Predictive operation and maintenance method and device for industrial equipment and electronic equipment

Abstract

The invention provides an industrial equipment predictive operation and maintenance method and device and electronic equipment, and relates to the field of data processing. The method comprises the following steps: acquiring operation state, resource flow and working condition data of industrial equipment sent by a multi-mode sensor; based on the operation state, the resource flow and the working condition data, constructing a symbiotic relationship graph; inputting the symbiotic relationship graph into a preset symbiotic network model to obtain a detection result; and performing predictive operation and maintenance on the industrial equipment according to a detection result. By implementing the technical scheme provided by the invention, the operation and maintenance real-time performance of the industrial equipment can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and specifically to a predictive operation and maintenance method, device and electronic equipment for industrial equipment. Background Art

[0002] In the traditional operation and maintenance of industrial equipment, post-failure repair has always been the main maintenance strategy. This method is based on repairing the equipment after it fails or its performance has significantly deteriorated, and relies on the obvious fault manifestation of the equipment or the scheduled maintenance cycle to determine the timing of maintenance. The advantage of post-failure repair is that it can delay the investment of maintenance resources and reduce maintenance costs in the short term.

[0003] However, although this method can effectively deal with simple equipment failures in some cases, it relies on intervention after the failure occurs, lacks timely data feedback and intelligent prediction capabilities, and equipment maintenance is often performed after equipment performance has degraded or failed, missing the optimal maintenance opportunity. Therefore, the above method leads to poor real-time operation and maintenance of industrial equipment.

[0004] Therefore, there is an urgent need for a predictive operation and maintenance method, device and electronic equipment for industrial equipment. Summary of the invention

[0005] The present application provides a method, device and electronic equipment for predictive operation and maintenance of industrial equipment, which are convenient for improving the real-time operation and maintenance of industrial equipment.

[0006] In a first aspect of the present application, a method for predictive operation and maintenance of industrial equipment is provided, the method comprising: obtaining operating status, resource flow and operating condition data for industrial equipment sent by a multimodal sensor; constructing a symbiotic relationship map based on the operating status, the resource flow and the operating condition data; inputting the symbiotic relationship map into a preset symbiotic network model to obtain a detection result; and performing predictive operation and maintenance on the industrial equipment based on the detection result.

[0007] By adopting the above technical solutions, through multimodal sensors, it is possible to fully understand the operating status, resource flow and working condition of the equipment. This multi-dimensional data fusion provides a more detailed basis for comprehensive monitoring of the equipment, so that the health status of the equipment can be evaluated from multiple angles. This more accurately reflects the true status of the equipment than single sensor data or traditional monitoring methods, reducing misdiagnosis or missed diagnosis caused by the limitation of a single data source. By mapping the operating status, resource flow and working condition data of the equipment into a symbiotic relationship map, the collaborative work, resource transfer and interdependence between the various devices can be clearly described. This map can reveal the complex synergy between devices, thereby helping operation and maintenance personnel to more accurately identify potential factors affecting equipment performance. It can also discover dependencies that may be overlooked in the system, thereby improving the accuracy of fault prediction. By inputting the symbiotic relationship map into the preset symbiotic network model, the equipment and its collaborative status can be dynamically monitored, and the entire system can be analyzed in real time. Compared with traditional experience-based maintenance methods, predictive operation and maintenance has higher accuracy and real-time performance, and can identify potential faults in advance and warn of maintenance needs. By intervening in advance, it is possible to avoid having to wait until a serious failure occurs before repairing the equipment, thus reducing downtime, repair costs, and production losses. Therefore, it is easy to improve the real-time operation and maintenance of industrial equipment.

[0008] Optionally, the symbiotic relationship map is constructed based on the operating status, the resource flow and the operating condition data, specifically including: determining the industrial equipment as the target node; determining the material, energy or signal flow between the equipment as the target edge according to the operating status, the resource flow and the operating condition data, one target edge corresponds to a target weight, and the target weight is used to represent the collaboration efficiency between the equipment; constructing the symbiotic relationship map according to the target node, the target edge and the target weight.

[0009] By adopting the above technical solutions, a collaborative network between devices is constructed by determining the flow of materials, energy or signals between devices. This map can not only show the operation of a single device, but also reveal the interactions and dependencies between devices, so that the synergy in the system can be clearly visualized. This helps to gain a deeper understanding of how devices work together and identify which devices are key collaborative nodes. By setting weights for each edge, the efficiency of collaboration between devices can be quantified. This weight can reflect the efficiency of resource flow, the smoothness of material transfer or the delay of signal transfer between devices. By monitoring these weights, the collaborative effect of the devices can be accurately evaluated, thereby identifying the links with low collaborative efficiency and providing clear optimization directions for operation and maintenance. By constructing a symbiotic relationship map, potential bottlenecks or key nodes in device collaboration can be discovered. By analyzing the target edges and target weights in the map, it is possible to find which devices have collaboration problems, thereby predicting the occurrence of equipment failures. This provides key information support for predictive maintenance. The symbiotic relationship map can integrate and visualize the operating status, resource flow and working condition data of multiple devices, providing strong support for predictive operation and maintenance. Based on the collaboration efficiency weights in the graph, the operation and maintenance system can dynamically monitor the status changes between devices, promptly detect collaboration failures or anomalies, and warn of potential failures in advance. This intelligent operation and maintenance strategy can reduce downtime, reduce maintenance costs, and improve equipment reliability.

[0010] Optionally, the symbiotic relationship map is input into a preset symbiotic network model to obtain a detection result, which specifically includes: extracting a feature group based on the target node, the target edge and the target weight; if it is determined through the preset symbiotic network model that the collaborative efficiency between devices fluctuates within a preset range, then the detection result is determined to be normal; if it is determined through the preset symbiotic network model that the similarity between the feature group and the preset feature is less than a preset similarity threshold, then the detection result is determined to be symbiotically abnormal.

[0011] By adopting the above technical solution, by analyzing the target nodes, target edges and target weights, feature groups are extracted from the symbiotic relationship map, and the collaborative efficiency between devices can be carefully evaluated. When the collaborative efficiency between devices fluctuates within the preset range, it means that the normal collaboration of the devices is not affected and the detection result is normal. This method can not only accurately capture the overall operating status of the system, but also monitor potential problems in real time when the collaborative status of the devices changes, providing more refined anomaly detection capabilities. By comparing the similarity between the feature group and the preset features, if the similarity is lower than the preset threshold, the system will consider that there is a symbiotic anomaly. This method can effectively detect changes in the collaborative relationship between devices and capture early signs of device failure in a timely manner. By comparing the symbiotic network model and feature similarity, the system can not only detect the failure of a single device, but also detect hidden problems in the collaborative process of the devices. This allows operation and maintenance personnel to make more scientific and intelligent decisions based on data. This process automatically detects fluctuations in the collaborative status of the equipment, can monitor the operation of industrial equipment in real time and automatically provide feedback based on the detection results. Since this process can continuously track changes in equipment status, the system can detect potential problems during equipment operation and respond promptly when anomalies are found without manual intervention. This automated monitoring not only improves operation and maintenance efficiency, but also avoids problems caused by human negligence.

[0012] Optionally, the method also includes: determining the vibration data, temperature data, current data and voltage data of the industrial equipment during operation based on the operating condition data; if it is determined that the difference between any one of the vibration data, the temperature data, the current data and the voltage data and the corresponding preset data is greater than or equal to a preset difference threshold, then determining that the detection result is locally abnormal.

[0013] By adopting the above technical solution, the operating status of the equipment can be comprehensively evaluated by simultaneously monitoring multiple key data such as vibration, temperature, current and voltage. Each data reflects the different working characteristics of the equipment. Vibration reflects the mechanical state, and temperature and current and voltage are closely related to the working state of electrical components. Through the comprehensive monitoring of these data, the health status of the equipment can be grasped in real time and the accuracy of detection can be improved. When certain abnormal phenomena occur during the operation of the equipment, these phenomena first manifest as local fluctuations in vibration, temperature, current or voltage. By setting a preset difference threshold to compare the difference between the current data and the standard data, these local anomalies can be detected in real time. By setting a preset difference threshold, the system can accurately detect slight changes in the status of the equipment. If a part of the equipment begins to degrade or become abnormal, the system will respond immediately based on the difference between vibration, temperature and other data, avoiding the risk of failing to detect equipment problems in time in traditional methods. Compared with a single monitoring indicator, this multi-dimensional data monitoring is more sensitive and can capture signs of equipment when minor faults occur. Early identification of local anomalies can prevent small faults from developing into big problems. Identification of local anomalies can help formulate more sophisticated maintenance strategies. This not only reduces unnecessary system-wide maintenance, but also effectively reduces maintenance costs and improves operation and maintenance efficiency.

[0014] Optionally, performing predictive operation and maintenance on the industrial equipment based on the detection result specifically includes: determining an abnormality category based on the detection result; if the abnormality category is determined to be a node abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the equipment body of the industrial equipment; if the abnormality category is determined to be an edge abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the collaborative efficiency of the industrial equipment; if the abnormality category is determined to be a symbiotic abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the collaborative problems between the industrial equipment and the associated equipment corresponding to the industrial equipment.

[0015] By adopting the above technical solution, by formulating corresponding operation and maintenance strategies according to different abnormality categories, it is possible to ensure that the operation and maintenance work is more accurate. Node abnormalities focus on equipment failures, edge abnormalities focus on the decline in the efficiency of collaboration between equipment, and symbiotic abnormalities focus on the coordination problems of the overall system. By flexibly selecting operation and maintenance strategies based on actual detection results, equipment problems can be more effectively located and solved, avoiding blind or excessive maintenance. By classifying the abnormality categories, the system can automatically decide whether to repair the equipment itself, equipment collaboration efficiency, or collaborative problems, thereby reducing the time for manual judgment and improving the operation and maintenance response speed. By accurately judging the abnormality categories and formulating targeted operation and maintenance strategies, excessive maintenance and unnecessary equipment replacement or downtime can be effectively avoided. Compared with traditional operation and maintenance strategies, this precise operation and maintenance method based on abnormality categories significantly reduces maintenance costs. Different operation and maintenance measures are taken for different types of abnormalities, so that the equipment can be maintained at the most suitable time and method. This method can not only improve the long-term availability of equipment, but also reduce the impact of failures on production efficiency and maintain the smooth operation of the production line.

[0016] Optionally, the method also includes: obtaining historical operation and maintenance data, the historical operation and maintenance data including the correspondence between abnormal categories and operation and maintenance personnel; determining target operation and maintenance personnel based on the abnormal categories and the correspondence; and sending the operation and maintenance strategy to the target operation and maintenance personnel, the operation and maintenance strategy including the location data of the industrial equipment.

[0017] By adopting the above technical solution, through the analysis of historical operation and maintenance data, appropriate operation and maintenance personnel can be accurately assigned to designated tasks based on past experience. Each operation and maintenance personnel has higher professionalism and experience in handling specific types of faults. Therefore, by matching the appropriate operation and maintenance personnel according to the exception category, the efficiency of handling faults can be greatly improved and the response time can be shortened. By assigning tasks to operation and maintenance personnel who are already familiar with specific types of exceptions, mistakes or delays caused by improper task assignment can be reduced. When the operation and maintenance personnel are more familiar with specific faults, they can diagnose the problem more accurately and take more appropriate repair measures, avoiding unnecessary errors caused by unfamiliarity with equipment or faults. Assigning work tasks that the operation and maintenance personnel are good at and familiar with can improve their work efficiency and satisfaction. When the operation and maintenance personnel can smoothly deal with the problems they are good at, the workload is reduced and the work pressure is also reduced, thereby improving their work enthusiasm and reducing employee turnover. Through accurate historical data analysis, the system can accurately match the abnormality category with the ability of the operation and maintenance personnel to ensure that each operation and maintenance personnel performs tasks at the right time and place. This method effectively optimizes resource allocation and avoids waste of resources and unnecessary personnel scheduling. At the same time, by matching the capabilities of the operation and maintenance personnel, it can also ensure that equipment problems are handled in a timely and efficient manner. By sending the location information of industrial equipment to the target operation and maintenance personnel, it can help the operation and maintenance personnel quickly locate the equipment problem and improve the efficiency of equipment repair. Equipment location data can ensure that the operation and maintenance personnel reach the correct equipment and site, reducing the time wasted due to unclear geographical location. Especially when the equipment location is relatively scattered or complex, location information is particularly important.

[0018] Optionally, the acquiring of the operating status, resource flow and operating condition data for the industrial equipment sent by the multimodal sensor specifically includes: receiving original detection data for the industrial equipment sent by the multimodal sensor; performing data processing on the original detection data to obtain the operating status, the resource flow and the operating condition data, and the data processing includes denoising, filtering, feature extraction and normalization.

[0019] By adopting the above technical solutions, the original detection data contains noise, errors or incomplete information. If these data are used directly, they may affect the results of subsequent analysis. Through denoising and filtering, unnecessary interference can be effectively reduced to ensure that the obtained data is more accurate and reliable. The cleaned and filtered raw data can better reflect the real state of the equipment, thereby providing higher quality input for subsequent analysis and decision-making. The raw data may be inconsistent or missing due to sensor problems, environmental factors or external interference. Through data processing, the inconsistent parts in the data can be eliminated to ensure that the data is more complete and avoid erroneous analysis and decision-making due to low data quality. At the same time, through normalization, the data will be converted into a standardized format, which facilitates the comparison and fusion of different data sources and improves the availability of data. Through feature extraction, key features can be extracted from the raw data, which can help the system more accurately judge the equipment status and identify potential problems. The processed data is more suitable for input to machine learning and data analysis models. The denoised and filtered data can better reflect the equipment status, the feature extracted data simplifies the information representation, and the normalization normalizes the data to the same dimension, so that the model can be trained and predicted more accurately. This process lays the foundation for further data modeling, predictive analysis and decision support. Through processing methods such as normalization and feature extraction, these different modal data can be processed uniformly to eliminate the differences between them and facilitate subsequent multimodal data fusion analysis. This enables the information obtained from multiple sensors to be effectively integrated, providing a more comprehensive and accurate perspective for equipment monitoring.

[0020] In a second aspect of the present application, a predictive operation and maintenance device for industrial equipment is provided, and the predictive operation and maintenance device for industrial equipment includes an acquisition module and a processing module, wherein the acquisition module is used to acquire the operating status, resource flow and operating condition data of the industrial equipment sent by the multimodal sensor; the processing module is used to construct a symbiotic relationship map based on the operating status, the resource flow and the operating condition data; the processing module is also used to input the symbiotic relationship map into a preset symbiotic network model to obtain a detection result; the processing module is also used to perform predictive operation and maintenance on the industrial equipment according to the detection result.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: Multimodal sensors provide a comprehensive understanding of the equipment's operating status, resource flow, and operating conditions. This multi-dimensional data fusion provides a more detailed basis for comprehensive monitoring of equipment, allowing the health of equipment to be evaluated from multiple perspectives. This more accurately reflects the true status of the equipment than single sensor data or traditional monitoring methods, reducing misdiagnosis or missed diagnosis due to the limitations of a single data source. By mapping the equipment's operating status, resource flow, and operating condition data into a symbiotic relationship map, the collaborative work, resource transfer, and interdependence between the various devices can be clearly described. This map can reveal the complex synergies between devices, thereby helping operation and maintenance personnel to more accurately identify potential factors that affect equipment performance. It can also discover dependencies that may be overlooked in the system, thereby improving the accuracy of fault prediction. By inputting the symbiotic relationship map into the preset symbiotic network model, the equipment and its collaborative status can be dynamically monitored, and the entire system can be analyzed in real time. Compared with traditional experience-based maintenance methods, predictive operation and maintenance has higher accuracy and real-time performance, can identify potential faults in advance, and warn of maintenance needs. By intervening in advance, it is possible to avoid equipment maintenance after a serious fault occurs, reducing downtime, maintenance costs, and production losses. Therefore, it is convenient to improve the real-time operation and maintenance of industrial equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of a predictive operation and maintenance method for industrial equipment provided in an embodiment of the present application; Figure 2 Another schematic diagram of a process flow of a predictive operation and maintenance method for industrial equipment provided in an embodiment of the present application; Figure 3 A schematic diagram of a module of a predictive operation and maintenance device for industrial equipment provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0026] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0028] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] In traditional industrial equipment operation and maintenance, post-failure repair has always been the main maintenance strategy. This method repairs the equipment after it fails or its performance has significantly deteriorated, and relies on the obvious signs of failure of the equipment or the scheduled maintenance cycle to determine the timing of maintenance. The advantage of post-failure repair is that it can delay the investment of maintenance resources, thereby reducing maintenance costs in the short term.

[0030] However, although this strategy is effective in dealing with some simple faults, it relies on intervention measures after the fault occurs and lacks the ability of real-time data feedback and intelligent prediction. Therefore, maintenance is often carried out after the equipment performance deteriorates or a fault occurs, missing the best time for maintenance. Therefore, this model leads to insufficient real-time operation and maintenance of industrial equipment.

[0031] In order to solve the above technical problems, the present application provides a predictive operation and maintenance method for industrial equipment. Figure 1 , Figure 1 A flowchart of a predictive operation and maintenance method for industrial equipment provided in an embodiment of the present application. The predictive operation and maintenance method for industrial equipment is applied to a server and includes steps S110 to S140, which are as follows: S110: Acquire operating status, resource flow, and operating condition data of industrial equipment sent by a multimodal sensor.

[0032] Specifically, a server is a high-performance computer used to store, process and transmit data. In industrial equipment operation and maintenance, servers are used to receive, store and analyze data from various sensors. Multimodal sensors refer to sensors that can collect multiple types of data simultaneously or separately. These data types include temperature, humidity, pressure, vibration, sound, image, etc. In industrial equipment operation and maintenance, multimodal sensors can provide more comprehensive and accurate equipment status information. The operating status refers to the working status of industrial equipment at a specific time and under specific conditions. For example, whether a motor is running, what is the speed, whether it is overheated, etc. In industrial equipment operation and maintenance, resource flow refers to the flow of materials, energy or information between equipment. For example, the flow speed of materials on the production line, energy consumption, real-time information transmission, etc. Working condition data refers to the data generated by the equipment under specific working environment and conditions. These data may include environmental factors such as temperature, humidity, pressure, as well as working parameters such as load and speed of the equipment.

[0033] For example, suppose an industrial production line contains multiple motors, sensors, and controllers. These devices are connected to the server via wired or wireless connections. Temperature sensors and vibration sensors are installed on each motor. The temperature sensor is used to monitor the temperature of the motor, and the vibration sensor is used to monitor the vibration of the motor. The material sensor on the production line is used to monitor the speed and position of the material flow. The energy sensor is used to monitor the energy consumption. The data collected by all sensors is sent to the server via wired or wireless connections. The server receives and stores this data for subsequent analysis and processing. The data analysis software on the server processes and analyzes the received data. For example, by analyzing the temperature data and vibration data of the motor, it can be determined whether the motor is overheated or has abnormal vibration. By analyzing the data of the material sensor, the real-time situation of the material flow can be understood. By analyzing the data of the energy sensor, energy consumption can be optimized and costs can be reduced.

[0034] In a possible implementation, the operating status, resource flow and working condition data for industrial equipment sent by the multimodal sensor are obtained, specifically including: receiving the original detection data for the industrial equipment sent by the multimodal sensor; processing the original detection data to obtain the operating status, resource flow and working condition data, and the data processing includes denoising, filtering, feature extraction and normalization.

[0035] Specifically, multimodal sensors can collect various types of data from industrial equipment, such as temperature, pressure, vibration, sound, etc. The server receives the raw data sent by these sensors through wired or wireless means. This data may be continuous, discrete, or contain timestamps. Data processing is the process of extracting useful information, reducing noise and interference, and converting raw data into a form that can be used for further analysis. Denoising is used to remove random noise or outliers in the data, which may be caused by sensor errors, transmission errors, or environmental factors. Filters smooth the data by applying filters to further reduce noise while retaining the main features of the signal. Feature extraction is to extract key features that can represent the equipment status, resource flow, and working conditions from the raw data. These features may be in the form of numerical values, vectors, or matrices. Normalization scales the feature data to a standard range, such as 0 to 1, so that the importance of different features can be fairly compared in subsequent analysis. After the above data processing steps, the server can extract the equipment's operating status, resource flow, and working condition data.

[0036] S120. Based on the operation status, resource flow and working condition data, a symbiotic relationship map is constructed.

[0037] Specifically, the server first receives and processes data from multimodal sensors to obtain the operating status, resource flow, and working condition data of the equipment. These data are the basis for building a symbiotic relationship map. The server then performs data association analysis, that is, exploring whether there is a correlation or causal relationship between different data. For example, the temperature of the equipment may be related to its vibration state, and the flow rate of the material may be affected by the operating state of the equipment. Based on the results of the data association analysis, the server will build a symbiotic relationship map. This map is displayed in a graphical way, where nodes represent different data points, such as temperature, vibration, flow, etc., and edges represent the interactions and dependencies between these data points. The map contains elements such as color coding, nodes of different sizes, and edges of different thicknesses or colors to represent different characteristics or importance of the data. By interpreting the map, users can identify which data points have close interactions and which data points may have an important impact on the overall performance or operating status of the equipment.

[0038] In a possible implementation, a symbiotic relationship map is constructed based on operating status, resource flow and operating condition data, specifically including: determining industrial equipment as target nodes; determining material, energy or signal flow between equipment as target edges based on operating status, resource flow and operating condition data, one target edge corresponds to a target weight, and the target weight is used to represent the collaboration efficiency between equipment; constructing a symbiotic relationship map based on target nodes, target edges and target weights.

[0039] Specifically, when constructing the symbiotic relationship map, each industrial device is regarded as an independent entity or node. These nodes represent different parts of the production line or system, such as motors, pumps, sensors, etc. In addition to the devices themselves as nodes, the interactions or relationships between devices are also regarded as important components in the map. These interactions are manifested as the flow of materials, energy or signals. For example, materials are transferred from one device to another, or energy is transferred from one device to another to drive its operation, or signals are transferred from one sensor to another for monitoring or control. These flows are represented as edges in the map, namely target edges. Each target edge is associated with a weight, which is used to quantify the efficiency of collaboration or the intensity of interaction between devices. The weight can be determined based on a variety of factors, such as the speed of material flow, the efficiency of energy transfer, the transmission quality of signals, etc. These weights reflect the degree of interaction between devices under specific conditions and are key indicators for evaluating the performance of the entire system. With target nodes, target edges and target weights, a complete symbiotic relationship map can be constructed. The graph is presented in a graphical way, where nodes represent devices, edges represent interactions between devices, and weights are represented by edge thickness, color, or other visual elements.

[0040] For example, suppose an industrial production line contains two main devices: Device A: a motor, Device B: a pump. In this example, both the motor and the pump are considered as target nodes. The motor transfers energy to the pump through the drive shaft to drive it to operate. This energy flow is represented as a target edge from the motor to the pump. Suppose the efficiency of energy transfer is evaluated by measuring the output power of the motor and the input power of the pump. If the output power of the motor is 100 kilowatts and the input power of the pump is 90 kilowatts, the efficiency of energy transfer is 90%, and this value can be used as the target weight. Finally, a symbiotic relationship graph can be constructed based on this information. In this graph, the motor and the pump are represented as two nodes with an edge between them representing the energy flow, and the thickness or color of the edge is used to represent the efficiency of energy transfer, that is, the target weight.

[0041] S130, inputting the symbiotic relationship map into a preset symbiotic network model to obtain a detection result.

[0042] Specifically, the symbiotic relationship graph is a graphical representation that shows the interactions and dependencies between different elements. These relationships may include material flow, energy transfer, signal communication, etc. The nodes in the graph represent different devices or system components, while the edges represent the interactions between these devices or components. The preset symbiotic network model is a trained machine learning model or algorithm that is specifically used to analyze the symbiotic relationship graph and extract useful information. This model is built based on graph neural network technology. The purpose of the model is to understand the structural information in the graph and the relationship between nodes and edges, so as to predict or detect the behavior, performance or potential problems of the system. The server passes the constructed symbiotic relationship graph as input data to the preset symbiotic network model. The preset symbiotic network model analyzes the input symbiotic relationship graph and outputs the detection results. The detection results may include system operation status evaluation, performance prediction, fault warning, optimization suggestions, etc. These results help operation and maintenance personnel understand the current status of the system and take necessary measures to ensure the stable operation of the system.

[0043] In one possible implementation, the symbiotic relationship map is input into a preset symbiotic network model to obtain a detection result, which specifically includes: extracting a feature group based on the target node, target edge and target weight; through the preset symbiotic network model, if it is determined that the collaborative efficiency between devices fluctuates within a preset range, then the detection result is determined to be normal; through the preset symbiotic network model, if it is determined that the similarity between the feature group and the preset feature is less than a preset similarity threshold, then the detection result is determined to be symbiotically abnormal.

[0044] Specifically, when the symbiotic relationship map is input into the preset symbiotic network model, the model first extracts a series of features based on the target nodes, target edges, and target weights in the map. These features include node attributes, such as equipment type, operating status, etc., and edge attributes, such as material flow rate, energy transfer efficiency, etc., as well as statistics or indicators calculated from these attributes, such as average synergy efficiency, maximum material flow rate, etc. These features are combined into a feature group for subsequent model analysis and detection. The preset symbiotic network model calculates the synergy efficiency, or similar performance indicators, in the feature group and compares it with the preset synergy efficiency range. If the calculated synergy efficiency fluctuates within the preset range, it means that the interaction and dependency between the devices are in a normal state, so the detection result is determined to be normal. The preset symbiotic network model also compares the extracted feature group with a set of preset features to evaluate the similarity between them. These preset features represent typical feature patterns or abnormal feature patterns when the system is operating normally. If the similarity between the feature group and the preset feature is less than the preset similarity threshold, it means that the current system operation state does not match the preset normal mode or abnormal mode, so the detection result is determined to be a symbiotic anomaly.

[0045] For example, suppose an industrial production line consists of multiple interconnected motors and sensors, and the server has built a symbiotic relationship map based on the data of these devices and sensors. The server inputs the map into the preset symbiotic network model. The model extracts a series of features, such as the average operating efficiency of the motor and the signal stability of the sensor, based on the nodes, edges, and weights in the map, and combines these features into a feature group. The model calculates the average operating efficiency of the motors in the feature group and compares it with the preset synergistic efficiency range, such as 80%-100%. If the calculated average operating efficiency fluctuates within this range, such as 90%, the detection result is determined to be normal. The model also compares the extracted feature group with a set of preset features, which may represent typical feature patterns when the production line is operating normally. If the similarity between the feature group and the preset features is less than the preset similarity threshold, such as 0.8, it means that the current operating state of the production line does not match the preset normal mode, and there may be some abnormality, so the detection result is determined to be a symbiotic abnormality. In this way, the server can use the symbiotic relationship map and the preset symbiotic network model to monitor the operating status of the industrial production line in real time, and take corresponding measures based on the detection results to ensure the stable operation of the production line.

[0046] S140. Perform predictive operation and maintenance of industrial equipment based on the detection results.

[0047] Specifically, the server has previously detected the operating status of industrial equipment through the symbiotic relationship map and the preset symbiotic network model, and obtained the detection results. These detection results may include information such as the current performance status of the equipment, potential fault warnings, and collaborative efficiency evaluation. Based on the detection results, the server will formulate and implement a series of predictive operation and maintenance strategies. These strategies may include regular maintenance plans, spare parts inventory management, preventive maintenance tasks, performance optimization suggestions, etc. In the process of implementing predictive operation and maintenance, the server will continuously monitor the real-time data of industrial equipment. By analyzing this data, the server can further evaluate the health status of the equipment, predict future performance trends, and identify any abnormalities in a timely manner. Based on the results of real-time data monitoring and analysis, the server may dynamically adjust the predictive operation and maintenance strategy. For example, if it is found that the performance of a certain device is declining faster than expected, the server may arrange maintenance tasks or increase spare parts inventory in advance.

[0048] In one possible implementation, predictive operation and maintenance are performed on industrial equipment based on the detection results, specifically including: determining the abnormality category based on the detection results; if the abnormality category is determined to be a node abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the equipment body of the industrial equipment; if the abnormality category is determined to be an edge abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the collaborative efficiency of the industrial equipment; if the abnormality category is determined to be a symbiotic abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the collaborative problems between the industrial equipment and the associated equipment corresponding to the industrial equipment.

[0049] Specifically, the server first determines the specific category of the anomaly based on the detection results. These anomaly categories may include node anomalies, edge anomalies, and symbiotic anomalies. Node anomalies refer to performance degradation, fault warning, and other problems that occur in a single device. Edge anomalies refer to problems with the interaction or dependency between devices, such as obstructed material flow and interrupted signal communication. Symbiotic anomalies refer to problems with the collaborative work of multiple devices, resulting in overall performance degradation or instability. Based on the determined anomaly categories, the server will formulate corresponding operation and maintenance strategies. For node anomalies, the operation and maintenance strategy focuses on predictive operation and maintenance of the device itself, such as regular inspections, preventive maintenance, and performance optimization. For edge anomalies, the operation and maintenance strategy focuses on improving the efficiency of collaboration between devices, such as optimizing material flow paths and enhancing signal communication stability. For symbiotic anomalies, the operation and maintenance strategy is more complex and requires comprehensive consideration of the collaborative issues between multiple devices, such as adjusting the working parameters of the equipment, optimizing the workflow, and increasing collaborative monitoring.

[0050] For example, suppose an industrial production line consists of multiple interconnected motors, sensors, and controllers. The server detects the operating status of the production line through the symbiotic relationship map and the preset symbiotic network model. The server detects that the temperature data of a motor has increased abnormally, and the coordination efficiency with other devices has decreased, which is initially judged as a node abnormality. Further analysis found that there were also problems with the signal communication between the motor and the adjacent sensors, which was manifested as data transmission delay and packet loss, which was determined to be an edge abnormality. At the same time, the server also noticed that the overall coordination of the motor with other devices was also affected, resulting in a decrease in the overall performance of the production line, which was determined to be a symbiotic abnormality. For node abnormalities, the server formulated a predictive operation and maintenance strategy for the motor, including increasing the frequency of temperature monitoring, arranging preventive maintenance tasks, and checking the cooling system. For edge abnormalities, the server optimized the signal transmission path, enhanced the stability of signal communication, and arranged professional technicians to debug sensors and motors. For symbiotic abnormalities, the server comprehensively considered the working parameters and work processes of multiple devices, adjusted the coordination mode between them, added collaborative monitoring functions, and organized a cross-departmental technical team to solve collaborative problems.

[0051] In one possible implementation, vibration data, temperature data, current data, and voltage data of industrial equipment during operation are determined based on operating condition data; if it is determined that the difference between any one of the vibration data, temperature data, current data, and voltage data and the corresponding preset data is greater than or equal to a preset difference threshold, the detection result is determined to be locally abnormal.

[0052] Specifically, in an embodiment of the present application, the operating data of interest include vibration data, temperature data, current data, and voltage data. These data are collected in real time by sensors and transmitted to a server or a monitoring system. The server or monitoring system will compare the collected operating data with the preset data. The preset data is a reference value or range set according to the normal operating status of the equipment, historical data, industry standards, or the manufacturer's recommendations. For each operating data, the server will calculate the difference between it and the preset data. If this difference is greater than or equal to the preset difference threshold, it is considered that the data item is abnormal. If any one of the vibration data, temperature data, current data, or voltage data is determined to be abnormal, then the overall detection result is determined to be a local abnormality. This means that the operating status of the equipment in a certain aspect deviates from the normal range and may require further inspection or maintenance.

[0053] For example, suppose that a motor on an industrial production line is running, and the server collects the following working condition data in real time through sensors: the current value of the vibration data is 0.05 mm / s, and the preset normal range is 0.01-0.04 mm / s; the current value of the temperature data is 85 degrees Celsius, and the preset normal range is 60-80 degrees Celsius; the current value of the current data is 10 amps, and the preset normal range is 8-12 amps; the current value of the voltage data is 220 volts, and the preset normal range is 210-230 volts. The difference between the vibration data and the preset data is 0.01 mm / s, which exceeds the preset difference threshold of 0.01 mm / s. Assume that the threshold is set to not exceed the maximum value of the preset range. The difference between the temperature data and the preset data is 5 degrees Celsius, which exceeds the preset difference threshold of 3 degrees Celsius. Assume that the threshold is set to not exceed the maximum value of the preset range minus a safety margin. The current data and the voltage data are both within the preset normal range, so the difference between the current data and the preset data does not exceed the threshold. Since the difference between at least one of the vibration data and the temperature data and the preset data exceeds the threshold, the detection result of the motor is determined to be a local abnormality. This means that the motor has abnormalities in vibration and temperature, and further inspection or maintenance may be required to ensure normal operation. In this way, the server can promptly detect local abnormalities in the operation of industrial equipment based on the comparison results of the working condition data with the preset data, so as to take corresponding measures to prevent potential failures or problems.

[0054] In one possible implementation, refer to Figure 2 , Figure 2 Another flow chart of a predictive operation and maintenance method for industrial equipment provided in an embodiment of the present application. The method includes steps S210 to S230, which are as follows: S210, obtaining historical operation and maintenance data, the historical operation and maintenance data including the correspondence between abnormal categories and operation and maintenance personnel; S220, determining the target operation and maintenance personnel according to the abnormal categories and the correspondence; S230, sending the operation and maintenance strategy to the target operation and maintenance personnel, the operation and maintenance strategy including the location data of the industrial equipment.

[0055] Specifically, historical operation and maintenance data is a record of equipment operation and maintenance over a period of time in the past, including the abnormal categories of equipment, such as mechanical failure, electrical failure, software failure, etc., and the information of the operation and maintenance personnel responsible for handling these abnormalities. These data are stored in a database or data warehouse and can be obtained through data query or data mining technology. By analyzing historical operation and maintenance data, a correspondence between abnormal categories and operation and maintenance personnel can be established. This correspondence may be based on factors such as the professional skills, experience, and success rate of handling similar abnormalities of the operation and maintenance personnel. For example, some operation and maintenance personnel may be good at handling mechanical failures, while others may be better at handling electrical or software problems. When a new abnormality occurs, the system automatically determines the most suitable operation and maintenance personnel as the target operation and maintenance personnel based on the current abnormality category and the previously established correspondence. This process may involve techniques such as matching algorithms or decision trees to ensure that the selected operation and maintenance personnel have the skills and experience required to handle the current abnormality. Once the target operation and maintenance personnel are determined, the system will send them an operation and maintenance strategy. The operation and maintenance strategy includes detailed operation steps, required tools, safety precautions, and location data of industrial equipment, such as the workshop, production line, and specific location of the equipment. This information helps operation and maintenance personnel quickly locate equipment, understand problems, and take appropriate maintenance measures.

[0056] For example, suppose a machine on a factory production line suddenly stops and displays an electrical fault alarm. The factory's server first queries the historical operation and maintenance data of similar electrical faults in the past. By analyzing the historical data, the server finds that Zhang San and Li Si, two operation and maintenance personnel, have successfully handled many electrical faults in the past, and their handling speed and quality are very high. Based on the current exception category and the previously established correspondence, the server selects Zhang San as the target operation and maintenance personnel. The server sends Zhang San an operation and maintenance strategy message, including detailed electrical fault troubleshooting steps, required tools, safety precautions, and the specific location data of the machine. After receiving the message, Zhang San quickly went to the designated location and began to troubleshoot and repair the fault according to the steps in the operation and maintenance strategy. In this way, the factory can use operation and maintenance resources more efficiently to ensure that equipment failures are handled promptly and professionally.

[0057] The present application also provides a predictive operation and maintenance device for industrial equipment, referring to Figure 3 , Figure 3 A module schematic diagram of a predictive operation and maintenance device for industrial equipment provided in an embodiment of the present application. The predictive operation and maintenance device for industrial equipment is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the operating status, resource flow and working condition data of the industrial equipment sent by the multimodal sensor; the processing module 32 constructs a symbiotic relationship map based on the operating status, resource flow and working condition data; the processing module 32 inputs the symbiotic relationship map into a preset symbiotic network model to obtain a detection result; the processing module 32 performs predictive operation and maintenance on the industrial equipment according to the detection result.

[0058] In a possible implementation, the processing module 32 constructs a symbiotic relationship map based on the operating status, resource flow and operating condition data, specifically including: the processing module 32 determines the industrial equipment as the target node; the processing module 32 determines the material, energy or signal flow between the equipment as the target edge according to the operating status, resource flow and operating condition data, and one target edge corresponds to a target weight, and the target weight is used to represent the collaboration efficiency between the equipment; the processing module 32 constructs a symbiotic relationship map according to the target node, target edge and target weight.

[0059] In a possible implementation, the processing module 32 inputs the symbiotic relationship map into a preset symbiotic network model to obtain a detection result, which specifically includes: the processing module 32 extracts a feature group based on the target node, the target edge and the target weight; the processing module 32 uses the preset symbiotic network model to determine that the detection result is normal if it is determined that the collaborative efficiency between the devices fluctuates within a preset range; the processing module 32 uses the preset symbiotic network model to determine that the detection result is symbiotically abnormal if it is determined that the similarity between the feature group and the preset feature is less than a preset similarity threshold.

[0060] In one possible implementation, the processing module 32 determines the vibration data, temperature data, current data, and voltage data of the industrial equipment during operation based on the operating condition data; if the processing module 32 determines that the difference between any one of the vibration data, temperature data, current data, and voltage data and the corresponding preset data is greater than or equal to a preset difference threshold, it determines that the detection result is locally abnormal.

[0061] In a possible implementation, the processing module 32 performs predictive operation and maintenance on the industrial equipment based on the detection results, specifically including: the processing module 32 determines the abnormality category based on the detection results; if the processing module 32 determines that the abnormality category is a node abnormality, the operation and maintenance strategy is determined to be predictive operation and maintenance of the equipment body of the industrial equipment; if the processing module 32 determines that the abnormality category is an edge abnormality, the operation and maintenance strategy is determined to be predictive operation and maintenance of the collaborative efficiency of the industrial equipment; if the processing module 32 determines that the abnormality category is a symbiotic abnormality, the operation and maintenance strategy is determined to be predictive operation and maintenance of the collaborative problems between the industrial equipment and the associated equipment corresponding to the industrial equipment.

[0062] In a possible implementation, the acquisition module 31 acquires historical operation and maintenance data, which includes the correspondence between abnormal categories and operation and maintenance personnel; the processing module 32 determines the target operation and maintenance personnel based on the abnormal categories and the correspondence; the processing module 32 sends the operation and maintenance strategy to the target operation and maintenance personnel, and the operation and maintenance strategy includes the location data of the industrial equipment.

[0063] In a possible implementation, the acquisition module 31 acquires the operating status, resource flow and operating condition data for industrial equipment sent by the multimodal sensor, specifically including: the acquisition module 31 receives the original detection data for industrial equipment sent by the multimodal sensor; the processing module 32 processes the original detection data to obtain the operating status, resource flow and operating condition data, and the data processing includes denoising, filtering, feature extraction and normalization.

[0064] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0065] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0066] The communication bus 42 is used to realize the connection and communication between these components.

[0067] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0068] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0069] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0070] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a predictive operation and maintenance method for industrial equipment.

[0071] exist Figure 4 In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program stored in the memory 45 for a predictive operation and maintenance method for industrial equipment. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0072] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0073] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0074] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0076] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0077] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0078] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0079] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A predictive operation and maintenance method for industrial equipment, characterized in that: The method comprises: Obtain operating status, resource flow, and operating condition data for industrial equipment sent by multimodal sensors; Based on the operating status, the resource flow and the operating condition data, a symbiotic relationship map is constructed; Inputting the symbiotic relationship map into a preset symbiotic network model to obtain a detection result; Based on the detection results, predictive operation and maintenance are performed on the industrial equipment.

2. The predictive operation and maintenance method for industrial equipment according to claim 1, characterized in that: The constructing of a symbiotic relationship map based on the operating status, the resource flow and the operating condition data specifically includes: Determining the industrial equipment as a target node; According to the operating state, the resource flow and the working condition data, determine the material, energy or signal flow between the devices as a target edge, one target edge corresponds to a target weight, and the target weight is used to represent the collaboration efficiency between the devices; The symbiotic relationship graph is constructed based on the target node, the target edge and the target weight.

3. The predictive operation and maintenance method for industrial equipment according to claim 2, characterized in that: The step of inputting the symbiotic relationship map into a preset symbiotic network model to obtain a detection result specifically includes: Extracting a feature group according to the target node, the target edge and the target weight; If it is determined through the preset symbiotic network model that the collaborative efficiency between the devices fluctuates within a preset range, then it is determined that the detection result is normal; Through the preset symbiotic network model, if it is determined that the similarity between the feature group and the preset feature is less than a preset similarity threshold, the detection result is determined to be symbiotically abnormal.

4. The predictive operation and maintenance method for industrial equipment according to claim 1, characterized in that: The method further comprises: Determining vibration data, temperature data, current data, and voltage data of the industrial equipment during operation according to the operating condition data; If it is determined that the difference between any one of the vibration data, the temperature data, the current data and the voltage data and the corresponding preset data is greater than or equal to a preset difference threshold, the detection result is determined to be partially abnormal.

5. The predictive operation and maintenance method for industrial equipment according to claim 1, characterized in that: The predictive operation and maintenance of the industrial equipment according to the detection result specifically includes: Determine an abnormality category according to the detection result; If it is determined that the abnormality category is a node abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the equipment body of the industrial equipment; If it is determined that the abnormality category is an edge abnormality, determining the operation and maintenance strategy to perform predictive operation and maintenance on the collaborative efficiency of the industrial equipment; If it is determined that the abnormality category is a symbiotic abnormality, the operation and maintenance strategy is determined to be predictive operation and maintenance of the coordination problem between the industrial equipment and the associated equipment corresponding to the industrial equipment.

6. The predictive operation and maintenance method for industrial equipment according to claim 5, characterized in that: The method further comprises: Acquire historical operation and maintenance data, wherein the historical operation and maintenance data includes a correspondence between abnormal categories and operation and maintenance personnel; Determining a target operation and maintenance personnel according to the abnormality category and the corresponding relationship; The operation and maintenance strategy is sent to the target operation and maintenance personnel, where the operation and maintenance strategy includes the location data of the industrial equipment.

7. The predictive operation and maintenance method for industrial equipment according to claim 1, characterized in that: The obtaining of the operating status, resource flow and working condition data of the industrial equipment sent by the multimodal sensor specifically includes: Receiving original detection data for the industrial equipment sent by the multimodal sensor; The original detection data is processed to obtain the operating status, the resource flow and the operating condition data, and the data processing includes denoising, filtering, feature extraction and normalization.

8. A predictive operation and maintenance device for industrial equipment, characterized in that: The industrial equipment predictive operation and maintenance device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire the operating status, resource flow and working condition data of the industrial equipment sent by the multimodal sensor; The processing module (32) is used to construct a symbiotic relationship map based on the operating state, the resource flow and the operating condition data; The processing module (32) is further used to input the symbiotic relationship map into a preset symbiotic network model to obtain a detection result; The processing module (32) is also used to perform predictive operation and maintenance on the industrial equipment based on the detection results.

9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images