Automatic production line control system and method based on Internet of Things

By analyzing historical processing records on the automated production line, screening target nodes and characteristic nodes, and adjusting processing parameter settings, the problem of inefficiency in processing different products is solved, and the overall efficiency of the production line is improved.

CN118915672AActive Publication Date: 2024-11-08山东电子职业技术学院

Patent Information

Application Number
CN202411079471.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-08
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

In automated production lines, it is difficult for the existing technology to effectively monitor and adjust the processing parameter settings, resulting in low efficiency and inconsistent parameter settings when processing different products, affecting production efficiency.

Method used

By collecting historical processing records on the automated production line, filtering out target nodes and feature nodes, calculating feature indexes and feature similarity thresholds, adjusting processing parameter settings in real time, optimizing the sequence of products to be processed, reducing parameter settings and adjustments, and improving processing efficiency.

Benefits of technology

By monitoring and adjusting the processing parameter settings, the parameter settings adjustment and switching of the processing equipment are reduced, the processing efficiency of the automated production line is improved, the inefficiency caused by inconsistent parameter settings is avoided, and a more efficient production process is achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915672A_ABST
    Figure CN118915672A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of automatic production line control, in particular to an automatic production line control system and method based on the Internet of Things. In the process of processing the corresponding products by the carding processing equipment, the efficiency influence caused by finishing adjustment and switching of the corresponding processing parameter setting is captured, and the similar deviation between the corresponding to-be-processed products is caused when the processing equipment performs adjustment and switching of the processing parameter setting; according to the method, the feature similarity threshold value for judging whether the corresponding processing parameter setting is adjusted or not is extracted for each target device, so that a necessary judgment basis is provided for judging whether the sequence of to-be-processed products to be operated by the corresponding target device is adjusted or not; and further improvement is realized on the basis of the existing operation processing efficiency of the automatic production line as far as possible.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of automated production line control, and in particular to an automated production line control system and method based on the Internet of Things. Background Art

[0002] Adaptive control technology is a method that uses feedback signals to adjust control strategies. It adjusts the control system in real time by monitoring process parameters, equipment status, product quality and other information. The adaptive adjustment of parameter settings in automated production processes mainly relies on adaptive control technology.

[0003] Adaptive control technology includes system identification, parameter estimation and controller design. System identification obtains the mathematical model and characteristic parameters of the system through real-time modeling and identification of the system, helps to understand the behavior of the system and provides a basis for the design of control strategies. Parameter estimation technology estimates process parameters through observation and analysis of real-time data, and updates the parameters of the controller in a timely manner to ensure that the control system can operate in the best state. According to the mathematical model of the system and the results of parameter estimation, a controller suitable for the current state is designed. The adaptive controller can adjust the control strategy according to real-time data to adapt to different working conditions and changes.

[0004] In the automated production process, the application of adaptive control technology is not limited to parameter setting and adjustment, but also includes the optimization of the entire production process. For example, in the application of automated production lines in unmanned factories, adaptive control strategies enable the system to adjust and optimize itself based on real-time feedback information, which is achieved through sensors, monitoring equipment and intelligent algorithms. This includes monitoring the operating status and product quality of the production line, and automatically adjusting the equipment's operating speed, production volume and processing parameters to achieve the best production results. In addition, the system can also automatically adjust the layout and scheduling of the production line according to changes in market demand and production plans, achieving flexibility and adaptability in the production process. Summary of the invention

[0005] The purpose of the present invention is to provide an automated production line control system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an automated production line control method based on the Internet of Things, the method comprising:

[0007] Step S1: Collect historical processing records for the processing equipment responsible for executing the corresponding processing procedures on the automated production line, sort all historical processing records of each processing equipment in chronological order, and assume that every two adjacent historical processing records constitute a historical processing node;

[0008] Step S2: for all historical processing nodes of each processing equipment, the target nodes are selected by sorting out the differences in the transition time of the job preparation extracted from the corresponding historical processing records; characteristic nodes are selected from the target nodes according to the deviations of the processing parameter settings presented in the corresponding historical processing records in each target node;

[0009] Step S3: Calculate the characteristic index of each processing equipment according to the characteristic distribution of the corresponding target node and characteristic node in all historical processing nodes of each processing equipment, and select the target equipment; extract the characteristic similarity threshold based on which the corresponding processing parameter setting is judged to be adjusted for each target equipment;

[0010] Step S4: In real time, in the automated production line, the product sequences to be processed that are to enter the corresponding workstations of each target device are respectively collected; based on the feature similarity threshold of each target device, for each target device, the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the currently collected product sequence to be processed, and the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the new product sequence to be processed after reordering and adjustment according to the corresponding optimal principle;

[0011] Step S5: predict and evaluate the total transition time consumed for job preparation in the process of executing the job processing of the corresponding sequence of products to be processed for each target device according to two different times; based on the difference in the total transition time, determine whether to adjust the sequence of products to be processed that the corresponding target device is about to operate.

[0012] Preferably, step S2 comprises:

[0013] Step S2-1: from each historical processing record of each processing equipment, respectively, capture the timestamp t1 when the corresponding product to be processed enters the working station of each processing equipment, capture the timestamp t2 when each processing equipment starts processing the corresponding product to be processed, and at the same time obtain the processing parameter settings executed by each processing equipment when processing the corresponding product to be processed; calculate the transition time T = t2-t1 of the corresponding processing equipment for preparing the operation of the corresponding product to be processed in each historical processing record;

[0014] Usually, different processing equipment is responsible for executing each processing step on an automated production line. The objects processed by each processing equipment are often products at the same production and processing stage, that is, semi-finished products at the same stage. However, even though they are at the same production and processing stage, there may be slight differences between the products, especially in the stage involving more refined processing, because in real scenarios, it is impossible to ensure that the input raw materials are exactly the same;

[0015] In more intelligent automated production lines, the corresponding processing equipment has relatively mature judgment and decision-making functions, which can automatically realize adaptive adjustment of processing parameter settings. Of course, it is not ruled out that in some other automated production lines, manual monitoring and control are required to adjust the processing parameter settings;

[0016] Step S2-2: When the transition time T extracted from the i-th historical processing record of a processing device i , and the transition duration T extracted from the i+1th historical processing record i+1 , satisfying |T i -T i+1 |>α, where α is the deviation duration threshold, and the historical processing node consisting of the i-th historical processing record and the i+1-th historical processing record is set as the target node;

[0017] Step S2-3: If in two historical processing records constituting a target node of a processing device, the processing parameter settings executed by the processing device when processing the corresponding product to be processed are not completely the same, the target node is determined to be a feature node.

[0018] Preferably, step S2 comprises:

[0019] Step S3-1: Calculate the characteristic index β=k / M for each processing equipment, where k is the total number of characteristic nodes extracted from all historical processing records of each processing equipment, and M is the total number of target nodes extracted from all historical processing records of each processing equipment; set the processing equipment with a characteristic index greater than the index threshold as the target equipment;

[0020] Step S3-2: Gather all feature nodes of each target device; for each feature node, capture the product to be processed that enters the workstation of the corresponding processing device in the two corresponding historical processing records, and obtain the similarity between the two products to be processed;

[0021] Step S3-3: The similarities extracted from all feature nodes of each target device are respectively aggregated to capture the minimum similarity for each target device; the minimum similarity is used as a feature similarity threshold to determine whether to adjust the processing parameter settings on the corresponding processing equipment.

[0022] Preferably, step S4 comprises:

[0023] Step S4-1: sequentially obtaining the similarity between two adjacent products to be processed in the product sequence to be processed, extracting the feature similarity threshold corresponding to each target device, and sequentially comparing the similarity with the feature similarity threshold;

[0024] Step S4-2: Accumulate the number of times that the corresponding similarity of each target device is less than the corresponding feature similarity threshold. If the accumulated number value is N, it is determined that if each target device performs processing operations according to the currently collected sequence of products to be processed, during the execution of the corresponding processing operations, N adjustments of the processing parameter settings are required;

[0025] That is, if there is a similarity between two adjacent products to be processed that is less than the feature similarity threshold once, it is determined that one adjustment of the processing parameter settings needs to be completed during future operation processing;

[0026] Step S4-3: When the accumulated number value N>1 for a certain target device, reorder the sequence of products to be processed collected for a certain target device in the manner that minimizes the number of times the similarity between two adjacent products to be processed is less than the feature similarity threshold of a certain target device, to obtain a new sequence of products to be processed; Obtain a new number value N' of the adjustment of the processing parameter settings that needs to be performed when a certain target device performs processing operations according to the new sequence of products to be processed.

[0027] Preferably, step S5 includes:

[0028] Step S5-1: When the number value N extracted for a certain target device and the new number value N' satisfy N'<N; respectively extract the historical processing records that are later in time sequence from each feature node of a certain target device, capture the transition duration of a certain target device for preparing operations on the corresponding products to be processed in the historical processing records that are later in time sequence, calculate the average value of all the extracted transition durations, and take the average value as the feature transition duration η corresponding to a certain target device;

[0029] Among them, the transition duration extracted from the historical processing records that are later in time sequence of each feature node of each target device often includes the time required for the target device to complete the switching of the previous execution of the processing parameter settings;

[0030] Step S5-2: When (N-N')×η>ξ, where ξ represents a threshold, remind the management personnel to adjust the current sequence of products to be processed of a certain target device to the new sequence of products to be processed.

[0031] To better implement the above method, an automated production line control system is also proposed. The system includes: a historical processing record management module, a node screening management module, a feature data extraction management module, a processing parameter setting adjustment judgment module, and an automated production line control management module;

[0032] The historical processing record management module is used to collect historical processing records of the processing equipment responsible for executing the corresponding processing procedures on the automated production line, sort all historical processing records of each processing equipment in chronological order, and set each two adjacent historical processing records to form a historical processing node;

[0033] The node screening management module is used to screen out target nodes from all historical processing nodes of each processing equipment by sorting out the differences in the transition time of job preparation extracted from the corresponding historical processing records; and screen out feature nodes from the target nodes according to the deviations of the processing parameter settings presented in the corresponding historical processing records in each target node;

[0034] The feature data extraction management module is used to calculate the feature index of each processing equipment and screen out the target equipment according to the feature distribution of the corresponding target node and feature node in all historical processing nodes of each processing equipment; extract the feature similarity threshold based on which the corresponding processing parameter setting is determined when adjusting each target equipment;

[0035] The processing parameter setting adjustment judgment module is used to collect the product sequences to be processed that are to enter the corresponding workstations of each target device in real time in the automated production line; based on the feature similarity threshold of each target device, judge the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the currently collected product sequence to be processed, and the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the new product sequence to be processed after reordering and adjustment according to the corresponding optimal principle.

[0036] The automated production line control management module is used to predict and evaluate the total transition time consumed for job preparation in the process of executing the job processing of the corresponding sequence of products to be processed for each target device at two different times; based on the difference in the total transition time, it is determined whether the sequence of products to be processed that the corresponding target device is about to operate should be adjusted.

[0037] Preferably, the node screening management module includes a target node extraction unit and a feature node extraction unit;

[0038] The target node extraction unit is used to screen out the target node for all historical processing nodes of each processing equipment by sorting out the differences in the transition time of the job preparation extracted from the corresponding historical processing records;

[0039] The characteristic node extraction unit is used to filter out characteristic nodes from the target nodes according to the deviation of the processing parameter settings presented by the corresponding historical processing records in each target node.

[0040] Preferably, the feature data extraction management module includes a target device extraction unit and a feature similarity threshold extraction unit;

[0041] A target device extraction unit is used to calculate a characteristic index for each processing device and screen out the target device according to the characteristic distribution of the corresponding target node and characteristic node in all historical processing nodes of each processing device;

[0042] The feature similarity threshold extraction unit is used to extract, for each target device, a feature similarity threshold used as a basis for determining whether to adjust the corresponding processing parameter setting.

[0043] Compared with the prior art, the beneficial effect achieved by the present invention is as follows: the present invention monitors the adjustment changes of the processing parameter settings executed by each processing equipment in the automated production line when completing the corresponding processing, combs through the efficiency impact caused by the adjustment and switching of the corresponding processing parameter settings of the processing equipment during the processing of the corresponding products, captures the similarity deviations between the corresponding products to be processed when causing the processing equipment to adjust and switch the processing parameter settings, extracts the feature similarity threshold based on which the corresponding processing parameter settings are judged for each target device, and then provides the necessary judgment basis for whether to adjust the sequence of products to be processed that the corresponding target device is about to operate, and further improves the existing processing efficiency of the automated production line by avoiding the adjustment and switching of processing parameter equipment in the corresponding processing equipment as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 It is a flow chart of an automated production line control method based on the Internet of Things of the present invention;

[0046] Figure 2 It is a structural schematic diagram of an automated production line control system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1-Figure 2The present invention provides a technical solution: an automated production line control method based on the Internet of Things, the method comprising:

[0049] Step S1: Collect historical processing records for the processing equipment responsible for executing the corresponding processing procedures on the automated production line, sort all historical processing records of each processing equipment in chronological order, and assume that every two adjacent historical processing records constitute a historical processing node;

[0050] Step S2: for all historical processing nodes of each processing equipment, the target nodes are selected by sorting out the differences in the transition time of the job preparation extracted from the corresponding historical processing records; characteristic nodes are selected from the target nodes according to the deviations of the processing parameter settings presented in the corresponding historical processing records in each target node;

[0051] Wherein, step S2 comprises:

[0052] Step S2-1: from each historical processing record of each processing equipment, respectively, capture the timestamp t1 when the corresponding product to be processed enters the working station of each processing equipment, capture the timestamp t2 when each processing equipment starts processing the corresponding product to be processed, and at the same time obtain the processing parameter settings executed by each processing equipment when processing the corresponding product to be processed; calculate the transition time T = t2-t1 of the corresponding processing equipment for preparing the operation of the corresponding product to be processed in each historical processing record;

[0053] Step S2-2: When the transition time T extracted from the i-th historical processing record of a processing device i , and the transition duration T extracted from the i+1th historical processing record i+1 , satisfying |T i -T i+1 |>α, where α is the deviation duration threshold, and the historical processing node consisting of the i-th historical processing record and the i+1-th historical processing record is set as the target node;

[0054] Step S2-3: if in two historical processing records constituting a target node of a processing device, the processing parameter settings executed by the processing device when processing the corresponding product to be processed are not completely the same, the target node is determined to be a feature node;

[0055] Step S3: Calculate the characteristic index of each processing equipment according to the characteristic distribution of the corresponding target node and characteristic node in all historical processing nodes of each processing equipment, and select the target equipment; extract the characteristic similarity threshold based on which the corresponding processing parameter setting is judged to be adjusted for each target equipment;

[0056] Wherein, step S3 comprises:

[0057] Step S3-1: Calculate the characteristic index β=k / M for each processing equipment, where k is the total number of characteristic nodes extracted from all historical processing records of each processing equipment, and M is the total number of target nodes extracted from all historical processing records of each processing equipment; set the processing equipment with a characteristic index greater than the index threshold as the target equipment;

[0058] Step S3-2: Gather all feature nodes of each target device; for each feature node, capture the product to be processed that enters the workstation of the corresponding processing device in the two corresponding historical processing records, and obtain the similarity between the two products to be processed;

[0059] Step S3-3: respectively collect the similarities extracted from all feature nodes of each target device, and capture the minimum similarity for each target device; and use the minimum similarity as the feature similarity threshold for determining whether to adjust the processing parameter settings on the corresponding processing equipment;

[0060] Step S4: In real time, in the automated production line, the product sequences to be processed that are to enter the corresponding workstations of each target device are respectively collected; based on the feature similarity threshold of each target device, for each target device, the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the currently collected product sequence to be processed, and the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the new product sequence to be processed after reordering and adjustment according to the corresponding optimal principle;

[0061] Wherein, step S4 comprises:

[0062] Step S4-1: sequentially obtaining the similarity between two adjacent products to be processed in the product sequence to be processed, extracting the feature similarity threshold corresponding to each target device, and sequentially comparing the similarity with the feature similarity threshold;

[0063] Step S4-2: accumulating the number of times that the corresponding similarity is less than the corresponding feature similarity threshold for each target device, if the accumulated number is N, it is determined that if each target device performs a processing operation according to the currently acquired sequence of products to be processed, it needs to adjust the processing parameter settings N times during the execution of the corresponding processing operation;

[0064] That is, if the similarity between two adjacent products to be processed is less than the feature similarity threshold, it is determined that the adjustment of the processing parameter settings needs to be completed in the future processing process;

[0065] Step S4-3: when the accumulated number of times N for a certain target device is greater than 1, the sequence of products to be processed collected by the certain target device is reordered in a manner such that the number of times the similarity between two adjacent products to be processed is less than the feature similarity threshold of the certain target device is minimized, so as to obtain a new sequence of products to be processed; and a new number of times N' that the processing parameter setting needs to be adjusted when the certain target device performs the processing operation according to the new sequence of products to be processed is obtained during the execution of the corresponding processing operation;

[0066] For example, the sequence of products to be processed currently extracted for a certain target device is {product 1, product 2, product 3, product 4}, and the similarity between product 1 and product 2 is less than the feature similarity threshold of a certain target device, the similarity between product 2 and product 3 is less than the feature similarity threshold of a certain target device, and the similarity between product 3 and product 4 is greater than the feature similarity threshold of a certain target device;

[0067] Therefore, it can be known that if a certain target device performs a processing operation according to the processing product sequence, in the process of executing the corresponding processing operation, the new number of processing parameter settings that need to be adjusted is N'=2;

[0068] Among them, if the sorting positions of product 2 and product 3 are swapped, that is, adjusted to a new sequence of products to be processed {product 1, product 3, product 2, product 4}, it is found that the similarity between product 1 and product 3 is greater than the feature similarity threshold of a certain target device, the similarity between product 3 and product 2 is less than the feature similarity threshold of a certain target device, and the similarity between product 2 and product 4 is greater than the feature similarity threshold of a certain target device;

[0069] Therefore, it can be known that if a certain target device performs a processing operation according to the processing product sequence, in the process of executing the corresponding processing operation, the new number of processing parameter settings that need to be adjusted is N'=1;

[0070] Step S5: predicting and evaluating the total transition time consumed for the operation preparation of each target device in the process of executing the operation processing of the corresponding sequence of products to be processed according to two different times; judging whether to adjust the sequence of products to be processed that the corresponding target device is about to operate according to the difference in the total transition time;

[0071] Wherein, step S5 comprises:

[0072] Step S5-1: When the number value N and the new number value N' extracted for a certain target device satisfy N' < N; respectively extract the historical processing records that are later in chronological order from each feature node of the certain target device, capture the transition duration of the certain target device for job preparation for the corresponding product to be processed in the historical processing records that are later in chronological order, calculate the average value of all the extracted transition durations, and take the average value as the characteristic transition duration η corresponding to the certain target device;

[0073] Step S5-2: When (N - N') × η > ξ, where ξ represents the threshold value, remind the management personnel to adjust the current product sequence to be processed of the certain target device to a new product sequence to be processed.

[0074] To better implement the above method, an automated production line control system is also proposed. The system includes: a historical processing record management module, a node screening management module, a feature data extraction management module, a processing parameter setting and adjustment judgment module, and an automated production line control management module;

[0075] The historical processing record management module is used to collect historical processing records of the processing equipment responsible for executing the corresponding processing procedures on the automated production line, sort all the historical processing records of each processing equipment in chronological order, and set every two adjacent historical processing records to form a historical processing node;

[0076] The node screening management module is used to screen out target nodes from all the historical processing nodes of each processing equipment by sorting out the differences in the transition durations of job preparation extracted from the corresponding historical processing records; and screen out feature nodes from the target nodes according to the deviation situations of the processing parameter settings presented in the corresponding historical processing records in each target node;

[0077] Among them, the node screening management module includes a target node extraction unit and a feature node extraction unit;

[0078] The target node extraction unit is used to screen out target nodes from all the historical processing nodes of each processing equipment by sorting out the differences in the transition durations of job preparation extracted from the corresponding historical processing records;

[0079] The feature node extraction unit is used to screen out feature nodes from the target nodes according to the deviation situations of the processing parameter settings presented in the corresponding historical processing records in each target node;

[0080] The feature data extraction management module is used to calculate the feature index of each processing equipment and screen out the target equipment according to the feature distribution of the corresponding target node and feature node in all historical processing nodes of each processing equipment; extract the feature similarity threshold based on which the corresponding processing parameter setting is determined when adjusting each target equipment;

[0081] Among them, the feature data extraction management module includes a target device extraction unit and a feature similarity threshold extraction unit;

[0082] A target device extraction unit is used to calculate a characteristic index for each processing device and screen out the target device according to the characteristic distribution of the corresponding target node and characteristic node in all historical processing nodes of each processing device;

[0083] A feature similarity threshold extraction unit is used to extract a feature similarity threshold for each target device to be used as a basis for determining whether to adjust the corresponding processing parameter setting;

[0084] The processing parameter setting adjustment judgment module is used to collect the product sequences to be processed that are to enter the corresponding workstations of each target device in real time in the automated production line; based on the feature similarity threshold of each target device, judge the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the currently collected product sequence to be processed, and the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the new product sequence to be processed after reordering and adjustment according to the corresponding optimal principle.

[0085] The automated production line control management module is used to predict and evaluate the total transition time consumed for job preparation in the process of executing the job processing of the corresponding sequence of products to be processed for each target device at two different times; based on the difference in the total transition time, it is determined whether the sequence of products to be processed that the corresponding target device is about to operate should be adjusted.

[0086] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0087] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automated production line control method based on the Internet of Things, characterized in that: The method comprises: Step S1: Collect historical processing records for the processing equipment responsible for executing the corresponding processing procedures on the automated production line, sort all historical processing records of each processing equipment in chronological order, and assume that every two adjacent historical processing records constitute a historical processing node; Step S2: for all historical processing nodes of each processing equipment, the target nodes are selected by sorting out the differences in the transition time of the job preparation extracted from the corresponding historical processing records; characteristic nodes are selected from the target nodes according to the deviations of the processing parameter settings presented in the corresponding historical processing records in each target node; Step S3: Calculate the characteristic index of each processing equipment according to the characteristic distribution of the corresponding target node and characteristic node in all historical processing nodes of each processing equipment, and select the target equipment; extract the characteristic similarity threshold based on which the corresponding processing parameter setting is judged to be adjusted for each target equipment; Step S4: In real time, in the automated production line, the product sequences to be processed that are to enter the corresponding workstations of each target device are respectively collected; based on the feature similarity threshold of each target device, for each target device, the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the currently collected product sequence to be processed, and the number of times the processing parameter settings need to be adjusted if the processing operation is performed according to the new product sequence to be processed after reordering and adjustment according to the corresponding optimal principle; Step S5: predict and evaluate the total transition time consumed for job preparation in the process of executing the job processing of the corresponding sequence of products to be processed for each target device according to two different times; based on the difference in the total transition time, determine whether to adjust the sequence of products to be processed that the corresponding target device is about to operate.

2. The method for controlling an automated production line based on the Internet of Things according to claim 1, characterized in that: The step S2 comprises: Step S2-1: from each historical processing record of each processing equipment, respectively, capture the timestamp t1 when the corresponding product to be processed enters the working station of each processing equipment, capture the timestamp t2 when each processing equipment starts processing the corresponding product to be processed, and simultaneously obtain the processing parameter settings executed by each processing equipment when processing the corresponding product to be processed; calculate the transition time T=t2-t1 of the corresponding processing equipment for preparing the operation of the corresponding product to be processed in each historical processing record; Step S2-2: When the transition time T extracted from the i-th historical processing record of a processing device i , and the transition duration T extracted from the i+1th historical processing record i+1 , satisfying |T i -T i+1 |>α, where α is the deviation duration threshold, and the historical processing node consisting of the i-th historical processing record and the i+1-th historical processing record is set as the target node; Step S2-3: If in two historical processing records constituting a target node of a processing device, the processing parameter settings executed by the processing device when processing the corresponding product to be processed are not completely the same, the target node is determined to be a feature node.

3. The method for controlling an automated production line based on the Internet of Things according to claim 2, characterized in that: The step S3 comprises: Step S3-1: Calculate the characteristic index β=k / M for each processing equipment, where k is the total number of characteristic nodes extracted from all historical processing records of each processing equipment, and M is the total number of target nodes extracted from all historical processing records of each processing equipment; set the processing equipment with a characteristic index greater than the index threshold as the target equipment; Step S3-2: Aggregate all the feature nodes of each target device; for each feature node in turn, capture the products to be processed at the operation stations of the corresponding processing devices in the two historical processing records it contains respectively, and obtain the similarity between the two products to be processed. Step S3-3: Aggregate the similarities extracted from all the feature nodes of each target device respectively, and capture the minimum similarity for each target device; use the minimum similarity as the characteristic similarity threshold for judging whether to adjust the setting of the processing parameters on the corresponding processing device.

4. The method for controlling an automated production line based on the Internet of Things according to claim 3, characterized in that: The said Step S4 includes: Step S4-1: Obtain the similarity between adjacent products to be processed in the sequence of products to be processed in turn, extract the characteristic similarity thresholds corresponding to each target device, and compare the similarity with the characteristic similarity thresholds in turn. Step S4-2: Accumulate the number of times that the corresponding similarity of each target device is less than the corresponding characteristic similarity threshold respectively. If the accumulated number value is N, judge that if each target device performs the processing operation according to the currently collected sequence of products to be processed, during the execution of the corresponding processing operation, N adjustments of the processing parameter settings are required. Step S4-3: When the accumulated number value N>1 for a certain target device, reorder the sequence of products to be processed collected for the certain target device in the way that the number of times the similarity between adjacent products to be processed is less than the characteristic similarity threshold of the certain target device is the smallest, to obtain a new sequence of products to be processed; obtain the new number value N' of the adjustments of the processing parameter settings required when the certain target device performs the processing operation according to the new sequence of products to be processed.

5. The method for controlling an automated production line based on the Internet of Things according to claim 4, characterized in that: The said Step S5 includes: Step S5-1: When the number value N extracted for a certain target device and the new number value N' satisfy N'<N; extract the historical processing records that are later in time sequence from each feature node of the certain target device, capture the transition duration of the certain target device for preparing the operation on the corresponding product to be processed in the historical processing record that is later in time sequence, calculate the average value of all the extracted transition durations, and use the average value as the characteristic transition duration η corresponding to the certain target device. Step S5-2: When (N - N')×η>ξ, where ξ represents the threshold, remind the management personnel to adjust the currently processed sequence of products of the certain target device to the new sequence of products to be processed.

6. An automated production line control system, used to execute an automated production line control method based on the Internet of Things as described in any one of claims 1 to 5, characterized in that: The said system includes: a historical processing record management module, a node screening management module, the said feature data extraction management module, a processing parameter setting adjustment judgment module, and an automated production line control management module; The historical processing record management module is used to collect the historical processing records of the processing devices responsible for executing the corresponding processing procedures on the automated production line, sort all the historical processing records of each processing device in chronological order, and set each adjacent two historical processing records as a historical processing node. The node screening management module is used to screen out target nodes for all historical processing nodes of each processing equipment by sorting out the differences in transition duration of job preparation extracted from the corresponding historical processing records; and screen out feature nodes from the target nodes according to the deviations of processing parameter settings presented in the corresponding historical processing records in each target node; The feature data extraction management module is used to calculate the feature index of each processing equipment and screen out the target equipment according to the feature distribution of the corresponding target node and feature node in all historical processing nodes of each processing equipment; extract the feature similarity threshold based on which the corresponding processing parameter setting is determined when adjusting each target equipment; The processing parameter setting adjustment judgment module is used to collect the product sequences to be processed that are to enter the corresponding workstations of each target device in real time in the automated production line; based on the feature similarity threshold of each target device, judge the number of times the processing parameter setting adjustment is required for each target device if the processing operation is performed according to the currently collected product sequence to be processed, and the number of times the processing parameter setting adjustment is required for each target device if the processing operation is performed according to the new product sequence to be processed after reordering and adjustment according to the corresponding optimal principle; The automated production line control management module is used to predict and evaluate the total transition time consumed for job preparation in the process of executing the job processing of the corresponding sequence of products to be processed for each target device at two different times; based on the difference in the total transition time, determine whether to adjust the sequence of products to be processed that the corresponding target device is about to operate.

7. An automated production line control system according to claim 6, characterized in that: The node screening management module includes a target node extraction unit and a feature node extraction unit; The target node extraction unit is used to screen out the target node for all historical processing nodes of each processing equipment by sorting out the differences in the transition duration of the job preparation extracted from the corresponding historical processing records; The characteristic node extraction unit is used to filter out characteristic nodes from the target nodes according to the deviation of the processing parameter settings presented by the corresponding historical processing records in each target node.

8. The automated production line control system according to claim 6, characterized in that: The feature data extraction management module includes a target device extraction unit and a feature similarity threshold extraction unit; The target device extraction unit is used to calculate the characteristic index of each processing device according to the characteristic distribution of the corresponding target node and the characteristic node in all historical processing nodes of each processing device, and screen out the target device; The feature similarity threshold extraction unit is used to extract, for each target device, a feature similarity threshold used as a basis for determining whether to adjust the corresponding processing parameter setting.

Citation Information

Patent Citations

  • Method for reducing switching times of mixed-model assembly line products of automobile

    CN101923342A

  • Intelligent digital twin simulation system for steel production process

    CN117930786A

  • Remote communication security management system and method based on industrial Internet of Things

    CN118075019A

  • Cuckoo improved PSO-based workshop scheduling method in digital twin environment

    CN118348930A

  • Method of optimizing machining simulation condition, machining simulation device, machining simulation system and program

    US20200293021A1

Cited By

  • Model optimization data management system based on interactive feedback field experience and application thereof

    CN119227912A

  • Model optimization data management system based on interactive feedback domain experience and its application

    CN119227912B

  • PP plastic cup production control system based on artificial intelligence

    CN119376364A

  • Coating production line scheduling method and device, storage medium and program product

    CN120491566A