An intelligent andon monitoring method and system based on digital workstation production line

Abstract

The present invention discloses an intelligent andon monitoring method and system based on a digital workstation production line, which belongs to the technical field of production management, and comprises an expectation module, an andon monitoring module and an expectation monitoring module; the expectation module is used for users to set monitoring expectations, analyze the monitoring expectations, obtain expected display data, display the expected display data to users, and determine target expectations; optimization processing is performed according to the expected display data corresponding to the target expectations; the andon monitoring module is used for production monitoring processing, and obtains corresponding monitoring processing record data; the expectation monitoring module is used for target expectation monitoring according to the monitoring processing record data, and determines expected abnormal data; identifies the target single expectation corresponding to the expected abnormal data; determines the optimization method according to the target single expectation and the expected abnormal data; integrates the optimization method, the target single expectation and the expected abnormal data into optimization adjustment data, and the user performs optimization adjustment according to the optimization adjustment data.

Description

Technical Field

[0001] The present invention belongs to the technical field of production management, and specifically relates to an intelligent andon monitoring method and system based on a digital workstation production line. Background Art

[0002] In the current manufacturing industry, with the accelerated advancement of digital transformation, enterprises have an increasingly urgent need for intelligent and refined management of production processes. However, many companies face the challenge of insufficient professional capabilities in the process of achieving this goal. Especially in the management of digital workstation production lines, due to the lack of effective monitoring methods and management tools, companies often find it difficult to grasp the operating status of the production line in real time, and it is difficult to discover and solve potential problems in a timely manner, resulting in a series of problems such as low production efficiency, waste of resources, and unstable product quality.

[0003] To solve this problem, enterprises began to explore intelligent andon monitoring systems based on digital workstation production lines. This system integrates advanced sensor technology, Internet of Things technology, big data analysis, and artificial intelligence algorithms to achieve real-time monitoring and intelligent early warning of each link on the production line. Enterprises can set corresponding monitoring indicators and processing expectations based on their own production needs and expectations. These expectations not only cover the overall operating efficiency of the production line, product quality and other macro aspects, but also go deep into the details of each workstation and each process.

[0004] However, in actual applications, due to the lack of professional personnel in some enterprises, the smart andon monitoring system cannot be adjusted in time according to enterprise needs, which leads to poor flexibility and affects the enterprise's usage experience. Therefore, how to better serve enterprises to use the smart andon monitoring system and realize intelligent management and control of production has become a problem that needs to be solved at present. Summary of the invention

[0005] In order to solve the problems existing in the above-mentioned solutions, the present invention provides an intelligent andon monitoring method and system based on a digital workstation production line.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An intelligent andon monitoring system based on a digital workstation production line includes an expectation module, an andon monitoring module and an expectation monitoring module; The expectation module is used for the user to set monitoring expectations, analyze the monitoring expectations, obtain expected display data, display the expected display data to the user, and determine the target expectation; and optimize the expected display data corresponding to the target expectation.

[0007] Further, the monitoring expectation setting method includes: Acquire the production line information of the user; match the corresponding historical production expectation data according to the production line information, and count various historical monitoring expectations according to the historical production expectation data; classify the historical monitoring expectations to obtain several expectation categories, and set corresponding expectation items for the expectation categories; According to the historical monitoring expectations corresponding to the expectation items, a potential expectation set is set, wherein the potential expectation set is composed of corresponding potential expectations; and a user expectation library is established according to the expectation items and the potential expectation set; An expectation auxiliary setting interface is generated according to the user expectation library, and the user sets monitoring expectations according to the expectation auxiliary setting interface, wherein the monitoring expectations are composed of individual expectations of various expectation items.

[0008] Furthermore, the method for generating the auxiliary setting interface is expected to include: Identify potential expectations according to the user expectation library, and obtain historical production monitoring data corresponding to the potential expectations; set the difficulty value and effect value of the potential expectations according to the historical production monitoring data; The priority value of the potential expectation is calculated according to the priority formula, and the priority formula is: YA=b 1 ×XG-b 2 ×100×ND; Where: YA is the priority value; b 1 , b 2 They are all proportional coefficients, and their value range is 0 1 ≤1,0 2 ≤1; XG is the effect value; ND is the difficulty value; Sorting the potential expectations in the potential expectation set in descending order of priority values ​​to obtain an expected sequence of the expected items; The monitoring expectations being applied by the user are identified in real time and marked as implementation expectations; corresponding markings are made within the expectation sequence according to the implementation expectations; and an expectation auxiliary setting interface is generated according to the expectation items and the expectation sequence.

[0009] Furthermore, the method for setting the difficulty value includes: A recognition model is established, and the expression of the recognition model is: ; Where: (s i , q) is the input data, s i represents the historical production monitoring data corresponding to the corresponding potential expectation, i=1, 2, ..., n, n is the number of historical production monitoring data; q is the corresponding potential expectation; s i →q indicates that the corresponding historical production monitoring data completes the potential expectation; the output data is the completion identification value WA(s i ​​,q), the completion recognition value is 1 or 0; Analyze the historical production monitoring data corresponding to the potential expectation through the completion identification model to obtain the corresponding completion identification value; Classifying the completed identification values ​​to obtain a plurality of completed identification classifications; The average value of the completed recognition values ​​within the completed recognition category is calculated and marked as a category representative value; and the potential expected difficulty value is set according to the category representative value.

[0010] Furthermore, the method for setting the effect value includes: The platform specifies the reference subject; identifies the corresponding potential expected reference standard based on the reference subject; Comparing historical production monitoring data with reference standards to determine the potential expected difference value; Calculate the corresponding effect value according to the effect value formula. The effect value formula is: XG = (1 + η) × XZ; Where: XG is the corresponding potential expected effect value; η is the difference value; XZ is the effect value corresponding to the reference standard.

[0011] Further, methods for analyzing monitoring expectations include: Identify each single expectation corresponding to the monitoring expectation, and collect corresponding expectation material data according to the single expectation; perform comparative analysis on the single expectation according to the expectation material data, and obtain expectation gap data corresponding to the single expectation; Recommend corresponding optimization methods to the user according to the expectation gap data; integrate the optimization methods and expectation gap data corresponding to each of the single expectations into expectation display data.

[0012] Furthermore, the method for determining the target expectation includes: The user determines whether to apply the monitoring expectation according to the expected display data; When the user determines to apply the monitoring expectation, marking the monitoring expectation as a target expectation; When the user determines not to apply the monitoring expectation, the user adjusts the monitoring expectation and obtains expected display data of a new monitoring expectation, and so on, until the user determines the target expectation.

[0013] The andon monitoring module is used to perform production monitoring processing and obtain corresponding monitoring processing record data.

[0014] The expectation monitoring module is used to perform target expectation monitoring based on the monitoring processing record data and determine the expected abnormal data; identify the target single expectation corresponding to the expected abnormal data; determine the optimization method based on the target single expectation and the expected abnormal data; integrate the optimization method, the target single expectation and the expected abnormal data into optimization adjustment data, display the optimization adjustment data to the user, and the user performs optimization adjustment based on the optimization adjustment data.

[0015] Furthermore, the method for determining the expected abnormal data includes: Defining expected abnormal data, wherein the expected abnormal data is monitoring processing record data that does not achieve target expectations; An expected anomaly recognition model is established, and the expression of the expected anomaly recognition model is: ; Where: KS j is the corresponding monitoring and processing record data, j = 1, 2, ..., m, m is the number of monitoring and processing record data; the output data is the expected abnormal value WB (KS j ), the expected outlier value is 1 or 0; Analyzing the monitoring process record data by using the expected abnormality recognition model to obtain expected abnormality values ​​of the monitoring process record data; The monitoring processing record data with the expected abnormal value of 1 is marked as expected abnormal data.

[0016] An intelligent andon monitoring method based on a digital workstation production line, the method comprising: The user sets the monitoring expectation, analyzes the monitoring expectation, obtains the expected display data, displays the expected display data to the user, and determines the target expectation; optimizes the expected display data according to the target expectation; Set up an andon monitoring module, perform production monitoring and processing through the andon monitoring module, and obtain corresponding monitoring and processing record data; Conduct target expectation monitoring based on monitoring and processing record data and determine expected abnormal data; identify target single item expectations corresponding to expected abnormal data; determine optimization methods based on target single item expectations and expected abnormal data; The optimization method, target single item expectation and expected abnormal data are integrated into optimization adjustment data, and the optimization adjustment data is displayed to the user, who then makes optimization adjustments based on the optimization adjustment data.

[0017] Compared with the prior art, the present invention has the following beneficial effects: Through the cooperation between the expectation module, the andon monitoring module and the expectation monitoring module, production monitoring can be carried out according to the target expectation, reducing the difficulty of using the intelligent andon monitoring system for users, while improving the flexibility of using the intelligent andon monitoring system, making it easier to adjust the intelligent andon monitoring system according to production needs. Through the intelligent andon monitoring system, enterprises can monitor the operating status of the production line in real time. Once an abnormality or failure is found, the system can quickly issue an alarm and notify relevant personnel. This real-time monitoring and response mechanism greatly shortens the time to solve problems, thereby avoiding production interruptions and delays and significantly improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0020] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] like Figure 1 As shown, an intelligent andon monitoring system based on a digital workstation production line includes an expectation module, an andon monitoring module and an expectation monitoring module; The expectation module is used for users to set monitoring expectations, analyze the input monitoring expectations, obtain expected display data, display the expected display data to the user, and the user determines the target expectation, and optimizes the expected display data corresponding to the target expectation.

[0022] Among them, monitoring expectations are the monitoring and processing effects that users expect to achieve in the production process. For example, users expect that when front-line workers find that a certain raw material is insufficient, they can provide feedback through smart andon button boxes within the expected time, and the corresponding raw material management personnel can dispatch the raw materials to the production line within the expected time. There are a variety of optional monitoring expectations depending on the differences in the products produced.

[0023] In one embodiment, the monitoring expectation may be directly set by the user according to actual needs, such as the user setting the monitoring expectation according to his own experience.

[0024] In one embodiment, for setting monitoring expectations, it is necessary to consider the differences in professional ability, experience, etc. of users, and assist users in setting monitoring expectations. The method includes: Obtain the user's production line information, including production products, production process, location of personnel in each relevant link, work flow and other related information; According to the production line information, the historical production expectation data of similar enterprises are matched, and various historical monitoring expectations are counted according to the historical production expectation data. The obtained historical monitoring expectations are classified, such as raw material management expectations, quality management expectations, production exception handling expectations, etc., and specifically classified according to the classification types preset by the platform; several expectation categories are obtained, and corresponding expectation items are set according to each expectation category, that is, one expectation category corresponds to one expectation item; a potential expectation set is set according to the historical monitoring expectations corresponding to the expectation items, and the potential expectation set is composed of several potential expectations, that is, the historical monitoring expectations are screened, and the remaining historical monitoring expectations are marked as potential expectations, such as deduplication, whether the current user can achieve it, etc.; a user expectation library is established according to each expectation item and the potential expectation set; and the user expectation library is dynamically updated according to technological changes and other conditions.

[0025] An expectation auxiliary setting interface is generated according to the user expectation library, and the user sets the monitoring expectation according to the expectation auxiliary setting interface. The monitoring expectation is composed of individual expectations of various expectation items.

[0026] In one embodiment, the expected auxiliary setting interface is generated according to the user expectation library. The expected auxiliary setting interface is a display interface that displays each expected item and the corresponding potential expected set. Therefore, the expected auxiliary setting interface can be generated in the existing manner.

[0027] In one embodiment, in order to facilitate users to set individual expectations for each expectation item, the individual expectation is the potential expectation of the expectation item selected by the user; the potential expectations in the potential expectation set are sorted, and the user can subsequently set appropriate individual expectations according to the sorting and actual situation. The sorting can be based on production management effect, difficulty of achieving expectations, etc.

[0028] Exemplarily, the historical production monitoring data corresponding to each potential expectation is obtained, which refers to the historical production monitoring data that is the same as the user's production line information or the difference is within the allowable range, and needs to have a certain reference, including the production monitoring situation data after the implementation of the potential expectation, such as completion data and management effect data after completion; the difficulty value and effect value of the potential expectation are set according to the historical production monitoring data; The priority value of the corresponding potential expectation is calculated according to the priority formula, and the priority formula is: YA=b 1 ×XG-b 2 ×100×ND; Where: YA is the priority value; b 1 , b 2 They are all proportional coefficients, and their value range is 0 1 ≤1,0 2 ≤1; XG is the effect value; ND is the difficulty value; Sort the potential expectations in the potential expectation set according to the obtained priority values ​​to obtain the expectation sequence corresponding to the expectation item; Identify the monitoring expectations being applied by the user in real time and mark them as implementation expectations; when the monitoring expectations are set for the first time, the implementation expectation is none; make corresponding marks in each expectation sequence according to the implementation expectation, that is, mark the potential expectations implemented in the expectation item; Generate an expected auxiliary setting interface based on the expected items and expected sequence.

[0029] In one embodiment, the difficulty value and effect value of the potential expectation are set according to historical production monitoring data, and numerical quantification can be performed based on existing analysis methods. The difficulty value is used to indicate the difficulty of achieving the potential expectation, and the effect value is used to indicate the effect of achieving the potential expectation.

[0030] In one embodiment, the method for setting the difficulty value includes: A completion recognition model is established. The completion recognition module is used to determine whether the corresponding potential expectations have been completed based on historical production monitoring data; direct recognition judgment is performed based on the completion result data; the expression of the completion recognition model is: ; Where: (s i , q) is the input data, s i represents the corresponding historical production monitoring data corresponding to the corresponding potential expectation, i=1, 2, ..., n, n is the number of historical production monitoring data; q is the corresponding potential expectation; s i →q indicates that the corresponding historical production monitoring data completes the potential expectation; the output data is the completion identification value WA(s i ,q), the completion recognition value is 1 or 0; The historical production monitoring data corresponding to the potential expectations is analyzed through the completion identification model to obtain the corresponding completion identification value; Classify the obtained completion identification values ​​according to the corresponding enterprises to obtain several completion identification classifications; Calculate the average value of the completed identification values ​​within the completed identification category, that is, sum them up and divide them by the number; mark the obtained average value as the category representative value of the completed identification category; ​​The potential expected difficulty value is set according to each classification representative value, that is, a representative classification representative value is set as the difficulty value by using the average value, mode, variance, etc.

[0031] In one embodiment, the method for setting the effect value includes: The platform specifies the reference subject, that is, the actual monitoring and processing effect of a user or enterprise on each potential expectation is used as a benchmark, and the selected user or enterprise is marked as the reference subject; Identify the reference standard of corresponding potential expectations according to the reference subject; Compare the historical production monitoring data with the reference standard to determine the difference in the monitoring treatment effect compared with the reference standard, such as 10% priority and 12% lag, etc. The difference degree can be determined from the perspectives of reaction time, efficiency, loss, etc. Lagging behind is negative and priority is positive, so if lagging behind is 12%, the difference degree is -12%; because there are multiple historical production monitoring data, a representative difference degree can be set by using the average, mode, variance, etc.; the obtained difference degree is marked as the difference value; Calculate the corresponding effect value according to the effect value formula. The effect value formula is: XG = (1 + η) × XZ; Where: XG is the corresponding potential expected effect value; η is the difference value; XZ is the effect value corresponding to the reference standard, which is generally set to 60, and can also be set to other values, depending on the platform's needs.

[0032] In one embodiment, a method for analyzing monitoring expectations includes: Identify each single expectation corresponding to the monitoring expectation, and collect the corresponding expectation material data at the user according to the single expectation, that is, the relevant data corresponding to the actual monitoring and processing method at the user, such as the scheduling history data corresponding to the raw material scheduling method; conduct comparative analysis on the single expectations according to the expected material data to determine whether the single expectation can be completed. If it cannot be completed, determine the current expectation gap data; use the current data recognition technology to judge and calculate the corresponding expectation gap data. For the single expectation that can be completed, the expectation gap data is none; integrate the expectation gap data corresponding to each single expectation into the expectation display data.

[0033] In one embodiment, after obtaining the expected gap data of each single expectation in accordance with the above embodiment, an optimization method that the user can adopt is recommended based on the expected gap data, that is, improving the original processing method so that it can overcome the expected gap data. One expected gap data can have multiple optimization methods, and the optimization method can be adjusting the smart andon monitoring system, optimizing the workflow, optimizing the network and other related methods; the corresponding optimization methods and expected gap data are integrated into expected display data.

[0034] In one embodiment, an intelligent model may be established based on existing intelligent algorithms to analyze monitoring expectations and determine expected display data.

[0035] In one embodiment, the expected display data is displayed to the user, and the user determines the target expectation; the user determines whether to implement the corresponding monitoring expectation based on the expected display data. If applicable, the corresponding monitoring expectation is marked as the target expectation and optimized according to the optimization method corresponding to the target expectation; otherwise, the monitoring expectation is readjusted and set until the target expectation is determined.

[0036] In one embodiment, for the generation of optimization methods, the platform can summarize various optimization methods, set training sets and validation sets based on the obtained optimization methods and the corresponding expected display data; select appropriate machine learning algorithms or deep learning models. For example, for classification tasks, you can choose logistic regression, support vector machine (SVM) or deep learning models, etc.; for regression tasks, you can choose linear regression, decision tree or neural network, etc. Use the selected algorithm and data to build a model. This includes setting model parameters, defining the structure of the model, etc.

[0037] The training set is fed into the model for training. During the training process, the model learns how to solve the problem based on the data. The performance of the model is optimized by adjusting the parameters of the model (such as learning rate, regularization parameters, etc.). This usually requires the use of techniques such as cross-validation to evaluate the effects of different parameter combinations. Appropriate hyperparameters (such as the number of network layers, number of neurons, etc.) are selected to further improve the performance of the model.

[0038] Use the validation set to evaluate the trained model to check the generalization ability of the model. Evaluation indicators can be selected according to task requirements, such as accuracy, recall, F1 value, etc. If the model performance is poor, you need to return to the previous steps to improve it.

[0039] The successfully trained intelligent model is marked as an optimization analysis model, and the expected display data is analyzed through the optimization analysis model to generate an optimization method.

[0040] In one embodiment, an optimization method may also be intelligently generated based on other existing methods.

[0041] The andon monitoring module is set up based on the existing andon monitoring system, including but not limited to the following devices: Intelligent andon button box: adopts industrial-grade design, has multiple alarm states, and can trigger and transmit alarm signals.

[0042] Display board: It uses a liquid crystal screen to clearly display the real-time status and abnormal information of the production line.

[0043] Industrial tablet or PDA handheld device: used for card check-in, exception handling, etc.

[0044] Sensor: used to collect parameters such as temperature, humidity, and pressure at the production site.

[0045] The andon monitoring module is used to perform production monitoring and processing, and obtain corresponding monitoring and processing record data; for example: real-time monitoring of the operation of the production line, including equipment status, production progress, personnel allocation, etc.; when a process is delayed, fails or has quality problems, the system can quickly detect and issue an alarm, and notify relevant personnel to deal with it in time. Real-time perception of safety hazards on the production line, such as overloaded operation of equipment, intrusion of personnel into dangerous areas, etc. When safety hazards are found, the system will issue an alarm in time and take corresponding measures, such as automatic shutdown or activation of fire-fighting equipment, to protect the lives of workers.

[0046] The expectation monitoring module is used to perform target expectation monitoring based on the monitoring processing record data and determine the expected abnormal data; identify the unfinished single expectations corresponding to the expected abnormal data and mark them as target single expectations; determine the optimization method based on the target single expectations and the expected abnormal data, that is, the expected display data can be determined based on the target single expectations and the expected abnormal data, and then analyze through the optimization analysis model in the above embodiment to obtain the optimization method, integrate the obtained optimization method, target single expectations and expected abnormal data into optimization adjustment data, display the optimization adjustment data to the user, and the user performs optimization adjustment based on the optimization adjustment data.

[0047] In one embodiment, a method for determining expected abnormal data includes: Define expected abnormal data, which are monitoring processing record data that do not meet target expectations; Establish an expected anomaly recognition model, the expression of the expected anomaly recognition model is: ; Where: KS j is the corresponding monitoring and processing record data, j = 1, 2, ..., m, m is the number of monitoring and processing record data; the output data is the expected abnormal value WB (KS j ), the expected outlier value is 1 or 0; Analyze the monitoring process record data through the expected anomaly recognition model to obtain the expected anomaly value of the corresponding monitoring process record data; The monitoring processing record data with the expected abnormal value of 1 is marked as expected abnormal data.

[0048] An intelligent andon monitoring method based on a digital workstation production line, the method comprising: The user sets the monitoring expectation, analyzes the monitoring expectation, obtains the expected display data, displays the expected display data to the user, and determines the target expectation; optimizes the expected display data according to the target expectation; Set up an andon monitoring module, perform production monitoring and processing through the andon monitoring module, and obtain corresponding monitoring and processing record data; Conduct target expectation monitoring based on monitoring and processing record data to determine expected abnormal data; identify target single expectations corresponding to expected abnormal data; determine optimization method based on target single expectations and expected abnormal data; integrate optimization method, target single expectations and expected abnormal data into optimization adjustment data, display the optimization adjustment data to users, and let users make optimization adjustments based on the optimization adjustment data.

[0049] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0050] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent andon monitoring system based on a digital workstation production line, characterized in that: It includes an expectation module, an Andon monitoring module, and an expectation monitoring module; The expectation module is used for the user to set monitoring expectations, analyze the monitoring expectations, obtain expected display data, display the expected display data to the user, determine the target expectation; perform optimization processing according to the expected display data corresponding to the target expectation; The Andon monitoring module is used for performing production monitoring processing to obtain corresponding monitoring processing record data; The expectation monitoring module is used for performing target expectation monitoring according to the monitoring processing record data to determine expected abnormal data; Identify the target single expectation corresponding to the expected abnormal data; determine the optimization method according to the target single expectation and the expected abnormal data; integrate the optimization method, the target single expectation, and the expected abnormal data into optimization adjustment data, and display the optimization adjustment data to the user, and the user performs optimization adjustment according to the optimization adjustment data.

2. According to claim 1, the intelligent andon monitoring system based on the digital workstation production line is characterized in that: The method for setting monitoring expectations includes: Obtain the production line information of the user; match the corresponding historical production expectation data according to the production line information, and count various historical monitoring expectations according to the historical production expectation data; classify the historical monitoring expectations to obtain several expectation classifications, and set corresponding expectation items for the expectation classifications; Set a potential expectation set according to the historical monitoring expectations corresponding to the expectation items, and the potential expectation set consists of corresponding potential expectations; establish a user expectation library according to the expectation items and the potential expectation set; Generate an expectation auxiliary setting interface according to the user expectation library, and the user sets monitoring expectations according to the expectation auxiliary setting interface, and the monitoring expectations are composed of single expectations of each expectation item.

3. According to claim 2, the intelligent andon monitoring system based on the digital workstation production line is characterized in that: The method for generating the expectation auxiliary setting interface includes: Identify the potential expectations in the user expectation library, and obtain the historical production monitoring data corresponding to the potential expectations; set the difficulty value and the effect value of the potential expectations according to the historical production monitoring data; Calculate the priority value of the potential expectation according to the priority formula, and the priority formula is: YA = b1×XG - b2×100×ND; In the formula: YA is the priority value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; XG is the effect value; ND is the difficulty value; Sort the potential expectations in the potential expectation set in descending order of the priority value to obtain the expectation sequence of the expectation items; Real-time identify the monitoring expectations being applied by the user, and mark them as implemented expectations; perform corresponding marking in the expectation sequence according to the implemented expectations; generate an expectation auxiliary setting interface according to the expectation items and the expectation sequence.

4. According to claim 3, the intelligent andon monitoring system based on the digital workstation production line is characterized in that: The method for setting the difficulty value includes: A recognition model is established, and the expression of the recognition model is: ; Where: (s i , q) is the input data, s i represents the historical production monitoring data corresponding to the corresponding potential expectation, i=1, 2, ..., n, n is the number of historical production monitoring data; q is the corresponding potential expectation; s i →q indicates that the corresponding historical production monitoring data completes the potential expectation; the output data is the completion identification value WA(s i ,q), the completion recognition value is 1 or 0; Analyze the historical production monitoring data corresponding to the potential expectation through the completion recognition model to obtain the corresponding completion recognition value; Classify the completion recognition values to obtain several completion recognition classifications; Calculate the average value of the completion recognition values within the completion recognition classification, and mark it as the classification representative value; set the difficulty value of the potential expectation according to the classification representative value.

5. According to claim 3, the intelligent andon monitoring system based on the digital workstation production line is characterized in that: The method for setting the effect value includes: Designate a reference subject by the platform party; identify the reference standard of the corresponding potential expectation according to the reference subject; Comparing historical production monitoring data with reference standards to determine the potential expected difference value; Calculate the corresponding effect value according to the effect value formula. The effect value formula is: XG = (1 + η) × XZ; Where: XG is the corresponding potential expected effect value; η is the difference value; XZ is the effect value corresponding to the reference standard.

6. According to claim 1, the intelligent andon monitoring system based on the digital workstation production line is characterized in that: Methods for analyzing monitoring expectations include: Identify each single expectation corresponding to the monitoring expectation, and collect corresponding expectation material data according to the single expectation; perform comparative analysis on the single expectation according to the expectation material data, and obtain expectation gap data corresponding to the single expectation; Recommend corresponding optimization methods to the user according to the expectation gap data; integrate the optimization methods and expectation gap data corresponding to each of the single expectations into expectation display data.

7. According to claim 1, the intelligent andon monitoring system based on the digital workstation production line is characterized in that: Methods for determining target expectations include: The user determines whether to apply the monitoring expectation according to the expected display data; When the user determines to apply the monitoring expectation, marking the monitoring expectation as a target expectation; When the user determines not to apply the monitoring expectation, the user adjusts the monitoring expectation and obtains expected display data of a new monitoring expectation, and so on, until the user determines the target expectation.

8. According to claim 1, the intelligent andon monitoring system based on the digital workstation production line is characterized in that: Methods for determining expected abnormal data include: Defining expected abnormal data, wherein the expected abnormal data is monitoring processing record data that does not achieve target expectations; An expected anomaly recognition model is established, and the expression of the expected anomaly recognition model is: ; Where: KS j is the corresponding monitoring and processing record data, j = 1, 2, ..., m, m is the number of monitoring and processing record data; the output data is the expected abnormal value WB (KS j ), the expected outlier value is 1 or 0; Analyzing the monitoring process record data by using the expected abnormality recognition model to obtain expected abnormality values ​​of the monitoring process record data; The monitoring processing record data with the expected abnormal value of 1 is marked as expected abnormal data.

9. An intelligent andon monitoring method based on a digital workstation production line, characterized in that: An intelligent andon monitoring system based on a digital workstation production line as claimed in any one of claims 1 to 8, the method comprising: The user sets the monitoring expectation, analyzes the monitoring expectation, obtains the expected display data, displays the expected display data to the user, and determines the target expectation; optimizes the expected display data according to the target expectation; Set up an andon monitoring module, perform production monitoring and processing through the andon monitoring module, and obtain corresponding monitoring and processing record data; Conduct target expectation monitoring based on monitoring and processing record data and determine expected abnormal data; identify target single item expectations corresponding to expected abnormal data; determine optimization methods based on target single item expectations and expected abnormal data; The optimization method, target single item expectation and expected abnormal data are integrated into optimization adjustment data, and the optimization adjustment data is displayed to the user, who then makes optimization adjustments based on the optimization adjustment data.

Images