3, the temperature-current timing correlation unit 121 includes: a data timing arrangement subunit 1211 for arranging the temperature values and the current values of the plurality of predetermined time points into a temperature timing input vector and a current timing input vector according to a time dimension; and a device parameter position-by-position response correlation subunit 1212 for calculating a position-by-position point division between the temperature timing input vector and the current timing input vector to obtain the temperature-current position-by-position response timing input vector. It should be appreciated that the temperature-current timing correlation unit 121 includes two sub-units, a data timing arrangement sub-unit 1211 and a device parameter position-by-position response correlation sub-unit 1212. Wherein the data timing arrangement sub-unit 1211 functions to arrange the temperature values and current values at a plurality of predetermined time points into a temperature timing input vector and a current timing input vector in a time dimension, which means that it arranges the temperature and current data in a time order to form a time-series vector for subsequent processing and analysis. The function of the device parameter position-by-position response correlation subunit 1212 is to calculate a position-by-position division operation between the temperature-time-series input vector and the current-time-series input vector to obtain a temperature-current position-by-position response time-series input vector, which means that it divides the temperature and current data at the same position to generate a new vector reflecting the position-by-position response relationship between the temperature and the current.
More specifically, the device state feature extraction unit 122 is configured to: and passing the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal through a CLIP model comprising a sequence encoder and an image encoder to obtain the initial multi-mode fusion feature matrix. In particular, here, the image encoder is an image feature extractor based on a convolutional neural network model, and the sequence encoder is a sequence encoder based on a one-dimensional convolutional neural network model.
It is worth mentioning that the convolutional neural network (Convolutional Neural Network, CNN) is a deep learning model, and the core idea of the convolutional neural network is to extract local features of input data by using a convolutional layer (Convolutional Layer) and a pooling layer (Pooling Layer), and classify or regress through a fully connected layer (Fully Connected Layer). The convolution layer performs a convolution operation on the input data using a set of learnable filters (also referred to as convolution kernels) to extract spatial features of the input data, the convolution operation can effectively capture local patterns in the image, and the feature of parameter sharing reduces the number of parameters of the network. After the convolutional layer, a nonlinear activation function (e.g., reLU) is typically applied to introduce nonlinear properties that increase the expressive power of the network. The pooling layer is used for reducing the space dimension of the output of the convolution layer, reducing the calculation amount and extracting more remarkable characteristics, and common pooling operations comprise maximum pooling and average pooling. The full connection layer connects the outputs of the preceding convolutional and pooling layers to one or more neurons for final classification or regression tasks. To reduce overfitting, dropout techniques are often used in convolutional neural networks, where the output of a portion of the neurons is randomly discarded with a certain probability during the training process. By stacking multiple convolutional layers, activation functions, pooling layers, and fully-connected layers, the convolutional neural network can gradually extract advanced features of input data and perform efficient classification and recognition. This architecture makes convolutional neural networks excellent in processing images and other data with a grid structure, and has achieved significant effort in many computer vision tasks.
It is worth mentioning that the one-dimensional convolutional neural network (1D Convolutional Neural Network,1D CNN) is a variant of the convolutional neural network for processing one-dimensional sequence data, and unlike the conventional two-dimensional convolutional neural network (2D CNN) for processing image data, the one-dimensional convolutional neural network applies a convolutional operation to extract local features in the sequence data. The basic structure of the one-dimensional convolutional neural network is similar to that of a traditional convolutional neural network, and the one-dimensional convolutional neural network comprises a convolutional layer, an activation function, a pooling layer, a full-connection layer and the like. The following are the main components of the one-dimensional convolutional neural network model: 1. input layer: receiving one-dimensional sequence data as input of a network; 2. convolution layer: the convolution layer performs convolution operation on input data by using a one-dimensional convolution kernel, so that local characteristics of the input data are extracted, and the convolution kernel performs convolution operation on the input sequence through a sliding window to obtain an output sequence; 3. activation function: after the convolutional layer, a nonlinear activation function (e.g., reLU) is typically applied to introduce nonlinear properties to increase the expressive power of the network; 4. pooling layer: the pooling layer is used for reducing the dimension of the output of the convolution layer, reducing the calculation amount and extracting more remarkable characteristics. Common pooling operations include maximum pooling and average pooling. 5. Full tie layer: the full connection layer connects the outputs of the preceding convolutional and pooling layers to one or more neurons for final classification, regression, or other tasks. The one-dimensional convolutional neural network has certain advantages when processing sequence data, can capture local modes and features in the sequence, and is suitable for tasks such as text classification, voice recognition, time sequence analysis and the like.
More specifically, as shown in fig. 4, the device state feature extraction unit 122 includes: a sequence encoding subunit 1221 configured to pass the temperature-current position-by-position response timing input vector through the sequence encoder to obtain a sequence feature vector; an image encoding subunit 1222 for passing the waveform image of the vibration signal through the image encoder to obtain an image feature vector; and a fusion subunit 1223, configured to fuse the sequence feature vector and the image feature vector to obtain the initial multi-modal fusion feature matrix.
In the technical scheme of the application, when the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal pass through a CLIP model comprising an image encoder and a sequence encoder to obtain an initial multi-mode fusion feature matrix, the sequence feature vector obtained by the temperature-current position-by-position response time sequence input vector through the sequence encoder and the image feature vector obtained by the waveform diagram of the vibration signal pass through the image encoder are multiplied by each other to obtain the initial multi-mode fusion feature matrix, so that only the feature value of a diagonal position in the initial multi-mode fusion feature matrix expresses the position-by-position corresponding feature of the sequence feature vector and the image feature vector, and the position-by-position fusion effect of the initial multi-mode fusion feature matrix on the sequence feature vector and the image feature vector is expected to be improved.
Here, the applicant of the present application considers the non-homogeneous point-by-point correspondence between the sequence feature vector obtained by extracting the sequence local correlation feature of the temperature-current position-by-time response timing input vector based on the one-dimensional convolution operation of the sequence encoder and the image feature vector obtained by extracting the image semantic local correlation feature of the waveform map of the vibration signal by the two-dimensional convolution operation of the image encoder, thereby, for the sequence feature vector, for example, recording asAnd the image feature vector, e.g. denoted/>Spatially adaptive point learning on non-homogeneous Hilbert-face to obtain fused feature vectors, e.g., denoted/>。
Thus, by characterizing the sequence with non-homogeneous Gilbert spatial metricsAnd the image feature vector/>Vector point correlations between the sequences are subjected to one-dimensional convolution, and the sequence feature vectors/>And the image feature vector/>Feature manifold of the high-dimensional feature representation of (a) has non-axis alignment (non-axis alignment) characteristics in a high-dimensional feature space, performs adaptive point learning toward a hyperplane in a face space of a manifold convergence hyperplane based on a Hilbert space, and performs adaptive point learning toward the hyperplane in a manner facing the sequence feature vector/>And the image feature vector/>The air measurement (aerial measurement) of each distribution convergence direction is corrected, so that the sequence characteristic vector/>, is improvedAnd the image feature vector/>Non-homogeneous point-by-point fusibility between the fusion feature vectors, thereby improving the fusion feature vectors/>Then, the fusion feature vector/>The multi-mode feature matrix is transposed and multiplied with the original multi-mode feature matrix to obtain a point-by-point fusion feature matrix, and the point-by-point fusion feature matrix is further fused with the original multi-mode fusion feature matrix, so that the position-by-position fusion effect of the original multi-mode fusion feature matrix on the sequence feature vector and the image feature vector can be improved, and the multi-mode fusion feature matrix is obtained.
Accordingly, in a specific example, the optimizing unit 123 is further configured to: fusing the sequence feature vector and the image feature vector by the following fusion formula to obtain a fused feature vector; wherein, the fusion formula is: Wherein/> Representing the sequence feature vector,/>Representing the image feature vector,/>Representing a transpose operation,/>，/>And/>Representing non-homogeneous minpoint distance based on Gilbert space, and/>And/>Is super-parameter,/>And/>Feature vector/>, respectivelyAndAnd feature vector/>And/>Are all row vectors,/>For multiplying by position points,/>For addition by position,/>Representing covariance matrix,/>Representing the fused feature vector; multiplying the fusion feature vector with a transpose vector of the fusion feature vector to obtain a point-by-point fusion feature matrix; and fusing the point-by-point fusion feature matrix and the initial multi-mode fusion feature matrix to obtain the multi-mode fusion feature matrix.
And further, the multi-mode fusion feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored equipment has faults or not. The method is characterized in that the working state characteristic information of the monitored equipment after characteristic optimization expression is utilized to carry out classification processing, so that whether the monitored equipment has faults or not is detected, and an alarm is timely given when the faults of the power distribution room equipment are detected, so that maintenance personnel can take corresponding measures in time.
Accordingly, the device fault detection module 130 is further configured to: and the multi-mode fusion feature matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored equipment has faults or not.
Accordingly, in one possible implementation manner, the multi-mode fusion feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the monitored device has a fault, and the method includes: expanding the multi-mode fusion feature matrix into classification feature vectors according to row vectors or column vectors; performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
That is, in the technical solution of the present disclosure, the label of the classifier includes that the monitored device has a fault (first label) and that the monitored device has no fault (second label), where the classifier determines, through a soft maximum function, to which classification label the multi-modal fusion feature matrix belongs. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether the monitored device has a fault", which is simply that there are two kinds of classification tags, and the probability that the output characteristic is the sum of the two classification tags sign, that is, p1 and p2 is one. Therefore, the classification result of whether the monitored equipment has faults is actually converted into the classified probability distribution conforming to the classification of the natural law through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether the monitored equipment has faults.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
It should be noted that the full-connection encoding (Fully Connected Encoding) refers to a process of encoding input data through a full-connection layer to obtain an encoded feature vector. Fully connected layers are a common layer type in convolutional neural networks, where each neuron is connected to all neurons of the previous layer, each connection having a weight for linear combination and nonlinear transformation of the inputs. In the multi-mode fusion task, after feature matrixes of a plurality of modes (such as images, audios, texts and the like) are fused, the fused feature matrixes can be unfolded into classified feature vectors in a mode of row vectors or column vectors. The classified feature vectors are then encoded by the full join layer, i.e., the input data is mapped to a higher dimensional feature space by linear combination and nonlinear transformation. The function of full-concatenated coding is to perform more complex feature extraction and representation of the input data to capture more information and patterns in the input data. Full-connectivity encoding may be implemented by a stack of multiple full-connectivity layers, each of which may incorporate different nonlinear activation functions, such as ReLU, sigmoid, etc., to increase the expressive power of the network. Through the combination of multiple fully connected layers, the network can learn gradually the high-level features and abstract representations in the input data. In the classification task, the coding classification feature vector obtained after full-connection coding can better represent the features of the input samples, and has better distinguishability. These encoded feature vectors can be input into the Softmax classification function of the classifier, and the final classification result is obtained by calculating the probability distribution of each class. In summary, full-join encoding performs linear combination and nonlinear transformation on input data through the full-join layer, maps the input data to a higher-dimensional feature space, extracts richer feature representations, and provides better input features for classification tasks.
Like this, can carry out automatic monitoring to the running state of electricity distribution room equipment to in time send out the alarm when detecting that electricity distribution room equipment has the trouble, so that maintenance personal can in time take corresponding measure, through this kind of mode, can improve the reliability of equipment, and reduce cost of maintenance, extension equipment life-span, thereby guarantee power supply's stability and reliability.
In summary, the operation maintenance management system 100 for intelligent power distribution room equipment according to the embodiments of the present disclosure is illustrated, which can implement automatic operation maintenance management for power distribution room equipment, and avoid the problems of low efficiency and low accuracy caused by manual fault detection, thereby improving reliability of the equipment, reducing maintenance cost, prolonging service life of the equipment, and guaranteeing stability and reliability of power supply.
As described above, the intelligent power distribution room equipment operation maintenance management system 100 according to the embodiment of the present disclosure may be implemented in various terminal equipment, for example, a server having an intelligent power distribution room equipment operation maintenance management algorithm, or the like. In one example, the intelligent power distribution room equipment operation maintenance management system 100 may be integrated into the terminal equipment as a software module and/or hardware module. For example, the intelligent power distribution room equipment operation maintenance management system 100 may be a software module in the operating system of the terminal equipment, or may be an application developed for the terminal equipment; of course, the intelligent power distribution room equipment operation maintenance management system 100 may also be one of a plurality of hardware modules of the terminal equipment.
Alternatively, in another example, the intelligent power distribution room equipment operation maintenance management system 100 and the terminal equipment may be separate devices, and the intelligent power distribution room equipment operation maintenance management system 100 may be connected to the terminal equipment through a wired and/or wireless network and transmit interactive information in a contracted data format.
Fig. 5 illustrates a flowchart of an intelligent power distribution room equipment operation maintenance management method according to an embodiment of the present disclosure. Fig. 6 shows a schematic diagram of a system architecture of an intelligent power distribution room equipment operation maintenance management method according to an embodiment of the present disclosure. As shown in fig. 5 and 6, an intelligent power distribution room equipment operation maintenance management method according to an embodiment of the present disclosure includes: s110, acquiring vibration signals of monitored equipment in a preset time period, and acquiring temperature values and current values of a plurality of preset time points in the preset time period; s120, carrying out time sequence collaborative correlation analysis on the temperature values and the current values of the plurality of preset time points and vibration signals of the preset time period to obtain equipment state characteristics; and S130, determining whether the monitored equipment has faults or not based on the equipment state characteristics.
In one possible implementation manner, performing time sequence collaborative correlation analysis on the temperature values and the current values of the plurality of preset time points and vibration signals of the preset time period to obtain equipment state characteristics, including: performing position-dependent coding on the temperature values and the current values of the plurality of preset time points to obtain a position-by-position response time sequence input vector of the temperature-current; and performing multi-mode association feature extraction on the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal to obtain a multi-mode fusion feature matrix as the equipment state feature.
In one possible implementation, the encoding the temperature values and the current values at the plurality of predetermined time points in a position-dependent manner to obtain a temperature-current position-by-position response time sequence input vector includes: arranging the temperature values and the current values of the plurality of preset time points into a temperature time sequence input vector and a current time sequence input vector according to a time dimension; and calculating a position-wise division between the temperature time sequence input vector and the current time sequence input vector to obtain the temperature-current position-by-position response time sequence input vector.
In one possible implementation manner, performing multi-mode correlation feature extraction on the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal to obtain a multi-mode fusion feature matrix as the device state feature, including: and passing the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal through a CLIP model comprising a sequence encoder and an image encoder to obtain the multi-mode fusion feature matrix.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described intelligent power distribution room equipment operation maintenance management method have been described in detail in the above description of the intelligent power distribution room equipment operation maintenance management system with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
Fig. 7 illustrates an application scenario diagram of an intelligent power distribution room equipment operation maintenance management system according to an embodiment of the present disclosure. As shown in fig. 7, in this application scenario, first, a vibration signal of a monitored device for a predetermined period of time (e.g., D1 illustrated in fig. 7) is acquired, and temperature values and current values for a plurality of predetermined time points within the predetermined period of time (e.g., D2 illustrated in fig. 7), and then the temperature values and current values for the plurality of predetermined time points are input to a server (e.g., S illustrated in fig. 7) where an intelligent electrical room device operation maintenance management algorithm is deployed, wherein the server is capable of using the intelligent electrical room device operation maintenance management algorithm to process the temperature values and current values for the plurality of predetermined time points, and the vibration signal for the predetermined period of time to obtain a classification result for indicating whether or not there is a fault in the monitored device.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (4)
1. An intelligent power distribution room equipment operation maintenance management system, characterized by comprising:
the data acquisition module is used for acquiring vibration signals of the monitored equipment in a preset time period, and temperature values and current values of a plurality of preset time points in the preset time period;
The device data time sequence association analysis module is used for performing time sequence collaborative association analysis on the temperature values and the current values of the plurality of preset time points and vibration signals of the preset time period to obtain device state characteristics; and
The equipment fault detection module is used for determining whether the monitored equipment has faults or not based on the equipment state characteristics;
the device data time sequence association analysis module comprises:
a temperature-current time sequence association unit, which is used for carrying out position association coding on the temperature values and the current values of the plurality of preset time points so as to obtain a position-by-position response time sequence input vector of the temperature-current;
the equipment state feature extraction unit is used for carrying out multi-mode association feature extraction on the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal so as to obtain an initial multi-mode fusion feature matrix; and
The optimizing unit is used for optimizing the initial multi-mode fusion feature matrix to obtain the multi-mode fusion feature matrix as the equipment state feature;
Wherein the temperature-current timing relating unit includes:
a data time sequence arrangement subunit, configured to arrange the temperature values and the current values at the plurality of predetermined time points into a temperature time sequence input vector and a current time sequence input vector according to a time dimension; and
The device parameter position-by-position response association subunit is used for calculating the division of the position-by-position points between the temperature time sequence input vector and the current time sequence input vector to obtain the temperature-current position-by-position response time sequence input vector;
Wherein, the equipment state feature extraction unit includes:
A sequence encoding subunit, configured to pass the temperature-current position-by-position response time sequence input vector through a sequence encoder to obtain a sequence feature vector;
An image coding subunit, configured to pass the waveform diagram of the vibration signal through an image encoder to obtain an image feature vector; and
A fusion subunit, configured to fuse the sequence feature vector and the image feature vector to obtain the initial multi-mode fusion feature matrix;
Wherein, the optimizing unit is used for:
fusing the sequence feature vector and the image feature vector by the following fusion formula to obtain a fused feature vector;
wherein, the fusion formula is:
，
Wherein, Representing the sequence feature vector,/>Representing the image feature vector,/>Indicating the operation of the transpose,，/>And/>Representing a non-homogeneous minpoint distance based on Hilbert space, and/>And/>Is the parameter of the ultrasonic wave to be used as the ultrasonic wave,And/>Feature vector/>, respectivelyAnd/>And feature vector/>And/>Are all row vectors,/>For multiplying by position points,/>For addition by position,/>Representing covariance matrix,/>Representing the fused feature vector;
multiplying the fusion feature vector with a transpose vector of the fusion feature vector to obtain a point-by-point fusion feature matrix; and
Fusing the point-by-point fusion feature matrix and the initial multi-mode fusion feature matrix to obtain the multi-mode fusion feature matrix;
In the optimization unit, by carrying out one-dimensional convolution on vector point association between the sequence feature vector and the image feature vector by using non-homogeneous hilbert space measurement, aiming at the non-axis alignment characteristic of a feature manifold represented by high-dimensional features of the sequence feature vector and the image feature vector in the high-dimensional feature space, carrying out self-adaptive point learning towards a hyperplane on a surface of a manifold convergence hyperplane based on the hilbert space, and carrying out correction on aerial measurement facing respective distribution convergence directions of the sequence feature vector and the image feature vector, thereby improving the fusion expression effect of the fusion feature vector, multiplying the fusion feature vector by the self-transposition of the fusion feature vector to obtain a point-by-point fusion feature matrix, and further fusing the multi-mode point-by-point fusion feature matrix with the initial multi-mode fusion feature matrix to improve the position-by-mode fusion feature matrix relative to the sequence feature vector and the image feature vector to obtain the point-by-point fusion feature matrix.
2. The intelligent power distribution room equipment operation maintenance management system according to claim 1, wherein the equipment state feature extraction unit is configured to:
and passing the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal through a CLIP model comprising a sequence encoder and an image encoder to obtain the initial multi-mode fusion feature matrix.
3. The intelligent power distribution room equipment operation maintenance management system of claim 2, wherein the equipment failure detection module is further configured to:
And the multi-mode fusion feature matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored equipment has faults or not.
4. An intelligent power distribution room equipment operation maintenance management method is characterized by comprising the following steps:
Acquiring vibration signals of monitored equipment in a preset time period, and acquiring temperature values and current values of a plurality of preset time points in the preset time period;
performing time sequence collaborative correlation analysis on the temperature values and the current values of the plurality of preset time points and vibration signals of the preset time period to obtain equipment state characteristics; and
Determining whether the monitored equipment has a fault or not based on the equipment state characteristics;
The method for analyzing the time sequence collaborative correlation of the vibration signals of the preset time points to obtain the equipment state characteristics comprises the following steps:
Performing position-dependent coding on the temperature values and the current values of the plurality of preset time points to obtain a position-by-position response time sequence input vector of the temperature-current;
Performing multi-mode association feature extraction on the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal to obtain an initial multi-mode fusion feature matrix;
optimizing the initial multi-mode fusion feature matrix to obtain a multi-mode fusion feature matrix serving as the equipment state feature;
Wherein the encoding of the temperature values and the current values at the plurality of predetermined time points in a position-dependent manner to obtain a temperature-current position-by-position response time sequence input vector comprises:
arranging the temperature values and the current values of the plurality of preset time points into a temperature time sequence input vector and a current time sequence input vector according to a time dimension; and
Dividing the point-by-point between the temperature time sequence input vector and the current time sequence input vector by the point-by-point to obtain a temperature-current position-by-position response time sequence input vector;
The multi-mode associated feature extraction is performed on the temperature-current position-by-position response time sequence input vector and the waveform diagram of the vibration signal to obtain an initial multi-mode fusion feature matrix, and the method comprises the following steps:
passing the temperature-current position-by-position response time sequence input vector through a sequence encoder to obtain a sequence characteristic vector;
passing the waveform diagram of the vibration signal through an image encoder to obtain an image feature vector; and
Fusing the sequence feature vector and the image feature vector to obtain the initial multi-mode fusion feature matrix;
The optimizing the initial multi-mode fusion feature matrix to obtain the multi-mode fusion feature matrix as the equipment state feature comprises the following steps:
fusing the sequence feature vector and the image feature vector by the following fusion formula to obtain a fused feature vector;
wherein, the fusion formula is:
，
Wherein, Representing the sequence feature vector,/>Representing the image feature vector,/>Indicating the operation of the transpose,，/>And/>Representing a non-homogeneous minpoint distance based on Hilbert space, and/>And/>Is the parameter of the ultrasonic wave to be used as the ultrasonic wave,And/>Feature vector/>, respectivelyAnd/>And feature vector/>And/>Are all row vectors,/>For multiplying by position points,/>For addition by position,/>Representing covariance matrix,/>Representing the fused feature vector;
multiplying the fusion feature vector with a transpose vector of the fusion feature vector to obtain a point-by-point fusion feature matrix; and
Fusing the point-by-point fusion feature matrix and the initial multi-mode fusion feature matrix to obtain the multi-mode fusion feature matrix;
The initial multi-mode fusion feature matrix is optimized to obtain a multi-mode fusion feature matrix as the equipment state feature, vector point association between the sequence feature vector and the image feature vector is subjected to one-dimensional convolution by using non-homogeneous Hilbert space measurement, non-axis alignment characteristics of feature manifolds represented by high-dimensional features of the sequence feature vector and the image feature vector in a high-dimensional feature space can be aimed at, self-adaptive point learning is carried out on a surface of a manifold convergence hyperplane based on the Hilbert space towards the hyperplane, and air measurement facing respective distribution convergence directions of the sequence feature vector and the image feature vector is taken as correction, so that non-homogeneous point-by-point fusion performance between the sequence feature vector and the image feature vector is improved, fusion expression effect of the fusion feature vector is improved, then the fusion feature vector is multiplied with the self-transposition of the fusion feature vector to obtain point-by-point fusion feature matrix, and the multi-mode fusion feature matrix is further fused with the initial multi-mode fusion feature matrix to improve fusion effect of the initial multi-mode fusion feature matrix on the sequence feature vector and the image feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310971741.3A CN116934304B (en) | 2023-08-03 | 2023-08-03 | Intelligent power distribution room equipment operation maintenance management system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310971741.3A CN116934304B (en) | 2023-08-03 | 2023-08-03 | Intelligent power distribution room equipment operation maintenance management system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116934304A CN116934304A (en) | 2023-10-24 |
| CN116934304B true CN116934304B (en) | 2024-06-07 |
Family
ID=88382533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310971741.3A Active CN116934304B (en) | 2023-08-03 | 2023-08-03 | Intelligent power distribution room equipment operation maintenance management system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934304B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117498262A (en) * | 2023-10-31 | 2024-02-02 | 神州技测(深圳)科技有限公司 | High-voltage direct-current electronic load switch protection circuit |
| CN117474357B (en) * | 2023-11-02 | 2024-08-02 | 深圳汉驰科技有限公司 | Power distribution room operation and maintenance management method and system based on deep learning |
| CN117634217B (en) * | 2023-12-22 | 2024-04-30 | 浙江万事达建设科技有限公司 | Intelligent building management system and method based on digital twinning |
| CN117494056B (en) * | 2023-12-29 | 2024-03-22 | 长春黄金设计院有限公司 | Equipment fault early warning system and method based on big data technology |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578007A (en) * | 2017-09-01 | 2018-01-12 | 杭州电子科技大学 | A kind of deep learning face identification method based on multi-feature fusion |
| CN114048568A (en) * | 2021-11-17 | 2022-02-15 | 大连理工大学 | Rotating machine fault diagnosis method based on multi-source migration fusion contraction framework |
| CN114861827A (en) * | 2022-05-27 | 2022-08-05 | 太原理工大学 | Coal mining machine prediction diagnosis and health management method based on multi-source data fusion |
| CN115410069A (en) * | 2022-08-25 | 2022-11-29 | 绍兴幺贰玖零科技有限公司 | Fault detection method and system based on multiple attention mechanism |
| CN115600140A (en) * | 2022-09-07 | 2023-01-13 | 五凌电力有限公司新能源分公司（Cn） | Fan variable pitch system fault identification method and system based on multi-source data fusion |
| CN116089871A (en) * | 2023-01-13 | 2023-05-09 | 重庆邮电大学 | Motor state monitoring method based on semantic reasoning and deep extreme learning machine |
| CN116124448A (en) * | 2023-01-09 | 2023-05-16 | 江西仪能新能源微电网协同创新有限公司 | Fault diagnosis system and method for wind power gear box |
| CN116150566A (en) * | 2023-04-20 | 2023-05-23 | 浙江浙能迈领环境科技有限公司 | Ship fuel supply safety monitoring system and method thereof |
| CN116494816A (en) * | 2023-06-30 | 2023-07-28 | 江西驴宝宝通卡科技有限公司 | Charging management system and method for charging pile |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131673B (en) * | 2020-09-30 | 2021-09-28 | 西南石油大学 | Engine surge fault prediction system and method based on fusion neural network model |
-
2023
- 2023-08-03 CN CN202310971741.3A patent/CN116934304B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578007A (en) * | 2017-09-01 | 2018-01-12 | 杭州电子科技大学 | A kind of deep learning face identification method based on multi-feature fusion |
| CN114048568A (en) * | 2021-11-17 | 2022-02-15 | 大连理工大学 | Rotating machine fault diagnosis method based on multi-source migration fusion contraction framework |
| CN114861827A (en) * | 2022-05-27 | 2022-08-05 | 太原理工大学 | Coal mining machine prediction diagnosis and health management method based on multi-source data fusion |
| CN115410069A (en) * | 2022-08-25 | 2022-11-29 | 绍兴幺贰玖零科技有限公司 | Fault detection method and system based on multiple attention mechanism |
| CN115600140A (en) * | 2022-09-07 | 2023-01-13 | 五凌电力有限公司新能源分公司（Cn） | Fan variable pitch system fault identification method and system based on multi-source data fusion |
| CN116124448A (en) * | 2023-01-09 | 2023-05-16 | 江西仪能新能源微电网协同创新有限公司 | Fault diagnosis system and method for wind power gear box |
| CN116089871A (en) * | 2023-01-13 | 2023-05-09 | 重庆邮电大学 | Motor state monitoring method based on semantic reasoning and deep extreme learning machine |
| CN116150566A (en) * | 2023-04-20 | 2023-05-23 | 浙江浙能迈领环境科技有限公司 | Ship fuel supply safety monitoring system and method thereof |
| CN116494816A (en) * | 2023-06-30 | 2023-07-28 | 江西驴宝宝通卡科技有限公司 | Charging management system and method for charging pile |
Non-Patent Citations (1)
| Title |
|---|
| 基于多特征融合与改进QPSO-RVM的万能式断路器故障振声诊断方法;孙曙光;于晗;杜太行;王景芹;赵黎媛;;电工技术学报(第19期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116934304A (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116934304B (en) | Intelligent power distribution room equipment operation maintenance management system and method thereof | |
| CN116639010B (en) | Intelligent control system and method for charging pile | |
| CN116893336B (en) | High-low voltage switching device and method thereof | |
| CN117034123B (en) | Fault monitoring system and method for fitness equipment | |
| CN117375237B (en) | Substation operation and maintenance method and system based on digital twin technology | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN116929815A (en) | Equipment working state monitoring system and method based on Internet of things | |
| CN117155706B (en) | Network abnormal behavior detection method and system | |
| CN116683648A (en) | Intelligent power distribution cabinet and control system thereof | |
| CN116700193A (en) | Factory workshop intelligent monitoring management system and method thereof | |
| CN116992226A (en) | Water pump motor fault detection method and system | |
| CN117676099B (en) | Security early warning method and system based on Internet of things | |
| CN117589233A (en) | Intelligent detection method and system for running state of relay protection device | |
| CN118098603A (en) | Intensive care clinical information system and method for eicu | |
| CN116909712A (en) | Intelligent task scheduling system and method based on machine learning | |
| CN117951646A (en) | Data fusion method and system based on edge cloud | |
| Wu et al. | Remaining useful life prediction of bearings with different failure types based on multi-feature and deep convolution transfer learning | |
| CN117192416A (en) | Battery monitoring system and method based on BMS system | |
| CN117485842A (en) | Method and system for monitoring attitude of wheel bucket cross beam of gate type bucket wheel machine in real time | |
| CN117011609A (en) | Automatic tracking system and method for textile processing progress | |
| CN117689278B (en) | Construction quality intelligent management system and method | |
| CN117520993B (en) | Electric drive axle test system and method thereof | |
| CN118003961B (en) | Intelligent charging pile group control system and method | |
| CN116730226B (en) | Safety intelligent supervision system and method for cantilever crane | |
| CN117668753A (en) | System and method for analyzing equipment performance based on industrial park |
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 | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 514000 In Fuda High tech Zone Industrial Park, Meixian District, Meizhou City, Guangdong Province Patentee after: Guangdong Junyao Technology Co.,Ltd. Country or region after: China Address before: 514000 In Fuda High tech Zone Industrial Park, Meixian District, Meizhou City, Guangdong Province Patentee before: Guangdong Junyao Holding Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |