Visualization method and system of pain signals in production process

Abstract

The present application discloses a method and system for visualizing pain signals in a production process, the method comprising: collecting and preprocessing data from multiple data sources in the production process of a target production environment to obtain a standard data stream; analyzing the standard data stream according to pre-configured dimension standards and metrics to obtain a set of production status quantization values ​​for determining whether there is a problem with the production environment; in the case where there is a target production status quantization value indicating that there is a problem with the production environment in the production status quantization value set, determining the target pain signal identification corresponding to each target production status quantization value according to a pre-configured pain signal identification table, switching the signal state corresponding to the target pain signal identification from a normal state to an abnormal state, and rendering the abnormal state through a preset visualization component to display a rendered visualization interface. Therefore, by using the embodiments of the present application, managers can quickly identify abnormal situations while improving production efficiency and product quality.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and system for visualizing pain signals in a production process. Background Art

[0002] As the global manufacturing industry transforms towards Industry 4.0 and smart manufacturing, the monitoring and management of production processes are becoming increasingly complex. This transformation has brought about a highly automated and intelligent production environment, in which machines, equipment, sensors and software systems are interconnected, generating a large amount of production data. These production data include not only real-time data in the production process, but also historical data, forecast data and environmental data, etc., forming a huge data ecosystem.

[0003] In the relevant technology, when processing production data, it usually relies on traditional charts and reports. However, in the modern industrial environment, the amount of data is huge and changes dynamically. The traditional data display method can no longer meet the needs, and it is difficult for managers to quickly identify abnormal situations. In the production process, there is often a lack of effective visual prompts when abnormalities occur. It is difficult for managers to realize the existence of problems in the first time, which leads to further expansion of the problem, thereby reducing production efficiency and product quality. Summary of the invention

[0004] The embodiments of the present application provide a method and system for visualizing pain signals in a production process. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0005] In a first aspect, an embodiment of the present application provides a method for visualizing pain signals during a production process, the method comprising:

[0006] Collect and preprocess data from multiple data sources in the production process of the target production environment to obtain a standard data stream. The multiple data sources include production lines, equipment sensors, and supply chain management systems.

[0007] Analyze the standard data stream according to the pre-configured dimension standards and metric standards to obtain a set of production status quantitative values ​​used to determine whether there are problems in the production environment;

[0008] In the case where there is a target production state quantization value indicating that there is a problem in the production environment in the production state quantization value set, a target pain signal identifier corresponding to each target production state quantization value is determined according to a pre-configured pain signal identifier table, and the pain signal is used to characterize a key performance indicator of the target production environment;

[0009] The signal state corresponding to the target pain signal identifier is switched from a normal state to an abnormal state, and the abnormal state is rendered through a preset visualization component to display a rendered visualization interface.

[0010] Optionally, collect and preprocess data from multiple data sources in the production process of the target production environment to obtain a standard data stream, including:

[0011] Extract data from multiple data sources during the production process of the target production environment;

[0012] Convert the data format and data type of the extracted data;

[0013] Load the converted data into the data warehouse to maintain the real-time and consistency of the data;

[0014] Remove noise, fill missing values, and deduplicate data in the data warehouse to obtain a standard data stream.

[0015] Optionally, each target production status quantified value carries a metric ID;

[0016] According to the pre-configured pain signal identification table, the target pain signal identification corresponding to each target production state quantization value is determined, including:

[0017] Obtaining a pre-configured pain signal identification table, wherein the pre-configured pain signal identification table includes a mapping relationship between a metric ID and a pain signal identification;

[0018] From the mapping relationship, obtain the pain signal identifier corresponding to the metric ID carried by each target production status quantization value;

[0019] The pain signal identifier corresponding to the measurement indicator ID carried by each target production status quantization value is used as the target pain signal identifier corresponding to each target production status quantization value.

[0020] Optionally, the method further includes:

[0021] For the target pain signal indicator that switches to an abnormal state, a detailed alarm record is constructed, and the detailed alarm record includes the occurrence time, signal state, alarm type, alarm content and responsible person;

[0022] Send the alarm details to the early warning terminal through the pre-set alarm notification mechanism;

[0023] Continue to execute the steps of collecting and preprocessing data from multiple data sources in the production process of the target production environment until there is no target production status quantization value in the production status quantization value set indicating that there is a problem with the production environment, and then switch the signal state corresponding to the target pain signal identifier from the abnormal state to the reset state.

[0024] Optionally, the dimension standards include a time dimension, an equipment parameter dimension, and a production location dimension;

[0025] According to the pre-configured dimension standards and metric standards, the standard data stream is analyzed to obtain a set of production status quantitative values ​​used to determine whether there are problems in the production environment, including:

[0026] Map the standard data stream to the time dimension, the equipment parameter dimension, and the production location dimension to classify and group the standard data stream to obtain data in multiple dimensions;

[0027] According to the metric standards, filter out the key data quantitative parameters of each dimension from multiple dimensional data;

[0028] Calculate production efficiency, failure rate, product qualification rate and equipment utilization rate based on key data quantification parameters of each dimension;

[0029] Production efficiency, failure rate, product qualification rate and equipment utilization rate are used as a set of production status quantitative values ​​for determining whether there are problems in the production environment.

[0030] Optionally, the time dimension includes year, month, day, hour, and minute; the equipment parameter dimension includes equipment ID, model, and status; and the production location dimension includes workshop, production line, and workstation;

[0031] Map the standard data stream to the time dimension, equipment parameter dimension, and production location dimension to obtain data in multiple dimensions, including:

[0032] Divide the standard data stream into data of different time periods according to year, month, day, hour and minute;

[0033] Divide the standard data stream into data sets of different devices according to device ID, model, and status;

[0034] Divide the standard data flow into data sets at different locations according to workshops, production lines and workstations;

[0035] The above divided data are grouped so that each group contains data records with the same dimensional features, thereby obtaining multiple groups of dimensional feature data;

[0036] Perform aggregation operations on each set of dimensional feature data to generate summary data for each dimension;

[0037] The summary data of each dimension is taken as multiple dimension data.

[0038] Optionally, based on the metric standard, filter out key data quantitative parameters of each dimension from multiple dimensional data, including:

[0039] Extract the data related to the metric from each dimension data to obtain the target data corresponding to each metric;

[0040] From the target data corresponding to each metric standard, identify and extract the key parameters that affect the metric standard, and obtain the key parameters corresponding to each metric standard;

[0041] Evaluate the importance of the key parameters corresponding to each metric and obtain the evaluation results;

[0042] According to the evaluation results, key parameters in each dimension data whose importance is less than a preset threshold are eliminated to obtain the key data quantitative parameters of each dimension.

[0043] Optionally, the importance of key parameters corresponding to each metric is evaluated to obtain evaluation results, including:

[0044] Multiple regression analysis algorithm was used to establish a multiple regression model;

[0045] Bind the metrics to the dependent variables of the multiple regression model, and bind the key parameters corresponding to each metric to the independent variables of the multiple regression model;

[0046] The least squares regression method is used to regress the multivariate regression model that binds the metrics and the key parameters corresponding to each metric to obtain the linear relationship between the independent variables and the dependent variables;

[0047] Based on the linear relationship between the independent variables and the dependent variable, the standardized regression coefficient is calculated;

[0048] Through the standardized regression coefficient, determine the contribution of the independent variable to the dependent variable;

[0049] The contribution of the independent variable to the dependent variable is taken as the evaluation result.

[0050] Optionally, from the target data corresponding to each metric standard, key parameters that affect the metric standard are identified and extracted to obtain the key parameters corresponding to each metric standard, including:

[0051] Extract multiple original parameters existing in the target data corresponding to each metric;

[0052] Input multiple original parameters existing in the target data corresponding to each metric into the preset sliding window one by one to match the similarity with the preset high-impact parameters in the preset sliding window, where the preset high-impact parameters are pre-configured based on experience data;

[0053] From multiple original parameters existing in the target data corresponding to each metric, identify and eliminate original parameters whose similarity is less than a preset threshold;

[0054] The remaining original parameters among the multiple original parameters existing in the target data corresponding to each metric after elimination are used as the key parameters corresponding to each metric.

[0055] In a second aspect, an embodiment of the present application provides a pain signal visualization system for a production process, the system comprising:

[0056] A data preprocessing module is used to collect and preprocess data from multiple data sources in the production process of the target production environment to obtain a standard data stream. The multiple data sources include production lines, equipment sensors, and supply chain management systems;

[0057] The data stream analysis module is used to analyze the standard data stream according to the pre-configured dimension standards and metric standards to obtain a set of production status quantitative values ​​used to determine whether there are problems in the production environment;

[0058] A pain signal identification determination module is used to determine the target pain signal identification corresponding to each target production state quantization value according to a pre-configured pain signal identification table when there is a target production state quantization value indicating that there is a problem in the production environment in the production state quantization value set, and the pain signal is used to characterize the key performance indicator of the target production environment;

[0059] The state switching module is used to switch the signal state corresponding to the target pain signal identifier from a normal state to an abnormal state, and render the abnormal state through a preset visualization component to display the rendered visualization interface.

[0060] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0061] In an embodiment of the present application, on the one hand, according to the pre-configured dimensional standards and metrics, the standard data stream is analyzed to obtain a set of production status quantization values ​​used to determine whether there are problems in the production environment. The pre-configured dimensional standards and metrics provide a set of standard production status indicators for data analysis, which can dynamically analyze massive amounts of data, allowing managers to quickly identify and respond to problems in the production environment, thereby improving the efficiency and response speed of production monitoring; on the other hand, according to the pre-configured pain signal identification table, the target pain signal identification corresponding to each target production status quantization value is determined. Using the pre-configured pain signal identification table, the system can determine the pain signal identification corresponding to each target production status quantization value. When the production status quantization value indicates that there is a problem with the production environment, the system can automatically switch from a normal state to an abnormal state, and display these anomalies through a visual interface to trigger an early warning. This method significantly improves the accuracy of anomaly detection and the timeliness of response.

[0062] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0064] Figure 1 It is a schematic diagram of a process of visualizing pain signals in a production process provided by an embodiment of the present application;

[0065] Figure 2 It is a data schematic diagram of a standardized data volume flow provided by this application;

[0066] Figure 3 It is a data representation intent of a mapping relationship provided by this application;

[0067] Figure 4 It is a structural schematic diagram of a pain signal visualization system for a production process provided by the present application;

[0068] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The following description and the accompanying drawings sufficiently illustrate specific embodiments of the present application to enable those skilled in the art to practice them.

[0070] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0071] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of systems and methods consistent with some aspects of the present application as detailed in the attached claims.

[0072] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0073] The present application provides a method and system for visualizing pain signals in a production process to solve the problems existing in the above-mentioned related technical problems. In an embodiment of the present application, on the one hand, according to the pre-configured dimensional standards and metric standards, the standard data stream is analyzed to obtain a set of production status quantization values ​​for determining whether there is a problem in the production environment. The pre-configured dimensional standards and metric standards provide a set of standard production status indicators for data analysis, which can dynamically analyze massive amounts of data, so that managers can quickly identify and respond to problems in the production environment, thereby improving the efficiency and response speed of production monitoring; on the other hand, according to the pre-configured pain signal identification table, the target pain signal identification corresponding to each target production status quantization value is determined. Using the pre-configured pain signal identification table, the system can determine the pain signal identification corresponding to each target production status quantization value. When the production status quantization value indicates that there is a problem in the production environment, the system can automatically switch from a normal state to an abnormal state, and display these anomalies through a visual interface to trigger an early warning. This method significantly improves the accuracy of anomaly detection and the timeliness of response, and is described in detail below using an exemplary embodiment.

[0074] The following will be combined with the attached Figure 1 -Attached Figure 3 , a method for visualizing pain signals in a production process provided by an embodiment of the present application is introduced in detail. The method can be implemented by a computer program and can be run on a visualizing pain signal system in a production process based on a von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0075] See also Figure 1 , which is a flowchart of a method for visualizing pain signals in a production process provided by the present application embodiment, and is applied to a server. Figure 1 As shown, the method of the embodiment of the present application may include the following steps:

[0076] S101, collecting and preprocessing data from multiple data sources in the production process of the target production environment to obtain a standard data stream, where the multiple data sources include production lines, equipment sensors, and supply chain management systems;

[0077] Among them, the target production environment is the specific production site that needs to be monitored and data analyzed, such as a factory workshop, an automated assembly line or a specific work area. The production process refers to the entire manufacturing process from raw material input to finished product output in the target production environment, including various stages such as processing, assembly, inspection, and packaging. Multiple data sources refer to different sources that can provide the required data in the production process. These sources may include physical equipment, software systems, or manual input. The production line refers to the combination of equipment and facilities that actually carry out production, such as machine tools, conveyor belts, robots, etc., which are directly involved in the manufacture of products. Equipment sensors refer to sensors installed on production line equipment, which are used to collect data such as equipment operating status and performance indicators, such as temperature, pressure, speed, etc. The supply chain management system is a software system used to manage supply chain activities. It involves raw material procurement, inventory management, logistics distribution, etc., and can provide supply chain-related data. Standard data stream refers to a set of data that has been preprocessed and meets specific format and quality requirements. These data can be further analyzed and processed.

[0078] In some embodiments of the present application, sensors and data acquisition systems are deployed in the target production environment to collect real-time status data of equipment on the production line, such as temperature, vibration, current, etc. The equipment control system of the production line is integrated with the supply chain management system to achieve data interoperability and collect order information, inventory levels, material flow and other data.

[0079] When the target production environment starts production, collect and preprocess the raw data from multiple data sources during the production process of the target production environment, clean the collected raw data, remove invalid or erroneous data points, and perform data standardization processing such as unit conversion and data normalization. Integrate information from different data sources in the database or data warehouse, and establish a standard data storage format for the data in the data warehouse to facilitate subsequent access and analysis.

[0080] In the embodiment of the present application, the specific process of collecting and preprocessing data from multiple data sources in the production process of the target production environment to obtain a standard data stream includes: extracting data from multiple data sources in the production process of the target production environment; converting the data format and data type of the extracted data; loading the converted data into a data warehouse to maintain the real-time and consistency of the data; removing noise, filling missing values, and deduplicating the data in the data warehouse to obtain a standard data stream. Standard data streams are, for example, Figure 2 shown.

[0081] S102, analyzing the standard data stream according to the pre-configured dimension standard and metric standard to obtain a set of production status quantitative values ​​for determining whether there is a problem in the production environment;

[0082] Among them, the dimension standard is the classification standard that has been set before data analysis, which is used to group data according to different attributes or characteristics. The dimension can be time (such as date, hour), equipment type, and production location number. The metric standard is used to filter out key data quantitative parameters. The production status quantification value refers to converting the production status into a numerical form for easy comparison and evaluation. For example, production efficiency can be quantified by the amount of output per unit time, and the failure rate can be expressed by the frequency of failures.

[0083] Among them, the dimensional standards include time dimension, equipment parameter dimension and production location dimension.

[0084] In an embodiment of the present application, according to pre-configured dimensional standards and metric standards, the standard data stream is analyzed to obtain a specific process of obtaining a set of production status quantization values ​​for determining whether there is a problem with the production environment, including: mapping the standard data stream to the time dimension, the equipment parameter dimension, and the production location dimension to classify and group the standard data stream to obtain multiple dimensional data; according to the metric standard, from the multiple dimensional data, the key data quantization parameters of each dimension are screened out; according to the key data quantization parameters of each dimension, the production efficiency, failure rate, product qualification rate, and equipment utilization rate are calculated; and the production efficiency, failure rate, product qualification rate, and equipment utilization rate are used as a set of production status quantization values ​​for determining whether there is a problem with the production environment.

[0085] In some embodiments, in order to organize data according to different categories, the preprocessed and standardized standard data stream is mapped to different dimensions, such as time dimension (which may include date, hour, etc.), equipment parameter dimension (which may include equipment type, model, etc.), production location dimension (which may include workshop, production line, etc.), and the mapped data is classified and grouped according to these dimensions to form multiple dimensional data. According to the metric standard (i.e., the predefined standard for evaluating production performance), key data quantitative parameters are screened out from the data of each dimension. These parameters are important indicators for evaluating production status and may include output, operating time, downtime, etc. Specific production performance indicators such as production efficiency, failure rate, product qualification rate, and equipment utilization are calculated using the screened key data quantitative parameters.

[0086] Among them, the time dimension includes year, month, day, hour, and minute; the equipment parameter dimension includes equipment ID, model, and status; and the production location dimension includes workshop, production line, and workstation.

[0087] In some embodiments of the present application, based on mapping the standard data stream to the time dimension, the equipment parameter dimension and the production location dimension, the specific process of obtaining multiple dimensional data includes: dividing the standard data stream into data of different time periods according to year, month, day, hour and minute; dividing the standard data stream into data sets of different devices according to equipment ID, model and status; dividing the standard data stream into data sets of different locations according to workshops, production lines and workstations; grouping the above divided data so that each group contains data records with the same dimensional features, and obtaining multiple groups of dimensional feature data; performing aggregation operations on each group of dimensional feature data to generate summary data of each dimension; and using the summary data of each dimension as multiple dimensional data.

[0088] In some embodiments of the present application, according to the metric standard, the specific process of screening out the key data quantification parameters of each dimension from multiple dimensional data includes: extracting data related to the metric standard from each dimensional data to obtain the target data corresponding to each metric standard; identifying and extracting the key parameters that affect the metric standard from the target data corresponding to each metric standard to obtain the key parameters corresponding to each metric standard; performing importance evaluation on the key parameters corresponding to each metric standard to obtain evaluation results; according to the evaluation results, eliminating the key parameters in each dimensional data whose importance is less than a preset threshold to obtain the key data quantification parameters of each dimension.

[0089] In some embodiments of the present application, an importance assessment is performed on the key parameters corresponding to each metric standard, and the specific process of obtaining the assessment results includes: using a multivariate regression analysis algorithm to establish a multivariate regression model; binding the metric standard to the dependent variable of the multivariate regression model, and binding the key parameters corresponding to each metric standard to the independent variable of the multivariate regression model; using the least squares method to regress the multivariate regression model that binds the metric standard and the key parameters corresponding to each metric standard to obtain a linear relationship between the independent variable and the dependent variable; calculating the standard regression coefficient based on the linear relationship between the independent variable and the dependent variable; determining the contribution of the independent variable to the dependent variable through the standard regression coefficient; and using the contribution of the independent variable to the dependent variable as the assessment result.

[0090] Specifically, from the target data corresponding to each metric standard, key parameters that affect the metric standard are identified and extracted, and the specific process of obtaining the key parameters corresponding to each metric standard includes: extracting multiple original parameters existing in the target data corresponding to each metric standard; inputting the multiple original parameters existing in the target data corresponding to each metric standard into a preset sliding window one by one to match the similarity with the preset high-impact parameters in the preset sliding window, and the preset high-impact parameters are pre-configured through empirical data; from the multiple original parameters existing in the target data corresponding to each metric standard, identifying and eliminating the original parameters whose similarity is less than a preset threshold; and using the remaining original parameters in the multiple original parameters existing in the target data corresponding to each metric standard after elimination as the key parameters corresponding to each metric standard.

[0091] In an embodiment of the present application, the pre-configured dimension standards and metric standards are dynamically selected through a preset dynamic library, providing a user-friendly interface that allows users to dynamically configure and adjust dimensions and metrics by dragging, selecting, etc. to meet visualization requirements in different scenarios.

[0092] S103, when there is a target production state quantization value indicating that there is a problem in the production environment in the production state quantization value set, determine the target pain signal identifier corresponding to each target production state quantization value according to a pre-configured pain signal identifier table, where the pain signal is used to characterize a key performance indicator of the target production environment;

[0093] The pre-configured pain signal identification table is a pre-configured table or database for storing identification information of pain signals, such as Figure 3 As shown. Pain signals are signals used to characterize key performance indicators in a production environment, and they are usually used for business early warning. The target pain signal identifier is used to trigger a specific early warning mechanism to notify relevant personnel or systems.

[0094] Each target production status quantified value carries a metric ID.

[0095] In an embodiment of the present application, the specific process of determining the target pain signal identification corresponding to each target production status quantization value according to a preconfigured pain signal identification table includes: obtaining a preconfigured pain signal identification table, the preconfigured pain signal identification table including a mapping relationship between a metric ID and a pain signal identification; from the mapping relationship, obtaining the pain signal identification corresponding to the metric ID carried by each target production status quantization value; and using the pain signal identification corresponding to the metric ID carried by each target production status quantization value as the target pain signal identification corresponding to each target production status quantization value.

[0096] S104, switching the signal state corresponding to the target pain signal identifier from a normal state to an abnormal state, and rendering the abnormal state through a preset visualization component to display a rendered visualization interface.

[0097] In some embodiments of the present application, the signal state corresponding to the target pain signal identifier can be switched from a normal state to an abnormal state, and the abnormal state can be rendered through a preset visualization component to display a rendered visualization interface.

[0098] Furthermore, for the target pain signal identifier that switches to an abnormal state, an alarm detail record is constructed, and the alarm detail record includes the occurrence time, signal state, alarm type, alarm content, and responsible person; the alarm detail record is sent to the early warning terminal through a pre-set alarm notification mechanism; the steps of collecting and pre-processing data from multiple data sources in the production process of the target production environment are continued until the target production state quantization value indicating that there is a problem with the production environment does not exist in the production state quantization value set, and the signal state corresponding to the target pain signal identifier is switched from the abnormal state to the reset state. The pre-set alarm notification mechanism includes pop-up windows, emails, text messages, and other methods.

[0099] Among them, the dashboard of the visualization component in this application provides various types of dashboard components, including line charts, bar charts, pie charts, scatter charts, radar charts, etc. Users can choose the appropriate chart type according to their needs to display the corresponding signal status of the pain signal.

[0100] In an embodiment of the present application, on the one hand, according to the pre-configured dimensional standards and metrics, the standard data stream is analyzed to obtain a set of production status quantization values ​​used to determine whether there are problems in the production environment. The pre-configured dimensional standards and metrics provide a set of standard production status indicators for data analysis, which can dynamically analyze massive amounts of data, allowing managers to quickly identify and respond to problems in the production environment, thereby improving the efficiency and response speed of production monitoring; on the other hand, according to the pre-configured pain signal identification table, the target pain signal identification corresponding to each target production status quantization value is determined. Using the pre-configured pain signal identification table, the system can determine the pain signal identification corresponding to each target production status quantization value. When the production status quantization value indicates that there is a problem with the production environment, the system can automatically switch from a normal state to an abnormal state, and display these anomalies through a visual interface to trigger an early warning. This method significantly improves the accuracy of anomaly detection and the timeliness of response.

[0101] The following is a system embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the system embodiment of the present application, please refer to the method embodiment of the present application.

[0102] See also Figure 4, which shows a schematic diagram of the structure of a pain signal visualization system for a production process provided by an exemplary embodiment of the present application. The pain signal visualization system for a production process can be implemented as all or part of an electronic device through software, hardware, or a combination of both. The system 1 includes a data preprocessing module 10, a data flow analysis module 20, a pain signal identification determination module 30, and a state switching module 40.

[0103] A data preprocessing module 10 is used to collect and preprocess data from multiple data sources in the production process of the target production environment to obtain a standard data stream, where the multiple data sources include production lines, equipment sensors, and supply chain management systems;

[0104] The data flow analysis module 20 is used to analyze the standard data flow according to the pre-configured dimension standard and metric standard to obtain a set of production status quantitative values ​​for determining whether there is a problem in the production environment;

[0105] The pain signal identification determination module 30 is used to determine the target pain signal identification corresponding to each target production state quantization value according to a pre-configured pain signal identification table when there is a target production state quantization value indicating that there is a problem in the production environment in the production state quantization value set, and the pain signal is used to characterize the key performance indicator of the target production environment;

[0106] The state switching module 40 is used to switch the signal state corresponding to the target pain signal identifier from a normal state to an abnormal state, and render the abnormal state through a preset visualization component to display a rendered visualization interface.

[0107] It should be noted that the pain signal visualization system for the production process provided by the above embodiment only uses the division of the above functional modules as an example when executing the pain signal visualization method for the production process. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the equipment is divided into different functional modules to complete all or part of the functions described above. In addition, the pain signal visualization system for the production process provided by the above embodiment and the pain signal visualization method for the production process belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0108] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0109] In an embodiment of the present application, on the one hand, according to the pre-configured dimensional standards and metrics, the standard data stream is analyzed to obtain a set of production status quantization values ​​used to determine whether there are problems in the production environment. The pre-configured dimensional standards and metrics provide a set of standard production status indicators for data analysis, which can dynamically analyze massive amounts of data, allowing managers to quickly identify and respond to problems in the production environment, thereby improving the efficiency and response speed of production monitoring; on the other hand, according to the pre-configured pain signal identification table, the target pain signal identification corresponding to each target production status quantization value is determined. Using the pre-configured pain signal identification table, the system can determine the pain signal identification corresponding to each target production status quantization value. When the production status quantization value indicates that there is a problem with the production environment, the system can automatically switch from a normal state to an abnormal state, and display these anomalies through a visual interface to trigger an early warning. This method significantly improves the accuracy of anomaly detection and the timeliness of response.

[0110] The present application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the method for visualizing pain signals in the production process provided by the above-mentioned various method embodiments.

[0111] The present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method for visualizing pain signals in the production process of each of the above-mentioned method embodiments.

[0112] See also Figure 5 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0113] The communication bus 1002 is used to realize the connection and communication between these components.

[0114] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0115] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0116] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0117] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may also be optionally at least one storage system located away from the aforementioned processor 1001. As Figure 5 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a pain signal visualization application for the production process.

[0118] exist Figure 5In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the pain signal visualization application of the production process stored in the memory 1005, and specifically perform the following operations:

[0119] Collect and preprocess data from multiple data sources in the production process of the target production environment to obtain a standard data stream. The multiple data sources include production lines, equipment sensors, and supply chain management systems.

[0120] Analyze the standard data stream according to the pre-configured dimension standards and metric standards to obtain a set of production status quantitative values ​​used to determine whether there are problems in the production environment;

[0121] In the case where there is a target production state quantization value indicating that there is a problem in the production environment in the production state quantization value set, a target pain signal identifier corresponding to each target production state quantization value is determined according to a pre-configured pain signal identifier table, and the pain signal is used to characterize a key performance indicator of the target production environment;

[0122] The signal state corresponding to the target pain signal identifier is switched from a normal state to an abnormal state, and the abnormal state is rendered through a preset visualization component to display a rendered visualization interface.

[0123] In one embodiment, when the processor 1001 collects and preprocesses data from multiple data sources in the production process of the target production environment to obtain a standard data stream, the processor 1001 specifically performs the following operations:

[0124] Extract data from multiple data sources during the production process of the target production environment;

[0125] Convert the data format and data type of the extracted data;

[0126] Load the converted data into the data warehouse to maintain the real-time and consistency of the data;

[0127] Remove noise, fill missing values, and deduplicate data in the data warehouse to obtain a standard data stream.

[0128] In one embodiment, when the processor 1001 determines the target pain signal identifier corresponding to each target production status quantization value according to the pre-configured pain signal identifier table, the following operations are specifically performed:

[0129] Obtaining a pre-configured pain signal identification table, wherein the pre-configured pain signal identification table includes a mapping relationship between a metric ID and a pain signal identification;

[0130] From the mapping relationship, obtain the pain signal identifier corresponding to the metric ID carried by each target production status quantization value;

[0131] The pain signal identifier corresponding to the measurement indicator ID carried by each target production status quantization value is used as the target pain signal identifier corresponding to each target production status quantization value.

[0132] In one embodiment, the processor 1001 further performs the following operations:

[0133] For the target pain signal indicator that switches to an abnormal state, a detailed alarm record is constructed, and the detailed alarm record includes the occurrence time, signal state, alarm type, alarm content and responsible person;

[0134] Send the alarm details to the early warning terminal through the pre-set alarm notification mechanism;

[0135] Continue to execute the steps of collecting and preprocessing data from multiple data sources in the production process of the target production environment until there is no target production status quantization value in the production status quantization value set indicating that there is a problem with the production environment, and then switch the signal state corresponding to the target pain signal identifier from the abnormal state to the reset state.

[0136] In one embodiment, when the processor 1001 analyzes the standard data stream according to the pre-configured dimension standard and metric standard to obtain a set of production status quantitative values ​​for determining whether there is a problem in the production environment, the processor 1001 specifically performs the following operations:

[0137] Map the standard data stream to the time dimension, the equipment parameter dimension, and the production location dimension to classify and group the standard data stream to obtain data in multiple dimensions;

[0138] According to the metric standards, filter out the key data quantitative parameters of each dimension from multiple dimensional data;

[0139] Calculate production efficiency, failure rate, product qualification rate and equipment utilization rate based on key data quantification parameters of each dimension;

[0140] Production efficiency, failure rate, product qualification rate and equipment utilization rate are used as a set of production status quantitative values ​​for determining whether there are problems in the production environment.

[0141] In one embodiment, when the processor 1001 maps the standard data stream to the time dimension, the equipment parameter dimension, and the production location dimension to obtain multiple dimensional data, the processor 1001 specifically performs the following operations:

[0142] Divide the standard data stream into data of different time periods according to year, month, day, hour and minute;

[0143] Divide the standard data stream into data sets of different devices according to device ID, model, and status;

[0144] Divide the standard data flow into data sets at different locations according to workshops, production lines and workstations;

[0145] The above divided data are grouped so that each group contains data records with the same dimensional features, thereby obtaining multiple groups of dimensional feature data;

[0146] Perform aggregation operations on each set of dimensional feature data to generate summary data for each dimension;

[0147] The summary data of each dimension is taken as multiple dimension data.

[0148] In one embodiment, when the processor 1001 performs the following operations when filtering out the key data quantification parameters of each dimension from the multiple dimensional data according to the metric standard:

[0149] Extract the data related to the metric from each dimension data to obtain the target data corresponding to each metric;

[0150] From the target data corresponding to each metric standard, identify and extract the key parameters that affect the metric standard, and obtain the key parameters corresponding to each metric standard;

[0151] Evaluate the importance of the key parameters corresponding to each metric and obtain the evaluation results;

[0152] According to the evaluation results, key parameters in each dimension data whose importance is less than a preset threshold are eliminated to obtain the key data quantitative parameters of each dimension.

[0153] In one embodiment, when the processor 1001 performs importance evaluation on the key parameters corresponding to each metric standard and obtains the evaluation result, the processor 1001 specifically performs the following operations:

[0154] Multiple regression analysis algorithm was used to establish a multiple regression model;

[0155] Bind the metrics to the dependent variables of the multiple regression model, and bind the key parameters corresponding to each metric to the independent variables of the multiple regression model;

[0156] The least squares regression method is used to regress the multivariate regression model that binds the metrics and the key parameters corresponding to each metric to obtain the linear relationship between the independent variables and the dependent variables;

[0157] Based on the linear relationship between the independent variables and the dependent variable, the standardized regression coefficient is calculated;

[0158] Through the standardized regression coefficient, the contribution of the independent variable to the dependent variable is determined;

[0159] The contribution of the independent variable to the dependent variable is taken as the evaluation result.

[0160] In one embodiment, when the processor 1001 identifies and extracts the key parameters that affect the metric from the target data corresponding to each metric to obtain the key parameters corresponding to each metric, the processor 1001 specifically performs the following operations:

[0161] Extract multiple original parameters existing in the target data corresponding to each metric;

[0162] Input multiple original parameters existing in the target data corresponding to each metric into the preset sliding window one by one to match the similarity with the preset high-impact parameters in the preset sliding window, where the preset high-impact parameters are pre-configured based on experience data;

[0163] From multiple original parameters existing in the target data corresponding to each metric, identify and eliminate original parameters whose similarity is less than a preset threshold;

[0164] The remaining original parameters among the multiple original parameters existing in the target data corresponding to each metric after elimination are used as the key parameters corresponding to each metric.

[0165] In an embodiment of the present application, on the one hand, according to the pre-configured dimensional standards and metrics, the standard data stream is analyzed to obtain a set of production status quantization values ​​used to determine whether there are problems in the production environment. The pre-configured dimensional standards and metrics provide a set of standard production status indicators for data analysis, which can dynamically analyze massive amounts of data, allowing managers to quickly identify and respond to problems in the production environment, thereby improving the efficiency and response speed of production monitoring; on the other hand, according to the pre-configured pain signal identification table, the target pain signal identification corresponding to each target production status quantization value is determined. Using the pre-configured pain signal identification table, the system can determine the pain signal identification corresponding to each target production status quantization value. When the production status quantization value indicates that there is a problem with the production environment, the system can automatically switch from a normal state to an abnormal state, and display these anomalies through a visual interface to trigger an early warning. This method significantly improves the accuracy of anomaly detection and the timeliness of response.

[0166] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program for visualizing the pain signals in the production process can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the embodiments of the above-mentioned methods. The storage medium of the program for visualizing the pain signals in the production process can be a disk, an optical disk, a read-only storage memory, or a random access storage memory, etc.

[0167] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for visualizing pain signals in a production process, characterized in that: The method comprises: Collect and preprocess data from multiple data sources in the production process of the target production environment to obtain a standard data stream, wherein the multiple data sources include production lines, equipment sensors, and supply chain management systems; According to the pre-configured dimension standards and metric standards, the standard data stream is analyzed to obtain a set of production status quantitative values ​​for determining whether there is a problem in the production environment; wherein, The dimension standards include time dimension, equipment parameter dimension and production location dimension; The step of analyzing the standard data stream according to the pre-configured dimension standard and metric standard to obtain a set of production status quantization values ​​for determining whether there is a problem in the production environment includes: Mapping the standard data stream to the time dimension, the equipment parameter dimension, and the production location dimension to classify and group the standard data stream to obtain multiple dimensional data; According to the metric standard, from the multiple dimensional data, filter out key data quantitative parameters of each dimension; Calculate production efficiency, failure rate, product qualification rate and equipment utilization rate based on the key data quantitative parameters of each dimension; The production efficiency, failure rate, product qualification rate and equipment utilization rate are used as a set of production status quantitative values ​​for determining whether there is a problem in the production environment; In the case where there is a target production state quantization value indicating that there is a problem with the production environment in the production state quantization value set, a target pain signal identifier corresponding to each target production state quantization value is determined according to a pre-configured pain signal identifier table, and the pain signal is used to characterize the key performance indicator of the target production environment; wherein, Each target production status quantified value carries a metric ID; The step of determining the target pain signal identifier corresponding to each target production state quantization value according to the pre-configured pain signal identifier table includes: Acquire a pre-configured pain signal identification table, wherein the pre-configured pain signal identification table includes a mapping relationship between a metric ID and a pain signal identification; From the mapping relationship, obtain the pain signal identifier corresponding to the measurement indicator ID carried by each target production status quantization value; Using the pain signal identifier corresponding to the measurement indicator ID carried by each target production state quantization value as the target pain signal identifier corresponding to each target production state quantization value; The signal state corresponding to the target pain signal identifier is switched from a normal state to an abnormal state, and the abnormal state is rendered through a preset visualization component to display a rendered visualization interface.

2. The method according to claim 1, characterized in that The collecting and preprocessing of data from multiple data sources in the production process of the target production environment to obtain a standard data stream includes: Extracting data from multiple data sources during the production process of the target production environment; Convert the data format and data type of the extracted data; Load the converted data into the data warehouse to maintain the real-time and consistency of the data; Remove noise, fill missing values, and deduplicate data in the data warehouse to obtain a standard data stream.

3. The method according to claim 1, characterized in that The method further comprises: For the target pain signal identifier switched to an abnormal state, construct an alarm detail record, wherein the alarm detail record includes the occurrence time, signal state, alarm type, alarm content and responsible person; Sending the alarm details to the early warning terminal through a preset alarm notification mechanism; Continue to execute the steps of collecting and preprocessing data from multiple data sources in the production process of the target production environment until there is no target production status quantization value in the production status quantization value set indicating that there is a problem with the production environment, and then switch the signal state corresponding to the target pain signal identifier from the abnormal state to the reset state.

4. The method according to claim 1, characterized in that: The time dimension includes year, month, day, hour, and minute; the equipment parameter dimension includes equipment ID, model, and status; and the production location dimension includes workshop, production line, and workstation; The standard data stream is mapped to the time dimension, the equipment parameter dimension and the production location dimension to obtain multiple dimensional data, including: Divide the standard data stream into data of different time periods according to the year, month, day, hour and minute; Divide the standard data stream into data sets of different devices according to the device ID, model, and status; Dividing the standard data stream into data sets at different locations according to the workshop, production line and workstation; The above divided data are grouped so that each group contains data records with the same dimensional features, thereby obtaining multiple groups of dimensional feature data; Perform aggregation operations on each set of dimensional feature data to generate summary data for each dimension; The summary data of each dimension is used as a plurality of dimensional data.

5. The method according to claim 1, characterized in that The step of screening out key data quantification parameters of each dimension from the multiple dimensional data according to the metric standard includes: Extracting data related to the metric from each dimension data to obtain target data corresponding to each metric; From the target data corresponding to each metric standard, identifying and extracting key parameters that have an impact on the metric standard, to obtain the key parameters corresponding to each metric standard; Performing importance evaluation on key parameters corresponding to each metric to obtain evaluation results; According to the evaluation results, key parameters in each dimension data whose importance is less than a preset threshold are eliminated to obtain quantitative parameters of key data in each dimension.

6. The method according to claim 5, characterized in that The importance evaluation of the key parameters corresponding to each metric standard is performed to obtain an evaluation result, including: Multiple regression analysis algorithm was used to establish a multiple regression model; Binding the metric to the dependent variable of the multiple regression model, and binding the key parameter corresponding to each metric to the independent variable of the multiple regression model; A multivariate regression model that binds the metric and the key parameters corresponding to each metric is regressed using the least squares method to obtain a linear relationship between the independent variable and the dependent variable; Calculate the standardized regression coefficient based on the linear relationship between the independent variable and the dependent variable; Determining the contribution of the independent variable to the dependent variable through the standard regression coefficient; The contribution of the independent variable to the dependent variable is taken as the evaluation result.

7. The method according to claim 5, characterized in that The step of identifying and extracting key parameters that have an impact on the metric from the target data corresponding to each metric to obtain the key parameters corresponding to each metric includes: Extracting a plurality of original parameters existing in the target data corresponding to each metric standard; Inputting multiple original parameters existing in the target data corresponding to each metric into a preset sliding window one by one to match the similarity with the preset high-impact parameters in the preset sliding window, wherein the preset high-impact parameters are pre-configured by empirical data; From the plurality of original parameters existing in the target data corresponding to each metric standard, identifying and eliminating the original parameters whose similarity is less than a preset threshold; The remaining original parameters among the multiple original parameters existing in the target data corresponding to each metric standard after elimination are used as the key parameters corresponding to each metric standard.

8. A pain signal visualization system for a production process, using the method according to any one of claims 1 to 7, characterized in that: The system comprises: A data preprocessing module, used to collect and preprocess data from multiple data sources in the production process of the target production environment to obtain a standard data stream, wherein the multiple data sources include production lines, equipment sensors, and supply chain management systems; A data flow analysis module, used to analyze the standard data flow according to pre-configured dimension standards and metric standards, and obtain a set of production status quantitative values ​​for determining whether there is a problem in the production environment; a pain signal identification determination module, configured to determine, when there is a target production state quantization value indicating that there is a problem with the production environment in the production state quantization value set, a target pain signal identification corresponding to each target production state quantization value according to a pre-configured pain signal identification table, wherein the pain signal is used to characterize a key performance indicator of the target production environment; The state switching module is used to switch the signal state corresponding to the target pain signal identifier from a normal state to an abnormal state, and render the abnormal state through a preset visualization component to display a rendered visualization interface.

Images