Textile production equipment recommendation scheduling method

Abstract

The invention relates to the technical field of textile industry, and discloses a textile production equipment recommendation scheduling method, which comprises the following steps: S1, extracting production process information: before scheduling, firstly extracting process information of a product to be produced from an order system; s2, obtaining candidate equipment information: after the production process information is obtained, extracting detailed information of all available equipment from an equipment management system; s3, judging a forced constraint condition; s4, multi-dimensional matching of priority conditions is carried out; s5, calculating the matching degree of the raw materials; s6, matching the opening value of the equipment; s7, scheduling optimization is carried out; and S8, generating a scheduling scheme. Through fine matching of process parameters and equipment parameters, the selected equipment can be ensured to be most suitable for the current production task, the equipment adjustment time and the production preparation time are reduced, so that the production efficiency is improved, the use of the equipment can be reasonably arranged, the downtime caused by frequent switching of the equipment or the process is reduced, and the production efficiency is improved. The continuous production capacity is improved.

Description

Technical Field

[0001] The invention relates to the technical field of textile industry, and in particular to a method for recommending and scheduling textile production equipment. Background Art

[0002] With the rapid development of the textile industry, modern textile production has increasingly higher requirements for efficiency, flexibility and product quality. Traditional scheduling methods for textile production equipment usually rely on manual experience or simple rule-making. These methods show obvious shortcomings when faced with complex production needs.

[0003] In traditional scheduling methods, equipment selection is often based on static standards and experience, lacking precise matching of real-time process requirements. With the increasing trend of product diversification, a single device is difficult to meet the production needs of different products, and it is impossible to efficiently match equipment and process parameters, resulting in frequent equipment adjustments and replacements during the production process, affecting production efficiency. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method for recommending scheduling of textile production equipment, which solves the problem that traditional scheduling methods affect production efficiency.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for recommending scheduling of textile production equipment, comprising the following steps:

[0006] S1: Extracting production process information: Before scheduling begins, first extract the process information of the product to be produced from the order system, including warp knitting category, machine gauge, number of combs, traverse mode, jacquard system / creel type / widening, raw material matching, opening, number of warps and machine speed;

[0007] S2: Obtain candidate equipment information: After obtaining the production process information, extract detailed information of all available equipment from the equipment management system, including equipment model and number, equipment process parameters, historical production records of the equipment, and maintenance status of the equipment;

[0008] S3: Determine mandatory constraints: In the initial screening stage of scheduling, it is necessary to determine whether the candidate equipment meets the most basic production requirements. The mandatory constraints mainly include warp knitting category matching, machine gauge matching, comb number matching, slitting mode matching, jacquard system / creel type / widening function matching and raw material matching;

[0009] S4: Multi-dimensional matching of priority conditions: After the initial mandatory constraint screening, the remaining candidate devices will undergo detailed matching evaluation based on the preset priority conditions;

[0010] First, each priority condition is assigned a certain weight according to its importance, then each device is scored according to its matching degree with the process parameters, and finally the comprehensive matching degree of each device is calculated based on the weighted scores of all conditions;

[0011] S5: Calculation of raw material matching

[0012] First, extract the raw material information on the current process sheet, then compare the raw materials of the current production task with the raw materials in the previous production task of the equipment, and finally match the comb number;

[0013] S6: Matching of device opening values

[0014] Extract the target product's opening value from the process sheet and check whether the equipment can support the required opening value. Equipment whose opening value is not within the equipment's support range will be excluded.

[0015] S7: Scheduling Optimization

[0016] After completing all matching steps, enter the scheduling optimization stage;

[0017] First, the scores of all matching conditions are weighted to obtain the comprehensive score of each candidate device. Then, the devices are sorted according to the comprehensive score, and the devices with the highest scores are selected first. Finally, when selecting devices, the current utilization rate of the device and whether it is in maintenance status need to be considered;

[0018] S8: Generate a scheduling plan

[0019] Generate the optimal production equipment scheduling plan based on the results of scheduling optimization;

[0020] First, clearly specify the production tasks of each device to ensure that each process step is assigned to the most suitable equipment. Then formulate a detailed production schedule, including the start and end time of each production stage. Finally, during the production process, establish a real-time monitoring system to monitor the operating status of the equipment and production progress.

[0021] In some embodiments, in the step S1, real-time process data is obtained from the ERP system or the MES system, the data is obtained in real time through an API interface, and integrated into the scheduling algorithm, and a data integrity check mechanism is established;

[0022] In addition to the process information of the current order, it is also necessary to retrieve the process data of similar orders in the past, analyze the performance of historical process parameters, perform cluster analysis on historical data, and identify common process parameter combinations and their corresponding production performance.

[0023] In some embodiments, in step S2, not only the current status of the device is obtained, but also the performance history and maintenance record of the device:

[0024] Establish an equipment performance database to record all technical parameters, production history, maintenance records and failure rates of each device. Use Internet of Things technology to achieve real-time monitoring of equipment status. Regularly extract equipment maintenance records from the equipment maintenance system to understand the equipment's maintenance cycle, last maintenance time and next maintenance plan. Finally, for equipment that has frequently failed in the past, the scheduling system automatically lowers its priority.

[0025] In some embodiments, in the S3 step, when the mandatory constraint conditions are matched with parameters, the linkage effect between the parameters is carried out, and the standards of the mandatory constraint conditions are dynamically adjusted according to the feedback of real-time data and historical production results, and the dynamic adjustment is based on data-driven.

[0026] In some embodiments, in the S4 step, the priority condition matching process is processed by introducing a machine learning model. By training the model and utilizing a large amount of historical data, the model learns which devices perform best under certain conditions, and automatically optimizes the matching strategy, and then dynamically adjusts the weights of different conditions, while performing a multi-objective optimization algorithm.

[0027] In some embodiments, in the step S5, when calculating the raw material matching degree, it is necessary not only to calculate the type and number of the raw material, but also to calculate the fineness, twist, and color consistency of the yarn. The raw material usage in the historical production records is analyzed by using big data analysis technology to identify which raw material combinations perform best on specific equipment, and incorporate this information into the matching degree calculation;

[0028] When matching raw materials, add the time factor, analyze the time dimension, predict how the equipment's ability to process certain raw materials changes over time, and adjust the schedule.

[0029] In some embodiments, in the step S6, an opening value adjustment database is established to record the opening value adjustment records of each device under different processes, and the opening value settings and actual production results of each device in past production tasks are analyzed.

[0030] In some embodiments, in the step S7, a genetic algorithm is introduced to optimize the equipment scheduling. The genetic algorithm continuously iterates and optimizes the scheduling scheme by simulating the process of natural selection and gene mutation, and finally finds the optimal solution. In each iteration, the actual performance and feedback of the equipment are added, and the data in actual production are fed back to the algorithm, so that it can continuously adjust and optimize the scheduling strategy;

[0031] During the production process, a real-time monitoring system is established to monitor the equipment's operating status, production progress, and product quality in real time;

[0032] By introducing an adaptive control algorithm, the system automatically corrects the scheduling plan when an abnormal situation is detected.

[0033] In some embodiments, in the step S8, the specific operation steps and precautions for each device are clearly defined in the scheduling plan. For tasks involving the collaborative work of multiple devices, the plan includes a detailed equipment handover plan;

[0034] Through deep integration with the production execution system, production progress can be tracked in real time, and the adjusted scheduling plan can be automatically generated and pushed to the operators.

[0035] The present invention provides a method for recommending scheduling of textile production equipment. It has the following beneficial effects:

[0036] 1. The present invention can ensure that the selected equipment is most suitable for the current production task through fine matching of process parameters and equipment parameters, reduce equipment adjustment time and production preparation time, thereby improving production efficiency. In addition, this method can reasonably arrange the use of equipment, reduce downtime caused by frequent switching of equipment or processes, and improve continuous production capacity.

[0037] 2. The present invention can reduce the occurrence rate of unqualified products through precise raw material matching and process parameter matching, thereby reducing the waste of raw materials. By reasonably arranging the use of equipment, reducing idle time and unnecessary startup times, it can optimize energy consumption and reduce production costs. By analyzing the operating status and maintenance records of the equipment in advance, it can avoid sudden failures of equipment during production, thereby reducing the high costs of emergency repairs.

[0038] 3. The method of the present invention can ensure the precise matching of equipment and process parameters, ensure the consistency and high quality of products in the production process, and reduce the proportion of unqualified products. The automated scheduling method reduces the chance of human intervention, thereby reducing quality problems caused by improper operation or scheduling errors. By real-time monitoring of equipment status and production progress, abnormal situations in production can be discovered and corrected in a timely manner, further ensuring product quality.

[0039] 4. The method of the present invention minimizes the idle time of equipment and improves the utilization rate of equipment through accurate scheduling algorithms. It reduces excessive use and frequent startup of equipment through reasonable scheduling, thereby extending the service life of equipment and reducing equipment depreciation costs. It prevents individual equipment from being overloaded or idle for a long time by arranging the work tasks of each device in a balanced manner, effectively extending the service life of the equipment and optimizing the overall equipment utilization rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention is a flowchart of a scheduling method for recommending textile production equipment. DETAILED DESCRIPTION

[0041] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings 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.

[0042] Please refer to the attached Figure 1 The embodiment of the present invention provides a method for recommending scheduling of textile production equipment, comprising the following steps:

[0043] S1: Extracting production process information

[0044] Before scheduling begins, the process information of the products to be produced must first be extracted from the order system. This step is crucial because all subsequent scheduling decisions are based on these process parameters.

[0045] Warp knitting category: defines the type of fabric structure of the product, such as double needle bed warp knitting or single needle bed warp knitting. This parameter determines the basic weaving structure of the product and directly affects the choice of equipment.

[0046] Machine number: Indicates the model or number of the required equipment. Different models of equipment may have different functional characteristics, such as different numbers of combs or slidable capabilities.

[0047] Number of bars: This is an important parameter of the machine and indicates how many bars there are on the machine. The number of bars determines the complexity and detail of the fabric, such as how many different yarns can be used when weaving.

[0048] Traverse mode: Indicates how the yarn moves laterally during the weaving process, including no traverse, unidirectional traverse or bidirectional traverse, etc. This parameter affects the final pattern and structure of the fabric.

[0049] Jacquard system / creel type / width: The Jacquard system determines the pattern weaving capabilities of the fabric, while the creel type and width function involve how the equipment supports different types and sizes of fabrics.

[0050] Raw material matching: involves the type, color, specification of yarn, etc. The selection of these raw materials is closely related to the historical production records of the equipment, ensuring that the same or similar materials can be seamlessly produced on the equipment.

[0051] Opening: refers to the opening of the fabric, which directly affects the density of the fabric. The opening value needs to match the physical capacity of the equipment.

[0052] Number of yarn heads: The number of yarn heads that can be installed on the equipment, which affects the head changing frequency and production efficiency during the production process.

[0053] Machine speed: that is, the operating speed of the equipment, which directly affects production efficiency and capacity.

[0054] S2: Get candidate device information

[0055] After obtaining the production process information, it is necessary to extract detailed information of all available equipment from the equipment management system:

[0056] Equipment model and number: Clarifying the equipment's identification information helps match specific process requirements.

[0057] Equipment process parameters: including the number of combs, traverse method, Jacquard system / creel type / widening, etc. This information determines the type and complexity of products that the equipment can handle.

[0058] Historical production records of the equipment: This part of information is very important because the previous production situation of the equipment can be used as a reference to determine whether the equipment is suitable for the current production task. For example, the type of raw materials and comb configuration of the products produced by the equipment most recently can be used to predict the adaptability of the equipment to the new task.

[0059] Equipment maintenance status: Check whether the equipment is in good operating condition, whether maintenance is required or a maintenance plan has been arranged, which will affect whether the equipment can participate in the current schedule.

[0060] S3: Determine mandatory constraints

[0061] In the initial screening stage of scheduling, it is necessary to determine whether the candidate equipment meets the most basic production requirements. These mandatory constraints mainly include:

[0062] Warp knitting category matching: Ensure that the candidate equipment can process a specific warp knitting category. For example, if the order requires the production of double needle bed warp knitting products, then all equipment that does not support double needle bed warp knitting will be excluded.

[0063] Machine model matching: Different models of equipment may have different physical or technical capabilities. For example, a specific model may only support a limited number of combs or a specific traverse method. Only equipment that meets these requirements can enter the next round of screening.

[0064] Matching the number of combs: The number of combs is a key factor in whether the equipment can handle a specific process. If a device with 5 combs is required, but the candidate equipment can only support 4 combs, the equipment will be excluded.

[0065] Traverse mode matching: The traverse mode determines the final structure and pattern of the fabric. If the production process requires a complex traverse mode (such as bidirectional traverse), but the equipment only supports simple traverse or no traverse, the equipment is not suitable for this task.

[0066] Jacquard system / creel type / widening function matching: This parameter involves the complex pattern and size requirements of the product, ensuring that the equipment can support these functions.

[0067] Raw material matching: Raw material matching at an early stage is done by checking whether the equipment can support the required raw materials. If the equipment cannot handle the specified yarn type or specification, it will be excluded.

[0068] S4: Multi-dimensional matching of priority conditions

[0069] After passing the initial mandatory constraint screening, the remaining candidate devices will undergo detailed matching evaluation based on the preset priority conditions.

[0070] Set weights: Each priority condition is assigned a certain weight according to its importance. For example, warp knitting category, machine gauge, number of guide bars, traverse mode, jacquard system / creel type / widening are usually considered key parameters and the weight is set to 100%. Other parameters such as raw material matching, opening, number of beams, and machine speed are assigned lower weights according to the specific situation.

[0071] Matching score: Each device is scored according to its matching degree with the process parameters. For example, if the number of combs in the device is exactly the same as the requirements, the score is 100%; if it deviates slightly (such as the device has one more or one less comb), the score is slightly lower.

[0072] Comprehensive matching degree calculation: The comprehensive matching degree of each device is calculated based on the weighted scores of all conditions. This score will be used to prioritize the devices.

[0073] S5: Calculation of raw material matching

[0074] In the process of equipment screening, the calculation of raw material matching is crucial. The detailed process of this step is as follows:

[0075] Extract the raw material information on the current process sheet: obtain the specific raw material parameters required for the current production task, including material number, yarn type, color, number of yarns, number of bobbins, etc.

[0076] Match the raw material information in the equipment's historical production records: Compare the raw materials of the current production task with the raw materials used in the equipment's last production task. For example, if the equipment used 5 kinds of raw materials last time, and 4 of them are the same as the current task, the matching degree is 80%. This matching degree can predict the stability and adaptability of the equipment in the current task.

[0077] Consider matching the number of bars: if the number of bars required for the current task matches the number of bars on the machine, and the raw material last used by the machine had the same configuration on these bars, the match will be higher.

[0078] S6: Matching of device opening values

[0079] The opening value is an important parameter to ensure that the equipment can produce products that meet the density requirements. The specific steps are as follows:

[0080] Extract the opening value on the process sheet: Extract the opening value of the target product from the process sheet. This value usually reflects the density requirement of the fabric.

[0081] Match the device's opening setting: Check whether the device can support the required opening value. For example, if the process requires an opening value of 4.5, and the device's opening setting range is 3.5-4.5, then the device meets the requirements; if the opening value is not within the range supported by the device, the device will be excluded.

[0082] Refine the opening matching rules: If the opening value range given on the process sheet is wide (for example, 4.0-5.0), the matching rules can be further refined, such as giving priority to equipment that can provide a more accurate match.

[0083] S7: Scheduling Optimization

[0084] After completing all matching steps, the scheduling optimization stage begins to ensure that the equipment finally selected not only meets production requirements but also enables efficient production.

[0085] Comprehensive score: The scores of all matching conditions are weighted to obtain the comprehensive score of each candidate device. The higher the score, the more suitable the device is for the current production task.

[0086] Sorting and filtering: Sort the devices according to their comprehensive scores, giving priority to the devices with the highest scores.

[0087] Consider equipment utilization and maintenance status: When selecting equipment, also consider the equipment's current utilization and whether it is in maintenance status. If two equipment have similar comprehensive scores, but one has a lower utilization rate or is about to undergo maintenance, you can choose the other equipment.

[0088] S8: Generate a scheduling plan

[0089] According to the results of scheduling optimization, generate the optimal production equipment scheduling plan. This plan should include the following:

[0090] Equipment allocation: clearly specify the production tasks of each equipment to ensure that each process step is assigned to the most appropriate equipment.

[0091] Scheduling: Develop a detailed production schedule, including the start and end time of each production stage, to ensure a smooth production process.

[0092] Real-time monitoring and feedback mechanism: During the production process, a real-time monitoring system is established to monitor the operating status of the equipment and the production progress. If an abnormal situation occurs, the scheduling plan is adjusted in time to ensure the continuity of production and product quality.

[0093] Continuous optimization: The scheduling plan should be flexible and dynamically adjusted according to production feedback and equipment status to cope with emergencies that may occur during production.

[0094] In step S1, refinement of production process information is extracted

[0095] In this part, we need to ensure that the process information obtained is not only comprehensive, but also takes into account the dynamic changes and history of each parameter. This includes:

[0096] Data sources and integration:

[0097] Get real-time process data from ERP or MES systems. These systems usually record detailed process requirements for each order. Data can be obtained in real time through API interfaces and integrated into scheduling algorithms.

[0098] Establish a data integrity check mechanism to ensure that the extracted process information is not missing or wrong. If the data is found to be incomplete or abnormal, communicate with the process engineer in time to correct the problem.

[0099] Historical data analysis:

[0100] In addition to the process information of the current order, the process data of similar orders in the past should also be retrieved to analyze the performance of historical process parameters. For example, some process parameters may perform better on a specific device than on other devices, and this information can be used as a reference for optimizing scheduling.

[0101] Cluster analysis of historical data can be performed to identify common process parameter combinations and their corresponding production performance. With these data, a preliminary model for process-equipment matching can be constructed.

[0102] In step S2, obtain the refinement of candidate device information

[0103] This step should not only capture the current status of the equipment, but also include the equipment’s performance history and maintenance records to make more accurate equipment recommendations.

[0104] Establishment of equipment performance database:

[0105] Establish an equipment performance database to record all technical parameters, production history, maintenance records, failure rates, etc. of each equipment. These data should be dynamic and can be updated at any time.

[0106] Use the Internet of Things (IoT) technology to monitor the status of equipment in real time. For example, use sensors to obtain information such as the temperature, vibration, and running speed of the equipment. These real-time data can help determine the health status of the equipment and thus affect scheduling decisions.

[0107] Equipment maintenance and repair records:

[0108] Regularly extract equipment maintenance records from equipment maintenance systems (such as CMMS systems). Understand the equipment's maintenance cycle, last maintenance time, and next maintenance plan, as this information has a direct impact on the equipment's availability.

[0109] For equipment that has a history of frequent failures, the scheduling system should automatically lower its priority unless it is clearly shown in the maintenance records that the equipment has been completely repaired and passed the test.

[0110] In step S3, the refinement of the mandatory constraints is determined

[0111] At this stage, the judgment of mandatory constraints should be more detailed and comprehensive considering the mutual influence between different process parameters.

[0112] Multi-parameter linkage judgment:

[0113] When matching warp knitting categories, machine gauges, number of combs and other parameters, the matching should not be done in isolation, but the linkage effect between the parameters should be considered. For example, some machine gauges perform best in a specific range of comb numbers, but may perform poorly in other ranges.

[0114] To avoid excluding potentially useful devices, a loose initial screening criteria can be designed, followed by further screening based on more detail in subsequent steps.

[0115] Dynamically adjust mandatory constraints:

[0116] Dynamically adjust the standards for mandatory constraints based on real-time data feedback and historical production results. For example, if a device can break through its design limits in certain specific situations (such as operating normally with more than the usual number of combs), you can consider relaxing these limits when matching.

[0117] This dynamic adjustment should be data-driven and combined with the experience of experts to ensure that the adjusted standards are flexible without affecting production quality.

[0118] In step S4, refinement of multi-dimensional matching of priority conditions

[0119] The matching process of priority conditions can be improved by introducing more complex algorithms and more refined scoring mechanisms.

[0120] Matching algorithm based on machine learning:

[0121] Introduce machine learning models (such as decision trees, random forests, etc.) to handle the matching of priority conditions. By training the model and using a large amount of historical data, the model can learn which devices perform best under certain conditions and automatically optimize the matching strategy.

[0122] These models can continuously learn and optimize themselves, and the matching accuracy will gradually improve as more data is input.

[0123] Weight optimization of condition matching:

[0124] The weights of different conditions are adjusted dynamically. For example, during a production season, if the supply of raw materials is tight, the weight of raw material matching can be increased to ensure that equipment selection can better adapt to the availability of raw materials.

[0125] Using a multi-objective optimization algorithm, we can maximize the scores of other priority conditions while meeting the process requirements. This method can optimize the weighted scores of each condition so that the final equipment selection meets the process requirements and improves production efficiency.

[0126] In step S5, the raw material matching degree is refined

[0127] For the calculation of raw material matching, the accuracy can be improved through more detailed comparison and dynamic adjustment strategies.

[0128] Refine the matching of raw material parameters:

[0129] When calculating the matching degree of raw materials, not only the type and number of raw materials should be considered, but also details such as yarn fineness, twist, color consistency, etc. These small differences can have a significant impact on the quality of the final product.

[0130] Using big data analytics, we analyze raw material usage in historical production records, identify which raw material combinations perform best on specific equipment, and incorporate this information into matching calculations.

[0131] Introducing the matching of time dimension:

[0132] When matching raw materials, consider the time factor. For example, some raw materials may deteriorate in performance after a long storage time, so when matching, give priority to equipment that has recently used the same or similar raw materials.

[0133] Through analysis of the time dimension, it is possible to predict how the equipment's ability to process certain raw materials changes over time and adjust the schedule.

[0134] In step S6, refinement of the equipment opening value

[0135] The matching of equipment opening values ​​should not only consider the current matching situation, but also combine the equipment's historical performance and future adjustment capabilities.

[0136] Dynamic adjustment mechanism of opening value:

[0137] In the actual production process, the opening value of the equipment may need to be fine-tuned according to the real-time state of the fabric. Therefore, when matching the opening value, the adjustment flexibility of the equipment can be considered. For example, although some equipment has a narrow opening value range, it has strong adjustment capabilities and can meet the process requirements through fine-tuning.

[0138] Establish a start-up value adjustment database to record the start-up value adjustment records of each device under different processes. These data can help predict the adjustment capacity of the equipment under the current process and influence scheduling decisions.

[0139] Historical performance analysis of equipment opening values:

[0140] Analyze the opening value settings and actual production results of each device in past production tasks. Through these data, it is possible to evaluate whether the actual opening capacity of the device is consistent with the theoretical value. If it is found that the actual performance of a certain device is better than its design parameters, the conditions can be appropriately relaxed during matching.

[0141] Refinement of schedule optimization in step S7

[0142] In the scheduling optimization stage, more complex optimization algorithms and feedback mechanisms can be used to further improve the accuracy and flexibility of scheduling.

[0143] Scheduling optimization based on genetic algorithm:

[0144] Genetic algorithms are introduced to optimize equipment scheduling. Genetic algorithms simulate the process of natural selection and gene mutation, continuously iterate and optimize scheduling plans, and finally find the optimal solution. This method is particularly suitable for dealing with multi-objective optimization problems, such as considering factors such as production efficiency, equipment utilization, and production costs at the same time.

[0145] In each generation of iteration, the actual performance and feedback of the equipment are taken into consideration, and the data from actual production is fed back to the algorithm so that it can continuously adjust and optimize the scheduling strategy.

[0146] Real-time feedback and dynamic adjustment mechanism:

[0147] During the production process, a real-time monitoring system is established to monitor the equipment's operating status, production progress, and product quality in real time. If the actual performance of the equipment is found to be inconsistent with the scheduling expectations (such as equipment failure or low production efficiency), the system should automatically adjust the schedule and reallocate tasks to ensure the continuity and efficiency of production.

[0148] By introducing adaptive control algorithms, the system can automatically correct the scheduling plan when abnormal conditions are detected, thus avoiding production delays caused by equipment problems.

[0149] In step S8, the detailed generation of the scheduling plan is

[0150] When generating the final scheduling plan, more practical operational factors need to be considered and the operability and flexibility of the plan must be ensured.

[0151] Refine the operation details of the scheduling plan:

[0152] In the scheduling plan, the specific operating steps and precautions for each device should be clearly stated. For example, the preparation work required for the equipment (such as changing yarn, adjusting the comb, etc.) should be explained in detail, as well as the problems that may be encountered during the production process and the corresponding countermeasures.

[0153] For tasks that involve multiple devices working together, the plan should include a detailed equipment handover plan to ensure smooth connection between the devices and avoid production interruptions due to improper handover.

[0154] Dynamic generation and adjustment mechanism:

[0155] The scheduling plan should have the ability to be dynamically generated and adjusted. For example, the system can dynamically generate new scheduling plans based on real-time data, or adjust existing plans to deal with emergencies (such as order changes or equipment failures).

[0156] Through deep integration with the Manufacturing Execution System (MES), production progress can be tracked in real time, and adjusted scheduling plans can be automatically generated and pushed to operators to ensure production continuity and efficiency.

[0157] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for recommending scheduling of textile production equipment, characterized in that: The following steps are involved: S1: Extracting production process information: Before scheduling begins, first extract the process information of the product to be produced from the order system, including warp knitting category, machine gauge, number of combs, traverse mode, jacquard system / creel type / widening, raw material matching, opening, number of warps and machine speed; S2: Obtain candidate equipment information: After obtaining the production process information, extract detailed information of all available equipment from the equipment management system, including equipment model and number, equipment process parameters, historical production records of the equipment, and maintenance status of the equipment; S3: Determine mandatory constraints: In the initial screening stage of scheduling, it is necessary to determine whether the candidate equipment meets the most basic production requirements. The mandatory constraints mainly include warp knitting category matching, machine gauge matching, comb number matching, slitting mode matching, jacquard system / creel type / widening function matching and raw material matching; S4: Multi-dimensional matching of priority conditions: After the initial mandatory constraint screening, the remaining candidate devices will undergo detailed matching evaluation based on the preset priority conditions; First, each priority condition is assigned a certain weight according to its importance, then each device is scored according to its matching degree with the process parameters, and finally the comprehensive matching degree of each device is calculated based on the weighted scores of all conditions; S5: Calculation of raw material matching: First, extract the raw material information on the current process sheet, then compare the raw materials of the current production task with the raw materials in the previous production task of the equipment, and finally match the comb number; S6: Matching of equipment opening values: Extract the opening values ​​of the target product from the process sheet and check whether the equipment can support the required opening values. Equipment whose opening values ​​are not within the equipment support range will be excluded. S7: Scheduling optimization: After completing all matching steps, the scheduling optimization phase begins. First, the scores of all matching conditions are weighted to obtain a comprehensive score for each candidate device. Then, the devices are sorted according to the comprehensive score, with the highest-scoring device being selected first. Finally, when selecting a device, the current utilization rate of the device and whether it is in maintenance status also need to be considered. S8: Generate scheduling plan: Generate the optimal scheduling plan for production equipment based on the results of scheduling optimization; first clearly specify the production tasks of each device to ensure that each process step is assigned to the most suitable equipment, and then formulate a detailed production schedule, including the start and end time of each production stage. Finally, during the production process, establish a real-time monitoring system to monitor the operating status of the equipment and production progress.

2. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In the step S1, real-time process data is obtained from the ERP system or MES system. The data is obtained in real time through the API interface and integrated into the scheduling algorithm, and a data integrity check mechanism is established; In addition to the process information of the current order, it is also necessary to retrieve the process data of similar orders in the past, analyze the performance of historical process parameters, perform cluster analysis on historical data, and identify common process parameter combinations and their corresponding production performance.

3. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In the S2 step, not only the current status of the equipment is obtained, but also the performance history and maintenance records of the equipment: Establish an equipment performance database to record all technical parameters, production history, maintenance records and failure rates of each device. Use Internet of Things technology to achieve real-time monitoring of equipment status. Regularly extract equipment maintenance records from the equipment maintenance system to understand the equipment's maintenance cycle, last maintenance time and next maintenance plan. Finally, for equipment that has frequently failed in the past, the scheduling system automatically lowers its priority.

4. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In the step S3, when the mandatory constraint conditions are matched with the parameters, the linkage effect between the parameters is carried out, and the standards of the mandatory constraint conditions are dynamically adjusted according to the feedback of real-time data and historical production results, and the dynamic adjustment is based on data-driven.

5. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In the S4 step, the priority condition matching process is processed by introducing a machine learning model. By training the model and utilizing a large amount of historical data, the model learns which devices perform best under certain conditions, automatically optimizes the matching strategy, and then dynamically adjusts the weights of different conditions while performing a multi-objective optimization algorithm.

6. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In the step S5, when calculating the raw material matching degree, it is necessary not only to calculate the type and number of the raw materials, but also to calculate the fineness, twist, and color consistency of the yarn. In addition, the raw material usage in the historical production records is analyzed by using big data analysis technology to identify which raw material combinations perform best on specific equipment, and incorporate this information into the matching degree calculation; When matching raw materials, add the time factor, analyze the time dimension, predict how the equipment's ability to process certain raw materials changes over time, and adjust the schedule.

7. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In the step S6, an opening value adjustment database is established to record the opening value adjustment records of each device under different processes, and the opening value settings and actual production results of each device in past production tasks are analyzed.

8. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In step S7, a genetic algorithm is introduced to optimize equipment scheduling. The genetic algorithm continuously iterates and optimizes the scheduling plan by simulating the process of natural selection and gene mutation, and finally finds the optimal solution. In each iteration, the actual performance and feedback of the equipment are added, and the data in actual production are fed back to the algorithm, so that it can continuously adjust and optimize the scheduling strategy; During the production process, a real-time monitoring system is established to monitor the equipment's operating status, production progress, and product quality in real time; By introducing an adaptive control algorithm, the system automatically corrects the scheduling plan when an abnormal situation is detected.

9. The method for recommending scheduling of textile production equipment according to claim 1, characterized in that: In step S8, the specific operation steps and precautions for each device are clearly defined in the scheduling plan. For tasks involving the collaborative work of multiple devices, the plan includes a detailed equipment handover plan; Through deep integration with the production execution system, production progress can be tracked in real time, and the adjusted scheduling plan can be automatically generated and pushed to the operators.

Images