Industrial production line integrated control method and system based on intelligent manufacturing unit

Abstract

The invention relates to the technical field of industrial production line control, in particular to an industrial production line integrated control method and system based on an intelligent manufacturing unit. When the intelligent manufacturing unit matching set of the model number to be produced is empty, retrieving a production log of the model number to be produced by taking the schedulable equipment model number set as a constraint; traversing the plurality of production line equipment model sequences, and performing sequence outlier analysis to obtain a plurality of equipment model sequence outlier factors; traversing the plurality of production line equipment model sequences, and carrying out yield statistics to obtain the yield of the plurality of equipment model sequences; and based on the yield of the plurality of equipment model sequence and the plurality of equipment model sequence outlier factors, selecting an outlier factor minimum sequence of which the yield is greater than a yield threshold, setting the outlier factor minimum sequence as a temporary intelligent manufacturing unit, performing associated storage with the to-be-produced model, and executing industrial production line integrated control. According to the invention, self-adaptive equipment combination configuration of the to-be-produced model without preset matching configuration and production line integrated control can be realized.

Description

Technical Field

[0001] This invention relates to the field of industrial production line control technology, and in particular to an integrated control method and system for industrial production lines based on intelligent manufacturing units. Background Technology

[0002] Intelligent manufacturing units are commonly used in flexible production lines. By associating and storing equipment combination schemes with product models, the corresponding scheme is invoked to control the production line when a product model is triggered, thus addressing scenarios of multi-variety, low-batch production. However, traditional intelligent manufacturing units are often in a static configuration mode, only adapting to preset models in the configuration library. When faced with new models that have not yet appeared and are ready for production, manual intervention is required to define the configuration. This results in insufficient adaptability, leading to low production response efficiency for new models, increased labor costs, and the potential impact on production quality and process stability due to errors in manual configuration. Summary of the Invention

[0003] This invention addresses the problems of low production response efficiency and increased labor costs in existing technologies for new models by providing an integrated control method and system for industrial production lines based on intelligent manufacturing units.

[0004] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides an integrated control method for industrial production lines based on intelligent manufacturing units, comprising: when the matching set of intelligent manufacturing units for the model to be produced is empty, retrieving the production log of the model to be produced with the set of schedulable equipment models as constraints, wherein the production log of the model to be produced includes a sequence of several production line equipment models; Traverse the series of production line equipment models and perform outlier analysis to obtain outlier factors for the series of equipment models. By iterating through the series of production line equipment models, the yield rate is statistically analyzed to obtain the yield rate of the series of equipment models. Based on the yield rate and outlier factor of the aforementioned equipment model sequences, the smallest outlier sequence with a yield rate greater than the yield rate threshold is selected and set as a temporary intelligent manufacturing unit. It is then associated with and stored with the model to be produced, and industrial production line integrated control is executed.

[0005] Optionally, when the smart manufacturing unit matching set for the model to be produced is empty, it includes: Obtain a user-defined intelligent manufacturing unit configuration library, wherein any intelligent manufacturing unit in the intelligent manufacturing unit configuration library is used to store a uniquely corresponding production line equipment model sequence and a preset product model; Input the model to be produced into the intelligent manufacturing unit configuration library to obtain the intelligent manufacturing unit matching set.

[0006] Optionally, based on the set of schedulable equipment models, retrieve the production logs of the models awaiting production, including: Using the model to be produced as a constraint, retrieve the production log of the first model to be produced, and extract the first production line equipment model sequence from the production log of the first model to be produced; When all production line equipment models in the first production line equipment model sequence are included in the schedulable equipment model set, the production log of the first model to be produced is added to the production log of the model to be produced. Otherwise, update the production log of the first model to be produced and execute the retrieval loop.

[0007] Optionally, the sequence of production line equipment models is traversed, and outlier analysis is performed to obtain outlier factors for the equipment model sequences, including: Perform pairwise deviation analysis on the series of production line equipment models to obtain the series deviation distance set; Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; From the sequence deviation distance set, filter the sequence deviation distances with the first production line equipment model sequence from near to far, satisfying a preset number of the first sequence deviation distance set; Calculate the mean of the first sequence deviation distance set, then take its reciprocal, set it as the local density of the first sequence, and add it to the sequence local density set; The ratio of the mean of the local density set of the sequence to the local density of the first sequence is calculated and set as the outlier factor of the first equipment model sequence. This outlier factor is then added to the plurality of equipment model sequences.

[0008] Specifically, pairwise deviation analysis is performed on the sequence of production line equipment models to obtain a sequence deviation distance set, including: Extract the first production line equipment model sequence and the second production line equipment model sequence from the aforementioned production line equipment model sequences; Count the number of different equipment models with the same serial number in the first production line equipment model sequence and the second production line equipment model sequence; Count the number of long sequence numbers in the equipment model sequence of the first production line and the equipment model sequence of the second production line; Calculate the ratio of the number of different device models with the same serial number to the number of serial numbers to obtain the first sequence deviation distance, and add it to the sequence deviation distance set.

[0009] Optionally, the yield rate of the aforementioned production line equipment model sequences is traversed to obtain the yield rate of the various equipment model sequences, including: Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; Using the equipment model sequence of the first production line and the model to be produced as constraints, retrieve the set of yield rate records and the set of production scale; Box plot analysis is performed on the yield rate record value set to obtain the selected yield rate record value set distributed within the box; Select a selected production scale set from the production scale set to filter the selected yield rate record value set; By iterating through the selected production scale set and comparing it with the sum of the production scales of the selected production scale set, a fitted weight set is obtained; Based on the fitted weight set, a weighted average is calculated on the selected yield rate record value set to obtain the yield rate of the first equipment model sequence, which is then added to the yield rates of the plurality of equipment model sequences.

[0010] Optionally, based on the yield rate of the plurality of equipment model sequences and the outlier factor of the plurality of equipment model sequences, the sequence with the smallest outlier factor whose yield rate is greater than the yield rate threshold is selected and set as a temporary intelligent manufacturing unit, further comprising: Using the minimum outlier sequence and the model to be produced as constraints, retrieve the production log of the minimum outlier sequence, and count the frequent fluctuation range of control parameters for each serial number device, which is set as the control parameter fluctuation range sequence. Based on the minimum outlier sequence, the equipment production logs of the schedulable equipment model set are matched, and the frequent fluctuation ranges of control parameters for each tag number of the equipment are statistically analyzed to obtain the set of control parameter fluctuation ranges to be analyzed and the set of equipment tag numbers. Based on the set of control parameter fluctuation intervals to be analyzed and the set of equipment tag numbers, determine whether there is an equipment tag number sequence that satisfies the control parameter fluctuation interval sequence. If there is, output the corresponding equipment tag number sequence and set it as the temporary intelligent manufacturing unit. If not, delete the minimum sequence of outliers and perform a cyclical selection of temporary intelligent manufacturing units.

[0011] Specifically, using the minimum outlier sequence and the model to be produced as constraints, the production log of the minimum outlier sequence is retrieved, and the frequent fluctuation intervals of control parameters for each serial number of equipment are statistically analyzed and set as the control parameter fluctuation interval sequence, including: Obtain the set of control parameter fluctuation intervals for the first sequence device; Extract the first attribute control parameter fluctuation range set from the first sequence number device control parameter fluctuation range set; The crossover ratio of the control parameter fluctuation range is subtracted from 1 as the fluctuation range distance parameter, and the concentrated control parameter fluctuation range of the first attribute control parameter fluctuation range set is sorted. Calculate the upper limit average of the fluctuation range of the centralized control parameter and set it as the upper limit of the frequent interval. Calculate the lower limit average of the fluctuation range of the centralized control parameter and set it as the lower limit of the frequent interval. Construct the frequent interval of the first attribute control parameter fluctuation and add it to the first sequence number control parameter fluctuation interval. Once all attributes of the first sequence device have been analyzed, the fluctuation range of the first sequence device's control parameter is added to the control parameter fluctuation range sequence.

[0012] Secondly, the present invention provides an integrated control system for industrial production lines based on intelligent manufacturing units, comprising: The production log retrieval module is used to retrieve the production logs of the model to be produced when the matching set of intelligent manufacturing units for the model to be produced is empty, with the set of schedulable equipment models as constraints. The production logs of the model to be produced include a series of production line equipment models. The sequence outlier analysis module is used to traverse the sequence of production line equipment models, perform sequence outlier analysis, and obtain the outlier factors of the sequence of equipment models. The yield rate statistics module is used to traverse the series of production line equipment models, perform yield rate statistics, and obtain the yield rate of the series of equipment models. The production line integration control module is used to select the smallest sequence of outliers with a yield rate greater than the yield rate threshold based on the yield rate and outlier factors of the several equipment model sequences, set it as a temporary intelligent manufacturing unit, store it in association with the model to be produced, and execute industrial production line integration control.

[0013] Thirdly, this application provides a storage medium storing a first computer program, which, when executed by a processor, implements the industrial production line integrated control method based on intelligent manufacturing units in the first aspect.

[0014] By implementing this invention, when the matching set of intelligent manufacturing units for a model to be produced is empty, the production log of the model to be produced can be retrieved with the set of schedulable equipment models as a constraint. The production log of the model to be produced includes several production line equipment model sequences, avoiding the pre-set matching configuration of the model to be produced and directly falling into the predicament of manual intervention. By retrieving historical production logs, usable equipment combination references can be mined. At the same time, with the set of schedulable equipment models as a constraint, it is ensured that the retrieved equipment model sequences have actual feasibility and provide basic data that fits the actual production conditions for subsequent screening.

[0015] By implementing this invention, it is possible to traverse the sequence of production line equipment models, perform sequence outlier analysis, obtain outlier factors for several equipment model sequences, accurately identify abnormal sequences that differ significantly from most valid sequences, exclude equipment combination schemes that deviate from conventional production logic, reduce the interference of abnormal data on subsequent screening, ensure the consistency and reliability of candidate equipment sequences, and provide a basis for screening schemes that conform to general production rules.

[0016] By implementing this invention, it is possible to traverse the several production line equipment model sequences, perform yield rate statistics, obtain the yield rates of several equipment model sequences, eliminate abnormal yield rate data through box plot analysis, and assign different weights based on production scale, so that the statistical yield rates are more in line with the actual production effect, accurately reflect the production quality level of each equipment model sequence, and provide accurate data support for subsequent screening based on quality dimensions.

[0017] By implementing this invention, based on the yield rate and outlier factor of the aforementioned equipment model sequences, the sequence with the smallest outlier factor whose yield rate is greater than the yield rate threshold can be selected as a temporary intelligent manufacturing unit. This unit is then associated with and stored in conjunction with the model to be produced. Integrated control of the industrial production line is then executed, achieving a dual screening logic of quality compliance and conformity to conventions. This ensures that production quality meets requirements and that the selected equipment sequence conforms to general production patterns. Effective configuration can be matched for new models to be produced without manual intervention. At the same time, the associated storage provides a reference for the production of similar models in the future, improving subsequent processing efficiency.

[0018] In summary, by implementing this invention, adaptive equipment combination configuration and production line integration control of production models without preset matching configuration can be realized. Temporary intelligent manufacturing units that meet production feasibility, quality requirements and conventional production rules can be automatically generated without manual intervention, effectively improving the adaptability of flexible production lines to multi-variety, small-batch production scenarios, while ensuring the stability and reliability of production quality and production process. Attached Figure Description

[0019] Figure 1 A flowchart illustrating the integrated control method for industrial production lines based on intelligent manufacturing units provided by this invention; Figure 2 A schematic diagram of the structure of the industrial production line integrated control system based on intelligent manufacturing units provided by the present invention; Figure 3 This is a schematic diagram of a storage medium provided by the present invention.

[0020] In the attached diagram, the components represented by each number are as follows: Production log retrieval module 11, sequence outlier analysis module 12, yield rate statistics module 13, production line integrated control module 14, first computer program 410, storage medium 400. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0023] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0024] Example 1, as Figure 1 As shown, this embodiment of the invention provides an integrated control method for industrial production lines based on intelligent manufacturing units, including: S100: When the intelligent manufacturing unit matching set of the model to be produced is empty, the production log of the model to be produced is retrieved with the set of schedulable equipment models as constraints, wherein the production log of the model to be produced includes several production line equipment model sequences. S200: Traverse the series of production line equipment models, perform outlier analysis, and obtain outlier factors for the series of equipment models. S300: Traverse the series of production line equipment models, perform yield rate statistics, and obtain the yield rate of the series of equipment models; S400: Based on the yield rate of the several equipment model sequences and the outlier factor of the several equipment model sequences, select the smallest outlier sequence with a yield rate greater than the yield rate threshold, set it as a temporary intelligent manufacturing unit, store it in association with the model to be produced, and perform integrated control of the industrial production line.

[0025] In step S100 of this application embodiment, when the intelligent manufacturing unit matching set of the model to be produced is empty, it includes: Obtain a user-defined intelligent manufacturing unit configuration library, wherein any intelligent manufacturing unit in the intelligent manufacturing unit configuration library is used to store a uniquely corresponding production line equipment model sequence and a preset product model; Input the model to be produced into the intelligent manufacturing unit configuration library to obtain the intelligent manufacturing unit matching set.

[0026] In step S100 of this application embodiment, the purpose of the above step is to determine whether there is a predefined corresponding intelligent manufacturing unit for the model to be produced. If the matching set is empty, it means that there is no readily available predefined intelligent manufacturing unit that can be used for the model to be produced, and a dynamic retrieval and configuration process needs to be started subsequently; if the matching set is not empty, the corresponding predefined intelligent manufacturing unit can be used directly without additional processing, thereby quickly filtering whether further adaptive configuration is needed and avoiding unnecessary process consumption.

[0027] Specifically, it is necessary to obtain a user-defined intelligent manufacturing unit configuration library, wherein any intelligent manufacturing unit in the intelligent manufacturing unit configuration library is used to store a uniquely corresponding production line equipment model sequence and a preset product model.

[0028] For example, the preset production line equipment model sequence corresponding to product model A is: Equipment X, Equipment Y, Equipment Z, and the preset production line equipment model sequence corresponding to product model B is: Equipment M, Equipment N. These correspondences are all pre-stored in the intelligent manufacturing unit configuration library.

[0029] Then, the model to be produced is input into the intelligent manufacturing unit configuration library to obtain the intelligent manufacturing unit matching set. That is, the model to be produced is input into this intelligent manufacturing unit configuration library and compared with all preset product models in the library. All intelligent manufacturing units corresponding to preset product models that match the model to be produced are collected to form the intelligent manufacturing unit matching set. For example, if the model to be produced is A, the intelligent manufacturing units corresponding to preset product model A in the intelligent manufacturing unit configuration library are filtered out to form the intelligent manufacturing unit matching set; if the model to be produced is C, and there is no intelligent manufacturing unit corresponding to preset product model C in the intelligent manufacturing unit configuration library, then the intelligent manufacturing unit matching set is empty.

[0030] In step S100 of this application embodiment, the production log of the model to be produced is retrieved based on the set of schedulable equipment models, including: Using the model to be produced as a constraint, retrieve the production log of the first model to be produced, and extract the first production line equipment model sequence from the production log of the first model to be produced; When all production line equipment models in the first production line equipment model sequence are included in the schedulable equipment model set, the production log of the first model to be produced is added to the production log of the model to be produced. Otherwise, update the production log of the first model to be produced and execute the retrieval loop.

[0031] In step S100 of this embodiment, the purpose of the above step is to filter out the production logs of the models to be produced that meet the current production conditions. By using the set of schedulable equipment models as a constraint, it is ensured that all equipment models in the production line equipment model sequence corresponding to the retrieved production logs can be found in the currently schedulable equipment. This avoids the subsequent selection of temporary intelligent manufacturing units from being unable to be implemented due to the inclusion of unschedulable equipment. Simultaneously, it accurately collects valid production logs, providing a reliable data foundation for subsequent sequence outlier analysis and yield rate statistics.

[0032] To achieve the above steps, it is first necessary to retrieve the production log of the first production model based on the model to be produced, and extract the first production line equipment model sequence from the production log of the first production model.

[0033] This means using the model to be produced as a constraint, retrieving the production logs of the first model to be produced, and extracting the equipment model sequence of the first production line from them. For example, if the model to be produced is C, the retrieved production logs of the first model to be produced would contain the equipment model sequence of the first production line: equipment P, equipment Q, and equipment R.

[0034] When all production line equipment models in the first production line equipment model sequence are included in the schedulable equipment model set, the production log of the first model to be produced is added to the production log of the model to be produced.

[0035] This involves determining whether all equipment models in the first production line's equipment model sequence are included in the set of schedulable equipment models. Continuing with the previous example, if the first production line's equipment model sequence is equipment P, equipment Q, and equipment R, and equipment R is not in the set of schedulable equipment models, then this first production line's equipment model sequence does not meet the condition. However, if another first production line's equipment model sequence is found to be equipment P, equipment Q, and equipment S, and all of its equipment models are in the set of schedulable equipment models, then the condition is met.

[0036] If the conditions are met, the corresponding production log for the first model awaiting production will be added to the production log for the model awaiting production. For example, the production logs for the first models awaiting production for devices P, Q, and S will be included in the production log for the model awaiting production.

[0037] Otherwise, update the production log of the first model to be produced and execute the retrieval loop.

[0038] If the conditions are not met, update the production log of the first model awaiting production, and re-execute the search loop until a production log that meets the conditions is found or all relevant logs are retrieved. For example, if the production logs of the first model awaiting production for equipment P, equipment Q, and equipment R do not meet the conditions, update the search objects, continue searching for other first model awaiting production logs, and repeat the above judgment process.

[0039] In step S200 of this application embodiment, sequence outlier analysis is performed to obtain outlier factors for several equipment model sequences, including: Perform pairwise deviation analysis on the series of production line equipment models to obtain the series deviation distance set; Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; From the sequence deviation distance set, filter the sequence deviation distances with the first production line equipment model sequence from near to far, satisfying a preset number of the first sequence deviation distance set; Calculate the mean of the first sequence deviation distance set, then take its reciprocal, set it as the local density of the first sequence, and add it to the sequence local density set; The ratio of the mean of the local density set of the sequence to the local density of the first sequence is calculated and set as the outlier factor of the first equipment model sequence. This outlier factor is then added to the plurality of equipment model sequences.

[0040] In this embodiment of the application, the purpose of step S200 is to quantify the deviation of each production line equipment model sequence. By calculating the outlier factor of the equipment model sequence, the production line equipment model sequence that is less different from most production line equipment model sequences and is more representative is distinguished. This provides key indicators for the subsequent selection of the optimal temporary intelligent manufacturing unit, avoids the selection of production line equipment model sequences that deviate from the general rule and have poor stability, and ensures the reliability of subsequent production control.

[0041] To achieve the above objectives, it is first necessary to perform pairwise deviation analysis on the series of production line equipment models to obtain the series deviation distance set.

[0042] In step S200 of this application embodiment, pairwise deviation analysis is performed on the sequence of production line equipment models to obtain a sequence deviation distance set, including: Extract the first production line equipment model sequence and the second production line equipment model sequence from the aforementioned production line equipment model sequences; Count the number of different equipment models with the same serial number in the first production line equipment model sequence and the second production line equipment model sequence; Count the number of long sequence numbers in the equipment model sequence of the first production line and the equipment model sequence of the second production line; Calculate the ratio of the number of different device models with the same serial number to the number of serial numbers to obtain the first sequence deviation distance, and add it to the sequence deviation distance set.

[0043] In this embodiment of the application, the purpose of obtaining the sequence deviation distance set is to quantify the degree of difference between any two production line equipment model sequences, and then to select more representative sequences.

[0044] Specifically, the first step is to extract the first production line equipment model sequence and the second production line equipment model sequence from the aforementioned production line equipment model sequences.

[0045] This involves extracting the first and second production line equipment model sequences from a set of production line equipment model sequences. For example, if the set of production line equipment model sequences includes sequence A: equipment 1, equipment 2, equipment 3; sequence B: equipment 1, equipment 4, equipment 3, equipment 5; and sequence C: equipment 6, equipment 2, equipment 3, then sequence A is extracted as the first production line equipment model sequence, and sequence B is extracted as the second production line equipment model sequence.

[0046] The second step is to count the number of different equipment models with the same serial number in the first production line equipment model sequence and the second production line equipment model sequence.

[0047] This involves counting the number of different equipment models with the same serial number in the equipment model sequence of the first production line and the equipment model sequence of the second production line. Continuing the example above, serial number 1 in sequence A is equipment 1, and serial number 1 in sequence B is equipment 1; they have the same serial number and the same equipment model. Serial number 2 in sequence A is equipment 2, and serial number 2 in sequence B is equipment 4; they have the same serial number but different equipment models. Serial number 3 in sequence A is equipment 3, and serial number 3 in sequence B is equipment 3; they have the same serial number and the same equipment model. Serial number 4 in sequence B is equipment 5; there is no corresponding equipment with serial number 4 in sequence A, so this serial number is not counted. Therefore, the number of different equipment models with the same serial number is 1.

[0048] The third step is to count the number of long sequence numbers in the first production line equipment model sequence and the second production line equipment model sequence.

[0049] Using the previous example, sequence A has 3 numbers and sequence B has 4 numbers. Therefore, the longer sequence is sequence B, which has 4 numbers.

[0050] The fourth step is to calculate the ratio of the number of different device models with the same serial number to the number of serial numbers, obtain the first sequence deviation distance, and add it to the sequence deviation distance set.

[0051] Using the previous example, the number of different device models with the same serial number is 1, and the number of serial numbers in the long sequence is 4. Therefore, the first sequence deviation distance is 1 / 4 = 0.25. This value is added to the sequence deviation distance set.

[0052] Repeat the above steps to extract different combinations as the first production line equipment model sequence and the second production line equipment model sequence. For example, extract sequence A and sequence C, sequence B and sequence C, calculate the corresponding first sequence deviation distance, add them all to the sequence deviation distance set, and finally form a complete sequence deviation distance set.

[0053] Furthermore, it is necessary to extract the first production line equipment model sequence from the aforementioned production line equipment model sequences; This involves extracting the first production line equipment model sequence from a series of production line equipment model sequences. For example, if the series of production line equipment model sequences include sequence 1: equipment A, equipment B, equipment C; sequence 2: equipment A, equipment D, equipment C; sequence 3: equipment E, equipment B, equipment F; and sequence 4: equipment A, equipment B, equipment D, then sequence 1 is extracted as the first production line equipment model sequence.

[0054] Then, from the sequence deviation distance set, the sequence deviation distances with the first production line equipment model sequence are filtered from near to far, satisfying a preset number of first sequence deviation distance sets.

[0055] Assuming the preset quantity is 3, the deviation distances related to sequence 1 in the sequence deviation distance set are 0.33 between sequence 1 and sequence 2, 0.25 between sequence 1 and sequence 4, and 0.67 between sequence 1 and sequence 3. Sorted from near to far, they are 0.25, 0.33, and 0.67. The first 3 are selected to form the first sequence deviation distance set of 0.25, 0.33, and 0.67.

[0056] Next, the mean of the first sequence deviation distance set is calculated, and its reciprocal is taken as the local density of the first sequence, which is then added to the sequence local density set.

[0057] Assume the mean of the first sequence deviation distance set is (0.25+0.33+0.67) / 3≈0.417, and the reciprocal is 1 / 0.417≈2.4, that is, the local density of the first sequence is 2.4, and add it to the sequence local density set.

[0058] Finally, the ratio of the mean of the local density set of the sequence to the local density of the first sequence is calculated and set as the outlier factor of the first equipment model sequence, and added to the outlier factors of the several equipment model sequences.

[0059] Suppose that the local density set of the sequence contains 2.4 for sequence 1, 2.1 for sequence 2, 1.8 for sequence 3, and 2.3 for sequence 4, with a mean of (2.4+2.1+1.8+2.3) / 4=2.15. The outlier factor of the first equipment model sequence is 2.15 / 2.4≈0.896. Add it to the outlier factors of several equipment model sequences.

[0060] Repeat the above steps to extract sequence 2, sequence 3, and sequence 4 as the first production line equipment model sequence. Calculate the first sequence deviation distance set, local density, and outlier factor for each sequence, and add them all to the corresponding set. Finally, obtain the outlier factor for all production line equipment model sequences.

[0061] In step S300 of this application embodiment, the yield rate is statistically analyzed by traversing the plurality of production line equipment model sequences to obtain the yield rate of the plurality of equipment model sequences, including: Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; Using the equipment model sequence of the first production line and the model to be produced as constraints, retrieve the set of yield rate records and the set of production scale; Box plot analysis is performed on the yield rate record value set to obtain the selected yield rate record value set distributed within the box; Select a selected production scale set from the production scale set to filter the selected yield rate record value set; By iterating through the selected production scale set and comparing it with the sum of the production scales of the selected production scale set, a fitted weight set is obtained; Based on the fitted weight set, a weighted average is calculated on the selected yield rate record value set to obtain the yield rate of the first equipment model sequence, which is then added to the yield rates of the plurality of equipment model sequences.

[0062] In this embodiment of the application, the purpose of step S300 is to accurately calculate the yield rate corresponding to each production line equipment model sequence. By eliminating abnormal yield rate data and assigning weights based on production scale, a yield rate of equipment model sequence that is more in line with the actual production situation is obtained. This provides a reliable quantitative basis for the subsequent selection of temporary intelligent manufacturing units that meet the yield rate standard, ensuring that the selected equipment model sequence can guarantee production quality.

[0063] To achieve the above objective, it is first necessary to extract the first production line equipment model sequence from the aforementioned production line equipment model sequences.

[0064] This involves extracting the first production line equipment model sequence from a set of production line equipment model sequences. For example, if the set of production line equipment model sequences includes sequence A: equipment X, equipment Y, equipment Z; and sequence B: equipment M, equipment Y, equipment Z, then sequence A is extracted as the first production line equipment model sequence.

[0065] Then, using the first production line equipment model sequence and the model to be produced as constraints, the yield rate record value set and the production scale set are retrieved.

[0066] Assuming the product model to be produced is product C, the set of yield records for producing product C using sequence A is found to be 92%, 93%, 85%, 95%, and 78%, with corresponding production scale sets of 500 units, 800 units, 300 units, 1000 units, and 200 units.

[0067] Next, a box plot analysis is performed on the set of yield rate records to obtain the selected set of yield rate records distributed within the box.

[0068] For example, box plot analysis revealed that 78% and 85% were outliers located outside the box. After removing them, the selected yield rate records distributed inside the box were 92%, 93%, and 95%.

[0069] Further, the selected production scale set is selected from the selected yield rate record value set.

[0070] For example, the production scales corresponding to the selected yield rate records of 92%, 93%, and 95% are 500 units, 800 units, and 1000 units, respectively. Therefore, the selected production scale set is 500 units, 800 units, and 1000 units.

[0071] Then, iterate through the selected production scale set and compare it with the sum of the production scales of the selected production scale set to obtain the fitted weight set.

[0072] For example, the selected production scale sum is 500 + 800 + 1000 = 2300 units. Calculate the ratio of each production scale to the production scale sum, such as: 500 / 2300 ≈ 0.217, 800 / 2300 ≈ 0.348, 1000 / 2300 ≈ 0.435. This yields the fitted weight set as 0.217, 0.348, and 0.435.

[0073] Finally, based on the fitted weight set, a weighted average is calculated on the selected yield rate record value set to obtain the yield rate of the first equipment model sequence, which is then added to the yield rates of the plurality of equipment model sequences.

[0074] Based on the fitted weight set, a weighted average is calculated on the selected set of yield rate records to obtain the yield rate of the first equipment model sequence, which is then added to the yield rates of several equipment model sequences. The weighted average calculation process is 92%×0.217+93%×0.348+95%×0.435≈93.7%, meaning the yield rate of the first equipment model sequence is 93.7%, and this is added to the yield rates of several equipment model sequences.

[0075] Repeat the above steps to extract the equipment model sequences of other production lines as the first production line equipment model sequence, calculate the yield rate of the corresponding equipment model sequence, add them all to the yield rate of several equipment model sequences, and finally obtain the yield rate of all production line equipment model sequences.

[0076] In step S400 of this embodiment, based on the yield rate of the plurality of equipment model sequences and the outlier factor of the plurality of equipment model sequences, the sequence with the smallest outlier factor whose yield rate is greater than the yield rate threshold is selected and set as a temporary intelligent manufacturing unit, and the process further includes: Using the minimum outlier sequence and the model to be produced as constraints, retrieve the production log of the minimum outlier sequence, and count the frequent fluctuation range of control parameters for each serial number device, which is set as the control parameter fluctuation range sequence. Based on the minimum outlier sequence, the equipment production logs of the schedulable equipment model set are matched, and the frequent fluctuation ranges of control parameters for each tag number of the equipment are statistically analyzed to obtain the set of control parameter fluctuation ranges to be analyzed and the set of equipment tag numbers. Based on the set of control parameter fluctuation intervals to be analyzed and the set of equipment tag numbers, determine whether there is an equipment tag number sequence that satisfies the control parameter fluctuation interval sequence. If there is, output the corresponding equipment tag number sequence and set it as the temporary intelligent manufacturing unit. If not, delete the minimum sequence of outliers and perform a cyclical selection of temporary intelligent manufacturing units.

[0077] In this embodiment of the application, the purpose of step S400 is to verify whether the initially selected minimum outlier sequence can be implemented in the currently schedulable equipment. By matching the fluctuation range of the equipment control parameters, it is ensured that the temporary intelligent manufacturing unit not only meets the requirements of yield and outlier, but also adapts to the operating capabilities of the existing schedulable equipment, avoiding the inability to carry out production normally or the product quality failing to meet the standards due to incompatible equipment parameters. At the same time, the cyclic selection mechanism ensures that the optimal temporary intelligent manufacturing unit that meets the actual production conditions can be found.

[0078] To achieve the above objectives, it is first necessary to use the minimum outlier sequence and the model to be produced as constraints to retrieve the production log of the minimum outlier sequence, and to count the frequent fluctuation range of the control parameters of each serial number device, which is set as the control parameter fluctuation range sequence.

[0079] In step S400 of this application embodiment, using the minimum outlier sequence and the model to be produced as constraints, the production log of the minimum outlier sequence is retrieved, and the frequent fluctuation intervals of control parameters for each serial number device are statistically analyzed and set as the control parameter fluctuation interval sequence, including: Obtain the set of control parameter fluctuation intervals for the first sequence device; Extract the first attribute control parameter fluctuation range set from the first sequence number device control parameter fluctuation range set; The crossover ratio of the control parameter fluctuation range is subtracted from 1 as the fluctuation range distance parameter, and the concentrated control parameter fluctuation range of the first attribute control parameter fluctuation range set is sorted. Calculate the upper limit average of the fluctuation range of the centralized control parameter and set it as the upper limit of the frequent interval. Calculate the lower limit average of the fluctuation range of the centralized control parameter and set it as the lower limit of the frequent interval. Construct the frequent interval of the first attribute control parameter fluctuation and add it to the first sequence number control parameter fluctuation interval. Once all attributes of the first sequence device have been analyzed, the fluctuation range of the first sequence device's control parameter is added to the control parameter fluctuation range sequence.

[0080] In step S400 of this application embodiment, the purpose of the above-mentioned subdivision step is to accurately determine the frequent fluctuation range of each attribute control parameter of each serial number device in the outlier factor minimum sequence, form a control parameter fluctuation range sequence, provide a clear standard for the parameter capability of subsequent matching of schedulable devices, ensure that the subsequent selected device number sequence can meet the production parameter requirements of the sequence, and ensure the operational stability and product quality consistency of the temporary intelligent manufacturing unit.

[0081] Specifically, the first step is to obtain the set of control parameter fluctuation ranges for the first sequence device.

[0082] Assume the smallest outlier sequence is: Equipment A, Equipment B, Equipment C; the first-order equipment is: Equipment A. Retrieve the production logs of its upcoming product model and extract the fluctuation ranges of the two core control parameters, temperature and pressure. This yields the control parameter fluctuation range set for the first-order equipment, including temperature and pressure fluctuation range sets. For example, the temperature fluctuation range sets are: 198-208℃, 200-210℃, 202-212℃, 199-209℃; the pressure fluctuation range sets are: 0.28-0.38MPa, 0.3-0.4MPa, 0.31-0.41MPa, 0.29-0.39MPa.

[0083] The second step is to extract the first attribute control parameter fluctuation range set from the first sequence number device control parameter fluctuation range set.

[0084] For example, if temperature is selected as the first attribute, the corresponding set of fluctuation ranges for the first attribute control parameters are 198-208℃, 200-210℃, 202-212℃, and 199-209℃.

[0085] The third step is to use 1 minus the intersection-union ratio of the control parameter fluctuation intervals as the fluctuation interval distance parameter to sort the centralized control parameter fluctuation intervals of the first attribute control parameter fluctuation interval set.

[0086] Specifically, the intersection-union ratio (IUR) is calculated as the ratio of the length of the intersection of two intervals to the length of the union of the two intervals. For example, to calculate the IUR of 198-208℃ and 200-210℃: the intersection is 200-208℃ with a length of 8℃; the union is 198-210℃ with a length of 12℃; the IUR is 8 / 12≈0.667, and the fluctuation interval distance parameter is 1-0.667≈0.333.

[0087] Calculate the fluctuation range distance parameter between each pair of all intervals under the first attribute in turn, and filter out the intervals with smaller distance parameters and higher degree of clustering. Assume that after filtering, the concentrated control parameter fluctuation ranges are 199-209℃, 200-210℃, and 202-212℃.

[0088] The fourth step is to calculate the upper limit average of the fluctuation range of the centralized control parameter and set it as the upper limit of the frequent interval. Calculate the lower limit average of the fluctuation range of the centralized control parameter and set it as the lower limit of the frequent interval. Construct the frequent interval of the first attribute control parameter fluctuation and add it to the fluctuation interval of the first sequence control parameter.

[0089] The upper limits of the centralized control parameter fluctuation range are 209℃, 210℃, and 212℃, with an average upper limit of (209+210+212) / 3=210.33℃, rounded to 210℃; the lower limits are 199℃, 200℃, and 202℃, with an average lower limit of (199+200+202) / 3=200.33℃, rounded to 200℃.

[0090] The control parameter fluctuation range for the first attribute temperature is then set to 200-210℃, and this range is added to the first sequence control parameter fluctuation range.

[0091] The fifth step is to add the control parameter fluctuation range of the first sequence number to the control parameter fluctuation range sequence after all attribute analysis of the first sequence number device is completed.

[0092] Analyze other attributes of the first-order device. For example, analyze the pressure attribute, and the final result shows that the pressure control parameter fluctuates frequently in the range of 0.3-0.4 MPa, which is added to the first-order control parameter fluctuation range. When all attributes of the first-order device are analyzed, the first-order control parameter fluctuation range is 200-210℃ and 0.3-0.4 MPa, which is added to the control parameter fluctuation range sequence.

[0093] The above steps are then performed sequentially on other devices in the minimum outlier sequence, such as the second device B and the third device C, to obtain the frequent fluctuation ranges of the control parameters for all their respective attributes, ultimately forming a complete sequence of control parameter fluctuation ranges.

[0094] Furthermore, based on the minimum outlier sequence, it is necessary to match the equipment production logs of the schedulable equipment model set, count the frequent fluctuation ranges of control parameters for each tag number of the equipment, and obtain the set of control parameter fluctuation ranges to be analyzed and the set of equipment tag numbers.

[0095] Assume the minimum outlier sequence is device X, device Y, and device Z. The set of schedulable device models includes device X, device Y, device Z, device M (same model as device X), and device N (same model as device Y). Each device corresponds to a unique device number, namely: number 101 (device X), number 102 (device M), number 201 (device Y), number 202 (device N), and number 301 (device Z).

[0096] Match the equipment model with the smallest outlier sequence, retrieve the production logs for each equipment tag number, and statistically analyze the frequent fluctuation ranges of core control parameters: Tag number 101 (equipment X) frequent temperature fluctuation range 180-190℃, frequent pressure fluctuation range 0.4-0.5MPa; Tag number 102 (equipment M) frequent temperature fluctuation range 182-192℃, frequent pressure fluctuation range 0.38-0.48MPa; Tag number 201 (equipment Y) frequent speed fluctuation range 2000-2100r / min; Tag number 202 (equipment N) frequent speed fluctuation range 1950-2050r / min; Tag number 301 (equipment Z) frequent flow rate fluctuation range 50-60L / h.

[0097] This results in the following set of control parameter fluctuation ranges to be analyzed: 180-190℃, 0.4-0.5MPa, 182-192℃, 0.38-0.48MPa, 2000-2100r / min, 1950-2050r / min, 50-60L / h, and equipment tag number set: 101, 102, 201, 202, 301.

[0098] Next, based on the set of fluctuation intervals of the control parameters to be analyzed and the set of equipment tag numbers, it is necessary to determine whether there is a sequence of equipment tag numbers that satisfies the sequence of fluctuation intervals of the control parameters. If there is, the corresponding sequence of equipment tag numbers is output and set as the temporary intelligent manufacturing unit.

[0099] Assuming that the previously obtained control parameter fluctuation range sequence is: temperature 180-190℃, speed 2000-2100r / min, flow rate 50-60L / h, the core parameter requirements of equipment types X, Y, and Z corresponding to the minimum outlier sequence are as follows.

[0100] The device tag number set is selected to match the tag numbers for each control parameter range. For example, the tag number 101 corresponds to a temperature of 180-190℃, the tag number 201 corresponds to a speed of 2000-2100 r / min, and the tag number 301 corresponds to a flow rate of 50-60 L / h, forming the device tag number sequence 101, 201, and 301. The parameter fluctuation range of this device tag number sequence fully meets the requirements of the control parameter fluctuation range sequence.

[0101] If not, delete the minimum sequence of outliers and perform a cyclical selection of temporary intelligent manufacturing units.

[0102] Assuming the control parameter fluctuation range sequence is temperature 175-185℃, speed 2050-2150r / min, and flow rate 55-65L / h, after searching the set of control parameter fluctuation ranges to be analyzed, it is found that the speed fluctuation range without equipment tag number can cover 2050-2150r / min, and there are no other dispatchable equipment of the same model that meet this requirement. Therefore, it is determined that there is no equipment tag number sequence that meets the conditions.

[0103] If the sequence with the smallest outlier factor is removed from the candidate equipment tag number sequence, the process returns to the previous screening step. The equipment tag number sequence with the smallest outlier factor and a yield rate greater than the yield rate threshold is selected from the remaining production line equipment model sequence. The matching and verification process is repeated until a suitable equipment tag number sequence is found as a temporary intelligent manufacturing unit, or it is confirmed that there is no available equipment tag number sequence.

[0104] Example 2, as Figure 2 As shown, based on the same inventive concept as the intelligent manufacturing unit-based industrial production line integrated control method provided in Embodiment 1, this embodiment of the invention also provides an intelligent manufacturing unit-based industrial production line integrated control system, including: The production log retrieval module 11 is used to retrieve the production log of the model to be produced when the intelligent manufacturing unit matching set of the model to be produced is empty, with the set of schedulable equipment models as a constraint. The production log of the model to be produced includes a series of production line equipment models. Sequence outlier analysis module 12 is used to traverse the several production line equipment model sequences, perform sequence outlier analysis, and obtain several equipment model sequence outlier factors. The yield rate statistics module 13 is used to traverse the series of production line equipment models, perform yield rate statistics, and obtain the yield rate of the series of equipment models. The production line integration control module 14 is used to select the smallest sequence of outliers with a yield rate greater than the yield rate threshold based on the yield rate of the plurality of equipment model sequences and the outlier factors of the plurality of equipment model sequences, set it as a temporary intelligent manufacturing unit, store it in association with the model to be produced, and perform industrial production line integration control.

[0105] Furthermore, the production log retrieval module 11 includes the following execution steps: Obtain a user-defined intelligent manufacturing unit configuration library, wherein any intelligent manufacturing unit in the intelligent manufacturing unit configuration library is used to store a uniquely corresponding production line equipment model sequence and a preset product model; Input the model to be produced into the intelligent manufacturing unit configuration library to obtain the intelligent manufacturing unit matching set.

[0106] Using the model to be produced as a constraint, retrieve the production log of the first model to be produced, and extract the first production line equipment model sequence from the production log of the first model to be produced; When all production line equipment models in the first production line equipment model sequence are included in the schedulable equipment model set, the production log of the first model to be produced is added to the production log of the model to be produced. Otherwise, update the production log of the first model to be produced and execute the retrieval loop.

[0107] Furthermore, the sequence outlier analysis module 12 includes the following execution steps: Perform pairwise deviation analysis on the series of production line equipment models to obtain the series deviation distance set; Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; From the sequence deviation distance set, filter the sequence deviation distances with the first production line equipment model sequence from near to far, satisfying a preset number of the first sequence deviation distance set; Calculate the mean of the first sequence deviation distance set, then take its reciprocal, set it as the local density of the first sequence, and add it to the sequence local density set; The ratio of the mean of the local density set of the sequence to the local density of the first sequence is calculated and set as the outlier factor of the first equipment model sequence. This outlier factor is then added to the plurality of equipment model sequences.

[0108] Specifically, pairwise deviation analysis is performed on the sequence of production line equipment models to obtain a sequence deviation distance set, including: Extract the first production line equipment model sequence and the second production line equipment model sequence from the aforementioned production line equipment model sequences; Count the number of different equipment models with the same serial number in the first production line equipment model sequence and the second production line equipment model sequence; Count the number of long sequence numbers in the equipment model sequence of the first production line and the equipment model sequence of the second production line; Calculate the ratio of the number of different device models with the same serial number to the number of serial numbers to obtain the first sequence deviation distance, and add it to the sequence deviation distance set.

[0109] Furthermore, the yield rate statistics module 13 includes the following execution steps: Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; Using the equipment model sequence of the first production line and the model to be produced as constraints, retrieve the set of yield rate records and the set of production scale; Box plot analysis is performed on the yield rate record value set to obtain the selected yield rate record value set distributed within the box; Select a selected production scale set from the production scale set to filter the selected yield rate record value set; By iterating through the selected production scale set and comparing it with the sum of the production scales of the selected production scale set, a fitted weight set is obtained; Based on the fitted weight set, a weighted average is calculated on the selected yield rate record value set to obtain the yield rate of the first equipment model sequence, which is then added to the yield rates of the plurality of equipment model sequences.

[0110] Furthermore, the production line integrated control module 14 includes the following execution steps: Using the minimum outlier sequence and the model to be produced as constraints, retrieve the production log of the minimum outlier sequence, and count the frequent fluctuation range of control parameters for each serial number device, which is set as the control parameter fluctuation range sequence. Based on the minimum outlier sequence, the equipment production logs of the schedulable equipment model set are matched, and the frequent fluctuation ranges of control parameters for each tag number of the equipment are statistically analyzed to obtain the set of control parameter fluctuation ranges to be analyzed and the set of equipment tag numbers. Based on the set of control parameter fluctuation intervals to be analyzed and the set of equipment tag numbers, determine whether there is an equipment tag number sequence that satisfies the control parameter fluctuation interval sequence. If there is, output the corresponding equipment tag number sequence and set it as the temporary intelligent manufacturing unit. If not, delete the minimum sequence of outliers and perform a cyclical selection of temporary intelligent manufacturing units.

[0111] Specifically, using the minimum outlier sequence and the model to be produced as constraints, the production log of the minimum outlier sequence is retrieved, and the frequent fluctuation intervals of control parameters for each serial number of equipment are statistically analyzed and set as the control parameter fluctuation interval sequence, including: Obtain the set of control parameter fluctuation intervals for the first sequence device; Extract the first attribute control parameter fluctuation range set from the first sequence number device control parameter fluctuation range set; The crossover ratio of the control parameter fluctuation range is subtracted from 1 as the fluctuation range distance parameter, and the concentrated control parameter fluctuation range of the first attribute control parameter fluctuation range set is sorted. Calculate the upper limit average of the fluctuation range of the centralized control parameter and set it as the upper limit of the frequent interval. Calculate the lower limit average of the fluctuation range of the centralized control parameter and set it as the lower limit of the frequent interval. Construct the frequent interval of the first attribute control parameter fluctuation and add it to the first sequence number control parameter fluctuation interval. Once all attributes of the first sequence device have been analyzed, the fluctuation range of the first sequence device's control parameter is added to the control parameter fluctuation range sequence.

[0112] Example 3, as Figure 3As shown, based on the same inventive concept as the industrial production line integrated control method based on intelligent manufacturing units provided in Embodiment 1, this embodiment of the invention also provides a storage medium 400. For example, the storage medium can be a non-transitory computer-readable storage medium, in which a first computer program 410 is stored. When the first computer program 410 is executed by a processor, it implements the industrial production line integrated control method based on intelligent manufacturing units as described in Embodiment 1.

[0113] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0114] Those skilled in the art will understand that embodiments of the present invention can provide methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Clearly, those skilled in the art can make various alterations and variations to the invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the invention and its equivalents, the invention is also intended to include these modifications and variations.

Claims

1. An integrated control method for industrial production lines based on intelligent manufacturing units, characterized in that, include: When the matching set of intelligent manufacturing units for the model to be produced is empty, the production log of the model to be produced is retrieved with the set of schedulable equipment models as a constraint. The production log of the model to be produced includes several production line equipment model sequences. Traverse the series of production line equipment models and perform outlier analysis to obtain outlier factors for the series of equipment models. By iterating through the series of production line equipment models, the yield rate is statistically analyzed to obtain the yield rate of the series of equipment models. Based on the yield rate and outlier factor of the aforementioned equipment model sequences, the smallest outlier sequence with a yield rate greater than the yield rate threshold is selected and set as a temporary intelligent manufacturing unit. It is then associated with and stored with the model to be produced, and industrial production line integrated control is executed.

2. The industrial production line integrated control method based on intelligent manufacturing units as described in claim 1, characterized in that, When the intelligent manufacturing unit matching set for the model to be produced is empty, it includes: Obtain a user-defined intelligent manufacturing unit configuration library, wherein any intelligent manufacturing unit in the intelligent manufacturing unit configuration library is used to store a uniquely corresponding production line equipment model sequence and a preset product model; Input the model to be produced into the intelligent manufacturing unit configuration library to obtain the intelligent manufacturing unit matching set.

3. The industrial production line integrated control method based on intelligent manufacturing units as described in claim 1, characterized in that, Using the set of schedulable equipment models as constraints, retrieve the production logs for models awaiting production, including: Using the model to be produced as a constraint, retrieve the production log of the first model to be produced, and extract the first production line equipment model sequence from the production log of the first model to be produced; When all production line equipment models in the first production line equipment model sequence are included in the schedulable equipment model set, the production log of the first model to be produced is added to the production log of the model to be produced. Otherwise, update the production log of the first model to be produced and execute the retrieval loop.

4. The industrial production line integrated control method based on intelligent manufacturing units as described in claim 1, characterized in that, By traversing the various production line equipment model sequences, outlier analysis is performed to obtain several outlier factors for the equipment model sequences, including: Perform pairwise deviation analysis on the series of production line equipment models to obtain the sequence deviation distance set; Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; From the sequence deviation distance set, filter the sequence deviation distances with the first production line equipment model sequence from near to far, satisfying a preset number of the first sequence deviation distance set; Calculate the mean of the first sequence deviation distance set, then take its reciprocal, set it as the local density of the first sequence, and add it to the sequence local density set; The ratio of the mean of the local density set of the sequence to the local density of the first sequence is calculated and set as the outlier factor of the first equipment model sequence. This outlier factor is then added to the plurality of equipment model sequences.

5. The industrial production line integrated control method based on intelligent manufacturing units as described in claim 4, characterized in that, Perform pairwise deviation analysis on the aforementioned production line equipment model sequences to obtain the sequence deviation distance set, including: Extract the first production line equipment model sequence and the second production line equipment model sequence from the aforementioned production line equipment model sequences; Count the number of different equipment models with the same serial number in the first production line equipment model sequence and the second production line equipment model sequence; Count the number of long sequence numbers in the equipment model sequence of the first production line and the equipment model sequence of the second production line; Calculate the ratio of the number of different device models with the same serial number to the number of serial numbers to obtain the first sequence deviation distance, and add it to the sequence deviation distance set.

6. The industrial production line integrated control method based on intelligent manufacturing units as described in claim 1, characterized in that, By iterating through the various production line equipment model sequences, yield rate statistics are performed to obtain the yield rates for several equipment model sequences, including: Extract the first production line equipment model sequence from the plurality of production line equipment model sequences; Using the equipment model sequence of the first production line and the model to be produced as constraints, retrieve the set of yield rate records and the set of production scale; Box plot analysis is performed on the yield rate record value set to obtain the selected yield rate record value set distributed within the box; Select a selected production scale set from the production scale set to filter the selected yield rate record value set; By iterating through the selected production scale set and comparing it with the sum of the production scales of the selected production scale set, a fitted weight set is obtained; Based on the fitted weight set, a weighted average is calculated on the selected yield rate record value set to obtain the yield rate of the first equipment model sequence, which is then added to the yield rates of the plurality of equipment model sequences.

7. The industrial production line integrated control method based on intelligent manufacturing units as described in claim 1, characterized in that, Based on the yield rate and outlier factor of the aforementioned equipment model sequences, the sequence with the smallest outlier factor whose yield rate is greater than the yield rate threshold is selected and designated as a temporary intelligent manufacturing unit, which also includes: Using the minimum outlier sequence and the model to be produced as constraints, retrieve the production log of the minimum outlier sequence, and count the frequent fluctuation range of control parameters for each serial number of equipment, which is set as the control parameter fluctuation range sequence. Based on the minimum outlier sequence, the equipment production logs of the schedulable equipment model set are matched, and the frequent fluctuation ranges of control parameters for each tag number of the equipment are statistically analyzed to obtain the set of control parameter fluctuation ranges to be analyzed and the set of equipment tag numbers. Based on the set of control parameter fluctuation intervals to be analyzed and the set of equipment tag numbers, determine whether there is an equipment tag number sequence that satisfies the control parameter fluctuation interval sequence. If there is, output the corresponding equipment tag number sequence and set it as the temporary intelligent manufacturing unit. If not, delete the minimum sequence of outliers and perform a cyclical selection of temporary intelligent manufacturing units.

8. The industrial production line integrated control method based on intelligent manufacturing units as described in claim 7, characterized in that, Using the minimum outlier sequence and the model to be produced as constraints, the production log of the minimum outlier sequence is retrieved, and the frequent fluctuation intervals of control parameters for each serial number of equipment are statistically analyzed and set as the control parameter fluctuation interval sequence, including: Obtain the set of control parameter fluctuation intervals for the first sequence device; Extract the first attribute control parameter fluctuation range set from the first sequence number device control parameter fluctuation range set; The crossover ratio of the control parameter fluctuation range is subtracted from 1 as the fluctuation range distance parameter, and the concentrated control parameter fluctuation range of the first attribute control parameter fluctuation range set is sorted. Calculate the upper limit average of the fluctuation range of the centralized control parameter and set it as the upper limit of the frequent interval. Calculate the lower limit average of the fluctuation range of the centralized control parameter and set it as the lower limit of the frequent interval. Construct the frequent interval of the first attribute control parameter fluctuation and add it to the first sequence number control parameter fluctuation interval. Once all attributes of the first sequence device have been analyzed, the fluctuation range of the first sequence device's control parameter is added to the control parameter fluctuation range sequence.

9. An integrated control system for industrial production lines based on intelligent manufacturing units, characterized in that, The system is used to implement the industrial production line integrated control method based on intelligent manufacturing units as described in any one of claims 1-8, including: The production log retrieval module is used to retrieve the production logs of the model to be produced when the matching set of intelligent manufacturing units for the model to be produced is empty, with the set of schedulable equipment models as constraints. The production logs of the model to be produced include a series of production line equipment models. The sequence outlier analysis module is used to traverse the sequence of production line equipment models, perform sequence outlier analysis, and obtain the outlier factors of the sequence of equipment models. The yield rate statistics module is used to traverse the series of production line equipment models, perform yield rate statistics, and obtain the yield rate of the series of equipment models. The production line integration control module is used to select the smallest sequence of outliers with a yield rate greater than the yield rate threshold based on the yield rate and outlier factors of the several equipment model sequences, set it as a temporary intelligent manufacturing unit, store it in association with the model to be produced, and execute industrial production line integration control.

10. A storage medium, characterized in that, The storage medium stores a first computer program, which, when executed by a processor, implements the industrial production line integrated control method based on intelligent manufacturing units as described in any one of claims 1-8.

Images