An industrial equipment behavior prediction method and system based on multi-source data fusion

Abstract

The application is suitable for the technical field of industrial simulation, and provides an industrial equipment behavior prediction method and system based on multi-source data fusion, which comprises the following steps: in response to a start operation instruction, feature parameter set information and real-time monitoring video stream information of a to-be-detected equipment are acquired based on a sensor; first evaluation result information is generated based on the feature parameter set information and predicted abnormal parameter set information; second evaluation result information is generated based on the real-time monitoring video stream information based on a target detection algorithm; and finally, abnormal prediction information is accurately generated based on the above information. Through the implementation of advanced monitoring and analysis technology, the application can realize the early prediction of the plugging abnormality of an oil pump, so that corresponding preventive measures can be taken before the abnormality occurs, the reliability and operation efficiency of the industrial equipment are significantly improved, the downtime caused by equipment failure can be effectively reduced, the maintenance cost is reduced, and the service life of the industrial equipment is prolonged.

Description

Technical Field

[0001] This application relates to the technical field of industrial simulation, and more specifically, to a method and system for predicting the behavior of industrial equipment based on multi-source data fusion. Background Technology

[0002] With the rapid development of intelligent manufacturing, intelligent management and maintenance of industrial equipment have become key to improving production efficiency and reducing operating costs. Oil pumps are crucial industrial equipment in oilfield production, primarily used to extract crude oil from underground to the surface.

[0003] Currently, the maintenance of oil pumps usually relies on periodic inspections, which not only easily leads to prolonged downtime of the oil pumps but may also cause more serious economic losses, resulting in low reliability and requiring further improvement. Summary of the Invention

[0004] Based on this, embodiments of this application provide a method and system for predicting the behavior of industrial equipment based on multi-source data fusion, in order to solve the problem of low reliability in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for predicting the behavior of industrial equipment based on multi-source data fusion, the method comprising: In response to the start command, based on preset sensors, it continuously acquires the characteristic parameter set information and real-time monitoring video stream information of the device under test; Based on the feature parameter set information and the preset prediction anomaly parameter set information, the first evaluation result information is generated; Based on a preset target detection algorithm, a second evaluation result is generated according to the real-time monitoring video stream information. Anomaly prediction information is generated based on the first evaluation result information and the second evaluation result information.

[0006] Compared with existing technologies, the beneficial effects are as follows: The industrial equipment behavior prediction method based on multi-source data fusion provided in this application embodiment allows the terminal device to first respond to the start-up command, continuously acquire feature parameter set information and real-time monitoring video stream information of the device to be detected based on preset sensors, then quickly generate first evaluation result information based on feature parameter set information and preset prediction anomaly parameter set information, then efficiently generate second evaluation result information based on preset target detection algorithm and real-time monitoring video stream information, and finally accurately generate anomaly prediction information based on first and second evaluation result information, thereby realizing early prediction of oil pump blockage anomalies, which is conducive to taking corresponding measures in advance, greatly improving reliability, and solving the problem of low reliability to a certain extent.

[0007] Secondly, embodiments of this application provide an industrial equipment behavior prediction system based on multi-source data fusion, the system comprising: Feature parameter set information acquisition module: In response to the start command, it continuously acquires the feature parameter set information and real-time monitoring video stream information of the device under test based on preset sensors; First evaluation result information generation module: used to generate first evaluation result information based on the feature parameter set information and the preset prediction anomaly parameter set information; The second evaluation result information generation module is used to generate second evaluation result information based on the real-time monitoring video stream information using a preset target detection algorithm. Anomaly prediction information generation module: used to generate anomaly prediction information based on the first evaluation result information and the second evaluation result information.

[0008] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0010] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0012] Figure 1 This is a flowchart illustrating an embodiment of the industrial equipment behavior prediction method provided in this application; Figure 2 This is a flowchart illustrating the process before step S200 in an embodiment of the industrial equipment behavior prediction method provided in this application. Figure 3 This is a flowchart illustrating step S200 in an industrial equipment behavior prediction method provided in an embodiment of this application. Figure 4 This is a flowchart illustrating step S300 in an embodiment of the industrial equipment behavior prediction method provided in this application. Figure 5This is a flowchart illustrating step S400 in an embodiment of the industrial equipment behavior prediction method provided in this application. Figure 6 This is a block diagram of an industrial equipment behavior prediction system provided in an embodiment of this application; Figure 7 This is a schematic diagram of a terminal device provided in an embodiment of this application. Detailed Implementation

[0013] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0014] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0015] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0016] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0017] Please see Figure 1 , Figure 1 This is a flowchart illustrating the industrial equipment behavior prediction method based on multi-source data fusion provided in this application embodiment. In this embodiment, the execution subject of the industrial equipment behavior prediction method is a terminal device. It is understood that the types of terminal devices include, but are not limited to, mobile phones, tablets, laptops, Ultra-Mobile Personal Computers (UMPCs), netbooks, Personal Digital Assistants (PDAs), etc. This application embodiment does not impose any restrictions on the specific type of terminal device.

[0018] Please see Figure 1 The industrial equipment behavior prediction method provided in this application includes, but is not limited to, the following steps: In S100, in response to the start-up command, the system continuously acquires the feature parameter set information and real-time monitoring video stream information of the device under test based on preset sensors.

[0019] Specifically, the terminal device can first respond to the start-up command and continuously acquire the characteristic parameter set information and real-time monitoring video stream information of the device under test based on preset sensors. The start-up command describes the start-up of the device under test, which can be an oil pump, including a heat exchanger. The characteristic parameter set information includes real-time pressure parameter information and real-time temperature parameter information. The real-time pressure parameter information describes the real-time pressure at the inlet and outlet of the heat exchanger, and the real-time temperature parameter information describes the real-time temperature of the heat exchanger.

[0020] Without loss of generality, real-time pressure parameter information can be obtained through a preset pressure sensor; real-time temperature parameter information can be obtained through a preset temperature sensor; and real-time monitoring video stream information can be obtained through a preset image sensor.

[0021] It should be noted that when a heat exchanger is blocked, the narrowed flow channels increase fluid resistance, leading to a significant and abnormal increase in pressure at the inlet and outlet of the heat exchanger. In severely blocked areas, "hot spots" will appear on the surface of the tube bundles or plates, resulting in abnormal temperature regions.

[0022] In S200, the first evaluation result information is generated based on the feature parameter set information and the preset prediction anomaly parameter set information.

[0023] Specifically, after the terminal device acquires the feature parameter set information and the real-time monitoring video stream information, the terminal device can accurately generate the first evaluation result information based on the feature parameter set information and the preset predicted anomaly parameter set information. The first evaluation result information includes the first normal operation information or the first predicted fault operation information. The first normal operation information is used to describe that the device under test is still in normal operation in the future. The first predicted fault operation information is used to describe that the device under test is about to be in fault operation.

[0024] Without loss of generality, the predicted anomaly parameter set information includes the predicted anomaly pressure average information and the predicted anomaly temperature average information. The predicted anomaly pressure average information is used to describe the predicted average pressure value when a blockage anomaly is about to occur, and the predicted anomaly temperature average information is used to describe the predicted average temperature value when a blockage anomaly is about to occur.

[0025] In some possible implementations, to determine accurate information about the predicted anomaly parameter set, please refer to [link / reference needed]. Figure 2 Before step S201, the method also includes, but is not limited to, the following steps: In S201, based on a preset sampling time period, multiple abnormal state information of the device under test and the abnormal time information corresponding to each abnormal state information are obtained.

[0026] Specifically, the terminal device can acquire multiple abnormal status information of the device under test and the abnormal time information corresponding to each abnormal status information based on a preset sampling time period. The sampling period can be one month or one week prior; the abnormal status information describes the blockage abnormality of the device under test; and the abnormal time information describes the moment when the blockage abnormality of the device under test was determined to have occurred within the sampling period.

[0027] In S202, based on the abnormal time information, according to the order of occurrence time, it is determined whether the time interval between any two abnormal state information is less than the preset association time threshold.

[0028] Specifically, after the terminal device obtains the abnormal status information and the abnormal time information, the terminal device can, based on the abnormal time information, sequentially determine whether the time interval between any two abnormal status information is less than a preset association time threshold in the order of their occurrence. The association time threshold can be customized, such as 5 minutes or 10 minutes.

[0029] In S203, if the time interval between two abnormal status information is less than the associated time threshold, the abnormal time information that occurred later is deleted, and the abnormal time information that occurred earlier is determined as the target time information.

[0030] Specifically, if the time interval between two abnormal status information is less than the associated time threshold, the terminal device can delete the abnormal time information that occurred later, retain the abnormal time information that occurred earlier, and determine the abnormal time information that occurred earlier as the target time information, thereby eliminating redundant abnormal status information that continues to be generated due to failure to stop operation in time when a blockage occurs.

[0031] In S204, for each target time information, the backtracking time information is determined according to the preset backtracking time interval value.

[0032] Specifically, after the terminal device determines the target time information, the terminal device can perform this processing for each target time information. According to the preset backtracking time interval value, the backtracking time information is determined. The occurrence time of the backtracking time information is earlier than the occurrence time of the target time information. The time interval between the backtracking time information and the target time information is the backtracking time interval value. The backtracking time interval value can be customized, such as 1 minute or 3 minutes.

[0033] In S205, based on the retrospective time information, the predicted abnormal pressure value information and the predicted abnormal temperature parameter value information are determined.

[0034] Specifically, after the terminal device determines the retrospective time information, it can determine the pressure value of the device under test in the retrospective time information as the predicted abnormal pressure value information, and determine the temperature value of the device under test in the retrospective time information as the predicted abnormal temperature parameter value information.

[0035] In S206, the average value of predicted abnormal pressure is generated based on multiple predicted abnormal pressure values.

[0036] Specifically, after the terminal device determines the predicted abnormal pressure value information and the predicted abnormal temperature parameter value information, the terminal device can generate the predicted abnormal pressure average value information based on the average of the sum of multiple predicted abnormal pressure value information.

[0037] In S207, the mean value information of the predicted abnormal temperature parameters is generated based on multiple predicted abnormal temperature parameter values.

[0038] Specifically, after the terminal device generates the predicted abnormal pressure average information, the terminal device can generate the predicted abnormal temperature parameter average information based on the average of the sum of multiple predicted abnormal temperature parameter values.

[0039] In some possible implementations, to generate the first evaluation result information, please refer to [link / reference]. Figure 3 Step S200 includes, but is not limited to, the following steps: In S210, pressure difference information is generated based on real-time pressure parameter information and predicted average abnormal pressure information.

[0040] Specifically, after the terminal device acquires the feature parameter set information and the real-time monitoring video stream information, the terminal device can generate pressure difference information by subtracting the predicted average abnormal pressure information from the real-time pressure parameter information.

[0041] In S220, temperature difference information is generated based on real-time temperature parameter information and predicted abnormal temperature parameter values.

[0042] Specifically, after the terminal device generates pressure difference information, it can generate temperature difference information by subtracting the predicted abnormal temperature parameter value from the real-time temperature parameter information.

[0043] In S230, it is determined whether the pressure difference information is less than the preset pressure threshold information and whether the temperature difference information is less than the preset temperature threshold information.

[0044] Specifically, after the terminal device generates temperature difference information, it can determine whether the pressure difference information is less than the preset pressure threshold information, and whether the temperature difference information is less than the preset temperature threshold information. Both the pressure threshold information and the temperature threshold information can be customized by maintenance personnel according to the specific situation of the device to be tested.

[0045] In S240, if the pressure difference information is less than the pressure threshold information and the temperature difference information is less than the temperature threshold information, then the first normal operation information is generated; otherwise, the first predicted fault operation information is generated.

[0046] Specifically, if the pressure difference information is less than the pressure threshold information and the temperature difference information is less than the temperature threshold information, the terminal device can generate the first normal operation information; otherwise, the terminal device can generate the first predicted fault operation information.

[0047] In S300, a second evaluation result is generated based on a preset target detection algorithm and real-time monitoring video stream information.

[0048] Specifically, after the terminal device generates the first evaluation result information, it can accurately generate the second evaluation result information based on the preset target detection algorithm and the real-time monitoring video stream information, thereby realizing the re-evaluation of the device under test. The second evaluation result information includes the second normal operation information or the second fault operation information. The second normal operation information is used to describe that the device under test is in a normal operation state after re-evaluation, and the second fault operation information is used to describe that the device under test is in a fault operation state after re-evaluation, that is, the device under test is in a blocked abnormality. The real-time monitoring video stream information includes multiple real-time monitoring image information.

[0049] In some possible implementations, for accurate generation of second evaluation result information, please refer to [link / reference]. Figure 4 Step S300 includes, but is not limited to, the following steps: In S310, for each real-time monitoring image, the contour information to be detected is determined based on a preset edge contour extraction algorithm.

[0050] Specifically, the terminal device can perform this processing on each real-time monitoring image information. Based on a preset edge contour extraction algorithm, it determines the contour information to be detected corresponding to each real-time monitoring image information. The edge contour extraction algorithm can be the Canny algorithm or the Sobel algorithm.

[0051] In S320, based on a preset target detection algorithm, the object type information corresponding to the contour information to be detected is determined according to the contour information to be detected.

[0052] Specifically, after the terminal device determines the contour information to be detected, it can determine the object type information corresponding to the contour information based on the preset target detection algorithm. The object type information describes the type corresponding to the contour information to be detected. The object type information includes device type information or other type information. The device type information describes the device itself, which is the device to be detected, i.e., the shape contour of the device itself. Other type information can be an oily area, which is the oily deposit area accumulated on the outer shell due to heat exchanger blockage.

[0053] In S330, if the object type information is device type information, then second normal operation information is generated; otherwise, second fault operation information is generated.

[0054] Specifically, if the object type information is device type information, it indicates that the outline in the real-time monitoring image information is the original shape outline of the device to be detected, so the terminal device can generate the second normal operation information; otherwise, it indicates that in addition to the original shape outline of the device to be detected, there are other dirt outlines in the outline of the real-time monitoring image information, so the terminal device can generate the second fault operation information.

[0055] In S400, anomaly prediction information is generated based on the first evaluation result information and the second evaluation result information.

[0056] Specifically, after the terminal device generates the second evaluation result information, it can comprehensively generate anomaly prediction information based on the first and second evaluation result information, thereby predicting the blockage anomaly of the heat exchanger in advance and facilitating the early implementation of corresponding measures. The anomaly prediction information includes anomaly height occurrence information or anomaly moderate occurrence information. Anomaly height occurrence information is used to describe the equipment under test with a very high probability of blockage anomaly, while anomaly moderate occurrence information is used to describe the equipment under test with a relatively high probability of blockage anomaly. The anomaly occurrence rate of anomaly moderate occurrence information is lower than that of anomaly height occurrence information.

[0057] In some possible implementations, for accurate generation of anomaly prediction information, please refer to [link / reference]. Figure 5 Step S400 includes, but is not limited to, the following steps: In S410, if the first evaluation result information is the first predicted fault operation information and the second evaluation result information is the second fault operation information, then abnormal height occurrence information is generated.

[0058] Specifically, if the first assessment result information is the first predicted fault operation information and the second assessment result information is the second fault operation information, then the terminal device can accurately generate abnormal height occurrence information.

[0059] In S420, if the first evaluation result information is the first predicted fault operation information, or the second evaluation result information is the second fault operation information, then the abnormality moderate occurrence information is generated.

[0060] Specifically, if the first assessment result information is the first predicted fault operation information, or the second assessment result information is the second fault operation information, then the terminal device can accurately generate the abnormality moderate occurrence information.

[0061] In one possible implementation, the terminal device can also incorporate a graph neural network (GNN) and a Transformer for state prediction to further assist in predicting the timing of heat exchanger blockage.

[0062] The implementation principle of the industrial equipment behavior prediction method based on multi-source data fusion in this application embodiment is as follows: The terminal device can first respond to the start-up command, continuously acquire the feature parameter set information and real-time monitoring video stream information of the device to be detected based on the preset sensors, and then quickly generate the first evaluation result information based on the feature parameter set information and the preset prediction anomaly parameter set information. Then, based on the preset target detection algorithm and the real-time monitoring video stream information, the second evaluation result information is efficiently generated. Finally, based on the first evaluation result information and the second evaluation result information, the anomaly prediction information is accurately generated, thereby realizing the early prediction of the blockage anomaly of the oil pump and greatly improving reliability.

[0063] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0064] Embodiments of this application also provide an industrial equipment behavior prediction system based on multi-source data fusion. For ease of explanation, only the parts relevant to this application are shown, such as... Figure 6 As shown, the system 60 includes: Feature parameter set information acquisition module 61: In response to the start-up command, it continuously acquires feature parameter set information and real-time monitoring video stream information of the device under test based on preset sensors; First evaluation result information generation module 62: used to generate first evaluation result information based on feature parameter set information and preset prediction anomaly parameter set information; Second evaluation result information generation module 63: used to generate second evaluation result information based on a preset target detection algorithm and real-time monitoring video stream information; Anomaly prediction information generation module 64: used to generate anomaly prediction information based on the first evaluation result information and the second evaluation result information.

[0065] Optionally, the predicted anomaly parameter set information includes the average predicted anomaly pressure parameter information and the average predicted anomaly temperature parameter information; the system 60 also includes: Abnormal status information acquisition module: used to acquire multiple abnormal status information of the device under test and the abnormal time information corresponding to each abnormal status information based on a preset sampling time period; Abnormal state information judgment module: Based on the abnormal time information, it is used to determine whether the time interval between any two abnormal state information is less than a preset association time threshold in the order of occurrence time from first to last. Target time information determination module: If the time interval between two abnormal status information is less than the associated time threshold, delete the abnormal time information that occurred later and determine the abnormal time information that occurred earlier as the target time information; Backtracking time information determination module: used to determine the backtracking time information for each target time information according to a preset backtracking time interval value, wherein the occurrence time of the backtracking time information is earlier than the occurrence time of the target time information, and the time interval between the backtracking time information and the target time information is the backtracking time interval value; Predicted abnormal pressure value information determination module: used to determine the predicted abnormal pressure value information and the predicted abnormal temperature parameter value information based on the backtracking time information; Predicted abnormal pressure mean information determination module: used to generate predicted abnormal pressure mean information based on multiple predicted abnormal pressure value information; Predicted abnormal temperature parameter mean information generation module: used to generate predicted abnormal temperature parameter mean information based on multiple predicted abnormal temperature parameter values.

[0066] Optionally, the feature parameter set information includes real-time pressure parameter information and real-time temperature parameter information, and the first evaluation result information includes first normal operation information or first predicted fault operation information; the aforementioned first evaluation result information generation module 62 includes: Pressure difference information generation submodule: used to generate pressure difference information based on real-time pressure parameter information and predicted abnormal pressure average information; Temperature difference information generation submodule: used to generate temperature difference information based on real-time temperature parameter information and predicted abnormal temperature parameter values; Pressure difference information judgment submodule: used to determine whether the pressure difference information is less than the preset pressure threshold information and whether the temperature difference information is less than the preset temperature threshold information; The first normal operation information generation submodule is used to generate first normal operation information if the pressure difference information is less than the pressure threshold information and the temperature difference information is less than the temperature threshold information; otherwise, it generates first predicted fault operation information.

[0067] Optionally, the second evaluation result information includes second normal operation information or second fault operation information, and the real-time monitoring video stream information includes multiple real-time monitoring image information; the aforementioned second evaluation result information generation module 63 includes: The submodule for determining the contour information to be detected is used to determine the contour information to be detected for each real-time monitoring image based on a preset edge contour extraction algorithm. Object type information determination submodule: Based on a preset target detection algorithm, this module determines the object type information corresponding to the outline information to be detected. The second normal operation information generation submodule is used to generate second normal operation information if the object type information is device type information, otherwise it generates second fault operation information.

[0068] Optionally, the anomaly prediction information includes information on the high degree of anomaly occurrence or information on the moderate degree of anomaly occurrence; the anomaly prediction information generation module 64 includes: Abnormal height occurrence information generation submodule: used to generate abnormal height occurrence information if the first evaluation result information is the first predicted fault operation information and the second evaluation result information is the second fault operation information; The submodule for generating information on moderate occurrence of anomalies is used to generate information on moderate occurrence of anomalies if the first evaluation result is the first predicted fault operation information or the second evaluation result is the second fault operation information.

[0069] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0070] This application also provides a terminal device, such as... Figure 7 As shown, the terminal device 70 of this embodiment includes: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71. When the processor 71 executes the computer program 73, it implements the steps in the above-described industrial equipment behavior prediction method embodiment, for example... Figure 1 Steps S100 to S400 are shown; or, when processor 71 executes computer program 73, it implements the functions of each module in the above-described device, for example... Figure 6 The functions of modules 61 to 64 are shown.

[0071] The terminal device 70 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device, and includes, but is not limited to, a processor 71 and a memory 72. Those skilled in the art will understand that... Figure 7 This is merely an example of terminal device 70 and does not constitute a limitation on terminal device 70. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device 70 may also include input / output devices, network access devices, buses, etc.

[0072] The processor 71 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0073] The memory 72 can be an internal storage unit of the terminal device 70, such as the hard disk or memory of the terminal device 70. The memory 72 can also be an external storage device of the terminal device 70, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device 70. Furthermore, the memory 72 can include both internal storage units and external storage devices of the terminal device 70. The memory 72 can also store computer program 73 and other programs and data required by the terminal device 70. The memory 72 can also be used to temporarily store data that has been output or will be output.

[0074] One embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0075] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the methods, principles and structures of this application should be covered within the scope of protection of this application.

Claims

1. A method for predicting the behavior of industrial equipment based on multi-source data fusion, characterized in that, The method includes: In response to the start command, based on preset sensors, it continuously acquires the characteristic parameter set information and real-time monitoring video stream information of the device under test; Based on the feature parameter set information and the preset prediction anomaly parameter set information, the first evaluation result information is generated; Based on a preset target detection algorithm, a second evaluation result is generated according to the real-time monitoring video stream information. Anomaly prediction information is generated based on the first evaluation result information and the second evaluation result information.

2. The method according to claim 1, characterized in that, The predicted anomaly parameter set information includes the average predicted anomaly pressure parameter information and the average predicted anomaly temperature parameter information; before generating the first evaluation result information based on the feature parameter set information and the preset predicted anomaly parameter set information, the method further includes: Based on a preset sampling time period, multiple abnormal state information of the device under test and the abnormal time information corresponding to each abnormal state information are obtained. Based on the abnormal time information, in chronological order of occurrence, it is determined whether the time interval between any two abnormal state information is less than a preset association time threshold. If the time interval between two abnormal status information is less than the associated time threshold, then the abnormal time information that occurred later is deleted, and the abnormal time information that occurred earlier is determined as the target time information. For each of the target time information, the backtracking time information is determined according to a preset backtracking time interval value, wherein the occurrence time of the backtracking time information is earlier than the occurrence time of the target time information, and the time interval between the backtracking time information and the target time information is the backtracking time interval value; Based on the backtracking time information, the predicted abnormal pressure value information and the predicted abnormal temperature parameter value information are determined; Based on the multiple predicted abnormal pressure values, generate the average predicted abnormal pressure information; Based on the multiple predicted abnormal temperature parameter values, the mean value of the predicted abnormal temperature parameters is generated.

3. The method according to claim 2, characterized in that, The feature parameter set information includes real-time pressure parameter information and real-time temperature parameter information; the first evaluation result information includes first normal operation information or first predicted fault operation information; the generation of the first evaluation result information based on the feature parameter set information and the preset predicted anomaly parameter set information includes: Based on the real-time pressure parameter information and the predicted average abnormal pressure information, pressure difference information is generated; Based on the real-time temperature parameter information and the predicted abnormal temperature parameter value information, temperature difference information is generated; Determine whether the pressure difference information is less than a preset pressure threshold information, and whether the temperature difference information is less than a preset temperature threshold information; If the pressure difference information is less than the pressure threshold information and the temperature difference information is less than the temperature threshold information, then the first normal operation information is generated; otherwise, the first predicted fault operation information is generated.

4. The method according to claim 3, characterized in that, The second evaluation result information includes second normal operation information or second fault operation information, and the real-time monitoring video stream information includes multiple real-time monitoring image information; The preset target detection algorithm generates second evaluation result information based on the real-time monitoring video stream information, including: For each of the real-time monitoring image information, the contour information to be detected is determined based on a preset edge contour extraction algorithm; Based on a preset target detection algorithm, the object type information corresponding to the contour information to be detected is determined according to the contour information to be detected. If the object type information is device type information, then the second normal operation information is generated; otherwise, the second fault operation information is generated.

5. The method according to claim 4, characterized in that, The anomaly prediction information includes information on the occurrence of a high degree of anomaly or information on the occurrence of a moderate degree of anomaly; the step of generating anomaly prediction information based on the first evaluation result information and the second evaluation result information includes: If the first evaluation result information is the first predicted fault operation information and the second evaluation result information is the second fault operation information, then abnormal height occurrence information is generated; If the first evaluation result information is the first predicted fault operation information, or the second evaluation result information is the second fault operation information, then an abnormality moderate occurrence information is generated.

6. An industrial equipment behavior prediction system based on multi-source data fusion, characterized in that, The system includes: Feature parameter set information acquisition module: In response to the start command, it continuously acquires the feature parameter set information and real-time monitoring video stream information of the device under test based on preset sensors; First evaluation result information generation module: used to generate first evaluation result information based on the feature parameter set information and the preset prediction anomaly parameter set information; The second evaluation result information generation module is used to generate second evaluation result information based on the real-time monitoring video stream information using a preset target detection algorithm. Anomaly prediction information generation module: used to generate anomaly prediction information based on the first evaluation result information and the second evaluation result information.

7. The system according to claim 6, characterized in that, The anomaly prediction information includes information on the high degree of anomaly occurrence or information on the moderate degree of anomaly occurrence; the anomaly prediction information generation module includes: Abnormal height occurrence information generation submodule: used to generate abnormal height occurrence information if the first evaluation result information is the first predicted fault operation information and the second evaluation result information is the second fault operation information; The submodule for generating information on moderate occurrence of anomalies is used to generate information on moderate occurrence of anomalies if the first evaluation result information is the first predicted fault operation information, or the second evaluation result information is the second fault operation information.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images