Automatic identification method and equipment for chemical batch production, medium and product

Abstract

The invention relates to the technical field of production management, in particular to a chemical batch production automatic identification method and device, a medium and a product. The method comprises the steps of obtaining historical production data and a production plan of a current batch, and determining reference production parameters of the current batch based on the historical production data and the production plan; production is started based on the reference production parameters, real-time production data and online inspection data are obtained, and the real-time production data comprise the production progress; in the production process of each working procedure of the current batch, dynamically adjusting production parameters of the working procedures based on the production plan, the online inspection data of the working procedures and the production progress; after the current batch is finished, a summary batch report of the current batch is generated, and the summary batch report comprises the sub-batch report of each working procedure. Deviation can be corrected in time, and stable product quality is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of production management technology, and in particular to a method, equipment, medium and product for automatic identification of chemical batch production. Background Art

[0002] As a core pillar of the modern industrial system, the chemical industry offers a rich and diverse range of products, particularly fine chemicals. To meet the personalized and customized needs of specific customers, intermittent or continuous-intermittent production models are often employed. This production model is characterized by relatively small production scales, small batches with a wide variety of products, complex production processes, stringent quality requirements, and high safety risks.

[0003] In the chemical production process, how to scientifically define and continuously optimize the "golden batch" benchmark value has been a long-standing challenge for companies. Due to the differences in production conditions such as raw material batches, equipment conditions, and operator habits, it is difficult to determine a uniformly applicable benchmark value. Traditionally, companies often set production parameters based on experience. This not only makes it difficult to ensure the stability of product quality, but also prevents effective process control during production. This leads to inconsistent product quality, low production efficiency, and difficulty in meeting market demand for high-quality, high-efficiency chemical products. Summary of the Invention

[0004] In order to solve the problem that the existing technology relies on manual experience to set production parameters, resulting in unstable product quality, the present application provides a chemical batch production automatic identification method, equipment, medium and product.

[0005] In the first aspect, the present application provides a method for automatic identification of chemical batch production, which adopts the following technical solutions: A method for automatic identification of chemical batch production, comprising: Acquiring historical production data and a production plan for a current batch, and determining baseline production parameters for the current batch based on the historical production data and the production plan; Starting production based on the baseline production parameters and acquiring real-time production data and online inspection data, wherein the real-time production data includes production progress; During the production process of each process of the current batch, dynamically adjusting the production parameters of the process based on the production plan, the online inspection data of the process and the production progress; After the current batch is completed, a summary batch report of the current batch is generated, and the summary batch report includes a sub-batch report of each process.

[0006] By adopting the above technical solutions, historical production data and current batch production plans are obtained to determine benchmark production parameters, providing a reliable reference for production and reducing blindness; production is based on benchmark parameters and data is obtained in real time to achieve dynamic monitoring of the production process; in process production, production parameters are dynamically adjusted based on multi-source data to correct deviations in a timely manner and ensure stable product quality; summary batch reports and sub-batch reports are generated after the batch is completed, which helps to analyze the entire production process and provide data support for subsequent production optimization and experience summary, thereby improving production efficiency, reducing costs, and enhancing the accuracy and controllability of chemical production.

[0007] In a preferred example, the present application may be further configured as follows: dynamically adjusting the production parameters of the process based on the production plan, the online inspection data of the process, and the production progress includes: During the production process of the current process, determining whether there are quality problems with the intermediate product based on the online inspection data of the current process; If so, formulate and implement parameter adjustment strategies until the quality of the newly produced intermediate products is up to standard; After the current process is completed, formulate a rework sub-plan for all intermediate products with quality problems and implement the rework sub-plan; The production parameters of the subsequent process of the current process are adjusted based on the production plan, the production schedule and the rework sub-plan.

[0008] By adopting the above technical solution, quality problems of intermediate products can be judged based on online inspection data in the current production process, so that potential risks in the production process can be detected in time, and unqualified products can be prevented from flowing into subsequent processes; if there are quality problems, parameter adjustment strategies will be formulated and implemented until the newly produced intermediate products are qualified, which can quickly correct production deviations and ensure stable product quality; after the process is completed, a rework sub-plan will be formulated and implemented for intermediate products with quality problems, which can minimize losses and improve the overall qualification rate of products; based on the production plan, production schedule and rework sub-plan, the production parameters of subsequent processes are adjusted to ensure the consistency and efficiency of the entire production process.

[0009] In a preferred example, the present application may be further configured as follows: formulating and executing a parameter adjustment strategy for the intermediate product with quality issues until the quality of the newly produced intermediate product is qualified includes: Determine the problem type of the intermediate product with quality problems, and retrieve a list of parameter adjustment methods corresponding to the problem type; Starting from the first parameter adjustment method in the parameter adjustment method list, each parameter adjustment method is executed in sequence, and a debugging production cycle is executed after each parameter adjustment method is executed, until the quality of the newly produced intermediate products in the debugging production cycle is qualified.

[0010] By adopting the above technical solution, the problem type of the intermediate product with quality problems can be determined, the root cause of the production problem can be accurately located, blind parameter adjustment can be avoided, and the targeted problem solving can be improved; the list of parameter adjustment methods corresponding to the problem type can be called up, and historical experience and pre-summarized effective methods can be used to provide multiple feasible ways to solve the problem, reducing the time for trial and error; starting from the first parameter adjustment method in the parameter adjustment method list, it is executed in sequence, and the production cycle is debugged after each execution, which can gradually verify the effectiveness of each adjustment method, ensuring that the most suitable parameter adjustment solution to solve the current quality problem is found in continuous attempts until the quality of the newly produced intermediate product is qualified, effectively ensuring product quality.

[0011] In a preferred example, the present application may be further configured as follows: adjusting the production parameters of the subsequent process of the current process based on the production plan, the production progress, and the rework sub-plan includes: estimating the end time of the current process based on the production progress and the rework sub-plan; estimating whether the production end time of the current batch has exceeded the estimated end time based on the estimated end time and the production plan; If the production end time of the current batch is exceeded, the production parameters of the subsequent process of the current process are adjusted.

[0012] By adopting the above technical solution, the estimated end time of the current process is estimated based on the production progress and rework sub-plan, so that the actual progress of the current process can be grasped in advance; then based on the estimated end time and the production plan, it is estimated whether the production end time of the current batch will be exceeded, so that it can be clearly judged whether the production cycle deviates from the plan and potential production delay risks are discovered in time; if the production end time is exceeded, the production parameters of the subsequent processes of the current process are adjusted, which can flexibly respond to emergencies in the production process and ensure that the entire production batch is completed on time by optimizing the production rhythm of the subsequent processes.

[0013] In a preferred example, the present application may be further configured as follows: determining the baseline production parameters of the current batch based on the historical production data and the production plan includes: determining a planned production volume and a maximum production duration from the production plan; Based on the historical production data, selecting from a plurality of historical batches a number of historical batches whose production duration for producing the planned production volume does not exceed the maximum production duration; Determining quality indicator data of the plurality of historical batches from the historical production data; A target batch is determined from the several historical batches based on the quality indicator data, and historical production parameters of the target batch are used as the benchmark production parameters.

[0014] By adopting the above technical solution, the planned production volume and maximum production time are determined from the production plan, which clarifies the goals and time limits for the subsequent screening of historical batches, ensuring that the production arrangements are reasonable and controllable; based on historical production data, historical batches with planned production volumes and time that do not exceed the standards are screened, which can exclude batches that do not meet the current production scale and time requirements, narrow the selection range, and improve screening efficiency; quality index data of several historical batches are determined, which provides a quantitative quality assessment basis for further determining the target batch; the target batch is determined based on the quality index data, and its historical production parameters are used as benchmark production parameters, so that the current batch production has a scientific and reliable reference standard.

[0015] In a preferred example, the present application may be further configured as follows: the method further includes: Determining, from the historical production data, a problem type of an intermediate product obtained in each historical process and a corresponding plurality of parameter adjustment methods, wherein the parameter adjustment method includes adjusting at least one production parameter; For each question type, a parameter adjustment method list for the question type is generated according to a plurality of parameter adjustment methods corresponding to the question type.

[0016] By adopting the above technical solution, the problem type and corresponding parameter adjustment method of the intermediate product of each historical process can be determined from historical production data, which can systematically sort out various problems and solutions that have occurred in past production; based on this, a list of parameter adjustment methods is generated for each problem type, and scattered experiences are systematized and structured to form a standardized problem-solving reference library.

[0017] In a preferred example, the present application may be further configured as follows: the method further includes: During the production process of each process of the current batch, estimating the estimated end time of the current process based on the production progress in the real-time production data; Periodically summarizing the real-time production data, online inspection data, and estimated end time of the current process to obtain a dynamic sub-batch report of the current process; After the current process is completed, the latest dynamic sub-batch report is used as the sub-batch report of the current process.

[0018] By adopting the above technical solution, when each process of the current batch is produced, the estimated end time of the current process is estimated based on the production progress in the real-time production data, which allows production management personnel to understand the progress of the process in advance, facilitating the reasonable arrangement of subsequent work and resource allocation; the real-time production data, online inspection data and estimated end time of the current process are periodically summarized to generate a dynamic sub-batch report, which can timely reflect key information such as quality and progress in the process of process production, and realize dynamic monitoring of the production process.

[0019] In a second aspect, the present application provides an electronic device, which adopts the following technical solution: one or more processors; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the automatic identification method for chemical batch production as described in any one of the first aspects.

[0020] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, which, when executed in a computer, causes the computer to execute the automatic identification method for chemical batch production as described in any one of the first aspects.

[0021] In a fourth aspect, the present application provides a computer program product that adopts the following technical solution: A computer program product includes a computer program. When the computer program is executed by a processor, it implements the automatic identification method for chemical batch production as described in any one of the first aspects.

[0022] In summary, this application has the following beneficial technical effects: This application determines the benchmark production parameters by obtaining historical production data and current batch production plans, providing a reliable reference for production and reducing blindness; produces based on the benchmark parameters and obtains data in real time to achieve dynamic monitoring of the production process; in process production, dynamically adjusts production parameters based on multi-source data to correct deviations in a timely manner and ensure stable product quality; generates summary batch reports and sub-batch reports after the batch is completed, which helps to analyze the entire production process and provide data support for subsequent production optimization and experience summary, thereby improving production efficiency, reducing costs, and enhancing the accuracy and controllability of chemical production. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for automatic identification of chemical batch production provided in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following is combined with Figure 1 -Attached Figure 2 This application is described in further detail.

[0025] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0026] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0028] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information requires the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0029] The present application embodiment provides a method for automatic identification of chemical batch production, such as Figure 1 As shown, the method provided in the embodiment of the present application is performed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101 to S104, wherein: S101. Obtain historical production data and a production plan for a current batch, and determine baseline production parameters for the current batch based on the historical production data and the production plan.

[0030] Specifically, the historical production data targets the same product type as the current batch to be produced. This data includes production information for multiple historical batches, including production parameters (adjustable parameters for each production equipment, such as temperature, pressure, and humidity), production duration, and product quality indicators. The production plan for the current batch is obtained from the company's production management system (such as an ERP system). The production plan includes information such as planned production volume, production start time, maximum production duration, and product quality requirements.

[0031] Then, the planned production volume and maximum production duration of the current batch are determined from the production plan, and several historical batches whose production durations of the planned production volume do not exceed the maximum production duration are selected from multiple historical batches of historical production data.

[0032] When the number of historical batches is one, the historical production parameters of this historical batch are used as the benchmark production parameters of the current batch. When the number of historical batches is greater than one, quality index data of the historical batches is determined from the historical production data, and a target historical batch is determined from the historical batches based on the quality index data, and the historical production parameters of the target historical batch are used as the benchmark production parameters of the current batch.

[0033] When no historical batch with a production duration that does not exceed the maximum production duration for the planned production volume can be screened out from multiple historical batches, the one with the largest production duration for the planned production volume is screened out from multiple historical batches of historical production data as the target historical batch, and a prompt signal is sent to the staff's terminal device. The staff can adjust the historical production parameters of the target historical batch to obtain the final benchmark production parameters.

[0034] S102. Start production based on the baseline production parameters and obtain real-time production data and online inspection data, where the real-time production data includes production progress.

[0035] Specifically, during the production process, production equipment readings are collected in real time, or sensors are installed on production equipment to collect production data. Real-time production data includes two types of parameters: adjustable parameters and non-adjustable parameters. Adjustable parameters are baseline production parameters that can be adjusted through electronic equipment or manual adjustments to production equipment. Non-adjustable parameters are passively changing data during the production process and cannot be adjusted. A standard parameter range can be pre-set for each type of non-adjustable parameter. Whether each non-adjustable parameter exceeds the corresponding standard parameter range is determined in real time. If so, an alarm signal is sent to indicate a production anomaly.

[0036] The historical production data of the target historical batch also includes the product quantity output by each historical process. Based on the raw material quantity of the target historical batch and the planned raw material quantity of the current batch, the expected output product quantity of each process in the current batch is estimated proportionally.

[0037] Real-time production data also includes the production progress of each process. The production progress can be determined at fixed intervals, with this fixed time period being considered a production cycle. The production progress includes the actual product output of the current process (the sum of the outputs of all production cycles prior to the current moment) and the expected product output. The ratio of the actual product output of the current process to the expected product output can also be calculated as a percentage of the production progress, although this is not limited in this embodiment.

[0038] Online inspection equipment (such as spectrometers, chromatographs, and quality sensors) is pre-installed on the production line based on product requirements. Inspections are performed at a preset collection frequency to generate online inspection data. The preset collection frequency corresponds to the fixed time period, and the collection period of the preset collection frequency is equal to the fixed time period.

[0039] S103. During the production process of each process of the current batch, dynamically adjust the production parameters of the process based on the production plan, the online inspection data of the process and the production progress.

[0040] Specifically, for the current process, during the production process of the current process, the product obtained through the current process is regarded as an intermediate product. Online inspection data is acquired based on a preset collection frequency. The period between each collection moment is regarded as a production mini-cycle. At each collection moment, the intermediate product obtained in the production mini-cycle before the collection moment is verified to obtain a set of online inspection data. If the online inspection data obtained at a certain collection moment indicates that the intermediate product has no quality issues, then it is determined that there are no production issues in the production mini-cycle before the collection moment. If the online inspection data obtained at a certain collection moment indicates that the intermediate product has a quality issue, then the intermediate product obtained in the production mini-cycle before the collection moment is determined to have a quality issue.

[0041] If quality issues are identified in an intermediate product at a certain point in the data collection process, a parameter adjustment strategy is developed to adjust production parameters until the newly produced intermediate product meets quality standards. After the current process is completed, a rework sub-plan is developed and executed for all intermediate products with quality issues. Production parameters for subsequent processes of the current process are then adjusted based on the production plan, production schedule, and rework sub-plan.

[0042] S104. After the current batch is completed, a summary batch report of the current batch is generated. The summary batch report includes a sub-batch report of each process.

[0043] Specifically, during the production of each process in the current batch, the estimated end time of the current process is estimated based on the production progress in real-time production data. The current process's real-time production data, online verification data, and estimated end time are periodically summarized to form a dynamic sub-batch completion report for the current process. After the current process completes, the latest dynamic sub-batch completion report is used as the sub-batch completion report for the current process.

[0044] This embodiment determines the benchmark production parameters by obtaining historical production data and the current batch production plan, providing a reliable reference for production and reducing blindness; production is based on the benchmark parameters and data is obtained in real time to achieve dynamic monitoring of the production process; in process production, production parameters are dynamically adjusted according to multi-source data to correct deviations in a timely manner and ensure stable product quality; after the batch is completed, a summary batch report and a sub-batch report are generated, which helps to analyze the entire production process and provide data support for subsequent production optimization and experience summary, thereby improving production efficiency, reducing costs, and enhancing the accuracy and controllability of chemical production.

[0045] A possible implementation of the embodiment of the present application is to determine the baseline production parameters of the current batch based on historical production data and a production plan, including: Determine the planned production volume and maximum production time from the production plan; Based on historical production data, several historical batches whose production duration of the planned production volume does not exceed the maximum production duration are selected from multiple historical batches; Determine quality index data of several historical batches from historical production data; A target batch is determined from several historical batches based on quality indicator data, and the historical production parameters of the target batch are used as benchmark production parameters.

[0046] In this embodiment, the planned production volume can be expressed as the specific number, weight, or volume of products, and the maximum production time represents the maximum time allowed to complete the production task for the batch. Historical production data covers production information for multiple batches, including each batch's production volume, production time, production parameters (such as temperature, pressure, reaction time, material ratio, etc.), and product quality indicators.

[0047] Then, the collected historical production data is screened. Screening method 1: directly screen historical batches whose production volume is equal to or close to the planned production volume of the current batch (the error does not exceed ±5% of the planned production volume). From the screened historical batches, further screen out several historical batches whose production time does not exceed the maximum production time of the current batch.

[0048] Screening method 2: Convert the historical production volumes of multiple batches in the historical production data. For each batch, calculate the ratio of the historical production volume to the historical production duration. Then, multiply the ratio by the planned production volume of the current batch as the production duration of the planned production volume for that batch. Then, select batches from the multiple batches whose planned production durations do not exceed the maximum production duration of the current batch.

[0049] Clearly define in advance the various indicators for evaluating the quality of the current batch of products. Common quality indicators include: product purity, impurity content, physical properties (such as density, particle size, etc.), chemical properties (such as pH, reactivity, etc.). Technical personnel can determine the quality indicators based on the needs of the current batch of products.

[0050] Based on the defined indicators, the quality indicator data of several historical batches is scored and calculated. Each indicator data of each historical batch is multiplied by the corresponding preset weight, and the results are added together. The weighted sum obtained is used as the quality score of the corresponding historical batch. The quality scores of several historical batches are compared, and the one with the highest quality score is selected as the target historical batch.

[0051] This embodiment determines the planned production volume and maximum production time from the production plan, clarifies the target and time limit for subsequent screening of historical batches, and ensures that the production arrangement is reasonable and controllable; based on historical production data, historical batches with planned production volume and duration that do not exceed the standard are screened, which can exclude batches that do not meet the current production scale and time requirements, narrow the selection range, and improve screening efficiency; determines the quality index data of several historical batches, and provides a quantitative quality assessment basis for further determining the target batch; determines the target batch based on the quality index data, and uses its historical production parameters as benchmark production parameters, so that the current batch production has a scientific and reliable reference standard.

[0052] In a possible implementation of the embodiment of the present application, the method further includes: Determining, from historical production data, a problem type of an intermediate product obtained in each historical process and a corresponding plurality of parameter adjustment methods, wherein the parameter adjustment method includes adjusting at least one production parameter; For each question type, a parameter adjustment method list of the question type is generated according to several parameter adjustment methods corresponding to the question type.

[0053] In this embodiment, historical production data is collated, and production data belonging to the same process is classified into one category. For the intermediate products of each process, the production data includes problems that occurred with the intermediate products of the process and corresponding solutions.

[0054] Take any process as the target process and identify the type of problem it faces from historical production data (e.g., if the ingredient content of an intermediate product doesn't meet the standard, the problem type is "unqualified ingredients"; if the particle size of an intermediate product doesn't meet the standard, the problem type is "abnormal particle size"). Query the parameter adjustment records for each problem, including the adjusted production parameters (such as temperature, pressure, flow rate, material ratio, etc.), the adjustment time, and the effect of the adjustment, and extract the parameter adjustment records that can solve the problem.

[0055] Any problem type generated by the target process is taken as the target problem type, and the parameter adjustment records adopted for the target problem type are summarized. If the number of parameter adjustment records is 1, the parameter adjustment method represented by the parameter adjustment record is written into the parameter adjustment method list.

[0056] If the number of parameter adjustment records is greater than one, different parameter adjustment records may represent the same parameter adjustment method. The system then iterates through each parameter adjustment record to determine the number of parameter adjustment records corresponding to each parameter adjustment method. The parameter adjustment methods are then sorted from largest to smallest based on the number of parameter adjustment records, resulting in a parameter adjustment method list. For example, a parameter adjustment method may be: lowering the reaction temperature by 2°C.

[0057] This embodiment determines the problem type and corresponding parameter adjustment method of the intermediate product of each historical process from historical production data, and can systematically sort out various problems and solutions that occurred in past production; based on this, a list of parameter adjustment methods is generated for each problem type, and scattered experiences are systematized and structured to form a standardized problem-solving reference library.

[0058] One possible implementation of the embodiment of the present application is to dynamically adjust the production parameters of a process based on the production plan, online inspection data of the process, and the production progress, including: During the production process of the current process, determine whether there are quality problems with the intermediate products based on the online inspection data of the current process; If so, formulate and implement parameter adjustment strategies until the quality of the newly produced intermediate products is up to standard; After the current process is completed, a rework sub-plan is developed for all intermediate products with quality issues and the rework sub-plan is implemented; Adjust the production parameters of subsequent operations of the current operation based on the production plan, production schedule and rework sub-plan.

[0059] In this embodiment, an online inspection device is used to collect various quality index data of the intermediate products obtained in the current process in a small production cycle before the current moment, such as component content, purity, particle size, density, color, etc. The online inspection device transmits the collected quality index data to the electronic device, and the electronic device associates the quality standard data of the intermediate products of the process in the production plan. The electronic device compares the obtained quality index data with the quality standard data. Different comparison rules can be set. For the component content, it is judged whether it is within the specified standard range; for the purity, whether it reaches the minimum purity requirement value, etc. If the online verification data exceeds the range allowed by the quality standard, it is determined that there is a quality problem with the intermediate product.

[0060] Among them, if the intermediate product is an independent product, the inspection method can be random inspection, and the percentage of the number of intermediate products with quality problems in the number of sampled products must be determined. If the percentage exceeds the preset lower limit of unqualified products, it is determined that the intermediate product has quality problems.

[0061] When it is determined that an intermediate product has a quality problem, the type of problem is determined, and a list of parameter adjustment methods corresponding to the problem type is retrieved. Starting with the first parameter adjustment method in the list, each parameter adjustment method is executed in sequence. After each parameter adjustment method is executed, a debugging production cycle is executed until the quality of the intermediate product produced during the debugging production cycle is qualified. The debugging production cycle can be equivalent to the production mini-cycle, or can be set by technicians based on actual needs, and this embodiment does not specifically limit this.

[0062] Furthermore, after the current process is completed, all intermediate products with quality issues in the current process are summarized and their product quantity, problem type, and other information are counted. Professionals such as process engineers and quality management personnel can formulate a rework sub-plan based on the specific circumstances of the problem products and input it into the electronic equipment. The rework sub-plan includes rework processes and rework parameters. The electronic equipment can also classify intermediate products with quality issues based on the problem type. For each problem type, a parameter adjustment method is selected from the parameter adjustment method list corresponding to the problem type, and the intermediate products of each problem type are reworked in turn according to the selected parameter adjustment method.

[0063] This embodiment determines the quality problems of intermediate products based on online inspection data in the current production process, which can timely detect potential risks in the production process and prevent unqualified products from flowing into subsequent processes; if there are quality problems, a parameter adjustment strategy is formulated and implemented until the newly produced intermediate products are qualified, which can quickly correct production deviations and ensure stable product quality; after the process is completed, a rework sub-plan is formulated and implemented for the intermediate products with quality problems, which can minimize losses and improve the overall qualification rate of the products; based on the production plan, production schedule and rework sub-plan, the production parameters of the subsequent processes are adjusted to ensure the consistency and efficiency of the entire production process.

[0064] A possible implementation of the embodiment of the present application is to formulate and execute a parameter adjustment strategy for an intermediate product with quality issues until the quality of the newly produced intermediate product is qualified, including: Determine the problem type of the intermediate product with quality issues and retrieve the list of parameter adjustment methods corresponding to the problem type; Starting from the first parameter adjustment method in the parameter adjustment method list, each parameter adjustment method is executed in sequence, and a debugging production cycle is executed after each parameter adjustment method is executed, until the quality of the intermediate product newly produced in the debugging production cycle is qualified.

[0065] In this embodiment, after the parameter adjustment is completed based on the selected parameter adjustment method, a debugging production cycle is started. After the debugging production cycle ends, the quality inspection of the newly produced intermediate products is carried out, and the quality index data obtained by the inspection is compared with the standard quality index in the production plan. If the quality of the newly produced intermediate products is qualified, the parameter adjustment operation is stopped and the normal production process is entered; if the quality is still unqualified, the next parameter adjustment method is selected from the parameter adjustment method list, and quality inspection is carried out, and the above steps are repeated until the quality of the newly produced intermediate products is qualified.

[0066] This embodiment can accurately locate the root cause of production problems by determining the problem type of intermediate products with quality problems, avoid blind parameter adjustment, and improve the targeted problem solving; call the parameter adjustment method list corresponding to the problem type, and use historical experience and pre-summarized effective methods to provide multiple feasible ways to solve the problem, reducing the time for trial and error; start from the first parameter adjustment method in the parameter adjustment method list and execute them in sequence, and debug the production cycle after each execution, which can gradually verify the effectiveness of each adjustment method, and ensure that the most suitable parameter adjustment solution to solve the current quality problem is found in continuous attempts until the quality of the newly produced intermediate products is qualified, effectively ensuring product quality.

[0067] A possible implementation of the embodiment of the present application is to adjust the production parameters of subsequent processes of the current process based on the production plan, production progress, and rework sub-plan, including: Estimate the end time of the current process based on the production progress and rework sub-plan; Estimate whether the production end time of the current batch will exceed the estimated end time based on the estimated end time and production plan; If the production end time of the current batch exceeds the limit, the production parameters of the subsequent processes of the current process are adjusted.

[0068] In this embodiment, the target historical batch includes the historical execution time of each process and the historical execution time of each step within each process. The historical execution time of each step in the historical production data of the target historical batch is used as the estimated execution time of that step. The rework sub-plan includes each step of the current process that requires rework. The estimated execution time of each step is determined by retrieving the historical production data of the target historical batch, and the estimated execution time of each step in the rework sub-plan is calculated as the sum of the estimated execution times of each step requiring rework.

[0069] The production progress information represents the current process's production progress, including completed production steps and the amount of product produced. Based on the production progress, the end time of the current process's regular flow (before the rework sub-plan begins) can be determined. At this point, the estimated end time of the current process is the sum of the estimated times for all steps in the rework sub-plan that require rework after the current time.

[0070] Retrieve the historical time of each process in the historical production data of the target historical batch, calculate the sum of the historical times of each process after the current process, and use the time after the current moment after the sum of the historical times as the production end time of the current batch.

[0071] Extract the planned production start time and maximum production duration from the production plan. The maximum production duration after the planned production start time is used as the latest production end time. Determine whether the production end time is later than the latest production end time. If so, the production end time of the current batch is considered to have exceeded. If not, the production end time of the current batch is considered to have not exceeded, and the subsequent production process will proceed according to the original baseline production parameters.

[0072] If the production end time of the current batch times out, the production parameters of the subsequent processes of the current process are adjusted. Specifically, the electronic device may pre-store parameter adjustment methods that can speed up production progress, such as increasing the operating power of the production equipment, speeding up the material conveying speed, etc. The specific adjustment method is not limited in this embodiment, and technicians can set it according to the product attributes of the current batch. The electronic device also stores the parameter safety range for each production equipment. Within the parameter safety range, the production parameters of the subsequent processes of the current process that can speed up production progress are randomly adjusted.

[0073] This embodiment estimates the estimated end time of the current process based on the production progress and the rework sub-plan, so that the actual progress of the current process can be grasped in advance; then, based on the estimated end time and the production plan, it estimates whether the production end time of the current batch will be exceeded, so that it can clearly judge whether the production cycle deviates from the plan and timely discover potential production delay risks; if the production end time is exceeded, the production parameters of the subsequent processes of the current process are adjusted, which can flexibly respond to emergencies in the production process and ensure that the entire production batch is completed on time by optimizing the production rhythm of the subsequent processes.

[0074] In a possible implementation of the embodiment of the present application, the method further includes: During the production process of each step of the current batch, the estimated end time of the current step is estimated based on the production progress in the real-time production data; Periodically summarize the real-time production data, online inspection data, and estimated end time of the current process to obtain a dynamic sub-batch report for the current process; After the current process is completed, the latest dynamic sub-batch report will be used as the sub-batch report of the current process.

[0075] In this embodiment, for the current process, the production progress can be the ratio of the amount of products completed at the current moment to the amount of products planned to be completed for the process in the production plan, or the ratio of completed production steps to the total steps of the process. The ratio of the length of time the current process has been in production to the production progress ratio is calculated to obtain the estimated total time of the process, and the time corresponding to the estimated total time after the current process starts production is used as the estimated end time of the current process. Among them, the production progress is determined once at a certain interval, and the estimated end time can be determined according to the determination frequency of the production progress, that is, every time the production progress is updated, the estimated end time is updated at the same time.

[0076] Furthermore, the real-time production data, online inspection data and estimated end time of the current process are periodically summarized to obtain a dynamic sub-batch report of the current process, wherein the periodicity may be equal to a preset collection frequency.

[0077] In addition, models can be trained using historical real-time production data and online inspection data. Deep learning algorithms, such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), are used to train extracted key features, build an initial batch recognition model, and upload it to the model execution platform. The model uploaded to the model execution platform tracks the real-time and business data collected by the data acquisition and storage modules in real time. Upon identifying batch signals, it records the relevant batch recognition results. The AI ​​system regularly extracts relevant batch data and model result data for batch model optimization training and verification to improve model accuracy and generalization capabilities, and then updates the data to the model execution platform. The system also retains an interface for manual verification. If errors are found in the batch results, the corresponding batch results can be manually updated, and the results will be automatically included in the model training set during the next model optimization cycle.

[0078] In the actual production process, real-time production data and online verification data are input into the trained recognition model, and the model automatically inputs the batch recognition results, including the batch end time.

[0079] In this embodiment, when each process of the current batch is produced, the estimated end time of the current process is estimated based on the production progress in the real-time production data, so that production management personnel can understand the progress of the process in advance, which is convenient for the reasonable arrangement of subsequent work and resource allocation; the real-time production data, online inspection data and estimated end time of the current process are periodically summarized to generate a dynamic sub-batch report, which can timely reflect key information such as quality and progress in the process of process production, and realize dynamic monitoring of the production process.

[0080] An electronic device is provided in an embodiment of the present application, such as Figure 2 As shown, Figure 2 The electronic device 200 shown includes a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, for example, via a bus 202. Optionally, the electronic device 200 may further include a transceiver 204. It should be noted that in actual applications, the number of transceivers 204 is not limited to one, and the structure of the electronic device 200 does not constitute a limitation on the embodiments of the present application.

[0081] Processor 201 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 201 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0082] The bus 202 may include a path for transmitting information between the above components. The bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 202 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but it does not mean that there is only one bus or one type of bus.

[0083] The memory 203 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0084] The memory 203 is used to store application code for executing the solution of the present application, and is controlled by the processor 201. The processor 201 is used to execute the application code stored in the memory 203 to implement the content shown in the embodiment of the automatic identification method for chemical batch production.

[0085] Figure 2 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0086] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the contents shown in the aforementioned embodiment of the automatic identification method for chemical batch production.

[0087] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0088] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the contents shown in the aforementioned embodiment of the automatic identification method for chemical batch production are implemented.

[0089] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for automatic identification of chemical batch production, characterized in that: include: Acquiring historical production data and a production plan for a current batch, and determining baseline production parameters for the current batch based on the historical production data and the production plan; Starting production based on the baseline production parameters and acquiring real-time production data and online inspection data, wherein the real-time production data includes production progress; During the production process of each process of the current batch, dynamically adjusting the production parameters of the process based on the production plan, the online inspection data of the process and the production progress; After the current batch is completed, a summary batch report of the current batch is generated, and the summary batch report includes a sub-batch report of each process.

2. The automatic identification method for chemical batch production according to claim 1, characterized in that: The dynamically adjusting the production parameters of the process based on the production plan, the online inspection data of the process and the production progress includes: During the production process of the current process, determining whether there are quality problems with the intermediate product based on the online inspection data of the current process; If so, formulate and implement parameter adjustment strategies until the quality of the newly produced intermediate products is up to standard; After the current process is completed, formulate a rework sub-plan for all intermediate products with quality problems and implement the rework sub-plan; The production parameters of the subsequent process of the current process are adjusted based on the production plan, the production schedule and the rework sub-plan.

3. The automatic identification method for chemical batch production according to claim 2, characterized in that: The parameter adjustment strategy for the intermediate product with quality problems is formulated and implemented until the quality of the newly produced intermediate product is qualified, including: Determine the problem type of the intermediate product with quality problems, and retrieve a list of parameter adjustment methods corresponding to the problem type; Starting from the first parameter adjustment method in the parameter adjustment method list, each parameter adjustment method is executed in sequence, and a debugging production cycle is executed after each parameter adjustment method is executed, until the quality of the newly produced intermediate products in the debugging production cycle is qualified.

4. The automatic identification method for chemical batch production according to claim 2, characterized in that: The adjusting the production parameters of the subsequent process of the current process based on the production plan, the production schedule and the rework sub-plan includes: estimating the end time of the current process based on the production progress and the rework sub-plan; estimating whether the production end time of the current batch has exceeded the estimated end time based on the estimated end time and the production plan; If the production end time of the current batch is exceeded, the production parameters of the subsequent process of the current process are adjusted.

5. The automatic identification method for chemical batch production according to claim 1, characterized in that: Determining the baseline production parameters for the current batch based on the historical production data and the production plan includes: determining a planned production volume and a maximum production duration from the production plan; Based on the historical production data, selecting from a plurality of historical batches a number of historical batches whose production duration for producing the planned production volume does not exceed the maximum production duration; Determining quality indicator data of the plurality of historical batches from the historical production data; A target batch is determined from the several historical batches based on the quality indicator data, and historical production parameters of the target batch are used as the benchmark production parameters.

6. The automatic identification method for chemical batch production according to claim 1, characterized in that: The method further comprises: Determining, from the historical production data, a problem type of an intermediate product obtained in each historical process and a corresponding plurality of parameter adjustment methods, wherein the parameter adjustment method includes adjusting at least one production parameter; For each question type, a parameter adjustment method list for the question type is generated according to a plurality of parameter adjustment methods corresponding to the question type.

7. The automatic identification method for chemical batch production according to claim 1, characterized in that: The method further comprises: During the production process of each process of the current batch, estimating the estimated end time of the current process based on the production progress in the real-time production data; Periodically summarize the real-time production data, online inspection data, and estimated end time of the current process to obtain a dynamic sub-batch report of the current process; After the current process is completed, the latest dynamic sub-batch report is used as the sub-batch report of the current process.

8. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the chemical batch production automatic identification method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the automatic identification method for chemical batch production according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the steps of the automatic identification method for chemical batch production according to any one of claims 1 to 7.

Images