Industrial data intelligent management method and system

Abstract

The invention relates to an industrial data intelligent management method and system, and relates to the field of industrial data processing, and the method comprises the steps: obtaining the total number of machining times and the number of abnormal machining times of each piece of workshop equipment in a preset historical time period, and determining a key operation part of any piece of workshop equipment, obtaining a processing video of each key operation part and sensor data corresponding to each key operation part when any workshop equipment is processed abnormally every time, determining a first abnormal degree of any workshop equipment based on the processing video and the sensor data, and obtaining an image of a finished product produced by any workshop equipment when the workshop equipment is processed abnormally every time; and determining a second abnormal degree of any workshop equipment based on the image, and determining an operation abnormal level of any workshop equipment based on the first abnormal degree and the second abnormal degree. According to the method and the device, more accurate abnormity judgment can be conveniently carried out on highly integrated processing equipment with a plurality of running parts with different functions.

Description

Technical Field

[0001] The present application relates to the field of industrial data processing, and in particular to an industrial data intelligent management method and system. Background Art

[0002] With the development of industrial technology, mechanical technology, etc., the degree of automation of processing equipment in industrial production is getting higher and higher, and the integration of processing equipment is also getting higher and higher. Today's processing equipment can usually realize multiple functions, such as material grabbing, transportation and processing at the same time. For example, a lathe with integrated robotic arm function can grab materials through the robotic arm, and the components on the robotic arm and the lathe that control the movement of props can operate simultaneously to carry out processing and production. These functions cooperate with processing at the same time to improve production efficiency.

[0003] At present, the way to judge whether there is an abnormality in the processing equipment in the workshop is to judge whether there is an abnormality in the operating state of the processing equipment based on the yield rate of the finished products processed by each processing equipment, or to install sensors on the processing equipment and judge whether there is an abnormality in the processing equipment based on the data of the sensors on the processing equipment. However, for processing equipment with high integration, these equipments integrate operating components that realize different functions. It is inconvenient and inaccurate to judge the degree of abnormality of the entire processing equipment based on multiple operating components with different functions. Therefore, how to accurately judge the abnormality of processing equipment with multiple operating components with different functions becomes a problem. Summary of the invention

[0004] In order to facilitate more accurate abnormality judgment of highly integrated processing equipment with multiple operating components with different functions, the present application provides an industrial data intelligent management method and system.

[0005] In the first aspect, the present application provides an industrial data intelligent management method, which adopts the following technical solution: An industrial data intelligent management method, comprising: Obtain the total number of processing times and number of processing exceptions for each workshop equipment within the preset historical time period; Determine the key operating components of any workshop equipment, and obtain the processing video of each key operating component and the sensor data corresponding to each key operating component each time a processing abnormality occurs in any workshop equipment; Determining a first abnormality level of any of the workshop equipment based on the processing video and the sensor data; Acquire images of finished products produced by any of the workshop equipment at each time of abnormal processing; determining a second abnormality level of any one of the workshop equipment based on the image; The abnormality level of operation of any one of the workshop equipment is determined based on the total number of processing times, the number of processing abnormalities, the first abnormality level, and the second abnormality level.

[0006] By adopting the above technical solution, the total number of processing times and the number of processing abnormalities of the workshop equipment within a preset historical time period are obtained, which is convenient for subsequent analysis of the proportion of abnormal finished products processed, and all key operating components are determined for any workshop equipment. The key operating components cooperate with each other to achieve the effect of simultaneous processing and production, and the processing video and sensor data of each key operating component are obtained at each processing abnormality. The sensor data represents the movement amount collected by the sensor for each key operating component, and the processing video records the specific conditions of the processing and operation of the key operating components at each processing abnormality. Therefore, the first abnormality degree can be accurately determined based on the processing video and the sensor data, and the image of the finished product produced by the workshop equipment at each processing abnormality is obtained. The image records the specific conditions of the finished product, so that it is convenient to determine the second abnormality degree of the workshop equipment based on the image, that is, the abnormality degree of the workshop equipment is characterized by the abnormality degree of the finished product, and it is more accurate and convenient to determine the overall operation abnormality level of the workshop equipment with a high degree of integration and operating components with multiple different functions by combining the total number of processing times, the number of processing abnormalities, the first abnormality degree represented by the key operating components, and the second abnormality degree represented by the finished product.

[0007] In another possible implementation, determining the first abnormality level of any workshop equipment based on the processing video and the sensor data includes: Performing feature recognition on the processing video to obtain feature points of each key operating component; Connecting feature points of each key operating component, and tracking the feature points based on the processed video to obtain a motion trajectory of the connection; Calculate the first similarity between the motion trajectory of each key operating component and the corresponding standard trajectory at each abnormal processing; determining a baseline component and a reference component from all key operating components based on the first similarity and the sensor data; Map the motion trajectories of all key operating components at each moment into the same coordinate system, and determine the distance and angle between each reference component and the reference component; determining a characteristic value of each reference component based on the angle, distance, and sensor data; Determine the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment; The first abnormality degree is determined based on the sub-abnormality degrees.

[0008] In another possible implementation, determining a benchmark component and a reference component from all key operating components based on the first similarity and the sensor data includes: Determining a first similarity average value based on the first similarity of each key operating component when all processing anomalies occur; Inversely infer the type of data collected by the corresponding sensor based on the action trajectory; Determining whether there is inconsistent data based on the inferred data and the sensor data; If so, determine the amount of inconsistent data and the amount of data deviation; Determining a trust value of the sensor based on the data amount and the data deviation amount; Determine the operation status value of each key operation component based on the trust value and the first similarity average value; The key operating component with the highest operating condition value is determined as a benchmark component, and the key operating components other than the benchmark component are determined as reference components.

[0009] In another possible implementation, determining the characteristic value of each reference component based on the angle, distance and sensor data; and determining the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment include: Determine a first difference between the angle and a standard angle at the time, and a second difference between the distance and a standard distance at the time; Determine the sensor data and the inverse data at each moment, and calculate the third difference between the inverse data and the sensor data at each moment; Calculate the product of the first difference and the second difference, and determine a first ratio of the product to the third difference as a characteristic value of each reference component at each time; Based on the characteristic value at each moment, the average value and variance of the characteristic values ​​at all moments of each processing abnormality are determined; A score representing the degree of the sub-abnormality is determined based on the eigenvalue mean value, the variance and the corresponding coefficients.

[0010] In another possible implementation, determining the second abnormality level of any workshop equipment based on the image includes: Calculating a second similarity between the image and a standard image of a standard finished product produced by any of the workshop equipment; Comparing the image with the standard image to determine inconsistent image regions; Determine a finished product abnormality value each time a processing abnormality occurs based on the second similarity and the number of image regions; The second abnormality degree is obtained by averaging the abnormal values ​​of finished products during all processing abnormalities.

[0011] In another possible implementation, determining the abnormality level of any workshop equipment operation based on the total number of processing times, the number of abnormal processing times, the first abnormality degree, and the second abnormality degree includes: Determining a second ratio of the number of processing abnormalities to the total number of processing times; Determine an overall abnormality score based on the first ratio, the first abnormality degree, the second abnormality degree, and respective corresponding coefficients; Determine a target preset score interval where the overall abnormality score is located from a plurality of preset score intervals, each preset score interval corresponding to a preset abnormality level; The preset abnormality level of the target preset score interval is determined as the abnormality level of any workshop equipment.

[0012] In another possible implementation, the method further includes: The equipment information of the workshop equipment whose abnormality level reaches the preset abnormality level threshold is sent to the terminal device of the manager.

[0013] In the second aspect, the present application provides an industrial data intelligent management system, which adopts the following technical solutions: An industrial data intelligent management system, comprising: The first acquisition module is used to obtain the total number of processing times and the number of abnormal processing times of each workshop equipment in a preset historical time period; The second acquisition module is used to determine the key operating components of any workshop equipment, and obtain the processing video of each key operating component and the sensor data corresponding to each key operating component each time the processing of any workshop equipment is abnormal; A first determination module, configured to determine a first abnormality level of any of the workshop equipment based on the processing video and the sensor data; A third acquisition module is used to acquire an image of a finished product produced by any of the workshop equipment each time a processing abnormality occurs; A second determination module, configured to determine a second abnormality level of any one of the workshop equipment based on the image; The third determination module is used to determine the abnormality level of operation of any workshop equipment based on the total number of processing times, the number of processing abnormalities, the first abnormality degree and the second abnormality degree.

[0014] By adopting the above technical solution, the first acquisition module obtains the total number of processing times and the number of processing abnormalities of the workshop equipment within a preset historical time period, which is convenient for subsequent analysis of the proportion of abnormal finished products processed. The second acquisition module determines all the key operating components for any workshop equipment. The key operating components cooperate with each other to achieve the effect of simultaneous processing and production. The processing video and sensor data of each key operating component are obtained at each processing abnormality. The sensor data represents the amount of movement of each key operating component collected by the sensor. The processing video records the specific situation of the processing and operation of the key operating component at each processing abnormality. Therefore, the first determination module can accurately determine the first abnormality degree according to the processing video and sensor data. The third acquisition module obtains the image of the finished product produced by the workshop equipment at each processing abnormality. The image records the specific situation of the finished product, so that the second determination module can determine the second abnormality degree of the workshop equipment according to the image, that is, the abnormality degree of the workshop equipment is represented by the abnormality degree of the finished product. The third determination module combines the total processing times, the number of processing abnormalities, the first abnormality degree represented by the key operating components, and the second abnormality degree represented by the finished product to determine the overall operation abnormality level of the workshop equipment with a high degree of integration and multiple operating components with different functions more accurately and conveniently.

[0015] In another possible implementation, when the first determination module determines the first abnormality level of any workshop equipment based on the processing video and the sensor data, it is specifically used to: Performing feature recognition on the processing video to obtain feature points of each key operating component; Connecting feature points of each key operating component, and tracking the feature points based on the processed video to obtain a motion trajectory of the connection; Calculate the first similarity between the motion trajectory of each key operating component and the corresponding standard trajectory at each abnormal processing; determining a baseline component and a reference component from all key operating components based on the first similarity and the sensor data; Map the motion trajectories of all key operating components at each moment into the same coordinate system, and determine the distance and angle between each reference component and the reference component; determining a characteristic value of each reference component based on the angle, distance, and sensor data; Determine the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment; The first abnormality degree is determined based on the sub-abnormality degrees.

[0016] In another possible implementation manner, when the first determination module determines the benchmark component and the reference component from all the key operating components based on the first similarity and the sensor data, it is specifically configured to: Determining a first similarity average value based on the first similarity of each key operating component when all processing anomalies occur; Inversely infer the type of data collected by the corresponding sensor based on the action trajectory; Determining whether there is inconsistent data based on the inferred data and the sensor data; If so, determine the amount of inconsistent data and the amount of data deviation; Determining a trust value of the sensor based on the data amount and the data deviation amount; Determine the operation status value of each key operation component based on the trust value and the first similarity average value; The key operating component with the highest operating condition value is determined as a benchmark component, and the key operating components other than the benchmark component are determined as reference components.

[0017] In another possible implementation, when the first determination module determines the characteristic value of each reference component based on the angle, distance, and sensor data; and determines the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment, it is specifically used to: Determine a first difference between the angle and a standard angle at the time, and a second difference between the distance and a standard distance at the time; Determine the sensor data and the inverse data at each moment, and calculate the third difference between the inverse data and the sensor data at each moment; Calculate the product of the first difference and the second difference, and determine a first ratio of the product to the third difference as a characteristic value of each reference component at each time; Based on the characteristic value at each moment, the average value and variance of the characteristic values ​​at all moments of each processing abnormality are determined; A score representing the degree of the sub-abnormality is determined based on the eigenvalue mean value, the variance and the corresponding coefficients.

[0018] In another possible implementation, when the second determination module determines the second abnormality degree of any workshop equipment based on the image, it is specifically configured to: Calculating a second similarity between the image and a standard image of a standard finished product produced by any of the workshop equipment; Comparing the image with the standard image to determine inconsistent image regions; Determine a finished product abnormality value each time a processing abnormality occurs based on the second similarity and the number of image regions; The second abnormality degree is obtained by averaging the abnormal values ​​of finished products during all processing abnormalities.

[0019] In another possible implementation, when the third determination module determines the abnormality level of operation of any workshop equipment based on the total number of processing times, the number of abnormal processing times, the first abnormality degree, and the second abnormality degree, it is specifically used to: Determining a second ratio of the number of processing abnormalities to the total number of processing times; Determine an overall abnormality score based on the first ratio, the first abnormality degree, the second abnormality degree, and respective corresponding coefficients; Determine a target preset score interval where the overall abnormality score is located from a plurality of preset score intervals, each preset score interval corresponding to a preset abnormality level; The preset abnormality level of the target preset score interval is determined as the abnormality level of any workshop equipment.

[0020] In another possible implementation, the system further includes: The sending module is used to send the equipment information of the workshop equipment whose abnormality level reaches the preset abnormality level threshold to the terminal device of the manager.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute an industrial data intelligent management method shown in any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute an industrial data intelligent management method as described in any one of the first aspects.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: The total number of processing times and the number of processing abnormalities of the workshop equipment within a preset historical time period are obtained to facilitate the subsequent analysis of the proportion of abnormal finished products processed. All key operating components are determined for any workshop equipment. The key operating components cooperate with each other to achieve the effect of simultaneous processing and production. The processing video and sensor data of each key operating component are obtained at each processing abnormality. The sensor data characterizes the amount of movement of each key operating component collected by the sensor. The processing video records the specific conditions of the processing and operation of the key operating components at each processing abnormality. Therefore, the first abnormality degree can be accurately determined based on the processing video and sensor data. The image of the finished product produced by the workshop equipment at each processing abnormality is obtained. The image records the specific conditions of the finished product, so that it is convenient to determine the second abnormality degree of the workshop equipment based on the image, that is, the abnormality degree of the workshop equipment is characterized by the abnormality degree of the finished product. It is more accurate and convenient to determine the overall operation abnormality level of the workshop equipment with a high degree of integration and operating components with multiple different functions by combining the total number of processing times, the number of processing abnormalities, the first abnormality degree characterized by the key operating components, and the second abnormality degree characterized by the finished product. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of an industrial data intelligent management method according to an embodiment of the present application.

[0025] Figure 2 It is a structural diagram of an industrial data intelligent management system according to an embodiment of the present application.

[0026] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] The present application is further described in detail below in conjunction with the accompanying drawings.

[0028] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0031] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0032] The embodiment of the present application provides an industrial data intelligent management method, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104, step S105 and step S106, wherein: S101, obtaining the total number of processing times and the number of processing exceptions of each workshop equipment in a preset historical time period.

[0033] For the embodiments of the present application, industrial production is carried out in the industry, and multiple workshop equipment is usually set up in the workshop to process and produce materials in different links. The number of processing times of each workshop equipment is usually counted by proximity switches, infrared sensors, etc. The number of times the processing is completed, these sensors are connected to the electronic equipment through wires, so that the electronic equipment can obtain the total number of processing times of each workshop equipment in the preset historical time period. When a processing anomaly occurs, the processing anomaly is usually marked by the staff and stored in the electronic equipment. The electronic equipment can determine the number of processing anomalies by accumulating and summing the number of processing anomalies of each workshop equipment. The preset historical time period can be the past week, the past half month, etc., and is usually set by the staff through a visual operation interface.

[0034] S102, determining the key operating components of any workshop equipment, and obtaining the processing video of each key operating component and the sensor data corresponding to each key operating component each time a processing abnormality occurs in any workshop equipment.

[0035] For the embodiment of the present application, the key operating components on each workshop equipment are different, for example, the key operating components of the stamping machine are the stamping rod, the push plate for pushing the stamped finished product out of the stamping table, etc. The key operating components of the mechanical wall or manipulator are the joints and the connecting walls of each section, etc. For highly integrated workshop equipment, such as a lathe with an integrated mechanical arm, the material is clamped by the mechanical arm, and the mechanical arm and the lathe cutter head move simultaneously to process the material, so the mechanical arm and the components that control the movement of the cutter head are all key operating components. The key operating components corresponding to each workshop equipment are different, and the staff stores the key operating components corresponding to each workshop equipment in the electronic device. Each key operating component corresponds to a sensor for collecting data, such as an angle sensor for collecting the rotation angle of the mechanical arm joint, a distance sensor for collecting the stroke of the stamping rod, etc. These sensors are connected to the electronic device through wires, so that the electronic device obtains the sensor data of the key operating component when the processing is abnormal. A camera device is installed on or around each key operating component to collect the processing video of the key operating component during the processing process. The camera device is connected to the electronic device through a wire, so that the electronic device obtains the processing video of the key operating component when the processing is abnormal.

[0036] S103: Determine a first abnormality level of any workshop equipment based on the processing video and sensor data.

[0037] For the embodiment of the present application, since the processing video records the specific working conditions of the key operating components when the processing abnormality occurs, and the sensor data records the movement amplitude of the key operating components when the processing abnormality occurs, the electronic device can accurately determine the first abnormality degree of any workshop equipment when the processing abnormality occurs based on the processing video and the sensor data. The electronic device determines the first abnormality degree of each workshop equipment through the processing video and the sensor data.

[0038] S104, acquiring images of finished products produced by any workshop equipment each time a processing abnormality occurs.

[0039] For the embodiment of the present application, after the workshop equipment completes the processing of the finished product, another camera device collects the image of the finished product, so as to facilitate the subsequent analysis of the abnormal processing of the finished product. The electronic device is connected to the camera device through a wire to obtain the image of the finished product at each abnormal processing.

[0040] S105, determining a second abnormality degree of any workshop equipment based on the image.

[0041] For the embodiment of the present application, the electronic device can determine the second abnormality degree of the workshop equipment based on the image of the finished product when the processing is abnormal, that is, the second abnormality degree of the workshop equipment is characterized by the abnormal condition of the finished product.

[0042] S106, determining the abnormality level of any workshop equipment operation based on the total number of processing times, the number of processing abnormalities, the first abnormality level, and the second abnormality level.

[0043] For the embodiment of the present application, the total number of processing times and the number of processing abnormalities are key factors in characterizing the degree of abnormality of the workshop equipment between the number of production times of the workshop equipment operation. The higher the proportion of processing abnormalities, the higher the degree of abnormality of the workshop equipment. The first degree of abnormality is the degree of abnormality characterized by the key operating components of the workshop equipment itself, and the second degree of abnormality is the degree of abnormality of the workshop equipment processing characterized by the finished product. Therefore, the electronic device combines the first degree of abnormality and the second degree of abnormality to comprehensively determine the operation abnormality level of any workshop equipment more accurately, that is, there are multiple components with different operating functions and the operation abnormality level of highly integrated workshop equipment is more accurate. The electronic device determines the operation abnormality level of each workshop equipment through the above-disclosed method.

[0044] In a possible implementation of the embodiment of the present application, in step S103, determining the first abnormality degree of any workshop equipment based on the processing video and the sensor data specifically includes step S1031 (not shown in the figure), step S1032 (not shown in the figure), step S1033 (not shown in the figure), step S1034 (not shown in the figure), step S1035 (not shown in the figure), step S1036 (not shown in the figure), step S1037 (not shown in the figure) and step S1038 (not shown in the figure), wherein: S1031, perform feature recognition on the processing video to obtain feature points of each key operating component.

[0045] For the embodiment of the present application, the electronic device inputs the processed video into the trained network model for feature recognition to obtain the feature points of each key operating component. The staff can spray or affix easily recognizable marks on the key points (i.e., feature points) of the key operating components, and then the feature points can be easily identified through the network model. The network model can be a convolutional neural network model or a recurrent neural network model.

[0046] S1032, connecting the feature points of each key operating component, and tracking the feature points based on the processed video to obtain the motion trajectory of the connection.

[0047] For the embodiment of the present application, after the electronic device determines the feature points of the key operating components, it connects the feature points and uses the lines to represent the processing actions of the key operating components. The feature points and the lines are then mapped in the processing video and the feature points of each frame are tracked to finally obtain the motion trajectory of the lines. The motion trajectory can represent the processing action of the key operating components when the processing is abnormal.

[0048] S1033, calculating a first similarity between the motion trajectory of each key operating component at each abnormal processing and the corresponding standard trajectory.

[0049] For the embodiment of the present application, each key operating component corresponds to a standard trajectory when operating normally, and is stored in an electronic device. After the electronic device determines the motion trajectory of a key operating component of a workshop equipment each time a processing abnormality occurs, the first similarity between the motion trajectory and the standard trajectory can be calculated for each processing abnormality. Specifically, the electronic device can input the motion trajectory during processing abnormalities and the standard trajectory into a trained network model to perform similarity calculations, and finally obtain the first similarity for each processing abnormality. The electronic device can also determine the similarity corresponding to each frame by calculating the cosine distance between the motion trajectory of each frame and the standard trajectory of the corresponding frame, and then calculate the similarity of all frames, and average the similarities of all frames to obtain the first similarity.

[0050] S1034 : Determine a benchmark component and a reference component from all key operating components based on the first similarity and the sensor data.

[0051] For the embodiment of the present application, when a processing anomaly occurs, the positional relationship between multiple key operating components during processing may be different, that is, there is a key operating component with an operating anomaly. In order to facilitate the determination of the positional relationship between multiple key operating components, the electronic device determines the benchmark component and the reference component based on the first similarity and sensor data. The reference component is a reference component other than the benchmark component among all key operating components. The benchmark component is a key operating component that has no abnormality or has a very low probability of abnormality. That is, the positional relationship between each reference component and the benchmark component is calculated based on the benchmark component. The higher the first similarity of the action trajectory of each key operating component during processing anomaly, the lower the probability of abnormality. The more normal the sensor data, the lower the probability of the key operating component appearing. Therefore, the electronic device can more accurately determine the benchmark component and the reference component based on the comprehensive analysis of the first similarity and sensor data.

[0052] S1035, mapping the motion trajectories of all key operating components at each moment into the same coordinate system, and determining the distance and angle between each reference component and the benchmark component.

[0053] For the embodiment of the present application, the electronic device maps the motion trajectories of all key operating components of a workshop equipment into the same coordinate system, which can be a three-dimensional rectangular coordinate system, so that the coordinates of each position on the motion trajectory, including the feature points, can be determined. The electronic device determines the center point coordinates of each motion trajectory based on the motion trajectories of all key operating components at each moment, and uses the center point coordinates to characterize the position of each motion trajectory. The electronic device then calculates the distance between each reference component and the reference component using the distance formula between two points in three-dimensional space. For angles, the staff can set the key parts of each key operating component in the electronic equipment in advance, and use the characteristic points on the key parts to connect the lines to characterize the key parts, so as to facilitate the subsequent calculation of the angle with the reference part. Usually, the rods with obvious movements such as travel, feed, and rotation during operation, such as some arms of the robot arm, the pressure rods on the punching machine, etc. For key operating components that can only be processed by rotation, the key points can be determined, and then the key points are connected to the origin of the coordinate system to characterize the key points. Then the electronic equipment calculates the slope of the line connecting the characteristic points of the key parts of each reference component and the slope of the line connecting the characteristic points of the reference part, and then uses the slope formula to calculate the angle θ. The formula is as follows: Tan(θ)=∣(m2-m1) / (1+m1×m2)∣ Where m2 is the slope corresponding to the benchmark component, m1 is the slope corresponding to the reference component, and θ is the angle.

[0054] The electronic device then uses the inverse tangent function on Tan(θ) to find the angle.

[0055] S1036, determining a characteristic value of each reference component based on the angle, distance, and sensor data.

[0056] For the embodiments of the present application, when all key operating components are operating normally, the angles and distances between them need to meet certain requirements. Therefore, if the angle between the reference component and the benchmark component, and the distance between the reference component and the benchmark component do not meet the corresponding angles and distances during normal operation, it means that there is an abnormality in the reference component, and the degree of abnormality is related to the actual values ​​of the angle and distance. Similarly, the degree of abnormality is also related to the corresponding sensor data. Therefore, the electronic device determines the characteristic value of each reference component that characterizes the abnormality at each moment based on the angle, distance and corresponding sensor data.

[0057] S1037, determining the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment.

[0058] For the embodiment of the present application, after the electronic device determines the characteristic value of each reference component at each moment, the characteristic values ​​of all moments during a complete processing abnormality are obtained, and then the electronic device can determine the sub-abnormality degree of each reference component during each processing abnormality.

[0059] S1038: Determine a first abnormality degree based on the sub-abnormality degrees.

[0060] For the embodiment of the present application, after the electronic device determines the sub-abnormality degree of each reference component at each processing abnormality, it can determine the abnormality degree corresponding to all processing abnormalities of each reference component within a preset historical time period, and finally the electronic device can comprehensively determine the first abnormality degree of the key operating components to characterize the workshop equipment according to the abnormality degree of each reference component at all processing abnormalities. For example, after the electronic device determines the sub-abnormality degree of a reference component at each processing abnormality, it calculates the average value of the sub-abnormality degrees at all processing abnormalities and uses the average value to characterize the abnormality degree of the reference component, and then sums the average values ​​calculated by the sub-abnormality degrees of all reference components to obtain the first abnormality degree of the workshop equipment.

[0061] In a possible implementation of the embodiment of the present application, when determining the benchmark component and the reference component from all key operating components based on the first similarity and the sensor data, step S1034 specifically includes step Sa (not shown in the figure), step Sb (not shown in the figure), step Sc (not shown in the figure), step Sd (not shown in the figure), step Se (not shown in the figure), step Sf (not shown in the figure) and step Sg (not shown in the figure), wherein: Sa, a first similarity average value is determined based on the first similarity of each key operating component when all processing anomalies occur.

[0062] For the embodiment of the present application, each key operating component has a corresponding first similarity each time a processing abnormality occurs, and then the electronic device calculates the first similarity average value of each key operating component through an average value calculation formula, and uses the first similarity average value to characterize the difference between the motion trajectory of each key operating component and the standard trajectory.

[0063] Sb, inverse data of the type of data collected by the corresponding sensor based on the action trajectory.

[0064] For the embodiments of the present application, the staff can set reference marks in advance within the range of the processing video collected by each key operating component. After the electronic device determines the motion trajectory, it can determine the distance or angle between the motion trajectory and the reference mark to characterize the actual motion data of the motion trajectory. For example, if a key operating component is a pressure rod that performs linear motion, the corresponding sensor data is the amount of linear motion. The electronic device can calculate the number of pixels from a certain feature point in the motion trajectory to the reference mark in the processing video, use the number of pixels to characterize the amount of linear motion of the pressure rod determined from the processing video, and then calculate the actual distance corresponding to the number of pixels through a preset scale. The actual distance is the reverse deduction data.

[0065] For another example, a key operating component is a rotating shaft, and the corresponding sensor data is the angle value of detecting the rotation angle. The electronic device can determine the connecting line from the feature points on the rotating shaft except the center of the circle to the reference position in the processing video, and then calculate the angle between the connecting line and the horizontal plane or other reference plane. This angle is the reverse deduction data.

[0066] The determined reverse inference data is the actual movement amount of the key operating components determined from the processing video when the processing is abnormal.

[0067] Sc, determine whether there is inconsistent data based on the inverse data and sensor data.

[0068] For the embodiment of the present application, the electronic device synchronously compares the reverse inference data with the sensor data at each processing abnormality, that is, compares the sensor data at the same time with the reverse inference data. If the reverse inference data at certain times is different from the sensor data, it is determined that inconsistent data exists.

[0069] Sd, if it exists, determines the amount of inconsistent data and the amount of data deviation.

[0070] For the embodiment of the present application, if there is inconsistent data, it means that there may be a large error in the sensor data or that a key operating component has an operating abnormality. Therefore, after the electronic device determines the inconsistent data, it counts all the inconsistent data to obtain the number of inconsistent data, that is, the data volume of the inconsistent data, and then sums the difference of the inconsistent data when all processing abnormalities occur. The summed result is the data volume of the inconsistent data of each key operating component when all processing abnormalities occur. The electronic device performs a difference calculation on each group of inconsistent data to obtain the difference of each group of inconsistent data, and then uses the average value calculation formula to determine the average value of the difference of all inconsistent data, and then sums the average value of the difference when all processing abnormalities occur, and uses the summed result to characterize the data deviation of each key operating component when all processing abnormalities occur.

[0071] Se, the trust value of the sensor is determined based on the amount of data and the amount of data deviation.

[0072] For the embodiment of the present application, the larger the number of inconsistencies, the larger the error of the sensor. Similarly, the larger the data deviation, the larger the error of the sensor. That is, the amount of data and the amount of data deviation are both key factors affecting the reliability of the sensor. Therefore, the staff sets different coefficients for the amount of data and the amount of data deviation and stores them in the electronic device. After the electronic device determines the amount of data and the amount of data deviation of the inconsistent data, since the amount of data and the amount of data deviation are inversely proportional to the reliability of the sensor, the electronic device calculates the inverse of the amount of data and the amount of data deviation and then calls the corresponding coefficients for weighted calculation to obtain the trust value of the sensor. The larger the trust value, the more reliable the sensor, and vice versa. The less reliable the sensor is, the worse its ability to monitor whether processing abnormalities occur in key operating components, and the less it can determine whether key operating components are abnormal.

[0073] Sf, determining the operation status value of each key operation component based on the trust value and the first similarity average value.

[0074] For the embodiment of the present application, the first similarity average value is the degree of abnormal operation of the key operating components determined from the processing video, and the trust value is the degree of reliability of monitoring the operation of the key operating components determined from the sensor, that is, the ability of the sensor to monitor whether the key operating components have processing abnormalities. The lower the trust value, the greater the sensor error, the higher the degree of sensor abnormality, and the worse the ability to prove that there is no abnormality in the key operating components. The higher the trust value, the closer the sensor data is to the inferred data, and the greater the possibility that the key operating components are operating normally. Therefore, the staff can set different coefficients for the first similarity average value and the trust value, and then the electronic device calls the corresponding coefficients for the trust value and the first similarity average value to perform weighted calculations to obtain the operating status value of each key operating component.

[0075] Sg, the key operating component with the highest operating condition value is determined as the benchmark component, and the key operating components other than the benchmark component are determined as reference components.

[0076] For the embodiment of the present application, the higher the operating status, the more standard the processing action of the key operating component is when the processing is abnormal, and the lower the degree of abnormality. Therefore, the key operating component with the highest operating status value can be determined as the component that does not have abnormal operation when the processing is abnormal, that is, the reference component. Other key operating components are determined as reference components. Calculating the distance and angle between the reference component and the reference component is equivalent to calculating the distance and angle between the key operating component with abnormal operation and the key operating component with normal operation. Therefore, it is more accurate to determine the operating status value of each key operating component through sensor data, reverse data, and the first similarity average value. Further, it is more accurate to determine the reference component and reference component from the key operating components through the operating status value.

[0077] A possible implementation of the embodiment of the present application is that in step S1036, the characteristic value of each reference component is determined based on the angle, distance and sensor data; in step S1037, the sub-abnormality degree of each reference component at each processing abnormality is determined based on the characteristic value at each moment, specifically including step S1 (not shown in the figure), step S2 (not shown in the figure), step S3 (not shown in the figure), step S4 (not shown in the figure) and step S5 (not shown in the figure), wherein, S1, determine a first difference between the angle and the standard angle at the time, and a second difference between the distance and the standard distance at the time.

[0078] For the embodiments of the present application, when the key operating components are undergoing normal standard processing, the angle between the reference component and the reference component at each moment needs to meet the requirements, that is, each moment corresponds to a standard angle, so the electronic device subtracts the angle at each moment from the standard angle at that moment to obtain a first difference, and the first difference represents the degree of deviation of the angle between the reference component and the reference component. The larger the first difference, the greater the degree of abnormal operation of the reference component. Similarly, when the key operating components are undergoing normal standard processing, the distance between the reference component and the reference component at each moment also needs to meet the requirements, that is, each moment corresponds to a standard distance, so the electronic device subtracts the distance at each moment from the standard distance at that moment to obtain a second difference, and the second difference represents the degree of deviation of the distance between the reference component and the reference component. The larger the second difference, the greater the degree of abnormal operation of the reference component. In other embodiments, a preset angle interval and a preset distance interval may be set at each moment in the electronic device to determine whether the first difference is within the preset angle interval and whether the second difference is within the preset distance interval. If not, the difference between the first difference and the nearest boundary of the preset angle interval is calculated, and the difference between the second difference and the nearest boundary of the preset distance interval is calculated. These two differences are used to characterize the degree of abnormal operation of the reference component.

[0079] S2, determining the sensor data and the inverse data at each moment, and calculating the third difference between the inverse data and the sensor data at each moment.

[0080] For the embodiment of the present application, the electronic device determines the sensor data and the inverse data of the reference component at each moment, and the electronic device subtracts the sensor data and the inverse data at the same moment to obtain a third difference. The larger the third difference at a certain moment, the greater the degree of abnormal operation of the reference component at that moment or the greater the sensor error.

[0081] S3, calculating the product of the first difference and the second difference, and determining a first ratio of the product to the third difference as a characteristic value of each reference component at each moment.

[0082] For the embodiment of the present application, it can be seen from step S1 that the first difference and the second difference are both proportional to the degree of abnormality of the reference component. Therefore, the electronic device can calculate the product of the first difference and the second difference. The larger the product, the greater the degree of abnormality of the reference component at a certain moment. The larger the third difference, the more unreliable the sensor is or the greater the degree of abnormality of the reference component. Therefore, the electronic device calculates a first ratio of the above product to the third difference, and uses the first ratio to represent a characteristic value of the degree of abnormality of the reference component at each moment. The characteristic value is used to more accurately calculate the degree of abnormality of each reference component during each subsequent processing abnormality.

[0083] S4, based on the characteristic value at each moment, determining the average value and variance of the characteristic values ​​at all moments when each machining abnormality occurs.

[0084] For the embodiment of the present application, for the entire process of a processing abnormality, the electronic device uses the eigenvalues ​​at all times to calculate the eigenvalue average value through the average value calculation formula, and uses the variance calculation formula to find the variance of the eigenvalue. The eigenvalue average value represents the overall abnormality degree of the entire process of a processing abnormality. The larger the eigenvalue average value, the greater the abnormality degree of the processing abnormality. The variance represents the degree of operation abnormality during the entire process of a processing abnormality. The larger the variance, the more unstable the reference component is during the processing abnormality, which further indicates that the degree of operation abnormality is greater.

[0085] S5, determining a score representing the abnormality degree of the sub-characteristic based on the eigenvalue mean value, the variance and the corresponding coefficients.

[0086] For the embodiments of the present application, in summary, the eigenvalue mean and variance are both key factors affecting the abnormality degree of the reference component during a processing abnormality. Therefore, the staff sets different coefficients for the eigenvalue mean and variance and stores them in the electronic device. After the electronic device determines the eigenvalue mean and variance, it calls the corresponding coefficients for weighted calculation to determine the sub-abnormality degree score of each reference component during each processing abnormality. The eigenvalue of the reference component at each moment is determined by the angle, distance, sensor data and reverse data between the reference component and the reference component during a processing abnormality, and then the sub-abnormality degree of the reference component during the processing abnormality is determined more accurately based on the eigenvalue at each moment. The electronic device determines the sub-abnormality degree of each reference component in the above manner.

[0087] In a possible implementation of the embodiment of the present application, in step S105, determining the second abnormality degree of any workshop equipment based on the image specifically includes step S1051 (not shown in the figure), step S1052 (not shown in the figure), step S1053 (not shown in the figure), and step S1054 (not shown in the figure), wherein: S1051, calculating a second similarity between the image and a standard image of a standard finished product produced by any workshop equipment.

[0088] For the embodiment of the present application, each qualified finished product produced by the workshop equipment corresponds to a standard finished product image, that is, a standard image. The electronic device calculates the second similarity between the image of the finished product produced when each processing abnormality occurs and the standard image. Specifically, the electronic device can input the image and the standard image into a trained network model to calculate the second similarity, thereby obtaining the second similarity. Specifically, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models. Or the electronic device calculates through the structural similarity metric (SSIM). It can also be calculated through cosine similarity, that is, the image and the standard image are represented as vectors, and the second similarity of the two images is characterized by calculating the cosine distance between the vectors.

[0089] S1052, comparing the image with the standard image to determine inconsistent image regions.

[0090] In the embodiment of the present application, the electronic device compares and maps the finished product image when the processing is abnormal with the standard image, thereby determining the inconsistent image area between the finished product and the standard image, and the inconsistent image area represents the degree of abnormality of the finished product.

[0091] S1053, determining a finished product abnormality value each time a processing abnormality occurs based on the second similarity and the number of image regions.

[0092] For the embodiment of the present application, the more inconsistent image areas there are, the higher the abnormality of the finished product is, which in turn indicates that the processing abnormality of the workshop equipment is higher. Therefore, the electronic device counts the inconsistent image areas to obtain the number of inconsistent image areas. The higher the second similarity, the closer the finished product is to the standard finished product, and the lower the abnormality, and vice versa. Therefore, the second similarity and the number of inconsistent image areas are both key factors in characterizing the abnormality of the finished product. Therefore, the staff sets different coefficients for the second similarity and the number of inconsistent image areas. After the electronic device determines the second similarity and the number of inconsistent image areas, it calls the corresponding coefficients for weighted calculation to obtain the finished product abnormality value of the finished product at each processing abnormality.

[0093] S1054, averaging the abnormal values ​​of finished products during all processing abnormalities to obtain a second abnormality degree.

[0094] For the embodiment of the present application, the electronic device determines the finished product abnormality value of a finished product when all processing abnormalities are performed by a workshop device within a preset historical time period through the above method, and determines the average value of the finished product abnormality value by the average value calculation formula for the finished product abnormality value of a finished product when all processing abnormalities are performed by a workshop device within a preset historical time period. The average value represents the second abnormality degree of the finished product produced by a workshop device within the preset historical time period, that is, the second abnormality degree represents the abnormality degree of the workshop device in producing finished products. By calculating the second similarity with the standard image and comparing it with the standard image to determine the inconsistent image area, it is more accurate to comprehensively determine the finished product abnormality value and the second abnormality degree by combining the second similarity and the number of inconsistent image areas.

[0095] In a possible implementation of the embodiment of the present application, in step S106, the abnormal level of operation of any workshop equipment is determined based on the total number of processing times, the number of abnormal processing times, the first abnormality degree, and the second abnormality degree, specifically including step S1061 (not shown in the figure), step S1062 (not shown in the figure), step S1063 (not shown in the figure), and step S1064 (not shown in the figure), wherein: S1061, determining a second ratio of the number of abnormal processing times to the total number of processing times.

[0096] S1062: Determine an overall abnormality score based on the first ratio, the first abnormality degree, the second abnormality degree, and their corresponding coefficients.

[0097] S1063: Determine a target preset score interval where the overall abnormality score is located from a plurality of preset score intervals.

[0098] Among them, each preset score interval corresponds to a preset abnormality level.

[0099] S1064: Determine the preset abnormality level of the target preset score interval as the abnormality level of any workshop equipment.

[0100] For the embodiment of the present application, the electronic device determines the second ratio of the number of abnormal processing times to the total number of processing times of a workshop equipment within a preset historical time period. The larger the second ratio is, the more abnormal finished products the workshop equipment processes, and the greater the abnormal degree of the workshop equipment. In summary, the second ratio characterizes the abnormal degree of the workshop equipment from the perspective of the proportion of abnormal finished products. The first abnormal degree is determined by the motion trajectory and sensor data of multiple key operating components (reference components) of a workshop equipment during abnormal processing, and the second abnormal degree is the abnormal degree of the workshop equipment characterized by the abnormal degree of the finished product processed during abnormal processing, and both have different degrees of influence on the overall abnormal degree of the workshop equipment. Therefore, the staff sets different coefficients for the second ratio, the first abnormal level, and the second abnormal level. After the electronic device determines the second ratio, the first abnormal level, and the second abnormal level of a workshop equipment, it can call the corresponding coefficients for weighted calculation to obtain a score, which can characterize the overall abnormal degree of a workshop equipment. In order to determine the abnormal level of the workshop equipment, the staff can set multiple preset score intervals according to experiments or actual measurements, and set a suitable abnormal level for each preset score interval according to experiments or actual measurements, that is, the preset abnormal level. After the electronic device determines the overall abnormality score, it compares the overall abnormality score with each preset score interval, thereby determining the preset score interval where the overall abnormality score is located, that is, the target preset score interval, and then the electronic device determines the preset abnormality level of the target preset score interval as the abnormality level of the workshop equipment. It is more accurate to comprehensively determine the overall abnormality level of the workshop equipment through the second ratio, the first abnormality degree and the second abnormality degree. The electronic device determines the abnormality level of each workshop equipment in the above manner.

[0101] In a possible implementation of the embodiment of the present application, step S106 further includes step S107 (not shown in the figure), wherein: S107, sending the equipment information of the workshop equipment whose abnormality level reaches the preset abnormality level threshold to the terminal device of the manager.

[0102] For the embodiment of the present application, the preset abnormality level threshold is a demarcation point for determining whether the abnormality of a workshop equipment is too large. If the preset abnormality level threshold is reached, it means that the abnormality of the workshop equipment is large and needs to be inspected and repaired immediately. Therefore, the electronic device compares the abnormality level of each workshop equipment with the preset abnormality level threshold, thereby determining the workshop equipment that reaches the preset abnormality level threshold. The equipment information of each workshop equipment is stored in the electronic device, and the equipment information includes the equipment name, operating time, etc. The electronic device searches for the equipment information of the workshop equipment that reaches the preset abnormality level threshold, and then sends the equipment information to the terminal device of the manager, for example, by sending a text message carrying the above-mentioned workshop equipment to the terminal device of the manager in the form of a text message, or sending a push message to the APP of the terminal device of the manager, so that the manager can be informed of the workshop equipment with excessive abnormality in a timely manner, so as to facilitate timely inspection and maintenance.

[0103] The above-mentioned embodiment introduces an industrial data intelligent management method from the perspective of method flow, and the following embodiment introduces an industrial data intelligent management system from the perspective of a virtual module or a virtual unit. Please refer to the following embodiment for details.

[0104] The present application embodiment provides an industrial data intelligent management system 20, such as Figure 2 As shown, the industrial data intelligent management system 20 may specifically include: The first acquisition module 201 is used to obtain the total number of processing times and the number of abnormal processing times of each workshop equipment in a preset historical time period; The second acquisition module 202 is used to determine the key operating components of any workshop equipment, and obtain the processing video of each key operating component and the sensor data corresponding to each key operating component when any workshop equipment has a processing abnormality each time; A first determination module 203, used to determine a first abnormality level of any workshop equipment based on the processing video and the sensor data; The third acquisition module 204 is used to acquire images of finished products produced by any workshop equipment each time a processing anomaly occurs; A second determination module 205, for determining a second abnormality level of any workshop equipment based on the image; The third determination module 206 is used to determine the abnormality level of any workshop equipment operation based on the total number of processing times, the number of processing abnormalities, the first abnormality level and the second abnormality level.

[0105] The embodiment of the present application discloses an industrial data intelligent management system 20, wherein the first acquisition module 201 acquires the total number of processing times and the number of processing abnormalities of the workshop equipment within a preset historical time period, so as to facilitate the subsequent analysis of the proportion of abnormal finished products processed, and the second acquisition module 202 determines all the key operating components of any workshop equipment, and the key operating components cooperate with each other to achieve the effect of simultaneous processing and production, and obtains the processing video and sensor data of each key operating component at each processing abnormality. The sensor data represents the movement amount collected by the sensor of each key operating component, and the processing video records the specific situation of the processing and operation of the key operating components at each processing abnormality. Therefore, the first determination module Block 203 can accurately determine the first abnormality level based on the processing video and sensor data. The third acquisition module 204 acquires the image of the finished product produced by the workshop equipment each time the processing is abnormal. The image records the specific situation of the finished product, so that the second determination module 205 can determine the second abnormality level of the workshop equipment based on the image, that is, the abnormality level of the workshop equipment is characterized by the abnormality level of the finished product. The third determination module 206 combines the total number of processing times, the number of processing abnormalities, the first abnormality level characterized by key operating components, and the second abnormality level characterized by the finished product to determine the overall operating abnormality level of the workshop equipment with a high degree of integration and operating components with multiple different functions more accurately and conveniently.

[0106] In a possible implementation of the embodiment of the present application, when the first determination module 203 determines the first abnormality level of any workshop equipment based on the processing video and the sensor data, it is specifically used to: Perform feature recognition on the processing video to obtain the feature points of each key operating component; Connect the feature points of each key running component and track the feature points based on the processed video to obtain the motion trajectory of the connection; Calculate the first similarity between the motion trajectory of each key operating component and the corresponding standard trajectory at each abnormal processing; determining a baseline component and a reference component from all critical operating components based on the first similarity and the sensor data; Map the motion trajectories of all key operating components at each moment into the same coordinate system, and determine the distance and angle between each reference component and the reference component; Determine a characteristic value of each reference component based on the angle, distance, and sensor data; Determine the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment; A first abnormality degree is determined based on the sub-abnormality degrees.

[0107] In a possible implementation of the embodiment of the present application, when the first determination module 203 determines the benchmark component and the reference component from all the key operating components based on the first similarity and the sensor data, it is specifically used to: Determining a first similarity average value based on the first similarity of each key operating component when all processing anomalies occur; Inversely infer the type of data collected by the corresponding sensor based on the action trajectory; Determine whether there is inconsistent data based on the inferred data and sensor data; If so, determine the amount of inconsistent data and the amount of data deviation; Determine the trust value of the sensor based on the amount of data and the amount of data deviation; Determine the operation status value of each key operation component based on the trust value and the first similarity average value; The key operating component with the highest operating condition value is determined as the benchmark component, and the key operating components other than the benchmark component are determined as reference components.

[0108] In a possible implementation of the embodiment of the present application, the first determination module 203 determines the characteristic value of each reference component based on the angle, distance and sensor data; and determines the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment, specifically for: Determine a first difference between the angle and the standard angle at the time, and a second difference between the distance and the standard distance at the time; Determine the sensor data and the inverse data at each moment, and calculate the third difference between the inverse data and the sensor data at each moment; Calculate the product of the first difference and the second difference, and determine a first ratio of the product to the third difference as a characteristic value of each reference component at each time; Based on the characteristic value at each moment, the average value and variance of the characteristic values ​​at all moments of each processing abnormality are determined; The score representing the abnormality degree of the sub-element is determined based on the eigenvalue mean value, variance and respective corresponding coefficients.

[0109] In a possible implementation of the embodiment of the present application, when the second determination module 205 determines the second abnormality level of any workshop equipment based on the image, it is specifically used to: Calculate a second similarity between the image and a standard image of a standard finished product produced by any workshop equipment; Compare the image with the standard image to determine inconsistent image areas; Determine a finished product abnormality value each time a processing abnormality occurs based on the second similarity and the number of image regions; The second abnormality level is obtained by averaging the abnormal values ​​of finished products during all processing abnormalities.

[0110] In a possible implementation of the embodiment of the present application, when the third determination module 206 determines the abnormality level of any workshop equipment operation based on the total number of processing times, the number of abnormal processing times, the first abnormality degree, and the second abnormality degree, it is specifically used to: Determining a second ratio of the number of abnormal processing times to the total number of processing times; Determine an overall abnormality score based on the first ratio, the first abnormality degree, the second abnormality degree, and respective corresponding coefficients; Determine a target preset score interval where the overall abnormality score is located from a plurality of preset score intervals, each preset score interval corresponding to a preset abnormality level; The preset abnormality level of the target preset score interval is determined as the abnormality level of any workshop equipment.

[0111] In a possible implementation of the embodiment of the present application, the system 20 further includes: The sending module is used to send the equipment information of the workshop equipment whose abnormality level reaches the preset abnormality level threshold to the terminal device of the manager.

[0112] In the embodiment of the present application, the first acquisition module 201, the second acquisition module 202 and the third acquisition module 204 may be the same acquisition module, or different acquisition modules, or partially the same acquisition modules. The first determination module 203, the second determination module 205 and the third determination module 206 may be the same determination module, or different determination modules, or partially the same acquisition modules.

[0113] Technical personnel in the relevant field can clearly understand that, for the convenience and brevity of description, the specific working process of an industrial data intelligent management system 20 described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0114] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0115] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0116] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0117] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0118] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0119] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0120] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment. Compared with the related art, in the embodiment of the present application, the total number of processing times and the number of processing abnormalities of the workshop equipment within a preset historical time period are obtained, which is convenient for subsequent analysis of the proportion of abnormal finished products processed, and all key operating components are determined for any workshop equipment. The key operating components cooperate with each other to achieve the effect of simultaneous processing and production, and the processing video and sensor data of each key operating component are obtained at each processing abnormality. The sensor data characterizes the movement amount of each key operating component collected by the sensor, and the processing video records the specific situation of the processing and operation of the key operating components at each processing abnormality. Therefore, the first abnormality degree can be accurately determined according to the processing video and the sensor data, and the image of the finished product produced by the workshop equipment at each processing abnormality is obtained. The image records the specific situation of the finished product, so that it is convenient to determine the second abnormality degree of the workshop equipment according to the image, that is, the abnormality degree of the workshop equipment is characterized by the abnormality degree of the finished product, and it is more accurate and convenient to determine the overall operation abnormality level of the workshop equipment with a high degree of integration and operating components with multiple different functions by combining the total processing times, the number of processing abnormalities, the first abnormality degree characterized by the key operating components, and the second abnormality degree characterized by the finished product.

[0121] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0122] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An industrial data intelligent management method, characterized in that: include: Obtain the total number of processing times and number of processing exceptions for each workshop equipment within the preset historical time period; Determine the key operating components of any workshop equipment, and obtain the processing video of each key operating component and the sensor data corresponding to each key operating component each time a processing abnormality occurs in any workshop equipment; Determining a first abnormality level of any of the workshop equipment based on the processing video and the sensor data; Acquire images of finished products produced by any of the workshop equipment at each time of abnormal processing; determining a second abnormality level of any one of the workshop equipment based on the image; The abnormality level of operation of any one of the workshop equipment is determined based on the total number of processing times, the number of processing abnormalities, the first abnormality level, and the second abnormality level.

2. The method for intelligent management of industrial data according to claim 1, characterized in that: The determining the first abnormality level of any workshop equipment based on the processing video and the sensor data includes: Performing feature recognition on the processing video to obtain feature points of each key operating component; Connecting feature points of each key operating component, and tracking the feature points based on the processed video to obtain a motion trajectory of the connection; Calculate the first similarity between the motion trajectory of each key operating component and the corresponding standard trajectory at each abnormal processing; determining a baseline component and a reference component from all key operating components based on the first similarity and the sensor data; Map the motion trajectories of all key operating components at each moment into the same coordinate system, and determine the distance and angle between each reference component and the reference component; determining a characteristic value of each reference component based on the angle, distance, and sensor data; Determine the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment; The first abnormality degree is determined based on the sub-abnormality degrees.

3. The method for intelligent management of industrial data according to claim 2, characterized in that: The step of determining a benchmark component and a reference component from all key operating components based on the first similarity and the sensor data includes: Determining a first similarity average value based on the first similarity of each key operating component when all processing anomalies occur; Inversely infer the type of data collected by the corresponding sensor based on the action trajectory; Determining whether there is inconsistent data based on the inferred data and the sensor data; If so, determine the amount of inconsistent data and the amount of data deviation; Determining a trust value of the sensor based on the data amount and the data deviation amount; Determine the operation status value of each key operation component based on the trust value and the first similarity average value; The key operating component with the highest operating condition value is determined as a benchmark component, and the key operating components other than the benchmark component are determined as reference components.

4. The method for intelligent management of industrial data according to claim 2, characterized in that: Determining a characteristic value of each reference component based on the angle, distance and sensor data; Determining the sub-abnormality degree of each reference component at each processing abnormality based on the characteristic value at each moment, including: Determine a first difference between the angle and a standard angle at the time, and a second difference between the distance and a standard distance at the time; Determine the sensor data and the inverse data at each moment, and calculate the third difference between the inverse data and the sensor data at each moment; Calculate the product of the first difference and the second difference, and determine a first ratio of the product to the third difference as a characteristic value of each reference component at each time; Based on the eigenvalues ​​at each moment, the average value and variance of the eigenvalues ​​at all moments of each processing abnormality are determined; A score representing the degree of the sub-abnormality is determined based on the eigenvalue mean value, the variance and the corresponding coefficients.

5. The method for intelligent management of industrial data according to claim 1, characterized in that: The determining the second abnormality degree of any one of the workshop equipment based on the image comprises: Calculating a second similarity between the image and a standard image of a standard finished product produced by any of the workshop equipment; Comparing the image with the standard image to determine inconsistent image regions; Determine a finished product abnormality value each time a processing abnormality occurs based on the second similarity and the number of image regions; The second abnormality degree is obtained by averaging the abnormal values ​​of finished products during all processing abnormalities.

6. The method for intelligent management of industrial data according to claim 1, characterized in that: The determining of the abnormality level of any workshop equipment operation based on the total number of processing times, the number of abnormal processing times, the first abnormality degree and the second abnormality degree includes: Determining a second ratio of the number of processing abnormalities to the total number of processing times; Determine an overall abnormality score based on the first ratio, the first abnormality degree, the second abnormality degree, and respective corresponding coefficients; Determine a target preset score interval where the overall abnormality score is located from a plurality of preset score intervals, each preset score interval corresponding to a preset abnormality level; The preset abnormality level of the target preset score interval is determined as the abnormality level of any workshop equipment.

7. An industrial data intelligent management method according to claim 1 or 6, characterized in that: The method further comprises: The equipment information of the workshop equipment whose abnormality level reaches the preset abnormality level threshold is sent to the terminal device of the manager.

8. An industrial data intelligent management system, characterized in that: include: The first acquisition module is used to obtain the total number of processing times and the number of processing exceptions of each workshop equipment in a preset historical time period; The second acquisition module is used to determine the key operating components of any workshop equipment, and obtain the processing video of each key operating component and the sensor data corresponding to each key operating component each time the processing of any workshop equipment is abnormal; A first determination module, configured to determine a first abnormality level of any of the workshop equipment based on the processing video and the sensor data; A third acquisition module is used to acquire an image of a finished product produced by any of the workshop equipment each time a processing abnormality occurs; A second determination module, configured to determine a second abnormality level of any one of the workshop equipment based on the image; The third determination module is used to determine the abnormality level of operation of any workshop equipment based on the total number of processing times, the number of processing abnormalities, the first abnormality degree and the second abnormality degree.

9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute an industrial data intelligent management method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the industrial data intelligent management method according to any one of claims 1 to 7.

Images