Operation and maintenance management system and method of intelligent network connection equipment
Through data processing algorithms based on artificial intelligence and deep learning, abnormal detection and early warning of intelligent connected devices are realized, which solves the problems of inefficiency and inability to prevent failures in traditional operation and maintenance management methods, and improves the efficiency and reliability of equipment management.
Patent Information
- Application Number
- CN202411506432.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The operation and maintenance management methods of traditional intelligent connected devices rely on manual regular inspections, which are inefficient and cannot prevent potential problems, resulting in increased equipment downtime and maintenance costs, especially in scenarios where the number of equipment is large and widely distributed, it is difficult to achieve efficient management.
Using data processing and analysis algorithms based on artificial intelligence and deep learning, the device's operating state parameters are collected by sensors, data subset segmentation, timing encoding and cluster contribution enhancement expression processing are performed to generate timing significant aggregation representation of the device's operating state. Used for equipment abnormality detection and early warning, realizing early failure warning and predictive maintenance.
It improves the overall efficiency and operating reliability of equipment management, reduces equipment downtime and maintenance costs, and realizes timely and effective operation and maintenance management of intelligent connected equipment.
Smart Images

Figure CN119027104A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent matching, and more specifically, to an operation and maintenance management system and method for intelligent networked devices. Background Art
[0002] With the rapid development of Internet of Things (IoT) technology, the application of intelligent networked devices is becoming more and more extensive, covering multiple fields such as automobiles, smart homes and industrial automation. These devices usually need to operate stably for a long time, and when failure occurs, they must be maintained or replaced in time to ensure that the overall performance of the system is not affected. Therefore, how to effectively manage and maintain these devices has become a key issue.
[0003] Traditional intelligent network equipment operation and maintenance management and fault detection methods usually rely on manual regular inspections or inspection and maintenance after the equipment stops working completely. This method is not only inefficient, but also often fails to prevent potential problems, resulting in increased equipment downtime and maintenance costs. Specifically, traditional operation and maintenance management methods are usually based on a post-event response model, that is, maintenance is only carried out when the equipment has obvious failures or stops working completely. This method cannot provide early warnings, and often leads to passive responses when failures occur, increasing equipment downtime and maintenance costs. In addition, regular manual inspections and maintenance are not only labor-intensive and material-intensive, but also inefficient. Especially in scenarios where the number of devices is large and widely distributed, traditional equipment operation and maintenance management methods are difficult to achieve efficient management.
[0004] Therefore, an optimized operation and maintenance management solution for intelligent connected devices is desired. Summary of the invention
[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an operation and maintenance management system and method for intelligent networked devices, which analyzes the data set of the collected and transmitted equipment operation status parameters by using data processing and analysis algorithms based on artificial intelligence and deep learning, so as to capture the time-series aggregation information about the equipment operation status, and use this dynamic time-series aggregation information to monitor equipment anomalies, which can timely discover and warn of abnormal conditions of intelligent networked devices, and help to carry out timely and effective equipment operation and maintenance management. Through such a more intelligent equipment operation and maintenance management method, it can provide a basis for early warning of faults and predictive maintenance of intelligent networked devices, which is conducive to improving the overall efficiency of equipment management and the reliability of equipment operation.
[0006] According to one aspect of the present application, a method for operation and maintenance management of intelligent networked devices is provided, which includes: collecting a data set of device operation status parameters of the intelligent networked devices through sensors; transmitting the data set of the device operation status parameters to a cloud processor; in the cloud processor, processing the data set of the device operation status parameters to determine whether there is an abnormality in the device working state of the intelligent networked devices, including: performing data subset segmentation on the data set of the device operation status parameters to obtain a set of data subsets of the device operation status parameters; performing time series encoding on the set of data subsets of the device operation status parameters to obtain a set of local time series correlation features of the device operation status parameters; performing feature aggregation processing based on clustering contribution enhanced expression on the set of local time series correlation features of the device operation status parameters to obtain a time series significant aggregation representation of the device operation status parameters; based on the time series significant The aggregation representation performs equipment anomaly detection to determine whether there is an abnormality in the equipment working state; in response to detecting that there is an abnormality in the equipment working state of the intelligent connected device, the detection result and the abnormality information are transmitted to the operation and maintenance terminal for display; wherein, the set of local time series correlation features of the equipment operation state parameters is subjected to feature aggregation processing based on clustering contribution enhanced expression to obtain a significant time series aggregation representation of the equipment operation state parameters, including: clustering analysis is performed on the set of local time series correlation feature vectors of the equipment operation state parameters to obtain a self-supervised cluster representation vector of the local time series correlation features of the equipment operation state parameters; based on the self-supervised cluster representation vector of the local time series correlation features of the equipment operation state parameters, feature clustering field modulation aggregation is performed on the set of local time series correlation feature vectors of the equipment operation state parameters to obtain a significant time series aggregation representation vector of the equipment operation state parameters as the significant time series aggregation representation of the equipment operation state parameters.
[0007] According to another aspect of the present application, an operation and maintenance management system for intelligent networked devices is provided, which includes: a data acquisition module, which is used to collect a data set of device operating status parameters of intelligent networked devices through sensors; a data transmission module, which is used to transmit the data set of device operating status parameters to a cloud processor; a data processing module, which is used to process the data set of device operating status parameters in the cloud processor to determine whether there is an abnormality in the device working state of the intelligent networked device; an abnormality detection module, which is used to transmit the detection result and abnormality information to an operation and maintenance terminal for display in response to detecting that there is an abnormality in the device working state of the intelligent networked device; wherein, in the cloud processor, processing the data set of the device operating status parameters to determine whether there is an abnormality in the device working state of the intelligent networked device includes: data subset segmentation of the data set of the device operating status parameters to obtain a set of data subsets of the device operating status parameters; time series encoding of the set of data subsets of the device operating status parameters to obtain a device operating state parameter set; A set of local time series correlation features of equipment operation status parameters; performing feature aggregation processing based on cluster contribution enhanced expression on the set of local time series correlation features of the equipment operation status parameters to obtain a significant time series aggregation representation of the equipment operation status parameters; performing equipment anomaly detection based on the significant time series aggregation representation of the equipment operation status parameters to determine whether there is an abnormality in the equipment working state; wherein, performing feature aggregation processing based on cluster contribution enhanced expression on the set of local time series correlation features of the equipment operation status parameters to obtain a significant time series aggregation representation of the equipment operation status parameters, including: performing cluster analysis on the set of local time series correlation feature vectors of the equipment operation status parameters to obtain a self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters; based on the self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters, performing feature clustering field modulation aggregation on the set of local time series correlation feature vectors of the equipment operation status parameters to obtain a significant time series aggregation representation vector of the equipment operation status parameters as the significant time series aggregation representation of the equipment operation status parameters.
[0008] Compared with the prior art, the operation and maintenance management system and method of intelligent networked equipment provided by this application analyzes the data set of these collected and transmitted equipment operation status parameters by using data processing and analysis algorithms based on artificial intelligence and deep learning, so as to capture the time-series aggregation information about the equipment operation status, and use this dynamic time-series aggregation information to monitor equipment anomalies, which can timely discover and warn of abnormal conditions of intelligent networked equipment, and help to carry out timely and effective equipment operation and maintenance management. Through such a more intelligent equipment operation and maintenance management method, it can provide a basis for early warning of faults and predictive maintenance of intelligent networked equipment, which is conducive to improving the overall efficiency of equipment management and the reliability of equipment operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0010] Figure 1 Flow chart of the operation and maintenance management method of the intelligent networked device according to the embodiment of the present application.
[0011] Figure 2 This is a data flow diagram of the operation and maintenance management method of the intelligent networked device according to the embodiment of the present application.
[0012] Figure 3 This is a flowchart of sub-step S3 of the operation and maintenance management method of the intelligent networked device according to an embodiment of the present application.
[0013] Figure 4 It is a block diagram of the operation and maintenance management system of the intelligent networked device according to the embodiment of the present application. DETAILED DESCRIPTION
[0014] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.
[0015] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.
[0016] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.
[0017] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.
[0018] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.
[0019] Traditional operation and maintenance management and fault detection methods for intelligent networked devices usually rely on regular manual inspections or inspection and maintenance after the equipment stops working completely. This method is not only inefficient, but also often fails to prevent potential problems, resulting in increased equipment downtime and maintenance costs. Specifically, traditional operation and maintenance management methods are usually based on a post-event response model, that is, maintenance is only carried out when the equipment has obvious failures or stops working completely. This method cannot provide early warnings, and often leads to passive responses when failures occur, increasing equipment downtime and maintenance costs. In addition, regular manual inspections and maintenance are not only labor-intensive and material-intensive, but also inefficient. Especially in scenarios where the number of devices is large and widely distributed, traditional equipment operation and maintenance management methods are difficult to achieve efficient management. Therefore, an optimized operation and maintenance management solution for intelligent networked devices is desired.
[0020] With the development of big data technology and cloud computing, remote monitoring and predictive maintenance have become possible. By analyzing the large amount of data generated during the operation of the equipment, it is possible to monitor the health of the equipment in real time and detect potential signs of failure in advance, so as to take measures to avoid equipment downtime. In the operation and maintenance management of intelligent networked equipment, sensors are key components for collecting equipment operating status parameters. Sensors can monitor various indicators of the equipment in real time, such as temperature, humidity, vibration, etc. After the data is collected, it is transmitted to the server or data center in the cloud through the network. In the cloud, advanced data analysis algorithms are used to process this data to identify whether the equipment is in normal working condition. If an abnormal situation is detected, this information needs to be fed back to the operation and maintenance personnel in a timely manner or directly trigger the corresponding maintenance operation.
[0021] Based on this, in the technical solution of the present application, a method for operation and maintenance management of intelligent networked equipment is proposed. Figure 1 Flow chart of the operation and maintenance management method of the intelligent networked device according to the embodiment of the present application. Figure 2 Schematic diagram of data flow of the operation and maintenance management method of intelligent networked devices according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the operation and maintenance management method of the intelligent networked device of the embodiment of the present application, the steps include: S1, collecting a data set of device operating status parameters of the intelligent networked device through a sensor; S2, transmitting the data set of the device operating status parameters to a cloud processor; S3, in the cloud processor, processing the data set of the device operating status parameters to determine whether there is an abnormality in the device working status of the intelligent networked device; S4, in response to detecting that there is an abnormality in the device working status of the intelligent networked device, transmitting the detection result and abnormality information to the operation and maintenance terminal for display.
[0022] In particular, the S1 collects data sets of equipment operating status parameters of intelligent networked equipment through sensors. Among them, the data sets of equipment operating status parameters include temperature, vibration amplitude and electrical parameter data. In the technical solution of this application, it is expected that the key operating parameters of the equipment are monitored in real time through sensors, and the equipment abnormality monitoring is performed using data processing and analysis algorithms. In this way, abnormal conditions of intelligent networked equipment can be discovered and warned in a timely manner, and it is helpful to carry out timely and effective equipment operation and maintenance management.
[0023] In particular, the S2 transmits the data set of the device operation status parameters to a cloud processor. The cloud processor can provide powerful computing power and storage resources, and can support complex data processing tasks, such as big data analysis, machine learning, etc.
[0024] In particular, in S3, in the cloud processor, the data set of the device operating status parameter is processed to determine whether there is an abnormality in the device operating status of the intelligent networked device. In a specific example of the present application, Figure 3 As shown, the S3 includes: S31, performing data subset segmentation on the data set of the equipment operation status parameters to obtain a set of data subsets of the equipment operation status parameters; S32, performing time series encoding on the set of data subsets of the equipment operation status parameters to obtain a set of local time series correlation features of the equipment operation status parameters; S33, performing feature aggregation processing based on clustering contribution enhanced expression on the set of local time series correlation features of the equipment operation status parameters to obtain a time series significant aggregation representation of the equipment operation status parameters; S34, performing equipment anomaly detection based on the time series significant aggregation representation of the equipment operation status parameters to determine whether there is an abnormality in the equipment working state.
[0025] Specifically, the S31 performs data subset segmentation on the data set of the equipment operation status parameters to obtain a collection of data subsets of the equipment operation status parameters. Considering that the original data set of the equipment operation status parameters is the data information collected by real-time monitoring of intelligent networked devices, such as temperature, vibration amplitude or full time domain information of electrical parameter data, the amount of data of this information is large. If it is directly processed, it may be difficult to discover the slight abnormal changes and fluctuations in the equipment operation status, and it is also difficult to comprehensively and meticulously integrate the timing information and change trends of the equipment operation status, resulting in a decrease in the accuracy of subsequent equipment working status and abnormal monitoring and early warning. Based on this, in the technical solution of the present application, the data set of the equipment operation status parameters is segmented into data subsets to obtain a collection of data subsets of the equipment operation status parameters. By performing data subset segmentation, the local time series correlation characteristics of the data subsets of each equipment operation status parameter can be extracted respectively, which helps to better understand the behavior patterns of the equipment in different time periods.
[0026] Specifically, the S32 performs time series encoding on the set of data subsets of the device operating state parameters to obtain a set of local time series correlation features of the device operating state parameters. In a specific example of the present application, the data subsets of each device operating state parameter in the set of data subsets of the device operating state parameters are input into the operating state parameter time series encoder based on the RNN model for encoding processing, so as to respectively extract the local time series representation information of the device operating state contained in the data subsets of each device operating state parameter, thereby obtaining a set of local time series correlation feature vectors of the device operating state parameters. In particular, the time series data of the device operating state parameters is processed by using a recursive neural network (RNN) model, because in many cases, the state of the device depends not only on the parameter value at the current moment, but also on historical data. The RNN model can capture this temporal dependency, thereby more accurately evaluating the operating status of the device and making decisions on whether an abnormality has occurred accordingly.
[0027] Specifically, the S33 performs feature aggregation processing based on cluster contribution enhancement expression on the set of local time series correlation features of the equipment operation status parameters to obtain a significant aggregation representation of the time series of the equipment operation status parameters. It should be understood that since each local time series correlation feature vector of the equipment operation status parameters in the set of local time series correlation feature vectors of the equipment operation status parameters respectively contains the local time series correlation feature information of the equipment operation status parameters in each local time period, these local time series features have a correlation relationship and importance semantics based on the full time domain. In other words, not all local time series features of the equipment operation status parameters have an important role and the same contribution to the subsequent equipment working status monitoring and anomaly detection. The information carried by some feature vectors is crucial to describing the operating status of the equipment, while the local time series features contained in some feature vectors have a smaller contribution to the subsequent tasks. Therefore, in order to extract the most meaningful features for subsequent equipment working status detection tasks from the set of local time series correlation feature vectors of the equipment operating status parameters, so as to more accurately identify the working status of the equipment, especially to detect whether there is an abnormality, in the technical solution of the present application, the set of local time series correlation features of the equipment operating status parameters is further subjected to feature aggregation processing based on clustering contribution enhanced expression to obtain a significant aggregation representation of the equipment operating status parameter time series.
[0028] In an embodiment of the present application, the set of local time series correlation features of the equipment operation status parameters is subjected to feature aggregation processing based on cluster contribution enhancement expression to obtain a significant aggregation representation of the equipment operation status parameters time series, including: first, cluster analysis is performed on the set of local time series correlation feature vectors of the equipment operation status parameters to obtain a self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters; that is, cluster analysis is performed on the set of local time series correlation feature vectors of the equipment operation status parameters using an unsupervised learning method, and the local time series pattern and structure of the equipment operation status parameters in the data are automatically discovered to generate a self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters. It should be understood that self-supervised clustering can reveal the inherent structure of the data, which helps the model learn meaningful representations of the time series features of the equipment operation status parameters without explicit labels, and enhances the model's understanding of the distribution of the time series features of the operation status parameters. Specifically, the specific process of performing cluster analysis on the set of local time series correlation feature vectors of the equipment operation status parameters to obtain the self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters includes: calculating the mean vector of the set of local time series correlation feature vectors of the equipment operation status parameters to obtain the self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters. Then, based on the self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters, the set of local time series correlation feature vectors of the equipment operation status parameters is subjected to feature clustering field modulation aggregation to obtain the equipment operation status parameter time series significant aggregation representation vector as the equipment operation status parameter time series significant aggregation representation.
[0029] Specifically, based on the self-supervised clustering representation vector of the local time series correlation feature of the equipment operation status parameter, the specific process of performing feature clustering field modulation aggregation on the set of the local time series correlation feature vectors of the equipment operation status parameter includes: first, calculating the implicit clustering contribution factor of each local time series correlation feature vector of the equipment operation status parameter in the set of the local time series correlation feature vector of the equipment operation status parameter relative to the self-supervised clustering representation vector of the local time series correlation feature of the equipment operation status parameter to obtain a sequence of implicit clustering contribution factors of the local time series correlation feature of the equipment operation status parameter; by calculating the implicit clustering contribution factor between the local time series correlation feature vector of each equipment operation status parameter and the self-supervised clustering representation vector of the local time series correlation feature of the equipment operation status parameter, it is possible to identify which local time series correlation features of the equipment operation status parameter have important contributions to the clustering results and the subsequent equipment working status detection tasks. This means that the information carried by these feature vectors is crucial to describing the operating status of the equipment. Based on this, different feature vectors can be given different weights, so as to highlight those information that are more meaningful to the equipment status judgment in the subsequent feature fusion process. Next, the sequence of implicit cluster contribution factors of the local time series correlation characteristics of the equipment operation status parameters is vectorized to obtain the distribution vector of the cluster contribution field of the local time series correlation characteristics of the equipment operation status parameters; that is, the sequence of implicit cluster contribution factors is integrated into the vector field by using data integration to construct the cluster contribution field. Further, the distribution vector of the cluster contribution field of the local time series correlation characteristics of the equipment operation status parameters is input into the cluster contribution field explicit modeling module based on the self-attention mechanism to obtain the cluster contribution field modulation weight vector of the local time series correlation characteristics of the equipment operation status parameters; here, the self-attention mechanism is used to perform explicit modeling of the cluster contribution degree of each fine-grained factor in the cluster contribution field based on the field autocorrelation global analysis, so as to strengthen the attention to the local time series characteristics of the equipment operation status parameters with large cluster contributions, while suppressing the expression of unimportant features, thereby improving the quality of feature representation and the accuracy of subsequent equipment working status detection. Finally, the characteristic values in the field modulation weight vector of the cluster contribution of the local time series correlation feature of the equipment operation status parameter are used as weights to calculate the weighted sum of the set of local time series correlation feature vectors of the equipment operation status parameter to obtain the time series significant aggregation representation vector of the equipment operation status parameter. Here, a comprehensive feature representation is provided through weighted fusion, which not only contains the original local time series feature information of the equipment operation status parameter, but also integrates the knowledge learned in the clustering process, so that the model can more accurately capture the key features of the data when processing complex tasks, thereby improving the performance and generalization ability of the model.In other words, the feature enhancement processing based on cluster contribution explicitly models the importance of the local time series correlation feature vector of each device operating status parameter, so that the final feature representation is more focused on the key features that truly reflect the device status. The advantage of this is that it can exclude those features that have little impact on the device status judgment, thereby improving the quality of feature representation.
[0030] More specifically, calculating the implicit clustering contribution factor of each local time series associated feature vector of the device operating state parameter in the set of the local time series associated feature vectors of the device operating state parameter relative to the local time series associated feature self-supervised clustering representation vector of the device operating state parameter to obtain a sequence of implicit clustering contribution factors of the local time series associated feature of the device operating state parameter, including: calculating the absolute value of the positional division between the local time series associated feature vector of the device operating state parameter and the local time series associated feature self-supervised clustering representation vector of the device operating state parameter to obtain the local time series self-supervised clustering interactive association feature vector of the device operating state parameter; calculating the local time series associated feature vector of the device operating state parameter with a base of 2; The logarithmic function value of each position feature value in the local time series self-supervised clustering interaction correlation feature vector is used to obtain the local time series self-supervised clustering interaction logarithmic representation vector of the equipment operation status parameters; the weighted sum of the feature values at each position in the local time series correlation feature vector of the equipment operation status parameters is calculated using the feature values at each position in the local time series self-supervised clustering interaction logarithmic representation vector of the equipment operation status parameters as the weighting coefficient to obtain the clustering contribution representation factor of the local time series correlation feature of the equipment operation status parameters; the exponential function value of the clustering contribution representation factor of the local time series correlation feature of the equipment operation status parameters is calculated with the natural constant e as the base to obtain the implicit clustering contribution factor of the local time series correlation feature of the equipment operation status parameters.
[0031] More specifically, the distribution vector of the cluster contribution field of the local temporal correlation feature of the equipment operation status parameters is input into the cluster contribution field explicit modeling module based on the self-attention mechanism to obtain the modulation weight vector of the local temporal correlation feature cluster contribution field of the equipment operation status parameters, including: calculating the matrix multiplication between the distribution vector of the local temporal correlation feature cluster contribution field of the equipment operation status parameters and the query weight matrix, the key weight matrix and the value weight matrix respectively to obtain the equipment operation status parameter cluster contribution field distribution query vector, the equipment operation status parameter cluster contribution field distribution key vector and the equipment operation status parameter cluster contribution field distribution value vector; calculating the multiplication between the equipment operation status parameter cluster contribution field distribution query vector and the transposed vector of the equipment operation status parameter cluster contribution field distribution key vector, and then dividing the obtained matrix by the square root of the length of the equipment operation status parameter cluster contribution field distribution key vector according to the position to obtain the query-key equipment operation status parameter cluster contribution field semantic interaction representation matrix; using The function normalizes the query-key device operating status parameter cluster contribution field semantic interaction representation matrix to obtain a normalized query-key device operating status parameter cluster contribution field semantic interaction representation matrix; calculates the multiplication between the device operating status parameter cluster contribution field distribution value vector and the query-key device operating status parameter cluster contribution field semantic interaction representation matrix to obtain the device operating status parameter local temporal correlation feature cluster contribution field modulation weight vector.
[0032] In summary, in the above embodiment, the set of local time series correlation features of the device operation status parameters is subjected to feature aggregation processing based on cluster contribution enhanced expression to obtain a significant aggregation representation of the time series of the device operation status parameters, including: performing feature aggregation processing based on cluster contribution enhanced expression on the set of local time series correlation features of the device operation status parameters using the following feature aggregation formula to obtain a significant aggregation representation of the time series of the device operation status parameters; wherein the feature aggregation formula is: ;in, is a set of local time series correlation feature vectors of the equipment operation status parameters, are respectively the first, second, and third in the set of local time series correlation feature vectors of the equipment operation status parameters. and The local time series correlation feature vector of the equipment operation status parameters, is the first in the set of local time series associated feature vectors of the equipment operation status parameters The local time series correlation feature vector of the equipment operation status parameters, is the number of feature vectors in the set of local time series associated feature vectors of the equipment operating status parameters, is the self-supervised clustering representation vector of the local temporal correlation features of the equipment operation status parameters, is the first in the set of local time series associated feature vectors of the equipment operation status parameters The local time series correlation feature vector of the equipment operation status parameters, For the The first The eigenvalues at the positions, is the first in the self-supervised clustering representation vector of the local temporal correlation feature of the equipment operation status parameter The eigenvalues at the positions, represents the logarithmic function value with base 2, represents the value of the natural exponential function, For the said The implicit clustering contribution factor of the local time series correlation feature of the equipment operation status parameters corresponding to the local time series correlation feature vector of the equipment operation status parameters is The distribution vector of the clustering contribution field of the local time series correlation characteristics of the operating state parameters of multiple devices is obtained by quantizing the implicit clustering contribution factors of the local time series correlation characteristics of the operating state parameters of the devices. , and They are query weight matrix, key weight matrix and value weight matrix respectively. , and are the query vector of the equipment operation status parameter cluster contribution field distribution, the key vector of the equipment operation status parameter cluster contribution field distribution, and the value vector of the equipment operation status parameter cluster contribution field distribution. The length of the key vector for the clustering contribution field distribution of the equipment operating status parameters, for function, is vector multiplication, Contribute field modulation weight vector to cluster local temporal correlation features of equipment operation status parameters, A time series significant aggregation representation vector of the device operating status parameters.
[0033] Specifically, the S34 performs equipment anomaly detection based on the significant aggregation representation of the equipment operating status parameters time series to determine whether the equipment working state is abnormal. In a specific example of the present application, the equipment operating status parameter time series significant aggregation representation vector is input into a classifier-based equipment anomaly detection module to obtain a detection result, and the detection result is used to indicate whether the equipment working state is abnormal. That is, the significant key feature aggregation representation information between the local time series features of the equipment operating status parameters is used for classification processing, so as to monitor the equipment working state and detect anomalies, which can timely discover and warn of abnormal conditions of intelligent networked equipment, and help to carry out timely and effective equipment operation and maintenance management. Through such a more intelligent equipment operation and maintenance management method, it can provide a basis for early warning of faults and predictive maintenance of intelligent networked equipment, which is conducive to improving the overall efficiency of equipment management and the reliability of equipment operation.
[0034] Preferably, in an example of the present application, inputting the device operating status parameter time series significant aggregation representation vector into a classifier-based device anomaly detection module to obtain a detection result includes: calculating the sum of the absolute values of each eigenvalue of the device operating status parameter time series significant aggregation representation vector to obtain a first device operating status parameter time series significant aggregation spatial structure value, and calculating the square root of the sum of the squares of each eigenvalue of the device operating status parameter time series significant aggregation representation vector to obtain a second device operating status parameter time series significant aggregation spatial structure value; multiplying each eigenvalue of the device operating status parameter time series significant aggregation representation vector with the first device operating status parameter time series significant aggregation spatial structure value and the second device operating status parameter time series significant aggregation spatial structure value to obtain a first device operating status parameter time series significant aggregation structure reference value and a second device operating status parameter time series significant aggregation structure reference value corresponding to each eigenvalue; multiplying each eigenvalue of the device operating status parameter time series significant aggregation representation vector with the length of the device operating status parameter time series significant aggregation representation vector and the square root of the length to obtain a value corresponding to each eigenvalue. The first device operating state parameter time series significant aggregation scale transformation value and the second device operating state parameter time series significant aggregation scale transformation value corresponding to the eigenvalue; the first device operating state parameter time series significant aggregation structure reference value is divided by the difference between the first device operating state parameter time series significant aggregation space structure value and the first device operating state parameter time series significant aggregation scale transformation value to obtain the first device operating state parameter time series significant aggregation transformation adjustment value; the second device operating state parameter time series significant aggregation structure reference value is divided by the difference between the second device operating state parameter time series significant aggregation space structure value and the second device operating state parameter time series significant aggregation scale transformation value to obtain the second device operating state parameter time series significant aggregation transformation adjustment value; the weighted sum of the first device operating state parameter time series significant aggregation transformation adjustment value and the second device operating state parameter time series significant aggregation transformation adjustment value is calculated to obtain each eigenvalue of the optimized device operating state parameter time series significant aggregation representation vector; and the optimized device operating state parameter time series significant aggregation representation vector is input into the classifier-based device anomaly detection module to obtain the detection result.
[0035] Here, the equipment operation status parameter time series significant aggregation representation vector is recorded as The optimization expression is: ;in, is the significant aggregation representation vector of the time series of the equipment operation status parameters, are the eigenvalues of the significant aggregation representation vector of the equipment operating status parameter time series, is the spatial structure value of the significant aggregation of the time series of the operating status parameters of the first device, is the time series significant aggregation spatial structure value of the operating status parameter of the second device, is the length of the time series significant aggregation representation vector of the equipment operating status parameters, represents the set of real numbers, is the time series significant aggregate transformation adjustment value of the operating state parameter of the first device, is the time series significant aggregation transformation adjustment value of the operating state parameter of the second device, is a first heart rate-body temperature time series feature significant interaction fusion transformation adjustment vector composed of the time series significant aggregation transformation adjustment values of the operating state parameters of the first equipment, is a second heart rate-body temperature time series feature significant interaction fusion transformation adjustment vector composed of the time series significant aggregation transformation adjustment values of each of the second device operating state parameters, is the weight hyperparameter, is the dot product, It's a little plus. is a time series significant aggregation representation vector of the optimized equipment operating status parameters.
[0036] That is, the applicant of the present application takes into account that each local time series correlation feature vector of the device operating status parameters in the set of local time series correlation feature vectors of the device operating status parameters respectively represents the sequence coding characteristics of the device operating status parameters in the local sample space domain, and when performing feature significance aggregation based on clustering contribution field analysis, the difference in spatial field clustering contribution of each local sample space domain in the global sample space domain will also make the spatial composite aggregation representation of the device operating status parameter time series significant aggregation representation vector have a complex spatial structure based on different spatial significance distribution structures, thereby expecting to improve its classification regression convergence and generalization effects under complex spatial structures.
[0037] Therefore, in the preferred example, for the spatial structure information of the feature set of the device operating state parameter time series significant aggregation representation vector in the high-dimensional space, the scale-based frame transformation of each feature value of the device operating state parameter time series significant aggregation representation vector is performed by taking the class norm space structured representation of the device operating state parameter time series significant aggregation representation vector as the reference window, and the spatial structure-based frame attention weight adjustment of each feature value of the device operating state parameter time series significant aggregation representation vector is realized to ensure the spatial transformation (translation, scaling and rotation) invariance of the device operating state parameter time series significant aggregation representation vector under the interaction of feature space, thereby improving the convergence and generalization effect of the classification regression of the feature set of the device operating state parameter time series significant aggregation representation vector under the complex spatial structure representation, and improving the accuracy of the detection result obtained by inputting it into the device anomaly detection module based on the classifier. In this way, the equipment working state monitoring and anomaly detection can be carried out more accurately, so as to timely discover and warn the abnormal situation of the intelligent networked equipment, and help to carry out timely and effective equipment operation and maintenance management.
[0038] In particular, in response to detecting that the working state of the intelligent networked device is abnormal, the detection result and abnormal information are transmitted to the operation and maintenance terminal for display. By monitoring the working state of the device in real time and quickly transmitting the abnormal information to the operation and maintenance personnel, it can be ensured that the device can be discovered in the first place when a failure or potential problem occurs, which is conducive to improving the overall efficiency of device management and the reliability of device operation.
[0039] In summary, the operation and maintenance management method of the intelligent networked equipment according to the embodiment of the present application is explained, which analyzes the data set of the collected and transmitted equipment operation status parameters by using data processing and analysis algorithms based on artificial intelligence and deep learning, so as to capture the time-series aggregation information about the equipment operation status, and use this dynamic time-series aggregation information to monitor equipment anomalies, which can timely discover and warn of abnormal conditions of intelligent networked equipment, and help to carry out timely and effective equipment operation and maintenance management. Through such a more intelligent equipment operation and maintenance management method, it can provide a basis for early warning of faults and predictive maintenance of intelligent networked equipment, which is conducive to improving the overall efficiency of equipment management and the reliability of equipment operation.
[0040] Furthermore, an operation and maintenance management system for intelligent networked equipment is also provided.
[0041] Figure 4 FIG. 1 is a block diagram of an operation and maintenance management system for an intelligent networked device according to an embodiment of the present application. Figure 4As shown, according to the operation and maintenance management system 300 of the intelligent networked device according to the embodiment of the present application, it includes: a data acquisition module 310, which is used to collect a data set of device operating status parameters of the intelligent networked device through sensors; a data transmission module 320, which is used to transmit the data set of the device operating status parameters to the cloud processor; a data processing module 330, which is used to process the data set of the device operating status parameters in the cloud processor to determine whether there is an abnormality in the device working status of the intelligent networked device; an abnormality detection module 340, which is used to transmit the detection result and abnormality information to the operation and maintenance terminal for display in response to detecting that there is an abnormality in the device working status of the intelligent networked device.
[0042] As described above, the operation and maintenance management system 300 of the intelligent networked device according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with an operation and maintenance management algorithm for the intelligent networked device. In one possible implementation, the operation and maintenance management system 300 of the intelligent networked device according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the operation and maintenance management system 300 of the intelligent networked device can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the operation and maintenance management system 300 of the intelligent networked device can also be one of the many hardware modules of the wireless terminal.
[0043] Alternatively, in another example, the operation and maintenance management system 300 of the intelligent connected device and the wireless terminal may also be separate devices, and the operation and maintenance management system 300 of the intelligent connected device may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.
[0044] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A method for operation and maintenance management of intelligent networked equipment, characterized in that: include: Collect data sets of equipment operating status parameters of intelligent networked equipment through sensors; transmitting the data set of the equipment operating status parameters to a cloud processor; In the cloud processor, the data set of the device operating status parameters is processed to determine whether the device working state of the intelligent networked device is abnormal, including: performing data subset segmentation on the data set of the device operating status parameters to obtain a set of data subsets of the device operating status parameters; performing time series encoding on the set of data subsets of the device operating status parameters to obtain a set of local time series correlation features of the device operating status parameters; performing feature aggregation processing based on clustering contribution enhanced expression on the set of local time series correlation features of the device operating status parameters to obtain a time series significant aggregation representation of the device operating status parameters; performing device anomaly detection based on the time series significant aggregation representation of the device operating status parameters to determine whether the device working state is abnormal; in response to detecting that the intelligent networked device There is an abnormality in the working state of the equipment, and the detection result and abnormal information are transmitted to the operation and maintenance terminal for display; wherein, the set of local time series correlation features of the equipment operation state parameters is subjected to feature aggregation processing based on cluster contribution enhanced expression to obtain a time series significant aggregation representation of the equipment operation state parameters, including: clustering analysis is performed on the set of local time series correlation feature vectors of the equipment operation state parameters to obtain a self-supervised cluster representation vector of the local time series correlation features of the equipment operation state parameters; based on the self-supervised cluster representation vector of the local time series correlation features of the equipment operation state parameters, feature clustering field modulation aggregation is performed on the set of local time series correlation feature vectors of the equipment operation state parameters to obtain a time series significant aggregation representation vector of the equipment operation state parameters as the time series significant aggregation representation of the equipment operation state parameters.
2. The operation and maintenance management method of the intelligent networked device according to claim 1, characterized in that: The set of data subsets of the device operating status parameters is time-series encoded to obtain a set of local time-series correlation features of the device operating status parameters, including: inputting the data subsets of each device operating status parameter in the set of data subsets of the device operating status parameters into an operating status parameter time-series sequence encoder based on an RNN model to obtain a set of local time-series correlation feature vectors of device operating status parameters as the set of local time-series correlation features of the device operating status parameters.
3. The operation and maintenance management method of the intelligent networked device according to claim 2, characterized in that: A cluster analysis is performed on the set of local time series correlation feature vectors of the equipment operation status parameters to obtain a self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters, including: calculating the mean vector of the set of local time series correlation feature vectors of the equipment operation status parameters to obtain a self-supervised cluster representation vector of the local time series correlation features of the equipment operation status parameters.
4. The operation and maintenance management method of the intelligent networked device according to claim 3 is characterized in that: Based on the self-supervised clustering representation vector of the local time series correlation feature of the equipment operation status parameters, the set of the local time series correlation feature vectors of the equipment operation status parameters is subjected to feature clustering field modulation aggregation to obtain a time series significant aggregation representation vector of the equipment operation status parameters as the time series significant aggregation representation of the equipment operation status parameters, including: calculating the implicit clustering contribution factor of each local time series correlation feature vector of the equipment operation status parameters in the set of the local time series correlation feature vectors of the equipment operation status parameters relative to the self-supervised clustering representation vector of the local time series correlation feature of the equipment operation status parameters to obtain a sequence of implicit clustering contribution factors of the local time series correlation feature of the equipment operation status parameters; The sequence of implicit clustering contribution factors of the local temporal correlation characteristics of the parameters is vectorized to obtain the clustering contribution field distribution vector of the local temporal correlation characteristics of the equipment operation status parameters; the clustering contribution field distribution vector of the local temporal correlation characteristics of the equipment operation status parameters is input into the clustering contribution field explicit modeling module based on the self-attention mechanism to obtain the clustering contribution field modulation weight vector of the local temporal correlation characteristics of the equipment operation status parameters; each eigenvalue in the clustering contribution field modulation weight vector of the local temporal correlation characteristics of the equipment operation status parameters is used as a weight to calculate the position-weighted sum of the set of the local temporal correlation feature vectors of the equipment operation status parameters to obtain the temporal significant aggregation representation vector of the equipment operation status parameters.
5. The operation and maintenance management method of the intelligent networked device according to claim 4, characterized in that: Calculate the implicit clustering contribution factor of each local time series associated feature vector of the device operating state parameter in the set of the local time series associated feature vectors of the device operating state parameter relative to the local time series associated feature self-supervised clustering representation vector of the device operating state parameter to obtain a sequence of implicit clustering contribution factors of the local time series associated feature of the device operating state parameter, including: calculating the absolute value of the positional division between the local time series associated feature vector of the device operating state parameter and the local time series associated feature self-supervised clustering representation vector of the device operating state parameter to obtain the local time series self-supervised clustering interactive association feature vector of the device operating state parameter; calculating the local time series self-supervised clustering representation vector of the device operating state parameter with a base of 2; The logarithmic function value of each position feature value in the local time series self-supervised clustering interaction correlation feature vector is calculated to obtain the local time series self-supervised clustering interaction logarithmic representation vector of the equipment operation status parameters; the weighted sum of the feature values at each position in the local time series correlation feature vector of the equipment operation status parameters is calculated using the feature values at each position as the weighting coefficient to obtain the clustering contribution representation factor of the local time series correlation feature of the equipment operation status parameters; the exponential function value of the clustering contribution representation factor of the local time series correlation feature of the equipment operation status parameters is calculated with the natural constant e as the base to obtain the implicit clustering contribution factor of the local time series correlation feature of the equipment operation status parameters.
6. The operation and maintenance management method of the intelligent networked device according to claim 5, characterized in that: The cluster contribution field distribution vector of the local temporal correlation feature of the equipment operation status parameters is input into the cluster contribution field explicit modeling module based on the self-attention mechanism to obtain the domain modulation weight vector of the local temporal correlation feature cluster contribution field of the equipment operation status parameters, including: calculating the matrix multiplication between the local temporal correlation feature cluster contribution field distribution vector of the equipment operation status parameters and the query weight matrix, the key weight matrix and the value weight matrix respectively to obtain the equipment operation status parameter cluster contribution field distribution query vector, the equipment operation status parameter cluster contribution field distribution key vector and the equipment operation status parameter cluster contribution field distribution value vector; calculating the multiplication between the equipment operation status parameter cluster contribution field distribution query vector and the transposed vector of the equipment operation status parameter cluster contribution field distribution key vector, dividing the obtained matrix by the square root of the length of the equipment operation status parameter cluster contribution field distribution key vector according to the position to obtain the query-key equipment operation status parameter cluster contribution field semantic interaction representation matrix; using The function normalizes the query-key device operating status parameter cluster contribution field semantic interaction representation matrix to obtain a normalized query-key device operating status parameter cluster contribution field semantic interaction representation matrix; calculates the multiplication between the device operating status parameter cluster contribution field distribution value vector and the query-key device operating status parameter cluster contribution field semantic interaction representation matrix to obtain the device operating status parameter local temporal correlation feature cluster contribution field modulation weight vector.
7. The operation and maintenance management method of the intelligent networked device according to claim 6, characterized in that: Based on the significant aggregation representation of the equipment operating status parameters in time series, equipment anomaly detection is performed to determine whether there is an abnormality in the equipment working status, including: inputting the significant aggregation representation vector of the equipment operating status parameters in time series into a classifier-based equipment anomaly detection module to obtain a detection result, and the detection result is used to indicate whether there is an abnormality in the equipment working status.
8. An operation and maintenance management system for intelligent networked devices, characterized in that: include: A data acquisition module, used to collect data sets of equipment operating status parameters of intelligent networked equipment through sensors; A data transmission module, used for transmitting the data set of the equipment operation status parameters to the cloud processor; A data processing module, configured to process the data set of the device operating status parameters in the cloud processor to determine whether there is an abnormality in the device operating status of the intelligent networked device; An anomaly detection module is used to transmit the detection result and anomaly information to the operation and maintenance terminal for display in response to detecting that the device working state of the intelligent networked device is abnormal; wherein, in the cloud processor, the data set of the device operating state parameters is processed to determine whether the device working state of the intelligent networked device is abnormal, including: data subset segmentation of the data set of the device operating state parameters to obtain a set of data subsets of the device operating state parameters; time series encoding of the set of data subsets of the device operating state parameters to obtain a set of local time series correlation features of the device operating state parameters; feature aggregation processing based on clustering contribution enhanced expression on the set of local time series correlation features of the device operating state parameters to obtain a significant aggregation representation of the time series of the device operating state parameters; based on the The significant temporal aggregation representation of the equipment operating status parameters is used to detect equipment anomalies and determine whether there is an abnormality in the equipment working state; wherein, the set of local temporal correlation features of the equipment operating status parameters is subjected to feature aggregation processing based on clustering contribution enhanced expression to obtain a significant temporal aggregation representation of the equipment operating status parameters, including: clustering analysis is performed on the set of local temporal correlation feature vectors of the equipment operating status parameters to obtain a self-supervised clustering representation vector of the local temporal correlation features of the equipment operating status parameters; based on the self-supervised clustering representation vector of the local temporal correlation features of the equipment operating status parameters, feature clustering field modulation aggregation is performed on the set of local temporal correlation feature vectors of the equipment operating status parameters to obtain a significant temporal aggregation representation vector of the equipment operating status parameters as the significant temporal aggregation representation of the equipment operating status parameters.
Citation Information
Patent Citations
Intelligent monitoring and early warning method and system for electric power operation and maintenance and storage medium
CN117578715A
Equipment operation process monitoring system
CN118656272A
Intelligent management and control system and method for maintenance operation of natural gas purification device
CN118672193A
Intelligent gas pressure pipeline detection system and method
CN118816111A
System and method for training an autoencoder to detect anomalous system behaviour
WO2023041907A1
Cited By
Power plant unit load distribution system and method
CN119417177A
Gas generator set monitoring system and method
CN119439856A
Online monitoring system and method for operation state of hot water boiler
CN119533578A
Power load dynamic distribution control system and method
CN119627901A
