Unattended production equipment monitoring method, system and storage medium

Abstract

The present invention discloses a production equipment monitoring method, system and storage medium based on unattended operation, belonging to the field of factory control technology. The method comprises: a sensor module sends collected equipment data to an analysis module; the analysis module inputs part of the equipment data as input data into a conversion function to calculate and obtain output data, and obtains equipment data of the same type as the output data, which is defined as target data; if the difference between the output data and the target data is greater than a first threshold value, the target data is defined as abnormal data, the production equipment generating the abnormal data is classified as a faulty equipment, and the equipment data of the faulty equipment is sent to a decision module; the decision module generates a processing plan for the faulty equipment, and the display module displays the distribution of the abnormal data and the corresponding processing plan. The fault diagnosis standard of the judgment equipment of the present invention can be changed according to the actual use situation, thereby improving the application scope of the diagnosis method and reducing the judgment error rate.

Description

Technical Field

[0001] The present invention belongs to the technical field of factory control, and in particular relates to a method, system and storage medium for monitoring production equipment based on unattended operation. Background Art

[0002] With the continuous advancement of smart factory construction, the application of Internet of Things technology in large industrial enterprises will become more and more extensive. In order to strive to improve the level of intelligent equipment control, improve management efficiency, and reduce equipment operation and maintenance costs, modern large-scale production enterprises are transforming to a "few people on duty, no one on duty" type of enterprise management mode. Among them, being able to understand and master the operating status of equipment in the control room or even remotely is one of the core functions of the unattended mode.

[0003] In order to achieve the purpose of remote monitoring of the equipment status, the following technical solutions are disclosed in the prior art. For example, Chinese patent document 1 with publication number CN115877802A discloses a production process data collection and monitoring method and system. The method collects basic data, production process data and production quality data of the production area, packages and generates a data set according to data classification, and then obtains target monitoring data from the data set, establishes data identification, establishes data judgment thresholds according to the data identification, and judges whether there is bad data in the acquired target monitoring data according to the threshold. For another example, Chinese patent document 2 with publication number CN117270480A discloses a production line monitoring method and system. The method parses the production setting information of each production item, constructs a monitoring set of the corresponding production item, and configures a first sensor to the production line segment and a second sensor to the production station; performs abnormal analysis according to the monitoring results of the sensor. The abnormal analysis is to compare the monitoring results with the standard results to determine the individual abnormal distribution of the same parameter index and the overall abnormal distribution of all parameter indexes.

[0004] In order to discover abnormal data in the monitoring results, the above-mentioned patent document 1 compares the equipment operating parameters obtained by monitoring with fixed thresholds, and patent document 2 compares the equipment operating parameters with standard results. In actual production, the various operating parameters of the equipment may change with the environment and its own usage. The method of comparing with fixed values ​​alone has a small scope of application and a high judgment error rate. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a method and system for monitoring production equipment based on unattended operation, so as to solve the problems existing in the above background technology.

[0006] In order to achieve the above-mentioned invention object, the present invention proposes a production equipment monitoring method based on unattended operation, comprising:

[0007] The sensor module collects equipment data of the production equipment, and the sensor module sends its own attribute information and the collected equipment data to the analysis module;

[0008] The analysis module stores a conversion function, and the conversion function is used to convert at least one of the device data into another type of the device data;

[0009] The analysis module selects the corresponding conversion function based on the attribute information, inputs part of the device data as input data into the conversion function to calculate and obtain output data, and obtains the device data of the same type as the output data, which is defined as target data;

[0010] If the difference between the output data and the target data is greater than a first threshold, the target data is defined as abnormal data, the production equipment generating the abnormal data is classified as a faulty equipment, and the analysis module sends the equipment data of the faulty equipment to the decision module;

[0011] The decision module analyzes the device data, generates a processing plan for the faulty device, and sends the processing plan to the display module, which displays the distribution of the abnormal data and the corresponding processing plan.

[0012] Furthermore, the display module displays the distribution status including the following steps:

[0013] The display module includes a data association diagram, which includes multiple nodes, each node represents a type of the device data, and connecting lines are set between the nodes. The connecting lines represent that there is a basic function between the two nodes, and the basic function is used to convert one type of the device data into another type of the device data. The display module marks the nodes representing the abnormal data with a preset color to show the distribution.

[0014] Furthermore, generating the data association graph includes the following steps:

[0015] After collecting a preset amount of each type of device data, the analysis module divides the device data into a first data set and a second data set, both of which are normal device data, extracts two types of device data from the first data set to construct the basic function, and if the basic function is successfully constructed, defines the two types of device data as associated data, constructs an initial topology graph, and includes nodes representing the device data, and connects the nodes with the basic function using the connecting lines;

[0016] Extract the associated data in pairs from the second data set, respectively define them as first data and second data, input the first data into the basic function to obtain the output data corresponding to the second data, calculate the ratio of the second data to the corresponding output data, extract the first data and the second data again, repeat this step until all the data in the second data set are extracted, and use the average value of the ratio as the available value of the basic function;

[0017] In the initial topology graph, the connection lines corresponding to the basic functions whose available values ​​are less than a second threshold are removed to obtain the data association graph.

[0018] Further, after the data association graph is generated, the conversion function is generated based on the following steps:

[0019] A node is extracted from the data association graph and defined as a main node, and other nodes with the connection line to the main node are defined as branch nodes. If one main node has at least two branch nodes, the device data corresponding to the main node in the first data set is extracted as a dependent variable, and the device data corresponding to the branch node in the first data set is extracted as an independent variable, and a comprehensive function is constructed based on the dependent variable and the independent variable.

[0020] The dependent variable and the independent variable are extracted from the second data set to calculate the optimized value of the comprehensive function; if the optimized value of the comprehensive function is greater than or equal to the available values ​​of all the basic functions under the main node, the comprehensive function is defined as the conversion function; otherwise, the basic function with the largest available value is defined as the conversion function.

[0021] Furthermore, a comparison table is provided in the analysis module, and the comparison table includes the conversion functions, each of the conversion functions corresponds to an input part and an output part, and the input part and the output part both include the attribute information of the sensor module. After receiving the device data, the analysis module searches for the corresponding conversion function based on the attribute information in combination with the comparison table. After the conversion function outputs the output data, the target data corresponding to the output data is obtained based on the attribute information of the output part in the comparison table.

[0022] Furthermore, when the analysis module uses the conversion function for calculation, if it is detected that there is missing device data, the missing device data is defined as missing data, a node representing the missing data is obtained from the data association graph and defined as a first node, a node connected to the first node and representing the target data is defined as a second node, and according to the conversion function between the first node and the second node, the device data of the second node is converted into the missing data.

[0023] Furthermore, the decision module includes a fault handling text and an analysis model. The analysis model determines the fault type of the production equipment based on the received equipment data, obtains the corresponding processing solution from the fault handling text based on the fault type, and sends the processing solution to the display module.

[0024] Furthermore, the display module displays the processing scheme including the following steps:

[0025] The display module includes a plant topographic map, in which a three-dimensional model of the production equipment is arranged. The display module changes the three-dimensional model of the faulty equipment to a preset color and displays the treatment plan at the same time.

[0026] The present invention also provides an unattended production equipment monitoring system, which is used to implement the unattended production equipment monitoring method described above, and the system includes:

[0027] A sensor module is used to collect equipment data of production equipment, and the sensor module sends its own attribute information and the collected equipment data to the analysis module;

[0028] an analysis module storing a conversion function, wherein the conversion function is used to convert at least one of the device data into another type of the device data; the analysis module selects the corresponding conversion function based on the attribute information, inputs part of the device data as input data into the conversion function to calculate and obtain output data, obtains the device data of the same type as the output data, and defines it as target data; if the difference between the output data and the target data is greater than a first threshold, defines the target data as abnormal data, classifies the production equipment that generates the abnormal data as a faulty equipment, and the analysis module sends the device data of the faulty equipment to the decision module;

[0029] A decision module, used for analyzing the device data, generating a processing plan for the faulty device, and sending the processing plan to the display module;

[0030] The display module is used to display the distribution of the abnormal data and the corresponding processing solution.

[0031] The present invention also discloses a computer storage medium, wherein the computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above-mentioned method.

[0032] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0033] The present invention first sets a conversion function in the analysis module so that the device data with correlation can be converted to each other according to the conversion function; after the analysis module receives one or more types of device data actually collected, it divides them into input data and output data, and inputs the device data belonging to the input data into the conversion function to obtain the output data, and compares the output data with the target data actually measured. If the two are close, it is considered that the device is normal, and if the two are greatly different, it is considered that the device may have a fault; because the output data changes with the input data, the judgment standard for judging whether the device is faulty is also constantly changing according to the actual situation, so the technical solution of the present invention can monitor the device status more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of the steps of the unattended production equipment monitoring method of the present invention;

[0035] Figure 2 It is a principle schematic diagram of the data association graph of the present invention;

[0036] Figure 3 It is a schematic diagram of the structure of the unattended production equipment monitoring system according to the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0038] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0039] like Figure 1 As shown, a method for monitoring production equipment based on unattended operation includes:

[0040] S1: The sensor module collects equipment data of the production equipment, and sends its own attribute information and the collected equipment data to the analysis module.

[0041] The production equipment includes ball mills, vibrating feed screens, transformers, belt conveyors, etc. The equipment data generated include temperature, vibration frequency, vibration intensity, conveying speed, voltage, etc. After each sensor module is installed on the equipment, it has unique attribute information. The attribute information is used to indicate the location of the sensor itself and the source of the collected equipment data. For example, the attribute information is the east side of factory A, transformer 1, temperature.

[0042] S2: The analysis module stores a conversion function, where the conversion function is used to convert at least one device data into another device data.

[0043] S3: The analysis module selects a corresponding conversion function based on the attribute information, inputs part of the device data as input data into the conversion function to calculate and obtain output data, and obtains device data of the same type as the output data, which is defined as target data.

[0044] S4: If the difference between the output data and the target data is greater than a first threshold, the target data is defined as abnormal data, the production equipment generating the abnormal data is classified as a faulty equipment, and the analysis module sends the equipment data of the faulty equipment to the decision module.

[0045] S5: The decision module analyzes the equipment data, generates a processing plan for the faulty equipment, and sends the processing plan to the display module, which displays the distribution of abnormal data and the corresponding processing plan.

[0046] The conversion function is a function formula generated in advance based on historical data, and its form is B=A+A1*W1+A2*W2++···+An *Wn, where A is a constant, B and A1-An are device data, and W1-Wn are coefficients. Through the above conversion function, the device data A1-An can be converted into device data B. For example, if there is a linear relationship between the conveying speed of the belt conveyor and the motor temperature and running time, then after knowing the conveying speed and running time, the motor temperature can be inferred based on the conveying speed.

[0047] After receiving the attribute information of the sensor, the analysis module can select the corresponding conversion function according to the attribute information. For example, if the received information represents the motor temperature, transmission speed and running time of the belt conveyor, the conversion function of the three is selected, and then the transmission speed and running time are input into the conversion function to obtain the output data of the motor temperature. The output data is then compared with the actual motor temperature received (ie, the target data) to obtain the difference between the two. If the difference is greater than a first threshold value set in advance, it indicates that the actual temperature of the motor does not match the theoretical temperature, and the motor may have failed. Therefore, the motor temperature is classified as abnormal data and the belt conveyor is classified as a faulty device.

[0048] In order to conduct a comprehensive diagnosis of the faulty equipment, the transmission speed, motor temperature and ambient temperature are also sent to the decision-making module for specific fault analysis, and then the corresponding processing plan is generated and displayed on the display module. The display module is, for example, a host computer or a personal handheld terminal. By automatically generating a processing plan, the workload of manual judgment can be reduced and the processing speed of equipment failure can be accelerated.

[0049] The present invention first sets a conversion function in the analysis module so that the device data with correlation can be converted to each other according to the conversion function; after the analysis module receives one or more types of device data actually collected, it divides them into input data and output data, and inputs the device data belonging to the input data into the conversion function to obtain the output data, and compares the output data with the target data actually measured. If the two are close, it is considered that the device is normal, and if the two are greatly different, it is considered that the device may have a fault; because the output data changes with the input data, the judgment standard for judging whether the device is faulty is also constantly changing according to the actual situation, so the technical solution of the present invention can monitor the device status more accurately.

[0050] It is particularly noteworthy that the fault diagnosis standard of the judgment device of the present invention can be changed according to the actual usage situation, thereby increasing the application scope of the diagnosis method and reducing the judgment error rate.

[0051] In this embodiment, the display module displays the distribution status and the processing scheme, including the following steps:

[0052] The display module includes a data association diagram, which includes multiple nodes. Each node represents a type of device data. Connection lines are set between the nodes. The connection lines represent the existence of basic functions between the two nodes. The basic functions are used to convert one type of device data into another type of device data. The display module marks the nodes representing abnormal data with preset colors to show the distribution.

[0053] like Figure 2The data association diagram is shown, and the data association diagram includes nodes A, B, C, and D. For example, A and C represent the conveying speed and running time of the belt conveyor, B represents the motor temperature, and D represents the motor rotation speed. Nodes A and D are connected, indicating that there is a correlation between the conveying speed and the motor speed. In the data association diagram, there is a basic function between the two nodes connected by the connecting line. Unlike the conversion function, the basic function has only one input data and output data. After determining which device data is abnormal data, the corresponding node is marked in red (i.e., the preset color). When relevant personnel view the data association diagram, they can easily find which data of which equipment is abnormal, and which device data is associated with the abnormal data, which is convenient for them to make subsequent decisions.

[0054] This embodiment generates a data association graph including the following steps:

[0055] After collecting a preset amount of data from each type of device, the analysis module divides the device data into a first data set and a second data set. Both the first data set and the second data set are normal device data. Two types of device data are extracted from the first data set to construct a basic function. If the basic function is successfully constructed, the two types of device data are defined as associated data, and an initial topology map is constructed. The initial topology map includes nodes representing device data, and the nodes with basic functions are connected using connecting lines.

[0056] In this embodiment, the preset number is set to 1000. First, the current device is manually ensured to be in normal operation to ensure that the collected device data is normal data. After the analysis module collects 1000 pieces of device data of all types, the device data is divided into a first data set and a second data set. When dividing, multiple sensor data of the same generation time will be divided into one data set. After that, the device data collected by the two types of sensors are extracted from the first data set. The multi-source linear regression method is used, and the linear regression equation between the two types of sensor data is established with the help of related tools, that is, the basic function. The related tool is Matlab software. If the basic function is successfully generated, it indicates that there is a correlation between the two types of device data, and the two are defined as associated data. Repeat this step until all combinations of device data are traversed. Finally, in the initial topology diagram containing only nodes, the two nodes with the basic function are connected with a connecting line.

[0057] Extract related data from the second data set in pairs, define them as first data and second data respectively, input the first data into the basic function to obtain output data corresponding to the second data, calculate the ratio of the second data to the corresponding output data, extract the first data and the second data again, repeat this step until all the data in the second data set are extracted, and take the average value of the ratio as the available value of the basic function.

[0058] In the initial topology graph, the connection lines corresponding to the basis functions whose available values ​​are less than the second threshold value are removed to obtain a data association graph.

[0059] In order to obtain a more accurate data association diagram, the present invention also extracts associated data from the second data set. For the convenience of description, the two types of data are defined as first data and second data, respectively. The first data is input into the corresponding basic function to obtain output data. For example, after the conveying speed is input into the basic function, the predicted motor temperature is obtained, and the ratio of the predicted motor temperature (output data) to the actual motor temperature (second data) is calculated. The smaller the ratio, the more accurate the establishment of the basic function. Repeat this step until the test of all device data in the second data set is completed, and the average value of the ratio is used as the available value of the basic function. If the available value is less than the second threshold, such as 0.3, it indicates that although the basic function is successfully established, in most cases, one type of device data cannot be well converted into another type of device data. Therefore, the connecting lines representing the basic functions with available values ​​less than 0.3 in the initial topology diagram are removed to obtain an optimized data association diagram.

[0060] After the data association graph is generated in this embodiment, a conversion function is generated based on the following steps:

[0061] A node is extracted from the data association graph and defined as the main node, and other nodes that are connected to the main node are defined as branch nodes. If a main node has at least two branch nodes, the device data corresponding to the main node in the first data set is extracted as the dependent variable, and the device data corresponding to the branch node in the first data set is extracted as the independent variable, and a comprehensive function is constructed based on the dependent variable and the independent variable.

[0062] Reference Figure 2 , for example from Figure 2 Node B is extracted as the main node, and nodes A and C are connected to node B, so nodes A and C are branch nodes. Due to the existence of two branch nodes, the device data corresponding to node B is used as the dependent variable, and the device data of nodes A and C are used as independent variables. A comprehensive function between the dependent variable and the independent variable is constructed based on the first data set.

[0063] Dependent variables and independent variables are extracted from the second data set to calculate the optimized value of the comprehensive function. If the optimized value of the comprehensive function is greater than or equal to the available values ​​of all basic functions under the main node, the comprehensive function is defined as the conversion function, otherwise the basic function with the largest available value is defined as the conversion function.

[0064] Here, the same method as that used to calculate the available values ​​of the basic functions mentioned above is used to calculate the optimized value of the comprehensive function. Basic function 1 is defined between nodes A and B, and basic function 2 is defined between nodes C and B. If the optimized value is greater than or equal to the available values ​​of basic functions 1 and 2, the comprehensive function is defined as a conversion function. When device data is subsequently received, the output data is calculated based on the two types of device data represented by nodes A and C and the comprehensive function. If the optimized value is greater than the available value of basic function 1 and less than the available value of basic function 2, basic function 2 is defined as a conversion function. When device data is subsequently received, the output data is calculated based on node C and basic function 2.

[0065] The purpose of the above technical solution is that the device data represented by nodes A and C can be converted into the basic function represented by node B through the basic function, so we try to construct a more comprehensive linear regression equation, which includes the device data represented by nodes A and C. If the constructed comprehensive function is better than the original basic function, it will be retained, so that the best conversion function can be obtained.

[0066] A comparison table is provided in the analysis module in this embodiment, and the comparison table includes conversion functions. Each conversion function corresponds to an input part and an output part, and the input part and the output part both include attribute information of the sensor module. After receiving the device data, the analysis module combines the comparison table and searches for the corresponding conversion function based on the attribute information. After the conversion function outputs the data, the target data corresponding to the output data is obtained based on the attribute information of the output part in the comparison table.

[0067] Specifically, the comparison table can be used to know which conversion function should be input into after receiving the device data collected by the sensor module. If there is conversion function 1 in the comparison table, the corresponding input part includes attribute information A and attribute information C, and the output part includes attribute information B. Attribute information A corresponds to device data A of node A, attribute information B corresponds to device data B of node B, and attribute information C corresponds to device data C of node C. After receiving attribute information A, B, and C, the analysis module can find conversion function 1 from the comparison table, input device data A and C into conversion function 1, and compare the obtained output data with device data B, thereby completing the process of comparing the output data with the target data.

[0068] When the analysis module of this implementation uses the conversion function for calculation, if missing device data is detected, the missing device data is defined as missing data, a node representing the missing data is obtained from the data association graph and defined as the first node, and a node connected to the first node and representing the target data is defined as the second node. According to the conversion function between the first node and the second node, the device data of the second node is converted into missing data.

[0069] Continue to refer to Figure 2 If the analysis module needs to use device data A and C for calculation, and only receives device data C, device data A is missing. Device data A is defined as missing data, node A is defined as the first node, and node D is set as the second node. According to the conversion function between node D and node A, the device data corresponding to node D is converted into the device data corresponding to node A, thereby supplementing the missing data.

[0070] In this embodiment, the decision module includes a fault handling text and an analysis model. The analysis model determines the fault type of the production equipment based on the received equipment data, obtains the corresponding processing solution from the fault handling text based on the fault type, and sends the processing solution to the display module.

[0071] The analysis model is a trained neural network model. After acquiring all the device data of the faulty device, it extracts the characteristic information in the device data. The characteristic information is pre-set, such as the time domain characteristics or frequency domain characteristics of the data. The characteristic information is then input into the analysis model for diagnosis. The analysis model will output the fault type of the device. After determining the fault type, the solution to the fault type can be found from the fault handling text, and the solution is extracted and sent to the display module for display.

[0072] The display module display processing solution of this embodiment includes the following steps:

[0073] The display module includes a plant topographic map, in which a three-dimensional model of the production equipment is arranged. The display module changes the three-dimensional model corresponding to the faulty equipment to a preset color and displays a treatment plan at the same time.

[0074] The display module of this embodiment also includes a factory topographic map, on which is drawn a three-dimensional model that is exactly the same as the actual equipment. By marking the three-dimensional model of the corresponding faulty equipment in red on the factory topographic map, relevant personnel can quickly confirm the location of the faulty equipment. In addition, the display module displays the processing plan generated by the decision in text form.

[0075] like Figure 3 As shown, the present invention also provides a production equipment monitoring system based on unattended operation, which is used to implement the above-mentioned production equipment monitoring method based on unattended operation, and the system includes:

[0076] The sensor module is used to collect equipment data of the production equipment. The sensor module sends its own attribute information and the collected equipment data to the analysis module;

[0077] An analysis module stores a conversion function, which is used to convert at least one device data into another device data. The analysis module selects a corresponding conversion function based on the attribute information, inputs part of the device data as input data into the conversion function to calculate and obtain output data, obtains device data of the same type as the output data, and defines it as target data. If the difference between the output data and the target data is greater than a first threshold, the target data is defined as abnormal data, and the production equipment that generates the abnormal data is classified as a faulty device. The analysis module sends the device data of the faulty device to the decision module;

[0078] The decision module is used to analyze the equipment data, generate a solution for the faulty equipment, and send the solution to the display module;

[0079] The display module is used to show the distribution of abnormal data and the corresponding processing solutions.

[0080] The present invention also discloses a computer storage medium, wherein the computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above method.

[0081] In particular, the unattended production equipment monitoring system in this embodiment also has functions such as remote assistance, graded alarm transmission, immediate release of diagnostic suggestions, graded confirmation of equipment abnormality alarms, and generation of a diagnostic decision knowledge base.

[0082] The monitoring system of the present invention can collect and record the equipment operation status change information, realize the one-to-one correspondence between the equipment operation status and the corresponding record, and ensure the objectivity and accuracy of data collection.

[0083] The decision-making module can also provide a basis for maintenance decisions. It can generate maintenance work orders based on alarms, which can be circulated in the system, and can also generate weekly, monthly, and annual reports for maintenance. It can initiate the annual, monthly, and weekly plan approval process for maintenance, and also has a reminder function, automatically determining the scope of lubrication equipment objects, lubricant types, addition quantities, cycles, etc. every day, realizing expiration reminders, and improving equipment reliability.

[0084] The present invention can also communicate data with other control systems, such as a smart factory platform, with RS485 / RS232 communication interface, and has OPC and Modbus communication interface functions.

[0085] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0086] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0088] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring production equipment based on unattended operation, characterized in that: include: The sensor module collects equipment data of the production equipment, and the sensor module sends its own attribute information and the collected equipment data to the analysis module; The analysis module stores a conversion function, and the conversion function is used to convert at least one of the device data into another type of the device data; The analysis module selects the corresponding conversion function based on the attribute information, inputs part of the device data as input data into the conversion function to calculate and obtain output data, and obtains the device data of the same type as the output data, which is defined as target data; If the difference between the output data and the target data is greater than a first threshold, the target data is defined as abnormal data, the production equipment generating the abnormal data is classified as a faulty equipment, and the analysis module sends the equipment data of the faulty equipment to the decision module; The decision module analyzes the device data, generates a processing plan for the faulty device, and sends the processing plan to the display module, which displays the distribution of the abnormal data and the corresponding processing plan; The display module displays the distribution status including the following steps: The display module includes a data association diagram, the data association diagram includes a plurality of nodes, each node represents a type of the device data, and a connecting line is provided between the nodes, the connecting line represents that there is a basic function between the two nodes, and the basic function is used to convert one type of the device data into another type of the device data. The display module marks the node representing the abnormal data with a preset color to display the distribution; Generating the data association graph comprises the following steps: After collecting a preset amount of each type of device data, the analysis module divides the device data into a first data set and a second data set, both of which are normal device data, extracts two types of device data from the first data set to construct the basic function, and if the basic function is successfully constructed, defines the two types of device data as associated data, constructs an initial topology graph, and includes nodes representing the device data, and connects the nodes with the basic function using the connecting lines; Extract the associated data in pairs from the second data set, respectively define them as first data and second data, input the first data into the basic function to obtain the output data corresponding to the second data, calculate the ratio of the second data to the corresponding output data, extract the first data and the second data again, repeat this step until all the data in the second data set are extracted, and use the average value of the ratio as the available value of the basic function; In the initial topology graph, the connection lines corresponding to the basic functions whose available values ​​are less than a second threshold are removed to obtain the data association graph; After the data association graph is generated, the conversion function is generated based on the following steps: A node is extracted from the data association graph and defined as a main node, and other nodes with the connection line to the main node are defined as branch nodes. If one main node has at least two branch nodes, the device data corresponding to the main node in the first data set is extracted as a dependent variable, and the device data corresponding to the branch node in the first data set is extracted as an independent variable, and a comprehensive function is constructed based on the dependent variable and the independent variable. The dependent variable and the independent variable are extracted from the second data set to calculate the optimized value of the comprehensive function; if the optimized value of the comprehensive function is greater than or equal to the available values ​​of all the basic functions under the main node, the comprehensive function is defined as the conversion function; otherwise, the basic function with the largest available value is defined as the conversion function.

2. The method according to claim 1, characterized in that A comparison table is provided in the analysis module, and the comparison table includes the conversion functions. Each conversion function corresponds to an input part and an output part, and the input part and the output part both include the attribute information of the sensor module. After receiving the device data, the analysis module searches for the corresponding conversion function based on the attribute information in combination with the comparison table. After the conversion function outputs the output data, the target data corresponding to the output data is obtained based on the attribute information of the output part in the comparison table.

3. The method according to claim 2, characterized in that When the analysis module uses the conversion function for calculation, if it is detected that there is missing device data, the missing device data is defined as missing data, a node representing the missing data is obtained from the data association graph and defined as a first node, a node connected to the first node and representing the target data is defined as a second node, and according to the conversion function between the first node and the second node, the device data of the second node is converted into the missing data.

4. The method according to claim 1, characterized in that The decision module includes a fault handling text and an analysis model. The analysis model determines the fault type of the production equipment based on the received equipment data, obtains the corresponding processing solution from the fault handling text based on the fault type, and sends the processing solution to the display module.

5. The method according to claim 1, characterized in that The display module displays the processing scheme including the following steps: The display module includes a plant topographic map, in which a three-dimensional model of the production equipment is arranged. The display module changes the three-dimensional model of the faulty equipment to a preset color and displays the treatment plan at the same time.

6. A production equipment monitoring system based on unattended operation, used to implement the method according to any one of claims 1 to 5, characterized in that: include: A sensor module is used to collect equipment data of production equipment, and the sensor module sends its own attribute information and the collected equipment data to the analysis module; The analysis module stores a conversion function, wherein the conversion function is used to convert at least one of the device data into another type of the device data. The analysis module selects the corresponding conversion function based on the attribute information, inputs part of the device data as input data into the conversion function to calculate and obtain output data, obtains the device data of the same type as the output data, and defines it as target data. If the difference between the output data and the target data is greater than a first threshold, the target data is defined as abnormal data, and the production equipment generating the abnormal data is classified as a faulty equipment. The analysis module sends the device data of the faulty equipment to the decision module. After collecting each type of the device data to a preset number, the analysis module divides the device data into a first data set and a second data set, wherein both the first data set and the second data set are normal device data, extracts two types of the device data from the first data set to construct a basic function, and if the basic function is successfully constructed, defines the two types of the device data as associated data, and constructs an initial topological graph, wherein the initial topological graph includes nodes representing the device data, and the nodes with the basic function are connected by connecting lines, and the associated data are extracted from the second data set in pairs, and are defined as first data and second data, respectively. Input the first data into the basic function to obtain the output data corresponding to the second data, calculate the ratio of the second data to the corresponding output data, extract the first data and the second data again, repeat this step until all the data in the second data set are extracted, take the average value of the ratio as the available value of the basic function, remove the connection lines corresponding to the basic functions whose available values ​​are less than the second threshold in the initial topology graph, obtain a data association graph, extract a node from the data association graph and define it as a main node, and define other nodes with the connection lines to the main node as branch nodes. If there are at least two branch nodes for a main node, extract the device data corresponding to the main node in the first data set as the dependent variable, extract the device data corresponding to the branch node in the first data set as the independent variable, construct a comprehensive function based on the dependent variable and the independent variable, extract the dependent variable and the independent variable from the second data set to calculate the optimized value of the comprehensive function, and if the optimized value of the comprehensive function is greater than or equal to the available values ​​of all the basic functions under the main node, define the comprehensive function as the conversion function, otherwise define the basic function with the largest available value as the conversion function; A decision module, used for analyzing the device data, generating a processing plan for the faulty device, and sending the processing plan to the display module; A display module is used to display the distribution of the abnormal data and the corresponding processing scheme. The display module includes the data association diagram, and the data association diagram includes multiple nodes, each node represents a type of the device data, and the connecting lines are set between the nodes. The connecting lines represent that the basic function exists between two nodes, and the basic function is used to convert one type of the device data into another type of the device data. The display module marks the nodes representing the abnormal data with a preset color to display the distribution.

7. A computer storage medium, characterized in that: The computer storage medium stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the method according to any one of claims 1 to 5.

Images