Hybrid flexible workshop joint scheduling system and method based on lighthouse factory
By adopting a hybrid flexible workshop joint scheduling system in the lighthouse factory, dynamically adjusting production task allocation and resource utilization, the problem that traditional scheduling methods are difficult to adapt to complex production environments is solved, and efficient and flexible production management is achieved.
Patent Information
- Application Number
- CN202411009360.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-15
AI Technical Summary
Traditional workshop scheduling methods are difficult to adapt to the complex and changing production environment and diverse task requirements of lighthouse factories, resulting in low resource utilization and extended production cycles.
The hybrid flexible workshop joint scheduling system based on the lighthouse factory dynamically adjusts production task allocation, optimizes resource utilization, identifies insufficient or overcapacity status, and makes corresponding adjustments through data preprocessing, feature extraction, capacity evaluation and real-time monitoring.
It significantly improves the flexibility and efficiency of production scheduling, realizes accurate monitoring and dynamic adjustment of the workshop production status, improves resource utilization, avoids resource waste, and shortens the production cycle.
Smart Images

Figure CN118963266A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of flexible workshop scheduling, and specifically relates to a hybrid flexible workshop joint scheduling system and method based on a lighthouse factory. Background Art
[0002] With the rapid development of modern manufacturing, lighthouse factories, as representatives of intelligent manufacturing, are gradually becoming an important driving force for the transformation and upgrading of the industry. Lighthouse factories have achieved significant improvements in production efficiency and effective cost control through highly integrated, automated and intelligent production systems. In order to ensure the production efficiency of lighthouse factories, joint scheduling of the hybrid flexible workshops involved is obviously necessary.
[0003] However, in the actual production process, lighthouse factories are faced with complex and changeable production environments and diverse production task requirements. Traditional workshop scheduling methods are often difficult to adapt to such dynamic changes, resulting in low resource utilization, extended production cycles and other problems. For example, when the production capacity of a production workshop is insufficient, it can only get assistance after the tasks of other workshops are completed, which will undoubtedly lead to an extension of the task completion cycle of the workshop, while workshops with excess capacity will cause idleness and waste of resources. Based on this, this solution provides a hybrid flexible workshop joint scheduling method for lighthouse factories to solve the above problems. Summary of the invention
[0004] The purpose of the present invention is to provide a hybrid flexible workshop joint scheduling system and method based on a lighthouse factory, which can dynamically adjust the production task allocation in real time, optimize resource utilization, shorten the production cycle, and improve overall production efficiency.
[0005] The technical solution adopted by the present invention is as follows:
[0006] The hybrid flexible workshop joint scheduling method based on the lighthouse factory includes:
[0007] Perform data preprocessing based on the production data obtained from each production workshop, and calibrate the preprocessed production data as benchmark data;
[0008] Extracting features from the benchmark data to obtain key production indicators, and evaluating the production capacity information of each production workshop based on the key production indicators;
[0009] Allocate production tasks to each production workshop based on the production capacity information, and monitor the progress of production tasks of each production workshop in real time;
[0010] Determine the production status of each production workshop according to the production task progress, wherein the production status includes insufficient production capacity status and excess production capacity status;
[0011] The capacity gap of the production workshop under the undercapacity state and the remaining capacity of the production workshop under the overcapacity state are calculated, and the production tasks of the production workshop under the overcapacity state are adjusted based on the capacity gap.
[0012] In a preferred solution, the step of preprocessing the data according to the acquired production data of each production workshop and calibrating the preprocessed production data as the reference data includes:
[0013] Obtain the original production data of each production workshop, and clean all the original production data to remove invalid, erroneous and duplicate data;
[0014] Standardize the cleaned original production data to obtain standardized data in the same dimension;
[0015] A time stamp is added to the normalized data, and the time-stamped normalized data is used as the baseline data.
[0016] In a preferred embodiment, the step of extracting features from the benchmark data to obtain key production indicators includes:
[0017] Acquire multiple production dimension information in the benchmark data, wherein the production dimension information includes workshop equipment status information, workshop production speed, material supply speed, raw material consumption information, and product qualification rate;
[0018] Obtaining workshop output, and based on the workshop output, performing correlation analysis on multiple production dimension information, and outputting the correlation between each production dimension information and the workshop output;
[0019] A screening threshold is obtained, and the screening threshold is compared with the correlation degree, and production dimension information with a correlation degree greater than the screening threshold is determined as a key production indicator.
[0020] In a preferred embodiment, the step of performing correlation analysis on multiple production dimension information based on the workshop output and outputting the correlation between each production dimension information and the workshop output includes:
[0021] Construct a historical monitoring period and collect change nodes of each production dimension information within the historical monitoring period;
[0022] Collect the unique change nodes of each production dimension information one by one and record them as a single change point;
[0023] Counting the fluctuation amount of each of the production dimension information at a single change point and the change amount of workshop output under the single change point, and combining the change amount of workshop output with the fluctuation amount of the production dimension information at a single change point to obtain the unit change amount of workshop output under each of the production dimension information;
[0024] A correlation distribution function is obtained, and the unit change of the workshop output under each of the production dimension information is input into the correlation distribution function, and the output result of the correlation distribution function is calibrated as the correlation between the production dimension information and the workshop output.
[0025] In a preferred embodiment, the step of evaluating the production capacity information of each production workshop according to the key production indicators includes:
[0026] Setting a plurality of sampling periods of equal duration within the historical monitoring period;
[0027] Performing difference processing on the key production indicators in adjacent sampling periods to obtain indicator fluctuations;
[0028] Obtaining an evaluation threshold value of each key production indicator, and comparing the evaluation threshold value with the indicator fluctuation amount;
[0029] If the evaluation threshold is less than the indicator fluctuation amount, it indicates that the corresponding key production indicator is a valid fluctuation, and the indicator fluctuation amount under the valid fluctuation is recorded as the valid fluctuation amount;
[0030] If the evaluation threshold is greater than or equal to the indicator fluctuation amount, it indicates that the corresponding key production indicator is an invalid fluctuation, and the indicator fluctuation amount under the invalid fluctuation will be ignored;
[0031] A first prediction function is obtained, and the effective fluctuation amount is input into the first prediction function, and an output result of the first prediction function is recorded as the production capacity information of the production workshop.
[0032] In a preferred solution, the step of determining the production status of each production workshop according to the production task progress includes:
[0033] Obtain the real-time workshop output of each production workshop and the preset allowable deviation range;
[0034] comparing the real-time workshop output with the allowable deviation range;
[0035] If the real-time workshop output is higher than the upper limit of the allowable deviation interval, it indicates that the production state of the production workshop is in an overcapacity state, and the difference between the real-time workshop output and the upper limit of the allowable deviation interval is recorded as the excess capacity;
[0036] If the real-time workshop output is within the allowable deviation range, it indicates that the production status of the production workshop is normal;
[0037] If the real-time workshop output is lower than the lower limit of the allowable deviation interval, it indicates that the production status of the production workshop is insufficient capacity, and the difference between the real-time workshop output and the lower limit of the allowable deviation interval is recorded as the capacity gap.
[0038] In a preferred solution, the step of adjusting the production tasks of the production workshop under the overcapacity state based on the production capacity gap includes:
[0039] Obtaining the capacity gap in the insufficient capacity state;
[0040] Obtaining the remaining capacity of the production workshop under the overcapacity state, and the response time of the production workshop to each capacity gap under the overcapacity state;
[0041] Predicting the increase in the capacity gap within the response time, and summing the capacity gap and the increase in the capacity gap to obtain a total capacity gap, and arranging the total capacity gap in descending order;
[0042] According to the total capacity gap and the surplus capacity of the workshop with excess capacity, the surplus capacity of the workshop with excess capacity is allocated to the workshop with insufficient capacity;
[0043] Among them, the allocation of the total capacity gap is carried out according to the size of the remaining capacity in the overcapacity interval.
[0044] In a preferred embodiment, the step of predicting the increase in the capacity gap within the response time and summing the capacity gap and the increase in the capacity gap to obtain the total capacity gap includes:
[0045] Obtain the occurrence node of the capacity gap, and perform backtracking offset based on the occurrence node to obtain a backtracking period;
[0046] Setting a plurality of sampling nodes within the backtracking period, and recording the production capacity at each of the sampling nodes as a condition parameter;
[0047] A second prediction function is obtained, and the response time and the condition parameter are input into the second prediction function together, and the output result of the second prediction function is calibrated as the increase in the production capacity gap.
[0048] The present invention also provides a hybrid flexible workshop joint scheduling system based on a lighthouse factory, using the above-mentioned hybrid flexible workshop joint scheduling method based on a lighthouse factory, including:
[0049] A data acquisition module, wherein the data acquisition module is used to perform data preprocessing based on the production data acquired from each production workshop, and calibrate the preprocessed production data as reference data;
[0050] A feature extraction module, the feature extraction module is used to extract features from the benchmark data to obtain key production indicators, and evaluate the production capacity information of each production workshop based on the key production indicators;
[0051] A production monitoring module, which is used to allocate production tasks to each production workshop according to the production capacity information and monitor the progress of production tasks of each production workshop in real time;
[0052] A status evaluation module, which is used to determine the production status of each production workshop according to the production task progress, wherein the production status includes an insufficient production capacity state and an excessive production capacity state;
[0053] The task adjustment module is used to calculate the capacity gap of the production workshop under the insufficient capacity state and the remaining capacity of the production workshop under the overcapacity state, and adjust the production tasks of the production workshop under the overcapacity state based on the capacity gap.
[0054] And, an electronic device, the electronic device comprising:
[0055] at least one processor;
[0056] and a memory communicatively coupled to the at least one processor;
[0057] Among them, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned hybrid flexible workshop joint scheduling method based on the lighthouse factory.
[0058] The technical effects achieved by the present invention are:
[0059] The present invention realizes accurate monitoring and dynamic adjustment of the workshop production status by analyzing the multi-dimensional data of the production workshop, and significantly improves the flexibility and efficiency of production scheduling. Specifically, it can not only capture the fluctuation of production dimension information in the production process in real time, but also quantify the specific impact of production dimension fluctuation on workshop output. In terms of capacity assessment, it distinguishes between effective fluctuations and invalid fluctuations, and avoids the interference of invalid fluctuations on capacity assessment. In terms of production status monitoring, by setting the allowable deviation interval, the refined management of workshop output is realized, and the state of overcapacity or undercapacity can be quickly identified, and the corresponding remaining capacity or capacity gap can be calculated. In the task adjustment link, an intelligent capacity gap prediction and dynamic adjustment mechanism is introduced, which effectively improves the utilization rate of production resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 It is a schematic flow chart of the method of the present invention;
[0061] Figure 2 It is a schematic diagram of the system module of the present invention;
[0062] Figure 3 It is a structural diagram of an electronic device of the present invention. DETAILED DESCRIPTION
[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.
[0066] See also Figure 1 As shown, the present invention provides a hybrid flexible workshop joint scheduling method based on a lighthouse factory, including:
[0067] S1. Perform data preprocessing based on the production data of each production workshop, and calibrate the preprocessed production data as benchmark data;
[0068] S2. Extract features from the benchmark data to obtain key production indicators, and evaluate the production capacity information of each production workshop based on the key production indicators;
[0069] S3. Allocate production tasks to each production workshop based on production capacity information, and monitor the progress of production tasks of each production workshop in real time;
[0070] S4. Determine the production status of each production workshop according to the production task progress, where the production status includes insufficient production capacity and excess production capacity;
[0071] S5. Calculate the capacity gap of the production workshop under the state of insufficient capacity and the remaining capacity of the production workshop under the state of overcapacity, and adjust the production tasks of the production workshop under the state of overcapacity based on the capacity gap.
[0072] As described in the above steps S1-S5, as the intelligence and digitalization level of lighthouse factories continues to improve, flexible scheduling and efficient management of production workshops have become key. In the process of continuing to deepen the intelligence and digital management of lighthouse factories, this implementation example adopts a dynamic adjustment strategy to improve overall production efficiency. First, it is necessary to collect production data from each production workshop. The production data includes but is not limited to production speed, product quality, material consumption, etc. Subsequently, the production data is preprocessed to eliminate noise and inconsistency in the data and improve data quality. The preprocessed data will be calibrated as baseline data as the basis for subsequent analysis. Then, feature extraction of the baseline data is required to identify key production indicators that affect production capacity. The key production indicators will be used to evaluate the production capacity of each production workshop and output the production capacity information of each production workshop. On this basis, production tasks will be assigned to each production workshop based on the production capacity information. In the task allocation process In the process, we will fully consider the actual production capacity of each workshop to ensure the rationality and scientificity of the production tasks. At the same time, we will track the progress of the production tasks of each production workshop in real time, so as to determine the production status of each production workshop according to the progress of the production tasks. The production status includes insufficient capacity and overcapacity. For the insufficient capacity state, it is necessary to calculate the capacity gap of the workshop so as to take corresponding measures to increase the capacity. For the overcapacity state, it is necessary to calculate the remaining capacity of the workshop so as to adjust the production tasks and use its remaining capacity to supplement the capacity gap. That is, based on the capacity gap, the production tasks in the overcapacity state are adjusted. For example, part of the human and material resources in the workshop in the overcapacity state are allocated to support the workshop with insufficient capacity. This can effectively improve production efficiency, reduce production costs, realize refined management and efficient operation of workshops, avoid waste of production resources, and improve production flexibility.
[0073] In a preferred embodiment, the steps of performing data preprocessing based on the production data of each production workshop obtained and calibrating the preprocessed production data as reference data include:
[0074] S101. Obtain the original production data of each production workshop, and clean all the original production data to remove invalid, erroneous and duplicate data;
[0075] S102, standardizing the cleaned original production data to obtain standardized data under the same dimension;
[0076] S103: Add a timestamp to the standardized data, and use the standardized data with the timestamp as the reference data.
[0077] As described in the above steps S101-S103, for the original production data from different production workshops, a series of data preprocessing operations need to be performed to ensure the accuracy and consistency of the data. First, the original production data must be collected from each production workshop. The original production data may contain some invalid information, erroneous records or duplicates, so the original production data needs to be cleaned accordingly. The cleaning process includes identifying and filtering out inaccurate or incomplete data to ensure that the remaining data can truly reflect the production situation. In order to enable the data to be compared and analyzed under the same dimension, the cleaned original data needs to be standardized. The standardization process will scale the data to a fixed range based on the distribution characteristics of the data, so that each data point can be evaluated on a standard scale. Finally, in order to track data changes and time series analysis, it is necessary to add timestamps to the standardized data. Timestamps can assist in tracking data changes over time. Finally, the standardized data with timestamps is used as baseline data for subsequent production analysis.
[0078] In a preferred embodiment, the step of extracting features from the benchmark data to obtain key production indicators includes:
[0079] S201, obtaining multiple production dimension information in the benchmark data, where the production dimension information includes workshop equipment status information, workshop production speed, material supply speed, raw material consumption information, and product qualification rate;
[0080] S202, obtaining workshop output, and based on the workshop output, performing correlation analysis on multiple production dimension information, and outputting the correlation between each production dimension information and the workshop output;
[0081] S203: Obtain a screening threshold, compare the screening threshold with the correlation, and determine the production dimension information with a correlation greater than the screening threshold as a key production indicator.
[0082] As described in the above steps S201-S203, after the benchmark data is output, multiple production dimension information in the benchmark data will be synchronously extracted. The production dimension information includes the status information of the workshop equipment, which refers to the operating status of the equipment during the production process and whether it needs maintenance or adjustment, the workshop production speed, that is, the number of products produced per hour on the production line, the material supply speed, that is, the speed at which raw materials or semi-finished products are supplied during the production process, the raw material consumption information, that is, the use of raw materials during the production process, and whether they need to be supplemented or adjusted, the product qualification rate, that is, the proportion of products that meet the quality standards. Then, the workshop output needs to be obtained, and based on the workshop output, the correlation analysis of each production dimension information is performed. The purpose of the correlation analysis is to find out the correlation between these production dimension information and the workshop output, so as to understand which production dimension information has a greater impact on the workshop output. This is specifically achieved by setting a screening threshold. The screening threshold is a critical value used to determine whether the correlation between the production dimension information and the workshop output is large enough. The key production indicator is output by comparing the obtained correlation with the screening threshold. If the correlation is greater than the screening threshold, the corresponding production dimension information will be determined as the key production indicator.
[0083] In a preferred embodiment, based on the workshop output, a correlation analysis is performed on multiple production dimension information, and the step of outputting the correlation between each production dimension information and the workshop output includes:
[0084] Step 1: Construct a historical monitoring period and collect the change nodes of each production dimension information within the historical monitoring period;
[0085] Step 2: Collect the unique change nodes of each production dimension information one by one and record them as a single change point;
[0086] Step 3: Count the fluctuation of each production dimension information at a single change point and the change of workshop output at a single change point, and combine the change of workshop output with the fluctuation of production dimension information at a single change point to obtain the unit change of workshop output under each production dimension information;
[0087] Step 4. Obtain the correlation distribution function, and input the unit change of the workshop output under each production dimension information into the correlation distribution function, and calibrate the output result of the correlation distribution function as the correlation between the production dimension information and the workshop output.
[0088] As described in the above steps Step 1-Step 4, in order to clarify the relationship between the workshop output and the production dimension information during the production process, it is necessary to conduct corresponding correlation analysis to determine. First, it is necessary to construct a historical monitoring period. The historical monitoring period should cover a sufficiently long time span so that the changes and fluctuations of each production dimension information over time can be captured. The specific time length needs to be set according to actual needs. During the historical monitoring period, the change nodes of each production dimension information will be collected. The appearance of the change node may have an impact on the real-time workshop output. Then, the unique change node of each production dimension information in all change nodes will be identified and collected one by one (under the unique change node, Only one production dimension information changes), this implementation method records it as a single change node, and at the same time, it also counts the fluctuation of the production dimension information at each single change point, and also records the change of the workshop output at the single change node. By comparing the change of the workshop output with the fluctuation of the production dimension information (dividing them), the unit change of the workshop output under each production dimension information can be obtained. After the unit change of the workshop output under each production dimension information is output, the correlation allocation function is introduced. The correlation allocation function can quantify the unit change of the workshop output under the production dimension information and its potential impact on the workshop output. The expression of the correlation allocation function is: In the formula, R represents the correlation between production dimension information and workshop output, b represents the unit change of workshop output under production dimension information, and n represents the number of production dimension information. By inputting the unit change of workshop output under each production dimension information into the above correlation distribution function, the correlation between each production dimension information and workshop output can be obtained, so as to determine the impact intensity of production dimension information on workshop output.
[0089] In a preferred embodiment, the step of evaluating the production capacity information of each production workshop according to the key production indicators includes:
[0090] S204, setting a plurality of sampling periods of equal time within the historical monitoring period;
[0091] S205, performing difference processing on key production indicators in adjacent sampling periods to obtain indicator fluctuations;
[0092] S206, obtaining the evaluation threshold of each key production indicator, and comparing the evaluation threshold with the indicator fluctuation amount;
[0093] If the evaluation threshold is less than the indicator fluctuation amount, it indicates that the corresponding key production indicator is an effective fluctuation, and the indicator fluctuation amount under the effective fluctuation is recorded as the effective fluctuation amount;
[0094] If the evaluation threshold is greater than or equal to the indicator fluctuation amount, it indicates that the corresponding key production indicator is invalid fluctuation, and the indicator fluctuation amount under invalid fluctuation will be ignored;
[0095] S207, obtaining a first prediction function, inputting the effective fluctuation amount into the first prediction function, and recording the output result of the first prediction function as the production capacity information of the production workshop.
[0096] As described in the above steps S204-S207, after the key production indicators are output, the production capacity information of each production workshop will be further evaluated. First, the historical monitoring time period must be divided into multiple sampling periods of equal length to facilitate a more detailed evaluation of the key production indicators. Specifically, the difference calculation of the key production indicators in adjacent sampling periods is required, that is, difference processing is performed. In this way, the fluctuation amount of the key production indicators in adjacent sampling periods can be obtained. Then, the evaluation threshold of each key production indicator needs to be determined. The evaluation threshold is a standard for distinguishing effective fluctuations from invalid fluctuations. Specifically, these evaluation thresholds are compared with the previously calculated values. If the evaluation threshold is less than the index fluctuation amount, it means that the fluctuation is valid, and it will be recorded as the valid fluctuation amount, which means that the production capacity of the production workshop has been actually affected. On the contrary, if the evaluation threshold is greater than or equal to the index fluctuation amount, it means that the fluctuation is invalid, and it will be ignored at this time, indicating that the production capacity of the production workshop has not been actually affected, and the current production capacity information can be kept unchanged. Finally, the first prediction function is introduced, and the valid fluctuation amount is input into the first prediction function, so as to determine the production capacity information of the production workshop according to the output result of the first prediction function. The expression of the first prediction function is: C d =C s +M g ×b, where C d represents the production capacity information of the production workshop under effective fluctuation, C s It represents the average production capacity of the production workshop during the historical monitoring period, M g It represents the fluctuation amount of the indicator under effective fluctuation. Based on the above formula, the production capacity information of the subsequent production workshop can be predicted, providing a preliminary basis for the allocation of production tasks.
[0097] In a preferred embodiment, the step of determining the production status of each production workshop according to the production task progress includes:
[0098] S401, obtaining the real-time workshop output of each production workshop and the preset allowable deviation range;
[0099] S402, comparing the real-time workshop output with the allowable deviation range;
[0100] If the real-time workshop output is higher than the upper limit of the allowable deviation interval, it indicates that the production status of the production workshop is in an overcapacity state, and the difference between the real-time workshop output and the upper limit of the allowable deviation interval is recorded as the remaining capacity;
[0101] If the real-time workshop output is within the allowable deviation range, it indicates that the production status of the production workshop is normal;
[0102] If the real-time workshop output is lower than the lower limit of the allowable deviation interval, it indicates that the production status of the production workshop is insufficient capacity, and the difference between the real-time workshop output and the lower limit of the allowable deviation interval is recorded as the capacity gap.
[0103] As described in the above steps S401-S402, in order to accurately grasp the execution status of the production task, it is necessary to collect the real-time workshop output of each production workshop, and at the same time, it is necessary to set a reasonable allowable deviation interval. The allowable deviation interval is calculated and determined in advance based on the production plan and production capacity, and is not specifically limited in this article. Then the real-time production data is compared with the preset allowable deviation interval. If the real-time workshop output exceeds the upper limit of the allowable deviation interval, it means that the production capacity of the production workshop is not fully utilized and there is a certain amount of surplus production capacity. At this time, it is necessary to record the difference between the real-time output and the upper limit of the allowable deviation interval, so as to obtain the surplus production capacity. If the real-time workshop output is found to be within the allowable deviation interval during the comparison process, this indicates that the production status of the production workshop is normal and the production task is proceeding smoothly as planned. However, if the real-time workshop output during the comparison process is lower than the lower limit of the allowable deviation interval, it means that the production capacity of the production workshop has not reached the expected level and there is a problem of insufficient production capacity. At this time, the difference between the real-time output and the lower limit of the allowable deviation interval will be recorded and output as a production capacity gap.
[0104] In a preferred embodiment, the step of adjusting the production tasks of the production workshop under the overcapacity state based on the capacity gap includes:
[0105] S501, obtaining the capacity gap in the state of insufficient capacity;
[0106] S502, obtaining the remaining capacity of the production workshop under the overcapacity state, and the response time of the production workshop to each capacity gap under the overcapacity state;
[0107] S503, predicting the increase in the capacity gap within the response time, and summing the capacity gap and the increase in the capacity gap to obtain a total capacity gap, and arranging the total capacity gap in descending order;
[0108] S504, allocating the surplus capacity of the workshop with excess capacity to the workshop with insufficient capacity based on the total capacity gap and the surplus capacity of the workshop with excess capacity;
[0109] Among them, the allocation of the total capacity gap is based on the size of the remaining capacity in the overcapacity range.
[0110] As described in the above steps S501-S504, in order to effectively respond to the production task adjustment of the production workshop under the state of overcapacity or undercapacity, it is first necessary to obtain the capacity gap under the condition of undercapacity, the remaining capacity of the production workshop under the condition of overcapacity, and the response time of the production interval to each capacity gap under the condition of overcapacity, that is, the time period from the occurrence of the capacity gap to the start of the workshop to fill the capacity gap. On this basis, it is necessary to predict the increase in the capacity gap within the response time, that is, the capacity gap will gradually increase within the response time, and it is necessary to clarify the increase in the capacity gap that may occur within the response time in order to match the appropriate production workshop with overcapacity. Then, the existing capacity gap and the predicted increase in the capacity gap are summarized and summed to obtain the total capacity gap. In order to allocate resources more effectively, this total capacity gap also needs to be calculated according to They are arranged in order from large to small so as to give priority to solving the largest capacity gap. Finally, a capacity allocation plan is formulated based on the total capacity gap and the remaining capacity of the overcapacity workshops. Specifically, the remaining capacity of the overcapacity workshops is allocated according to the size of the capacity gap to make up for the production needs of the workshops with insufficient capacity. The key is to ensure that the remaining capacity of the overcapacity workshops can be used most effectively. Of course, the urgency of the production tasks of each workshop must also be taken into account, which requires the intervention of relevant management personnel. No additional elaboration is given in this article. Throughout the process, the allocation principle of the total capacity gap is based on the size of the remaining capacity of the overcapacity workshops. That is, the larger the remaining capacity of the workshop, the higher the possibility of filling the capacity gap, thereby increasing the capacity utilization rate of each production workshop, reducing resource waste and improving production efficiency.
[0111] In a preferred embodiment, the step of predicting the increase in the capacity gap within the response time includes:
[0112] Obtain the occurrence node of the capacity gap, and use the occurrence node as a benchmark to perform backtracking offset to obtain the backtracking period;
[0113] Set multiple sampling nodes within the retrospective period, and record the capacity at each sampling node as a conditional parameter;
[0114] A second prediction function is obtained, and the response time and the condition parameter are input into the second prediction function together, and the output result of the second prediction function is calibrated as the increase in the capacity gap.
[0115] In this implementation, the response time can be preset based on historical production experience. After the response time is determined, it is also necessary to determine the specific time when the capacity gap occurs, that is, the occurrence node of the capacity gap. Then, this occurrence node is used as a reference point to trace back a period of time. In this implementation, this period of time is the backtracking period. During the backtracking period, multiple sampling nodes are set at equal intervals. The sampling nodes represent different time points in a period of time before the capacity gap occurs, and the workshop output under these sampling nodes is recorded as a conditional parameter. Then, the second prediction function is introduced to predict the increase in the capacity gap according to the response time and the conditional parameter. The expression of the second prediction function is: In the formula, C z represents the increase in capacity gap, T represents the length of the lookback period, t represents the length of the response time, m represents the number of sampling nodes, and C j It represents the conditional parameter. By inputting the response time and the conditional parameter into the second prediction function together, the predicted value of the increase in the capacity gap within the response time can be output, providing corresponding data support for the calculation of the total capacity increase.
[0116] See also Figure 2 The hybrid flexible workshop joint scheduling system based on the lighthouse factory uses the above hybrid flexible workshop joint scheduling method based on the lighthouse factory, including:
[0117] The data acquisition module is used to perform data preprocessing based on the production data obtained from each production workshop, and calibrate the preprocessed production data as the benchmark data;
[0118] Feature extraction module: The feature extraction module is used to extract features from the benchmark data to obtain key production indicators, and evaluate the production capacity information of each production workshop based on the key production indicators;
[0119] Production monitoring module: The production monitoring module is used to allocate production tasks to each production workshop based on production capacity information and monitor the progress of production tasks of each production workshop in real time;
[0120] A status evaluation module is used to determine the production status of each production workshop according to the production task progress, wherein the production status includes insufficient capacity status and excess capacity status;
[0121] The task adjustment module is used to calculate the capacity gap of the production workshop under the state of insufficient capacity and the remaining capacity of the production workshop under the state of overcapacity, and adjust the production tasks of the production workshop under the state of overcapacity based on the capacity gap.
[0122] In the above, the system includes a data acquisition module, a feature extraction module, a production monitoring module, a status evaluation module and a task adjustment module. The data acquisition module is responsible for collecting production data from various production workshops. The production data may include production speed, product quality, material consumption and other indicators. The data acquisition module will perform corresponding preprocessing on these raw data, such as removing erroneous data, filling missing values, etc., to ensure the accuracy of subsequent analysis. After the preprocessing is completed, the production data will be calibrated as benchmark data to provide pre-data support for subsequent analysis and scheduling. The feature extraction module will extract key production indicators from the benchmark data. Through the key production indicators, the production capacity of each production workshop can be comprehensively evaluated to understand the production capacity information of each workshop. The production monitoring module will allocate reasonable production tasks to each production workshop based on the capacity evaluation results to ensure that each The production tasks of each workshop are matched with its production capacity to avoid overwork or waste of resources. At the same time, the production monitoring module will monitor the progress of production tasks of each production workshop in real time to adjust and optimize the production plan in time. The status evaluation module will accurately judge the production status of each production workshop according to the progress of production tasks. The production status includes insufficient capacity and overcapacity. The status evaluation module will also judge whether the workshop needs to increase production resources or adjust the production plan through data analysis to ensure the smooth and efficient production process. The task adjustment module will calculate the capacity gap of the production workshop under the condition of insufficient capacity, and adjust the production tasks of the production workshop under the condition of overcapacity, and fill the capacity gap according to the remaining capacity to avoid waste of resources in the overcapacity workshop, realize mutual scheduling and optimization of production workshops, and improve production efficiency.
[0123] See also Figure 3 , an electronic device, the electronic device comprising:
[0124] at least one processor;
[0125] and a memory communicatively coupled to the at least one processor;
[0126] Among them, the memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned hybrid flexible workshop joint scheduling method based on the lighthouse factory.
[0127] The processor of the above electronic device can be a central processing unit (CPU) or a graphics processing unit (GPU), or other types of special or general processors. These processors are responsible for executing computer programs stored in the memory to realize the hybrid flexible workshop joint scheduling function of the lighthouse factory. The memory, as the center of data storage and access, not only stores the operating system and necessary application software, but also stores computer programs for executing scheduling methods. When these programs are running on the processor, they can automatically complete a series of operations such as data collection, feature extraction, production monitoring, status evaluation and task adjustment, thereby realizing intelligent scheduling of the production workshop. In addition, the electronic device also includes input and output devices and an operator. The input and output devices are responsible for receiving user instructions, displaying system status and production data, including keyboards, mice, touch screens, displays, etc. They provide users with interactive interfaces so that users can conveniently operate and manage the system. The operator assists the processor in completing complex mathematical and logical operations to ensure that the scheduling system can efficiently and accurately process large amounts of data.
[0128] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.
[0129] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.
Claims
1. Hybrid flexible workshop joint scheduling method based on lighthouse factory, Features: include: Perform data preprocessing based on the production data obtained from each production workshop, and calibrate the preprocessed production data as benchmark data; Extracting features from the benchmark data to obtain key production indicators, and evaluating the production capacity information of each production workshop based on the key production indicators; Allocate production tasks to each production workshop based on the production capacity information, and monitor the progress of production tasks of each production workshop in real time; Determine the production status of each production workshop according to the production task progress, wherein the production status includes insufficient production capacity status and excess production capacity status; The capacity gap of the production workshop under the undercapacity state and the remaining capacity of the production workshop under the overcapacity state are calculated, and the production tasks of the production workshop under the overcapacity state are adjusted based on the capacity gap.
2. According to the hybrid flexible workshop joint scheduling method based on the lighthouse factory according to claim 1, Features: The step of preprocessing the data according to the obtained production data of each production workshop and calibrating the preprocessed production data as the reference data includes: Obtain the original production data of each production workshop, and clean all the original production data to remove invalid, erroneous and duplicate data; Standardize the cleaned original production data to obtain standardized data in the same dimension; A time stamp is added to the normalized data, and the time-stamped normalized data is used as the baseline data.
3. According to the hybrid flexible workshop joint scheduling method based on lighthouse factory according to claim 1, Features: The step of extracting features from the benchmark data to obtain key production indicators includes: Acquire multiple production dimension information in the benchmark data, wherein the production dimension information includes workshop equipment status information, workshop production speed, material supply speed, raw material consumption information, and product qualification rate; Obtaining workshop output, and based on the workshop output, performing correlation analysis on multiple production dimension information, and outputting the correlation between each production dimension information and the workshop output; A screening threshold is obtained, and the screening threshold is compared with the correlation degree, and production dimension information with a correlation degree greater than the screening threshold is determined as a key production indicator.
4. According to claim 3, the hybrid flexible workshop joint scheduling method based on the lighthouse factory, Features: The step of performing correlation analysis on multiple production dimension information based on the workshop output and outputting the correlation between each production dimension information and the workshop output includes: Construct a historical monitoring period and collect change nodes of each production dimension information within the historical monitoring period; Collect the unique change nodes of each production dimension information one by one and record them as a single change point; Counting the fluctuation amount of each of the production dimension information at a single change point and the change amount of workshop output under the single change point, and combining the change amount of workshop output with the fluctuation amount of the production dimension information at a single change point to obtain the unit change amount of workshop output under each of the production dimension information; A correlation distribution function is obtained, and the unit change of the workshop output under each of the production dimension information is input into the correlation distribution function, and the output result of the correlation distribution function is calibrated as the correlation between the production dimension information and the workshop output.
5. According to claim 4, the hybrid flexible workshop joint scheduling method based on the lighthouse factory, Features: The step of evaluating the production capacity information of each production workshop according to the key production indicators includes: Setting a plurality of sampling periods of equal duration within the historical monitoring period; Performing difference processing on the key production indicators in adjacent sampling periods to obtain indicator fluctuations; Obtaining an evaluation threshold value of each key production indicator, and comparing the evaluation threshold value with the indicator fluctuation amount; If the evaluation threshold is less than the indicator fluctuation amount, it indicates that the corresponding key production indicator is a valid fluctuation, and the indicator fluctuation amount under the valid fluctuation is recorded as the valid fluctuation amount; If the evaluation threshold is greater than or equal to the indicator fluctuation amount, it indicates that the corresponding key production indicator is an invalid fluctuation, and the indicator fluctuation amount under the invalid fluctuation will be ignored; A first prediction function is obtained, and the effective fluctuation amount is input into the first prediction function, and an output result of the first prediction function is recorded as the production capacity information of the production workshop.
6. The hybrid flexible workshop joint scheduling method based on lighthouse factory according to claim 1, Features: The step of determining the production status of each production workshop according to the production task progress includes: Obtain the real-time workshop output of each production workshop and the preset allowable deviation range; comparing the real-time workshop output with the allowable deviation range; If the real-time workshop output is higher than the upper limit of the allowable deviation interval, it indicates that the production state of the production workshop is in an overcapacity state, and the difference between the real-time workshop output and the upper limit of the allowable deviation interval is recorded as the excess capacity; If the real-time workshop output is within the allowable deviation range, it indicates that the production status of the production workshop is normal; If the real-time workshop output is lower than the lower limit of the allowable deviation interval, it indicates that the production status of the production workshop is insufficient capacity, and the difference between the real-time workshop output and the lower limit of the allowable deviation interval is recorded as the capacity gap.
7. According to claim 1, the hybrid flexible workshop joint scheduling method based on the lighthouse factory, Features: The step of adjusting the production tasks of the production workshop under the overcapacity state based on the production capacity gap includes: Obtaining the capacity gap in the insufficient capacity state; Obtaining the remaining capacity of the production workshop under the overcapacity state, and the response time of the production workshop to each capacity gap under the overcapacity state; Predicting the increase in the capacity gap within the response time, and summing the capacity gap and the increase in the capacity gap to obtain a total capacity gap, and arranging the total capacity gap in descending order; According to the total capacity gap and the surplus capacity of the workshop with excess capacity, the surplus capacity of the workshop with excess capacity is allocated to the workshop with insufficient capacity; Among them, the allocation of the total capacity gap is carried out according to the size of the remaining capacity in the overcapacity interval.
8. According to claim 1, the hybrid flexible workshop joint scheduling method based on the lighthouse factory, Features: The step of predicting the increase in the capacity gap within the response time includes: Obtain the occurrence node of the capacity gap, and perform backtracking offset based on the occurrence node to obtain a backtracking period; Setting a plurality of sampling nodes within the backtracking period, and recording the production capacity at each of the sampling nodes as a condition parameter; A second prediction function is obtained, and the response time and the condition parameter are input into the second prediction function together, and the output result of the second prediction function is calibrated as the increase in the production capacity gap.
9. A hybrid flexible workshop joint scheduling system based on a lighthouse factory, using the hybrid flexible workshop joint scheduling method based on a lighthouse factory as claimed in any one of claims 1 to 8, Features: include: A data acquisition module, wherein the data acquisition module is used to perform data preprocessing based on the production data acquired from each production workshop, and calibrate the preprocessed production data as reference data; A feature extraction module, the feature extraction module is used to extract features from the benchmark data to obtain key production indicators, and evaluate the production capacity information of each production workshop based on the key production indicators; A production monitoring module, which is used to allocate production tasks to each production workshop according to the production capacity information and monitor the progress of production tasks of each production workshop in real time; A status evaluation module, which is used to determine the production status of each production workshop according to the production task progress, wherein the production status includes an insufficient production capacity state and an excessive production capacity state; The task adjustment module is used to calculate the capacity gap of the production workshop under the insufficient capacity state and the remaining capacity of the production workshop under the overcapacity state, and adjust the production tasks of the production workshop under the overcapacity state based on the capacity gap.
10. An electronic device, Features: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; In which, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the hybrid flexible workshop joint scheduling method based on the lighthouse factory as described in any one of claims 1 to 8.
