Industrial equipment risk analysis system and method based on data reconstruction
By analyzing the operating data of each component of industrial equipment twice, it is divided into actual risk components, predicted risk components and normal components, the problem of unavailability of equipment correlation risks in the prior art is solved, and the risk types and Accurate judgment of grades and efficiency improvement.
Patent Information
- Application Number
- CN202410413130.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-08
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-04-08
AI Technical Summary
The existing industrial equipment risk analysis system cannot effectively analyze the correlation risks and risk hazards of each component in the equipment, resulting in the inability to accurately determine the risk type and level of the equipment.
A data reconstruction industrial equipment risk analysis system is designed, including component initial analysis module, component reanalysis module and equipment analysis module. By analyzing the operating data of each component of industrial equipment, it is divided into actual risk components and predictions. Risk parts and normal parts, and comprehensive analysis is carried out according to risk type and level.
It realizes a comprehensive analysis of various components of industrial equipment, accurately judges the risk type and level, improves the efficiency of risk detection and analysis, and optimizes the detection range.
Smart Images

Figure CN118211725B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of equipment detection, and more specifically, to a data reconstructed industrial equipment risk analysis system and method. Background Art
[0002] In the field of industrial production, safe production and stable production are very important standards. In order to ensure safe production and stable production during the production process of current industrial equipment, it is necessary to use a corresponding risk analysis system to analyze in real time whether there are corresponding risks in the industrial equipment.
[0003] The current risk analysis system can only analyze whether industrial equipment has corresponding risks through corresponding data indicators. This analysis system can only analyze the risks of industrial equipment on a large scale, but cannot analyze the related risk problems and potential risks of various components in the industrial equipment, and thus cannot accurately determine the risk type of industrial equipment. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present invention aims to provide an industrial equipment risk analysis system and method with data reconstruction.
[0005] To achieve the above object, the present invention provides the following technical solutions:
[0006] A data reconstructed industrial equipment risk analysis system, comprising a component initial analysis module, a component re-analysis module, and an equipment analysis module;
[0007] The component preliminary analysis module divides each component into actual risk components, normal components and components to be analyzed according to the operation data of each component in the industrial equipment;
[0008] The component re-analysis module performs a secondary analysis on the components to be analyzed, and divides the components to be analyzed into predicted risk components and normal components;
[0009] The equipment analysis module analyzes the risk type and risk level of industrial equipment.
[0010] Furthermore, based on the operating data of each component in the industrial equipment, each component is divided into actual risk components, normal components and components to be analyzed. Specifically, when the industrial equipment starts to run, the operating data of each component in the industrial equipment is obtained based on M cycles, and a component operation log is generated in each cycle. The component operation log is used as the input data of the corresponding component operation analysis model to obtain a risk score. According to the risk score, the components are divided into actual risk components, normal components and components to be analyzed. When a component is marked as an actual risk component, a component risk record is synchronously generated.
[0011] Furthermore, the component operation log includes component operation data and component operation time. The risk score ranges from (0 to 5]. The larger the risk score value, the greater the operation risk of the component. The component risk record includes the risk score and component risk time.
[0012] Furthermore, the components to be analyzed are subjected to secondary analysis to be divided into predicted risk components and normal components. Specifically, k risk control values F obtained by continuous analysis of the components to be analyzed before the current time of the system are obtained. k , k is the sequence number of the risk control value, k=1, 2, 3…, K, sort all the risk control values in the order of the cycle, calculate the difference between the adjacent next risk control value and the previous risk control value after sorting, get the risk control change value, set the risk control change value threshold, when the risk control change value is greater than or equal to the risk control change value threshold, mark the risk control change value as a high risk control change value, sum up all the high risk control change values, get the total high risk control change value, and mark it as GBZ, get the total number of times the risk control change value is marked as a high risk control change value, and mark it as ZCS, when the risk control change value is less than the risk control change value threshold, do not do the corresponding processing, get the risk control value F of the component to be analyzed k , using the formula The risk analysis value FXF of the component to be analyzed is obtained, where b1 is the total risk control high-variable value coefficient, b2 is the risk control high-variable value times coefficient, and b3 is the total risk control value coefficient. The components to be analyzed are divided into predicted risk components and normal components according to the risk analysis value.
[0013] Furthermore, the risk control value F of the component to be analyzed k It can be obtained by: obtaining the risk score of the part to be analyzed last week and marking it as FXP, obtaining the total number of risk-related parts marked as risky parts in the last period and marking it as BJZ, obtaining the total number of risk-related parts with the part to be analyzed and marking it as HSL, and using the formula Get the risk control value F k , where a1 is the risk score coefficient, a2 is the risk component quantity coefficient, and a3 is the associated component quantity coefficient.
[0014] Furthermore, whether two components are risk-related components is obtained in the following manner: all component risk records of the two components before the current time of the system are obtained, the risk correlation between the two components is obtained by using a similarity calculation method, and a risk correlation threshold is set. When the risk correlation is greater than or equal to the risk correlation threshold, the two components are marked as risk-related components. When the risk correlation is less than the risk correlation threshold, no corresponding processing is performed.
[0015] Further, the risk type and risk level of the industrial equipment are analyzed, specifically: the number of actual risk components in the industrial equipment is summed with the number of predicted risk components to obtain the total number of risk components;
[0016] When the total number of risk components is 0, no corresponding processing is performed;
[0017] When the total number of risk components is 1, the independent risk level of the industrial equipment is determined based on the risk scores of the actual risk components;
[0018] When the total number of risk components is greater than 1, obtain the component risk value BJ of each actual risk component in the industrial equipment i , obtain the total number of times each actual risk component was marked as an actual risk component before the current system, and mark it as CS, using the formula The linkage risk value Sz of the industrial equipment is obtained, and the linkage risk level of the industrial equipment is determined according to the linkage risk value.
[0019] Furthermore, the component risk value of the actual risk component is obtained by: obtaining the risk score of the actual risk component and marking it as SJP, obtaining the total number of risk-related components with the actual risk component marked as predicted risk components and marking it as HWZ, and using the formula Get the component risk value BJ of the actual risk component i , i is the number of the actual risk component, i=1, 2, 3…, n, where c1 is the coefficient of the number of risk-related components.
[0020] Furthermore, a data reconstruction industrial equipment risk analysis method includes the following steps:
[0021] Step 1: According to the operation data of each component in the industrial equipment, the components are divided into actual risk components, normal components and components to be analyzed;
[0022] Step 2: Perform secondary analysis on the parts to be analyzed and divide them into predicted risk parts and normal parts;
[0023] Step 3: Based on the actual risk components in the industrial equipment and the predicted number of risk components, determine whether the risk type of the industrial equipment is an independent risk type or a linkage risk type, and analyze the risk level of the industrial equipment based on the risk type.
[0024] Compared with the prior art, the present invention has the following beneficial effects:
[0025] 1. The method of the present invention can conduct a comprehensive analysis of each component in the industrial equipment, and accurately determine the risk level of the industrial equipment according to the risk type of the industrial equipment. According to the risk type and risk level of the industrial equipment, the detection and analysis scope of the industrial equipment risk can be gradually optimized;
[0026] 2. Through the component initial analysis module and the component re-analysis module, the actual risk components and predicted risk components in the industrial equipment are obtained through two independent analyses, and the operating risks of each component in the industrial equipment are comprehensively analyzed. Through the equipment analysis module, the risk type of industrial equipment can be intelligently judged according to the number of actual risk components and predicted risk components. On the basis of ensuring accurate analysis of industrial equipment risks, the efficiency of risk analysis of industrial equipment is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 A flowchart of a data reconstruction industrial equipment risk analysis method;
[0028] Figure 2 It is a principle block diagram of the component preliminary analysis module of the present invention;
[0029] Figure 3 It is a principle block diagram of the component reanalysis module of the present invention. DETAILED DESCRIPTION
[0030] Example 1
[0031] Reference Figures 2 to 3 , a data reconstructed industrial equipment risk analysis system, including a component initial analysis module, a component re-analysis module, and an equipment analysis module.
[0032] First of all, industrial equipment can be roughly divided into the following categories: processing and manufacturing equipment (including but not limited to lathes, milling machines, grinders, planers and other machines), production equipment (including but not limited to machine tools, injection molding machines, extruders and other machines), transportation equipment (including but not limited to cranes, forklifts, conveyor belts, automated conveyor lines, lifts, electric transport vehicles and other machines), safety equipment (including but not limited to safety doors, safety sensors, explosion-proof equipment, fire-fighting equipment, safety signs and other machines), water treatment equipment (including but not limited to sewage treatment equipment, reverse osmosis equipment and coagulation and sedimentation equipment and other machines), electronic equipment (including but not limited to printed circuit board production lines, surface mounting equipment and electronic packaging equipment and other machines), automotive parts processing equipment (including but not limited to turning equipment, stamping equipment and laser welding equipment and other machines), plastic product processing equipment (including but not limited to injection molding equipment, extruders and blow molding machines and other equipment).
[0033] Each piece of industrial equipment consists of multiple components, which work together to meet the working requirements of the industrial equipment.
[0034] The component preliminary analysis module divides each component into actual risk components, normal components and components to be analyzed according to the operating data of each component in the industrial equipment. Specifically:
[0035] When the industrial equipment starts to operate, the operating data of each component in the industrial equipment is obtained based on the M cycle, and a component operation log is generated in each cycle. The component operation log includes but is not limited to the component operation data and the component operation time.
[0036] Taking the injection molding machine as an example, the injection molding machine includes but is not limited to components such as the mold opening motor, injection molding motor, and ejector motor. When the injection molding machine starts running, the operating data of the mold opening motor, injection molding motor, and ejector motor in the injection molding machine are obtained based on the M cycle (the operating data of the motor includes but is not limited to motor power, motor temperature, and motor speed). Each cycle generates a mold opening motor operation log, an injection molding motor operation log, and an ejector motor operation log. The unit of the component operation time of the mold opening motor operation log, the injection molding motor operation log, and the ejector motor operation log is min.
[0037] Generate an operation analysis model for the corresponding component. The operation analysis model for the corresponding component is obtained in the following way: obtain multiple component operation logs of the component (the component operation logs can be obtained through experiments or in the actual production process), use the component operation logs as training data for the neural network model, assign risk scores to the training data, and iteratively train the training data through the training set and the validation set to obtain the operation analysis model. The larger the risk score value, the greater the operation risk of the component.
[0038] Taking the mold opening motor in the injection molding machine as an example, the operation analysis model of the mold opening motor is obtained in the following way: obtain multiple mold opening motor operation logs, use the mold opening motor operation logs as training data for the neural network model, assign risk scores to the training data, and iteratively train the training data through training sets and validation sets to obtain the operation analysis model of the mold opening motor.
[0039] The component operation log is used as the input data of the corresponding component operation analysis model to obtain the risk score. The value range of the risk score is (0~5]. A high risk score and a low risk score are set, where the high risk score is greater than the low risk score. When the risk score is greater than or equal to the high risk score, the component is marked as an actual risk component and a component risk record is generated at this moment. The component risk record includes the risk score and the component risk moment (that is, the time when the component is marked as an actual risk component). When the risk score is less than or equal to the high risk score, the component is marked as a normal component. When the risk score is between the high risk score and the low risk score, the component is marked as a component to be analyzed.
[0040] The component re-analysis module performs secondary analysis on the components to be analyzed and divides the components to be analyzed into predicted risk components and normal components. Specifically:
[0041] Obtain the risk analysis value of the component to be analyzed. The risk analysis value of the component to be analyzed is obtained by the following steps: Obtain k risk control values F obtained by continuous analysis of the component to be analyzed before the current time of the system k , k is the sequence number of the risk control value, k=1, 2, 3…, K, sort all the risk control values in the order of the cycle, calculate the difference between the next adjacent risk control value after sorting and the previous risk control value, get the risk control change value, set the risk control change value threshold, when the risk control change value is greater than or equal to the risk control change value threshold, mark the risk control change value as a high risk control change value, sum up all the high risk control change values, get the total high risk control change value, and mark it as GBZ, get the total number of times the risk control change value is marked as a high risk control change value, and mark it as ZCS, when the risk control change value is less than the risk control change value threshold, do not do the corresponding processing, and get the risk control value F of the component to be analyzed k, Using the formula The risk analysis value FXF of the component to be analyzed is obtained, where b1 is the total risk control high variable value coefficient, b2 is the risk control high variable value times coefficient, b3 is the total risk control value coefficient, the value of b1 is 0.98, the value of b2 is 0.96, and the value of b3 is 0.83. A risk analysis threshold is set. When the risk analysis value is greater than or equal to the risk analysis threshold, the component to be analyzed is marked as a predicted risk component. When the risk analysis value is less than the risk analysis threshold, the component to be analyzed is marked as a normal component.
[0042] Risk control value F k It can be obtained by: obtaining the risk score of the part to be analyzed last week and marking it as FXP, obtaining the total number of risk-related parts marked as risky parts in the last period and marking it as BJZ, obtaining the total number of risk-related parts with the part to be analyzed and marking it as HSL, and using the formula Get the risk control value F k , where a1 is the risk score coefficient, a2 is the risk component quantity coefficient, and a3 is the associated component quantity coefficient. The value of a1 is 0.57, the value of a2 is 0.16, and the value of a3 is 0.42.
[0043] Whether two components are risk-related components is obtained in the following way:
[0044] The risk correlation between every two components in the industrial equipment is calculated. The risk correlation between every two components in the industrial equipment is obtained by the following steps: mark the two components as component A and component B respectively, obtain all component risk records of component A and component B before the current time of the system, and obtain the risk correlation between component A and component B by using the similarity calculation method.
[0045] For example: Based on the component risk records of component A and component B, the risk frequency (the risk moment can be calculated based on the component risk moment in the component risk record), risk intensity (derived from the risk score), and risk frequency (derived from the number of component risk records) of component A can be analyzed respectively. The cosine similarity calculation formula can be used to obtain the similarity between component A and component B in risk frequency, risk intensity, and risk frequency, and the calculated similarity is marked as risk correlation.
[0046] Set a risk correlation threshold. When the risk correlation is greater than or equal to the risk correlation threshold, the two components are marked as risk-related components. When the risk correlation is less than the risk correlation threshold, no corresponding processing is performed.
[0047] A component initial analysis module and a component re-analysis module are set up to obtain the actual risk components and predicted risk components in the industrial equipment through two independent analyses, and comprehensively analyze the operation risk of each component in the industrial equipment.
[0048] The equipment analysis module analyzes the risk type and risk level of industrial equipment, specifically:
[0049] The number of actual risk components in the industrial equipment and the number of predicted risk components are summed to obtain the total number of risk components.
[0050] When the total number of risk components is 0, no corresponding processing is performed.
[0051] When the total number of risk components is 1, the independent risk level of the industrial equipment is determined according to the risk scores of the actual risk components.
[0052] The risk score of the actual risk component is marked as Ls, and the range of each risk score Ls is set to correspond to an independent risk level, where the range of the risk score Ls includes (0, L1], (L1, L2], …, (Ls-1, Ls], and the independent risk levels include independent risk level 1, independent risk level 2, …, independent risk level s-1, and independent risk level s. When Ls∈(0, L1], it means that the industrial equipment is at independent risk level 1, where the higher the independent risk level 1, the higher the operating risk of the component of the industrial equipment.
[0053] When the total number of risk components is greater than 1, obtain the component risk value BJ of each actual risk component in the industrial equipment i The component risk value of the actual risk component is obtained by: obtaining the risk score of the actual risk component and marking it as SJP, obtaining the total number of risk-related components with the actual risk component marked as predicted risk components and marking it as HWZ, and using the formula Get the component risk value BJ of the actual risk component i , i is the number of the actual risk component, i=1, 2, 3…, n, where c1 is the coefficient of the number of risk-related components.
[0054] Get the total number of times each actual risk component was marked as an actual risk component before the system is currently marked, and mark it as CS, using the formula The linkage risk value Sz of the industrial equipment is obtained, and the linkage risk level of the industrial equipment is determined according to the linkage risk value.
[0055] The range of each equipment risk value Sz is set to correspond to a linkage risk level, where the range of the equipment risk value Sz includes (0, S1], (S1, S2], …, (Sz-1, Sz], and the linkage risk levels include linkage risk level 1, linkage risk level 2, …, linkage risk level z-1, linkage risk level z. When Sz∈(0, S1], it means that the industrial equipment is at linkage risk level 1, where the higher the linkage risk level, the higher the linkage risk of each component of the industrial equipment during operation.
[0056] Through the equipment analysis module, the risk type of industrial equipment can be intelligently determined based on the actual risk components and the predicted risk components.
[0057] Example 2
[0058] Reference Figure 1 , a data reconstruction industrial equipment risk analysis method, comprising the following steps:
[0059] Step 1: Based on the operating data of each component in the industrial equipment, classify each component into actual risk components, normal components, and components to be analyzed.
[0060] Step 2: Perform secondary analysis on the parts to be analyzed and divide them into predicted risk parts and normal parts.
[0061] Through steps one and two, a comprehensive analysis can be conducted on each component in the industrial equipment. Through two independent analyses, the actual risk components and predicted risk components in the industrial equipment can be obtained, which facilitates the subsequent intelligent analysis of the operating risks of the industrial equipment.
[0062] Step 3: Based on the actual risk components in the industrial equipment and the predicted number of risk components, determine whether the risk type of the industrial equipment is an independent risk type or a linkage risk type, and analyze the risk level of the industrial equipment based on the risk type.
[0063] Through step three, the risk type of industrial equipment can be intelligently determined based on the actual risk components and the predicted number of risk components, and the risk level of the industrial equipment can be accurately determined based on the risk type of the industrial equipment. The detection and analysis scope of industrial equipment risks can be gradually optimized based on the risk type and risk level of the industrial equipment.
[0064] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0065] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0066] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean 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 the present application.
[0067] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0069] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0070] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.
[0071] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A data reconstruction industrial equipment risk analysis system, characterized in that: It includes component initial analysis module, component re-analysis module and equipment analysis module; The component preliminary analysis module divides each component into actual risk components, normal components and components to be analyzed according to the operation data of each component in the industrial equipment; The component re-analysis module performs a secondary analysis on the components to be analyzed, and divides the components to be analyzed into predicted risk components and normal components; The equipment analysis module analyzes the risk type and risk level of industrial equipment; Perform secondary analysis on the components to be analyzed and divide them into predicted risk components and normal components. Specifically, obtain the k risk control values F obtained by continuous analysis of the components to be analyzed before the current time of the system. k , k is the sequence number of the risk control value, k = 1, 2, 3..., K, all risk control values are sorted in periodic order, the difference between the adjacent next risk control value and the previous risk control value after sorting is calculated to obtain the risk control change value, and the risk control change value threshold is set. When the risk control change value is greater than or equal to the risk control change value threshold, the risk control change value is marked as a high risk control change value, and all the high risk control change values are summed to obtain the total high risk control change value, and marked as GBZ, and the total number of times the risk control change value is marked as a high risk control change value is obtained, and marked as ZCS. When the risk control change value is less than the risk control change value threshold, no corresponding processing is performed, and the risk control value F of the component to be analyzed is obtained. k , using the formula The risk analysis value FXF of the component to be analyzed is obtained, where b1 is the total risk control high-variable value coefficient, b2 is the risk control high-variable value times coefficient, and b3 is the total risk control value coefficient. The component to be analyzed is divided into predicted risk components and normal components according to the risk analysis value; The risk control value F of the component to be analyzed k It can be obtained by: obtaining the risk score of the part to be analyzed last week and marking it as FXP, obtaining the total number of risk-related parts marked as risky parts in the last period and marking it as BJZ, obtaining the total number of risk-related parts with the part to be analyzed and marking it as HSL, and using the formula Get the risk control value F k , where a1 is the risk score coefficient, a2 is the risk component quantity coefficient, and a3 is the associated component quantity coefficient; Whether two components are risk-associated components is obtained in the following manner: all component risk records of the two components before the current time of the system are obtained, the risk correlation between the two components is obtained by similarity calculation, and a risk correlation threshold is set. When the risk correlation is greater than or equal to the risk correlation threshold, the two components are marked as risk-associated components. When the risk correlation is less than the risk correlation threshold, no corresponding processing is performed. Analyze the risk type and risk level of industrial equipment, specifically: sum the number of actual risk components in the industrial equipment and the number of predicted risk components to obtain the total number of risk components; When the total number of risk components is 0, no corresponding processing is performed; When the total number of risk components is 1, the independent risk level of the industrial equipment is determined based on the risk scores of the actual risk components; When the total number of risk components is greater than 1, obtain the component risk value BJ of each actual risk component in the industrial equipment i , obtain the total number of times each actual risk component was marked as an actual risk component before the current system, and mark it as CS, using the formula The linkage risk value Sz of the industrial equipment is obtained, where i is the number of the actual risk component, i=1, 2, 3..., n, and the linkage risk level of the industrial equipment is determined according to the linkage risk value.
2. The data reconstruction industrial equipment risk analysis system according to claim 1 is characterized in that: According to the operation data of each component in the industrial equipment, each component is divided into actual risk components, normal components and components to be analyzed. Specifically, when the industrial equipment starts to run, the operation data of each component in the industrial equipment is obtained based on the M cycle, and a component operation log is generated in each cycle. The component operation log is used as the input data of the corresponding component operation analysis model to obtain a risk score. According to the risk score, the components are divided into actual risk components, normal components and components to be analyzed. When a component is marked as an actual risk component, a component risk record is generated.
3. The data reconstruction industrial equipment risk analysis system according to claim 2 is characterized in that: The component operation log includes component operation data and component operation time. The risk score ranges from (0 to 5]. The larger the risk score value, the greater the operation risk of the component. The component risk record includes the risk score and component risk time.
4. The data reconstruction industrial equipment risk analysis system according to claim 1, characterized in that: The component risk value of the actual risk component is obtained by: obtaining the risk score of the actual risk component and marking it as SJP, obtaining the total number of risk-related components with the actual risk component marked as predicted risk components and marking it as HWZ, and using the formula BJ i =SJP×HWZ×c1 to obtain the component risk value BJ of the actual risk component i , i is the number of the actual risk component, i = 1, 2, 3..., n, where c1 is the coefficient of the number of risk-related components.
5. A data reconstructed industrial equipment risk analysis method, applied to a data reconstructed industrial equipment risk analysis system according to claim 1, characterized in that: The steps include: Step 1: According to the operation data of each component in the industrial equipment, the components are divided into actual risk components, normal components and components to be analyzed; Step 2: Perform secondary analysis on the parts to be analyzed and divide them into predicted risk parts and normal parts; Step 3: Based on the actual risk components in the industrial equipment and the predicted number of risk components, determine whether the risk type of the industrial equipment is an independent risk type or a linkage risk type, and analyze the risk level of the industrial equipment based on the risk type.
Citation Information
Patent Citations
Device for online monitoring and fault diagnosis of spring of vibrating screen for mining and method thereof
CN102494882A
Secondary equipment overhaul and technical innovation decision determination method and system
CN106779280A
Risk assessment method, system and device and storage medium
CN109740865A
Coal-fired boiler heating surface depth fault early warning system based on industrial internet
CN113837539A
Risk control method
CN114757757A
