Artificial intelligence driven intelligent manufacturing system scheduling method

Abstract

The present invention relates to the field of scheduling technology, specifically an artificial intelligence-driven intelligent manufacturing system scheduling method, comprising the following steps: real-time monitoring of order status parameters of a manufacturing execution system, identifying equipment failure shutdown signals or order insertion signals, extracting associated equipment codes and current work order numbers, and establishing core disturbance information pairs. The present invention monitors the order status parameters of a manufacturing execution system in real time, dynamically identifies equipment failure shutdown signals and order insertion signals, and extracts equipment codes and current work order numbers, thereby being able to construct core disturbance information pairs that are highly correlated with disturbance sources, ensuring the pertinence and accuracy of the scheduling process response. Combined with the original planned completion time of the affected process, the local delay caused by the disturbance is evaluated, and the delay amount of the overall plan is gradually deduced to characterize the diffusion trend of the disturbance in the production progress and define the scheduling adjustment time window.

Description

Technical Field

[0001] The present invention relates to the field of scheduling technology, and in particular to an artificial intelligence-driven intelligent manufacturing system scheduling method. Background Art

[0002] The field of scheduling technology is a key component of intelligent manufacturing and industrial automation systems. It mainly focuses on how to reasonably arrange and optimize the operation sequence, resource allocation and execution timing in the production process under limited time, resource and task constraints.

[0003] Existing technologies mainly rely on preset job sequences and static resource allocation logic to execute scheduling tasks. In scenarios where disturbance events occur frequently or task structures are complex, the lack of in-depth analysis of real-time data and dynamic understanding of resource status often leads to delayed scheduling responses. Sudden equipment failure signals are often confused with ordinary process pauses, and scheduling interventions after order insertion lack precision, resulting in duplicate scheduling of some processes or intensified resource conflicts. At the same time, the impact of human resource status on scheduling stability is often ignored in traditional scheduling processes, and the continuous workload of operators cannot be reasonably dispersed, which in turn leads to process errors, output quality fluctuations and other problems. Therefore, improvement is needed. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the existing technology and propose an artificial intelligence driven intelligent manufacturing system scheduling method.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: an artificial intelligence-driven intelligent manufacturing system scheduling method, comprising the following steps:

[0006] Real-time monitoring of order status parameters in the manufacturing execution system, identification of equipment failure shutdown signals or order insertion signals, extraction of associated equipment codes and current work order numbers, and establishment of core disturbance information pairs;

[0007] Based on the core disturbance information pair, the expected completion time of the affected process in the current production activity of the intelligent manufacturing system is evaluated to obtain an expected delay value for a single process. Based on the expected delay value for a single process and combined with the original planned completion time of all affected processes, the delay amount of the overall plan is calculated to determine the scheduling adjustment time window;

[0008] According to the resource changes reflected by the scheduling adjustment time window and the core disturbance information, the processing capacity and material supply cycle of the alternative equipment associated with the affected process are retrieved to obtain a set of available alternative resource parameters. Based on the set of available alternative resource parameters and in comparison with the production efficiency index, a resource combination is selected for replacement to form a preliminary scheduling operation instruction to cope with the disturbance;

[0009] Based on the preliminary scheduling operation instructions for responding to the disturbance, the continuous operation time and skill proficiency of the target process operators are obtained, and the personnel's real-time status evaluation value is obtained. Based on the personnel's real-time status evaluation value, personnel allocation optimization is performed to generate a personnel scheduling execution plan.

[0010] Preferably, the steps of obtaining the core disturbance information pair are:

[0011] Collect order status parameters in real time, analyze and judge the equipment failure shutdown signal and order insertion signal in the order status parameters respectively, and extract the equipment failure shutdown signal and order insertion signal;

[0012] Based on the equipment failure shutdown signal and the order insertion signal, the corresponding equipment code and the current work order number are retrieved, and an association relationship between the equipment failure shutdown signal and the equipment code, and an association relationship between the order insertion signal and the current work order number are respectively established to form association mapping information;

[0013] Based on the association mapping information, the device code and the current work order number are combined and matched, and the code data and the work order data are bound in the form of a key-value pair to form a core disturbance information pair.

[0014] Preferably, the steps for obtaining the estimated delay value of a single process are:

[0015] Based on the core disturbance information pair, the affected process numbers in the current production activity are located, and the planned completion time, unit standard working hours, resource start time, and resource recovery time of each affected process are extracted to form a set of production scheduling parameters for the affected processes;

[0016] According to the affected process scheduling parameter set, the difference between the resource recovery available time and the actual resource start time is calculated to obtain the resource available delay length, and the affected process schedule offset data group is generated;

[0017] Based on the affected process progress deviation data group, a single process estimated delay value is calculated.

[0018] Preferably, the steps for obtaining the scheduling adjustment time window are:

[0019] Based on the estimated delay value of the single process, the delay values ​​of all affected processes are aggregated in order of process numbers, and each delay value is matched one-to-one with the original planned completion time of the corresponding process to generate a comparison table of affected process plans;

[0020] According to the affected process plan comparison table, the affected processes are sorted by their original planned completion time, the delay value corresponding to the process with the latest planned completion time is extracted, and the delay value is added to the original planned completion time to obtain the maximum delay time point of the overall plan;

[0021] Based on the maximum delay time point of the overall plan, the time difference between the end time of the current global production scheduling cycle of the intelligent manufacturing system and the maximum delay time point of the overall plan is compared to determine whether the scheduling adjustment requirement duration exceeds the acceptable range and obtain the scheduling adjustment time window.

[0022] Preferably, the steps for obtaining the available alternative resource parameter set are:

[0023] Based on the equipment code and current work order number identified in the scheduling adjustment time window and the core disturbance information, query the associated equipment resource database and order resource mapping table in the intelligent manufacturing system, extract the equipment configuration records and original material call records associated with the affected process, and generate an affected process resource binding information set;

[0024] Based on the affected process resource binding information set, search the equipment capability database for equipment items with the same process characteristics as the bound equipment, screen the equipment processing capability parameters with available idle time periods within the scheduling adjustment time window, and simultaneously search the corresponding material supply time intervals in the material supply plan table to generate a list of candidate resource capability and material supply cycle combinations;

[0025] Based on the list of candidate resource capabilities and material supply cycle combinations, identify combinations with processing capability equivalence, time cycle matching, and scheduling compatibility, screen the equipment processing capabilities and material supply cycles that meet the replaceable conditions within the time window, and obtain a set of available alternative resource parameters.

[0026] Preferably, the steps for obtaining the preliminary scheduling operation instructions for coping with the disturbance are:

[0027] Based on the available alternative resource parameter set, the unit processing output, unit operation time, scheduling adjustment time window length and material supply cycle length corresponding to each resource combination are extracted to construct standardized resource combination index items to form a resource combination performance index set;

[0028] Calculating the efficiency matching value of the resource combination according to the resource combination performance indicator set;

[0029] Based on the efficiency matching values ​​of the resource combinations, the resource combinations are sorted from high to low according to their efficiency matching values, and resource combinations with efficiency matching values ​​greater than the average production efficiency threshold are selected to form preliminary scheduling operation instructions to cope with disturbances.

[0030] Preferably, the steps for obtaining the personnel's real-time status evaluation value are:

[0031] Based on the preliminary scheduling instructions for coping with the disturbance, the target process information corresponding to each scheduling instruction is extracted, the operator number bound to the process is matched, the operator task record database is queried, the continuous working time period of each operator in the current cycle is obtained, and the target process operator working time information set is generated;

[0032] Based on the target process operator's working time information set, combined with the operator's training record file and performance evaluation form, the skill level, completion efficiency and error rate of each operator in the corresponding process category are extracted to generate the operator's real-time status evaluation value.

[0033] Preferably, the steps for obtaining the personnel scheduling execution plan are:

[0034] Based on the personnel's real-time status evaluation value, extract each operator's skill proficiency level, total continuous operation time, and number of currently assigned tasks to form a personnel operation capability status set;

[0035] Calculating a personnel suitability score based on the personnel operational capability status set;

[0036] Based on the personnel suitability score, all candidate operators are sorted in descending order, and the personnel with the highest personnel suitability score are selected in order of process matching priority for scheduling and allocation to generate a personnel scheduling execution plan.

[0037] Compared with the prior art, the advantages and positive effects of the present invention are:

[0038] By monitoring the order status parameters of the manufacturing execution system in real time, dynamically identifying equipment failure shutdown signals and order insertion signals, and extracting the equipment code and current work order number, this method can construct a core disturbance information pair that is highly correlated with the disturbance source, ensuring the targeted and accurate response of the scheduling process. Combined with the original planned completion time of the affected process, the local delay caused by the disturbance is assessed, and the overall planned delay is gradually deduced. The diffusion trend of the disturbance in the production schedule is characterized, and the scheduling adjustment time window is defined. Based on the resource change characteristics and the scheduling adjustment time window, the processing capacity and material supply cycle of alternative equipment are retrieved, and a set of available alternative resource parameters is screened and formed. Quantified selection is performed based on the efficiency matching value, improving the rationality of resource replacement and the operability of scheduling execution. At the staffing level, the continuous working time and skill proficiency of the operators of the target process are combined to calculate the personnel's real-time status evaluation value, and then the personnel allocation optimization operation is performed accordingly, so that the scheduling results are more in line with the actual human resource status and avoid the increase in error rate caused by high-intensity work. In summary, we have achieved rapid response to abnormal conditions, scientific screening of resource utilization, and adaptation of personnel scheduling, thereby improving the recovery efficiency, resource coordination, and task fulfillment rate of the production system in the face of disturbances. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the steps of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0041] See also Figure 1 The present invention provides a technical solution, an artificial intelligence-driven intelligent manufacturing system scheduling method, comprising the following steps:

[0042] Real-time monitoring of order status parameters in the manufacturing execution system, identification of equipment failure shutdown signals or order insertion signals, extraction of associated equipment codes and current work order numbers, and establishment of core disturbance information pairs;

[0043] Based on the core disturbance information pair, the expected completion time of the affected process in the current production activity of the intelligent manufacturing system is evaluated to obtain the expected delay value of each process. Based on the expected delay value of each process and the original planned completion time of all affected processes, the delay of the overall plan is calculated to determine the scheduling adjustment time window.

[0044] Based on the resource changes reflected by the scheduling adjustment time window and the core disturbance information, the processing capacity and material supply cycle of the alternative equipment associated with the affected process are retrieved, and the available alternative resource parameter set is obtained. Based on the available alternative resource parameter set and the production efficiency index, a resource combination is selected for replacement to form a preliminary scheduling operation instruction to deal with the disturbance;

[0045] Based on the preliminary scheduling instructions for dealing with disturbances, the continuous working time and skill proficiency of the operators in the target process are obtained, and the personnel's real-time status evaluation value is obtained. Based on the personnel's real-time status evaluation value, personnel allocation is optimized and a personnel scheduling execution plan is generated.

[0046] The steps for obtaining the core perturbation information pair are:

[0047] Collect order status parameters in real time, analyze and judge the equipment failure shutdown signal and order insertion signal in the order status parameters respectively, and extract the equipment failure shutdown signal and order insertion signal;

[0048] Based on the equipment failure shutdown signal and the order insertion signal, the corresponding equipment code and the current work order number are retrieved, and the association relationship between the equipment failure shutdown signal and the equipment code, and the association relationship between the order insertion signal and the current work order number are established respectively, forming association mapping information;

[0049] Based on the association mapping information, the device code and the current work order number are combined and matched, and the code data and the work order data are bound in the form of key-value pairs to form a core disturbance information pair.

[0050] Specifically, the order status parameters are collected in real time. The specific operation is to continuously receive the original information stream containing timestamps, event sources, event types and detailed data from various monitoring points or data interfaces of the manufacturing execution system (MES), such as equipment controller logs, database table change flows of the order management module, and manual entry terminals. These original information streams are first structured and parsed. For example, if the data is in JSON format, the values ​​of fields with key names such as "eventType", "sourceID", and "payload" are extracted. If it is PLC raw data, it is converted according to the preset byte offset and data type rules. Subsequently, the equipment fault shutdown signal in the parsed order status parameters is judged based on a preset "equipment fault feature library". This database is compiled by equipment maintenance engineers based on equipment manuals, historical fault records, and daily operation and maintenance experience, and is reviewed and updated at least once a quarter. It lists in detail the specific fault codes, status indicators, or abnormal operating parameter modes of various types of equipment. For example, for a model A machining center, when "Error_Code:503" or "Operational_Status:Emergency_Halt" appears in its status parameters, or its spindle load exceeds 150% of the rated load for 10 consecutive seconds (the 150% threshold is obtained by statistically analyzing the operating data of this model of equipment 5 minutes before a typical fault, taking 1.5 times the sum of the historical average overload peak and one standard deviation. For example, if the historical average overload peak is 130% and the standard deviation is 10%, the threshold is , for example, the actual setting of 150% is based on a balance between safety redundancy and early warning (the specific value is 150%). This is then determined as an equipment failure shutdown signal. Order insertion signals are determined based on an "order change rule set" defined by the production planning department during initial system deployment based on order processing priorities and emergency response processes. For example, if the order status parameter indicates a new order has been created and its priority field is marked as "expedited" or "VIP," or if the scheduled start time of an existing order is advanced by more than 24 hours (this 24-hour threshold is an empirical value set by the production planning department based on average order processing cycles and material preparation lead times to ensure sufficient window for resource coordination), then this is determined to be an order insertion signal. After completing this judgment, the system classifies and aggregates the identified specific equipment failure shutdown signal instances (such as "spindle overload failure of equipment number CNC001") and order insertion signal instances (such as "order number PO20250523001 marked as emergency insertion") to obtain extracted equipment failure shutdown signals and order insertion signals.

[0051] Based on the equipment failure shutdown signal and order insertion signal extracted in the previous step, the system performs subsequent retrieval and association operations. For each identified equipment failure shutdown signal, for example, the signal content is "Equipment No. CNC001 has a spindle overload failure, time 2025-05-23 10:30:15", the system will parse the key equipment identification information from the signal, that is, "CNC001", and then use "CNC001" as the query key to search in the pre-established and maintained "Equipment Basic Information Table". This table records in detail the static attributes of all equipment in the workshop, including the equipment's unique code, model, location, production line, etc. For example, if the search results confirm that the standard equipment code corresponding to "CNC001" is "EQP-MC-001", a direct association relationship will be established between this equipment failure shutdown signal and the equipment code "EQP-MC-001", and recorded as (fault signal ID: FS001, For each identified order insertion signal, for example, the signal content is "Order number PO20250523001 is marked as urgent insertion, product code PD007", the system also parses out the core order identifier "PO20250523001" from it, which is regarded as the current work order number. Subsequently, this order insertion signal is directly associated with the current work order number "PO20250523001" and recorded as pairing information such as (Insert signal ID: IS001, Current work order number: "PO20250523001"). These individually established associations are aggregated and stored to form a temporary association mapping information set. Each item in the set clearly indicates a specific disturbance signal and its directly corresponding equipment code or current work order number, providing structured input for subsequent disturbance impact analysis to obtain association mapping information.

[0052] Based on the association mapping information set formed in the previous stage, which includes the pairing of equipment fault shutdown signals and equipment codes, as well as the pairing of order insertion signals and current work order numbers, the system further performs a combination matching operation, aiming to clarify the impact of an equipment dimension and an order dimension for each disturbance. Specifically, if the entry in the association mapping information is an equipment fault type, for example (fault signal ID: FS001, equipment code: "EQP-MC-001"), the system will query the "work order execution status table" in the real-time production database of the manufacturing execution system (MES) based on "EQP-MC-001" and the timestamp of the fault occurrence (obtained by the association of fault signal ID: FS001). This table records The query logic for the work order information currently or recently processed by each device is to filter out the work order numbers with the status of "in progress" or "assigned but not started" on the device "EQP-MC-001" when the fault occurs. If there are multiple work orders, the one most directly affected is selected based on the work order priority and planned start time. For example, if the current work order number is "WO202505007", "EQP-MC-001" is bound to "WO202505007". If the entry in the associated mapping information is of order insertion type, for example (insert signal ID: IS001, current work order number: "PO20250523001"), the system needs to assign a new work order number to this newly inserted work order number "PO202505 23001" matches one or a group of initial target equipment codes. This matching process first consults the "Product Process Path Master Data Table", which is maintained by the process engineer and defines the standard processing procedures for each product (the product code is obtained by querying the current work order number) and the eligible equipment types and optional equipment list for each procedure. For example, the product of work order "PO20250523001" needs to go through the "Milling" process, and the eligible equipment type is "DX-500 CNC Milling Machine". The optional equipment includes "EQP-ML-003" and "EQP-ML-004". The system then queries the current load, maintenance plan and expected idle time of these optional equipment in conjunction with the "Equipment Real-time Status Table" to select the optimal equipment code. For example, if you select "EQP-ML-003", which is expected to be available the earliest, then bind "EQP-ML-003" to "PO20250523001". After completing all combination matching, the system will perform the final data structured binding on these pairs consisting of equipment codes and current work order numbers in the form of key-value pairs, such as {"equipment code": "EQP-MC-001", "current work order number": "WO202505007", "disturbance type": "equipment failure"} or {"equipment code": "EQP-ML-003", "current work order number": "PO20250523001", "disturbance type": "order insertion"}, thereby forming a core disturbance information pair.

[0053] The steps to obtain the expected delay value of a single process are:

[0054] Based on the core disturbance information pair, the affected process numbers in the current production activity are located. The planned completion time, unit standard working hours, resource start time, and resource recovery time of each affected process are extracted to form a set of production scheduling parameters for the affected processes.

[0055] Based on the affected process scheduling parameter set, the difference between the resource recovery availability time and the actual resource start time is calculated to obtain the resource availability delay length, and the affected process schedule offset data group is generated;

[0056] Based on the affected process progress offset data group, calculate the expected delay value of a single process. The calculation formula is:

[0057] ;

[0058] in, is the estimated delay value of a single process of the cth affected process, is the estimated completion time of the cth affected process, is the original planned completion time of the cth affected process, is the unit standard working time of the cth affected process, is the resource available delay length of the cth affected process, Minimum time constant to prevent the denominator from being zero.

[0059] Specifically, based on the core disturbance information pair obtained in the above steps, the system first analyzes the information pair to determine whether the disturbance source is a device failure or an order insertion, as well as the associated device code and current work order number, and then locates the specific process number in the current overall production plan that is directly or indirectly affected by the disturbance. For example, if the core disturbance information pair indicates that the device "EQP-001" has a failure and the process "OP-123B" of the work order "WO-123" is being processed at the time, then "OP-123B" is the first affected process. At the same time, the corresponding processes of all other work orders that originally planned to use the device before "EQP-001" was repaired (such as the process "OP-124A" of the work order "WO-124") and the process "OP-123B" are also affected. All subsequent processes of the order "WO-123" on "EQP-001" are identified as affected processes. If the core disturbance information indicates that a new work order "WO-789" is inserted into the equipment "EQP-002", all processes originally planned to use "EQP-002" during and after the time period occupied by "WO-789" (for example, process "OP-456C" of work order "WO-456") are identified as affected processes. After all affected process numbers are identified, the system extracts the original planned completion time for each identified affected process number from the production plan database and process path master data. This time is the exact time when the process is expected to end if no disturbance occurs. Unit standard working hours, this working hour is the standard working time required to complete one unit of product in this process based on historical data statistics or working hour quota standards. It extracts the resource start time of this process in the original plan, as well as a key resource recovery available time. For equipment failure disturbances, this resource recovery available time refers to the time point when the faulty equipment is expected to be put back into production. This time point is usually estimated by the maintenance department based on the fault diagnosis results and maintenance resource conditions. For example, by consulting the equipment maintenance record system, it is known that the estimated repair time of equipment "EQP-001" is 14:00 on May 26, 2025. For order insertion disturbances, the resource recovery available time refers to the time when the originally occupied resources are used to process the inserted order. This results in the time point at which it can actually start providing services to the subsequent affected processes. For example, if the inserted work order "WO-789" is expected to take 4 hours on the equipment "EQP-002", and its start time squeezes out the planned start time of the original process "OP-456C", then for "OP-456C", the resource recovery availability time of the equipment "EQP-002" is the estimated completion time of "WO-789" on "EQP-002". Through the above extraction, the system integrates the process number, original planned completion time, unit standard working hours, original resource start time, and calculated or obtained resource recovery availability time of each affected process to form a set of production scheduling parameters for the affected processes.

[0060] Based on the affected process scheduling parameter set formed in the previous step, which includes the original resource plan start time and the updated resource recovery availability time of each affected process, the system then calculates the resource availability delay length for each affected process. The calculation is achieved by comparing the resource recovery availability time of the corresponding process with the actual resource start time of the original plan for the process. The specific calculation method is to subtract the actual resource start time of the process in the original plan from the resource recovery availability time of the specific affected process. The difference is preliminarily determined as the delay in resource availability. For example, in the original production plan of an affected process "OP-X", the planned start time of the required resource "RES-Y" is 08:00 on May 26, 2025. Due to a disturbance event (such as a failure of "RES-Y" or the processing of an emergency insertion order), the resource recovery availability of "RES-Y" is delayed. If the time is updated to 11:30 on May 26, 2025, the time difference between the two is 3 hours and 30 minutes. Taking into account that the resource recovery time may be earlier than or equal to the original planned resource start time (for example, the fault is repaired in advance), a negative delay length should not be generated at this time. Therefore, the final resource available delay length takes the larger one between the calculated difference and zero. That is, if the calculated difference is negative or zero, the resource available delay length of the process is recorded as zero, indicating that there is no substantial resource availability delay. If the difference is positive, the positive value is the resource available delay length of this process. For example, for the above-mentioned process "OP-X", its resource available delay length is 3 hours and 30 minutes. The system traverses each process in the affected process scheduling parameter set, performs this calculation, and pairs each process number with its corresponding resource available delay length to generate an affected process progress offset data group.

[0061] formula: The benefit of the formula is that it comprehensively assesses the expected degree of delay of a single process after a disturbance occurs. It does not simply look at the absolute length of delay, but rather relativizes and normalizes the degree of deviation from the planned completion time and the degree of delay in resource availability. It combines the two effects through a quasi-Euclidean distance method, thereby more accurately reflecting the relative severity of the impact of the disturbance on processes of different nature and different calibrated working hours. This allows managers to identify the bottleneck processes that are most "destructive" to the overall plan, so as to prioritize resource allocation or take countermeasures. The first square term focuses on the deviation of the execution efficiency of the process itself from the plan, and the second square term focuses on the constraints of upstream resource supply on process execution. The combination of the two can comprehensively characterize the source and extent of delay;

[0062] parameter The steps for obtaining are as follows: , which represents the estimated completion time of the cth affected process. This time is not directly extracted, but recalculated based on the impact of the disturbance. First, the original planned start time of the cth affected process is obtained. and total standard working hours (If the unit standard working time refers to a single piece, it needs to be multiplied by the number of work orders), and the available resource delay length of the process is obtained from the previous step , then the actual available start time of the resource for this process Add the original planned resource start time to , the actual earliest start time of the process , the final estimated completion time , all times need to be converted into a unified unit. For example, the original planned start time of process OP001 is the 100th hour of the production cycle, and its total standard working hours are The resource availability delay length is 8 hours The original planned resource usage start time is also the 100th hour, so the actual available start time of the resource is Hours, actual earliest start time hours, therefore, the estimated completion time Hour;

[0063] parameter The steps for obtaining are as follows: represents the original planned completion time of the cth affected process. This parameter is directly extracted from the original production plan data stored in the Manufacturing Execution System (MES). It corresponds to the expected end time of process c according to the initial schedule when no disturbance occurs. For example, for process OP001, the planned completion time recorded in the original production plan is the 108th hour of the production cycle. Hour;

[0064] parameter The steps for obtaining are as follows: , which represents the unit standard working hours of the cth affected process, or more precisely, the total standard working hours required to complete the process task. This data comes from the enterprise's established process database or standard working hour quota table, which records in detail the standard time required for each process to process a specific product or component on a specific device. This standard time is usually set and regularly maintained by the industrial engineering department through time research, historical data averaging, and other methods. For example, the total standard processing time defined in the process database for process OP001 is 8 hours (this value has taken into account the product of the processing batch of this process in the work order and the standard working time per piece, or is directly defined as the standard total time consumption of the task package). Hour;

[0065] parameter The step of obtaining is, which represents the resource available delay length of the c-th affected process. This parameter is calculated by the previous step "generating the affected process schedule offset data group", that is, , which quantifies the delay in the time when the resources originally planned to be allocated to process c can actually start service relative to the original plan due to reasons such as equipment failure repair or priority processing of inserted orders. For example, for process OP001, the resource availability delay length calculated in the previous step is 4 hours, then Hour;

[0066] parameter The steps to obtain is, which represents a minimum time constant to prevent the denominator from being zero, select Hour.

[0067] Calculation process: Take process OP001 as an example, and substitute the obtained parameter values ​​for calculation: Hour, Hour, Hour, Hour, Substituting the parameters into the formula yields 0.5013.

[0068] The result shows that the single process delay value of process OP001 is expected to be It is approximately 0.5013, which is a dimensionless relative delay indicator. This value comprehensively reflects the degree of deviation of the planned completion time of process OP001 compared with its own standard working hours, as well as the proportion of its resource availability delay relative to its new estimated completion time. The size of this value can be used to horizontally compare the delay severity of different affected processes.

[0069] The steps for obtaining the scheduling adjustment time window are as follows:

[0070] Based on the estimated delay value of a single process, the delay values ​​of all affected processes are aggregated in order of process numbers. Each delay value is matched one-to-one with the original planned completion time of the corresponding process to generate a comparison table of affected process plans.

[0071] According to the affected process plan comparison table, sort the affected processes by their original planned completion time, extract the delay value corresponding to the process with the latest planned completion time, and add this delay value to the original planned completion time to obtain the maximum delay time point of the overall plan;

[0072] Based on the maximum delay time point of the overall plan, the time difference between the end time of the current global scheduling cycle of the intelligent manufacturing system and the maximum delay time point of the overall plan is compared to determine whether the scheduling adjustment demand duration exceeds the acceptable range and obtain the scheduling adjustment time window.

[0073] Specifically, the estimated delay value of each affected process calculated in the previous step , and in the calculation The original planned completion time of each step involved in the process and estimated completion time The system first collects this information in a structured manner. Specifically, the system traverses all processes identified as affected by the previous steps and creates a record for each affected process. The record contains at least the unique number of the process, the estimated delay value of the single process calculated for the process, and the delay time of the affected process. , the planned completion time of the process set in the original production plan , and the estimated completion time after reassessment due to the disturbance , then, the system preliminarily sorts or sorts these records according to the number of each process (for example, according to the alphanumeric order of the process number or its natural order in the process route) to ensure that all affected processes are included in the processing scope without omission. On this basis, the core operation is to calculate the single process delay value for each process. The corresponding original planned completion time and estimated completion time Strict one-to-one matching is performed to ensure data consistency and accuracy. For example, if the estimated delay value of a single process "OPN-102B" is calculated to be 0.45, its original planned completion time is 16:00 on the 5th day, and the estimated completion time is 18:00 on the 5th day, then this information is accurately associated with the "OPN-102B" record. This process does not involve new threshold judgments or complex calculations, but mainly involves data organization and verification. After completing the data matching of all affected processes, a structured data list or table is formed, namely the affected process plan comparison table.

[0074] According to the affected process plan comparison table generated in the previous stage, the table contains the process number and original planned completion time of each affected process. , and a key parameter, the estimated completion time of the process The system first compares all the items in the affected process plan comparison table, based on the original planned completion time of each process. Sort in ascending order. After sorting, the last record in the table corresponds to the affected process with the latest planned completion time in the original plan. The system then extracts its original planned completion time from this record. and estimated completion time Then calculate the actual delay time of the latest process in the original planned completion time, and calculate the actual delay time as the estimated completion time of the process Subtract its original planned completion time ,get , then the actual delay time calculated is Added back to the original planned completion time for the operation The specific operation is The result is actually the estimated completion time of the affected process with the latest completion time in the original plan after considering the disturbance. For example, if after sorting, the process with the latest original planned completion time is "OPN-205C", its original planned completion time The estimated completion time is 17:00 on the 8th day If it is 20:00 on the 8th day, then the delay time is The maximum delay time of the entire plan is determined as 3 hours, which is added to 17:00 on the 8th day, resulting in 20:00 on the 8th day.

[0075] Based on the maximum delay time point of the overall plan obtained in the previous step, for example, it is determined to be the 120th hour of the current production cycle. The system then compares this time point with the end time of the current global scheduling cycle preset in the intelligent manufacturing system. The end time of the global scheduling cycle, for example, the 128th hour of the current cycle, is a fixed time point set by the production planning department based on the overall production order delivery commitment, resource availability, and reserved regular buffer time (for example, the weekly production plan is 40 hours, but the end time of the global scheduling cycle may be set to the 48th hour, including an 8-hour fixed buffer). The time difference between the two is calculated by subtracting the maximum delay time point of the overall plan from the end time of the global scheduling cycle, that is, Hours. This difference represents the remaining surplus or excess of the entire plan beyond the end time of the global scheduling cycle after the disturbance occurs. Subsequently, the system determines whether the demand duration of the scheduling adjustment exceeds the acceptable range. The "accommodative range" here is not a single fixed value, but is reflected by comparing the degree of compliance of the adjusted plan with the global scheduling cycle. The specific judgment logic is: if the calculated time difference is positive or zero (such as 8 hours above), it means that the maximum delay time point of the overall plan is still within the end time of the global scheduling cycle. At this time, the scheduling adjustment demand can be accommodated in time. If the time difference is negative (for example, the maximum delay time point of the overall plan is the 130th hour, the difference is hours), it means that the overall plan has exceeded the preset global production cycle end time, and the excess time is 2 hours. At this time, the scheduling adjustment demand time has exceeded the zero surplus range that can be accommodated. Further, the system will refer to a "maximum allowed excess threshold". For example, the production department stipulates that the global production cycle is allowed to exceed 2% at most. If the current cycle is 128 hours, the allowed excess If the 2-hour excess obtained by the above calculation does not exceed this 2.56 hours, it is considered to be still within the "urgent accommodation range", otherwise it is completely beyond the accommodation range. According to this judgment result and the actual surplus or excess, the system finally determines and outputs a scheduling adjustment time window, which usually refers to the period from the current moment to the maximum delay time point of the overall plan (the 120th hour), and is accompanied by a status indicator to indicate whether it is within the accommodation range, the emergency accommodation range, or has exceeded the range, thereby obtaining the scheduling adjustment time window.

[0076] The steps to obtain the available alternative resource parameter set are:

[0077] Based on the equipment code and current work order number identified in the scheduling adjustment time window and the core disturbance information, the associated equipment resource database and order resource mapping table in the intelligent manufacturing system are queried to extract the equipment configuration records and original material call records associated with the affected process, and generate the affected process resource binding information set;

[0078] Based on the resource binding information set for the affected process, search the equipment capability database for equipment items with the same process characteristics as the bound equipment. Filter the processing capability parameters of equipment with available idle periods within the scheduling adjustment time window. Simultaneously search the corresponding material supply time intervals in the material supply schedule to generate a list of candidate resource capability and material supply cycle combinations.

[0079] Based on the list of candidate resource capabilities and material supply cycle combinations, identify combinations with processing capability equivalence, time cycle matching, and scheduling compatibility, screen the equipment processing capabilities and material supply cycles that meet the replaceable conditions within the time window, and obtain a set of available alternative resource parameters.

[0080] Specifically, based on the scheduling adjustment time window determined in the previous step and the key equipment code and current work order number identified in the core disturbance information pair obtained in the earlier step, the system first parses the core disturbance information pair to clarify the specific disturbance type (for example, equipment "EQP-X" failure or new order "WO-Y" insertion), and then re-identifies all process numbers directly or indirectly affected by this disturbance. For each identified affected process, the system initiates a query request to the central database of the intelligent manufacturing system, specifically accessing the "equipment resource database" to obtain detailed configuration records of the equipment originally planned to be bound to the process (for example, equipment "EQP-X"). These records include the model of the equipment, the currently installed specific tool group information, the running control program version, and key performance parameters such as rated processing speed, accuracy level, etc. The database is jointly maintained by the equipment management department and process engineers, and the data comes from equipment archives and fixed During the parameter calibration period, the system will also query the "Order Resource Mapping Table" and the associated Material Requirements Planning (MRP) system data to extract the detailed material call records of the affected process in the original plan, including the specific material codes of the required raw materials and semi-finished products, planned quantities, planned arrival times, and designated warehouse or supplier information. For example, for the affected process "PROC-101", the query results may show that it was originally planned to be processed on the equipment "CNC-05", the equipment configuration requires the use of tool group "TG-A12", the control program is "NC-P101_V2", and the required material "MAT-AL-003" is planned to be supplied in a quantity of 10 pieces, which should be supplied by warehouse "WH-B" 2 hours before the start of the scheduling adjustment time window. The system integrates all the equipment configuration details and original material requirement information extracted for each affected process to form a structured resource binding information set for the affected process.

[0081] Based on the affected process resource binding information set generated in the previous step, which details the equipment originally bound to each affected process, its configuration, and required materials, and combined with the determined scheduling adjustment time window, the system performs an alternative resource search process for each affected process. First, based on the process characteristics of the originally bound equipment recorded in the affected process resource binding information set (for example, by querying the equipment code, the processing type is marked as "five-axis precision milling", the worktable size range is "500mm-800mm", and the machinable material is "titanium alloy" in the "equipment capability library"), the system searches the "equipment capability library" to screen out other candidate equipment items with the same or highly similar process characteristics. The "same process characteristics" judgment criteria here are pre-defined by the process department. For example, for "five-axis precision milling", the search results are allowed to include equipment marked as "five-axis general milling" but whose historical processing accuracy statistics (for example, the average tolerance of similar parts processed in the past six months meets more than 80% of the original equipment, and this 80% is the acceptable lower limit set by engineering experience) can meet the quality requirements of the current process. Then, the screened out equipment items are selected. For each candidate piece of equipment, the system queries its current real-time status and future pre-scheduled schedule to determine whether it has sufficient, continuous, available idle time within the scheduling adjustment window (e.g., within the next 24 hours from the current time). This idle time must accommodate the entire processing time of the affected process (including estimated equipment adjustment and setup time). The system also records the specific processing capacity parameters of these candidate pieces of equipment (such as actual speed range, feed rate, and expected processing efficiency). Simultaneously, based on the original material call records in the resource binding information set for the affected process, the system queries the "Material Supply Plan" to obtain the corresponding material's current inventory level, in-transit quantity, and the supplier's promised delivery interval or the exact time of the next arrival batch. For example, if material "MAT-AL-003" currently has 5 pieces in stock and 10 pieces in transit, and is expected to arrive in 2 hours, the supplier's standard delivery cycle is 24 hours. This process generates a list of candidate resource capacity and material supply cycle combinations for each affected process, including candidate replacement equipment, their available time periods, processing parameters, and the current and near-term availability of supporting materials.

[0082] Based on the list of candidate resource capabilities and material supply cycle combinations generated in the previous stage, which provides several potential (alternative equipment, material supply) combination options for each affected process, the system begins to carefully screen and evaluate these combinations. First, it identifies processing capability equivalence. This not only involves comparing process types, but also comparing the specific technical parameters of the candidate equipment (for example, maximum cutting force, maximum spindle speed, and tool magazine capacity) with the processing requirements of the affected process (for example, process "PROC-101" requires a cutting force of no less than 500N and a speed of 8000rpm). Only when the key parameters of the candidate equipment meet or exceed the process requirements (this requirement is specified in the process design document) is it considered to have preliminary processing capability equivalence. For example, if the maximum cutting force of a candidate equipment is 480N, it does not meet the equivalence. Next, it identifies time period matching. The system needs to verify that the starting point of the available idle period of the candidate equipment is not earlier than the estimated supply time of the required materials, and that the length of the idle period is sufficient to complete the entire process (including the preparation time for the changeover, which is calculated based on historical data, such as similar equipment). The average production changeover time is 0.5 hours. Furthermore, the estimated completion time of the process on the replacement equipment must fall within the previously determined scheduling adjustment window. Scheduling compatibility is then identified. The system evaluates whether selecting a particular combination will adversely impact other processes or overall production goals. For example, whether it would excessively occupy a scarce auxiliary resource (such as a skilled craftsperson team) or violate shop-level scheduling rules (such as "consecutive processes for the same order should be scheduled on geographically close equipment groups whenever possible," a rule established by the production supervisor based on shop floor layout and logistics efficiency). Combinations that do not meet compatibility requirements are eliminated. For example, if an alternative equipment meets the first two requirements but its operation requires the only available senior technician, who is already reserved for a higher-priority, urgent task, then this combination is incompatible. Through this multi-dimensional, multi-conditional, item-by-item identification and screening, the system ultimately selects combinations of equipment processing capacity and material supply cycle that simultaneously meet processing capacity equivalence, time cycle matching, and scheduling compatibility and can complete the replacement operation within the scheduling adjustment window, forming a set of available alternative resource parameters.

[0083] The steps to obtain the preliminary scheduling instructions to deal with disturbances are:

[0084] Based on the available alternative resource parameter set, the unit processing output, unit operation time, scheduling adjustment time window length and material supply cycle length corresponding to each resource combination are extracted to construct standardized resource combination index items and form a resource combination performance index set;

[0085] According to the resource combination performance indicator set, the efficiency matching value of the resource combination is calculated. The calculation formula is:

[0086] ;

[0087] in, is the efficiency matching value of the kth resource combination, is the unit processing output of the kth resource combination, is the unit operation time of the kth resource combination, Adjust the time window length for scheduling the k-th resource combination, is the material supply cycle length of the kth resource combination, Minimum time constant to prevent the denominator from being zero;

[0088] Based on the efficiency matching value of the resource combination, the resource combinations are sorted from high to low according to their efficiency matching value, and the resource combinations with efficiency matching values ​​greater than the average production efficiency threshold are selected to form preliminary scheduling operation instructions to deal with disturbances.

[0089] Specifically, based on the available alternative resource parameter set obtained in the previous step, which provides several groups of feasible alternative equipment and their associated material supply information for each affected process, the system then extracts and structures a series of key performance indicators for each resource combination. Specifically, for the kth resource combination (for example, assigning the affected process X to alternative equipment M and using material B from supplier S), the system first extracts its "unit processing output" , this data is defined as the output quantity of a standard production batch (the quantity of which is specified by the work order information of process X, such as 100 pieces) when processing process X on alternative equipment M. This value is usually equal to the standard quantity of the batch, and then the "unit operation time" is extracted. , which means that the replacement equipment M completes the above-mentioned standard production batch (i.e. The total effective operation time required for the process (quantity of output) includes the necessary setup and adjustment time on the equipment M for the process, the actual processing time, and the cleanup or turnaround time after the process is completed. These time data are obtained from the historical statistics or standard working time table of similar processes of the corresponding equipment M in the equipment capability library. In addition, the "scheduling adjustment time window length" is extracted. , which is calculated in the previous step, represents the total time from the current decision moment to the time when the entire plan affected by the disturbance must be adjusted and completed to reach a new stable state (that is, the maximum delay time point of the overall plan). For the resource combination evaluation of the current batch, this The value is a unified constraint condition. Finally, extract the "material supply cycle time" , which is the shortest waiting time from the current moment until all materials required for process X (such as material B) are ready and available for use by alternative equipment M. This information comes from the material supply cycle recorded in the available alternative resource parameter set. All these extracted 、 、 and The numerical values ​​are jointly constructed into a standardized resource combination indicator item. The system generates such an indicator item for each available alternative resource combination, and together they form a set of resource combination performance indicators.

[0090] formula: The benefit of the formula is that it provides a method for quantitatively evaluating the comprehensive effectiveness of alternative resource combinations, taking into account not only the inherent processing efficiency of the resource combination itself (i.e., the output capacity per unit time), but also the ), a penalty factor is also introduced, which is related to the timeliness of material supply ( ) and the available scheduling adjustment time window length ( ), this penalty factor The basic efficiency score is dynamically adjusted. If the material supply delay is too long, approaching or even exceeding the entire adjustment window, the efficiency matching value of the combination will decrease or even become zero. This automatically eliminates unrealistic options due to material problems during decision-making, even if the equipment processing speed is very fast. This design enables the system to select the overall optimal resource under the current material and time constraints, rather than one-sidedly pursuing the theoretical maximum speed, thereby improving the practical feasibility and robustness of the scheduling plan.

[0091] parameter The steps for obtaining are as follows: , which represents the unit processing output of the kth resource combination for processing a certain affected process, which refers to the standardized batch or quantity to be completed by the process in a complete operation cycle. This value is directly derived from the production order or the planned output in the bill of materials (BOM) of the work order to which the affected process belongs. For a specific affected process, The value is fixed and does not change with the selected k-th resource combination. For example, if the process "OP-A35" is currently being evaluated and its work order "WO-2025007" requires the production of 100 products, then for all resource combinations k considered for "OP-A35", the corresponding 100 pieces each;

[0092] parameter The acquisition steps are as follows, which represents the kth group of resource combinations to complete the above The total unit operation time required for unit processing output includes all the time required to perform the process "OP-A35" on this specific alternative equipment, including the preparation time for equipment adjustment and program loading, the actual cutting or processing operation time, and the necessary cleaning or conversion time after the process is completed. This data is extracted from the "equipment capability library" or historical production data of the manufacturing execution system (MES). The query is performed on the alternative equipment (the core of resource combination k) and the specific process type. For example, for resource combination 1 (selecting equipment M1 to process process "OP-A35"), the query shows that the total operation time to complete 100 pieces is 5.0 hours, so For resource combination 2 (selecting equipment M2), the query results in a total operation time of 4.5 hours, so Hour;

[0093] parameter The steps for obtaining are as follows: , which represents the length of the scheduling adjustment time window faced by the kth group of resource combinations. This length is determined after a series of evaluations (such as calculating the maximum delay time point of the overall plan) after the disturbance occurs, starting from the current decision moment ( ) to the latest time point when the overall plan is expected to be completed after all affected processes have been adjusted ( ), this The value is the same for all resource combinations k evaluated under the same disturbance event, which reflects the overall time constraint for the system to make effective adjustments. For example, if the current time is the 100th hour of the production cycle, and the maximum delay time point of the overall plan is calculated to be the 132nd hour, then Hour;

[0094] parameter The acquisition step is, which represents the material supply cycle time required for the k-th resource combination to be fully prepared and available for its core replacement equipment to start processing the target process. This time is from the current decision moment ( ) to the latest time point when all necessary materials (determined by the process BOM) arrive at the designated alternative equipment or its buffer and complete the pre-steps such as inspection. This information comes from the material supply information associated with each resource combination recorded in the "Available Alternative Resource Parameter Set" generated in the previous step. For example, for resource combination 1 (equipment M1), the required materials are in stock and can be used immediately, then For resource combination 2 (equipment M2), a key special material needs to be urgently allocated from an external supplier, and it is estimated that it will take 3 hours to be delivered and processed. Hour;

[0095] parameter The steps for obtaining are as follows, which represent a method to prevent Time denominator There are zero accidents (e.g. Extremely small or negative abnormal conditions, although logically should be positive) and set the minimum positive time constant, set Hour.

[0096] Calculation process: Assume Hour, . Hour, Hour.

[0097] ;

[0098] ;

[0099] ;

[0100] This result shows that the efficiency matching value of resource combination 1 The efficiency matching value of resource combination 2 is 25. It is about 24.750. Although the theoretical equipment processing speed of resource combination 2 (28.571 units / hour) is higher than that of resource combination 1 (25 units / hour), due to its long material supply cycle time The efficiency matching value is larger (8 hours), which is more obviously reduced and eventually lower than the resource combination 1 with timely material supply. These efficiency matching values ​​will be used for subsequent sorting and screening.

[0101] Based on the efficiency matching value calculated for each set of available alternative resource combinations in the previous step The system first combines these resources with their corresponding efficiency matching values ​​and then Sort from high to low to form an ordered candidate list. For example, if the efficiency matching values ​​of the three resource combinations are calculated as , , , then the sorted list is A, B, C. Next, the system needs to filter this ordered list according to an "average production efficiency threshold". The method of setting this threshold is: first refer to the standard production efficiency that can be achieved by the equipment allocated to the affected process in the original production plan (that is, when no disturbance occurs). The standard efficiency is obtained from the process database or MES historical data. For example, the standard production efficiency of process "OP-A35" on the original equipment is 22 units per hour. Then, based on the current production urgency and the acceptable performance degradation range, a percentage coefficient is set. For example, for general disturbances, the acceptable efficiency lower limit is 80% of the original standard efficiency. For very urgent orders, this coefficient may be reduced to 70%. This percentage coefficient is dynamically determined by the production planning department according to the emergency response level regulations in the "Production Operation Management Manual". If the current disturbance is general, the average production efficiency threshold is calculated as , the system then traverses the sorted candidate list and selects all efficiency matching values For a resource combination greater than 17.6 units / hour, in the above example, 、 and All are greater than 17.6, so these three resource combinations are selected. These selected resource combinations, arranged in order of merit, constitute the preliminary scheduling operation instructions to deal with the current disturbance.

[0102] The steps to obtain the personnel's immediate status evaluation value are as follows:

[0103] Based on the preliminary scheduling instructions for dealing with disturbances, the target process information corresponding to each scheduling instruction is extracted, the operator number bound to the process is matched, the operator task record database is queried, the continuous working time period of each operator in the current cycle is obtained, and the target process operator working time information set is generated;

[0104] Based on the target process operator's working time information set, combined with the operator's training record files and performance evaluation form, the skill level, completion efficiency and error rate of each operator in the corresponding process category are extracted to generate the operator's real-time status evaluation value.

[0105] Specifically, based on the preliminary scheduling instructions for dealing with disturbances obtained after screening and sorting in the previous step, this instruction set contains recommended alternative resource combinations (mainly alternative equipment) that are optimized according to efficiency for each affected process. For each specific instruction in this instruction set (that is, each "affected process-selected alternative equipment" pairing), the system first accurately extracts the target process number corresponding to the instruction and its detailed information, such as the process "OPN-102B" and its processing requirements, the corresponding products, etc. Then, in order to subsequently allocate suitable operators, the system needs to query the "Process-Skill and Qualification Requirements Library", which is jointly maintained by the process department and the human resources department. It clarifies the minimum skill level, special operation certification (such as high-precision welding certificate) and safety training requirements required for each process category or operation of specific equipment (such as the alternative equipment selected in the instruction). Based on these requirements, the system preliminarily matches and screens out a list of all operator numbers that are qualified to perform the target process in the "Operator Information Library" to obtain this qualified operator. After compiling the operator list, the system further queries the "Operator Task Record Database," which records each operator's daily work task start and end times, task types, and rest breaks in real time or near real time. For each qualified operator in the list, the system retrieves all work records for the "current cycle," defined here as the period from the start of the scheduled shift (for example, 8:00 a.m.) to the current query time (for example, 2:30 p.m.). The system analyzes these records and calculates the cumulative duration of all actual work performed by each operator during the current cycle. It specifically identifies the most recent continuous working period uninterrupted by a valid rest break (a valid rest break is defined as a continuous, uninterrupted rest break of more than 30 minutes). The system then aggregates the extracted target process information, the numbers of the qualified operators matching that process, and each qualified operator's cumulative working hours and most recent continuous working hours during the current cycle to generate a target process operator working time information set.

[0106] Based on the target process operator operation time information set generated in the previous step, which already includes the target process and the number of each potentially qualified operator and their recent operation time data, the system then makes a further refined assessment of the professional capabilities and current status of each candidate operator. This process is completed by integrating data sources from different management systems. First, the system queries the "operator training record file" based on the candidate operator's number and the category of the target process (for example, "precision CNC milling five-axis operation"). This file is maintained by the human resources department and records in detail the employee's previous skill training content, the assessment level passed, the qualification certification obtained and its validity period. From it, the operator's official certified "skill level" for the current target process category is extracted, for example, it is divided into four levels: junior (L1), intermediate (L2), senior (L3), and technician (L4). This level classification standard is formulated according to the company's internal "Job Skill Assessment Standard", which is reviewed and updated by the technical committee every year to ensure that the operator's skills are synchronized with the equipment process requirements. Subsequently, the system connects to the "production performance" data center. The MES system queries the operator's historical "completion efficiency" when performing processes of the same or similar category as the current target process within the past evaluation cycle (for example, the last three months). This efficiency is typically recorded as the inverse of the ratio of the actual time taken to complete the task to the standard working time, or as a percentage. For example, if an operator's average efficiency score for this type of process over the past three months is 95 points (out of 100, where 100 points exactly meets the standard working time), and the historical "error rate" is recorded as the percentage of defective products produced when the operator performs this process as a percentage of the total output, or the percentage of processes requiring rework as a percentage of the total number of completed processes, for example, 0.5%, these performance data are derived from actual production data and quality inspection results collected by the MES system. The system extracts the skill level, historical completion efficiency, and historical error rate for each candidate operator, along with the existing work duration information, and combines them into a multi-dimensional set of real-time personnel status evaluation values. Each set of evaluation values ​​fully describes the candidate operator's current comprehensive status on a specific process task.

[0107] The steps for obtaining the personnel scheduling execution plan are as follows:

[0108] Based on the personnel's immediate status assessment value, the skill proficiency level, total continuous operation time and number of currently assigned tasks of each operator are extracted to form a personnel operation capability status set;

[0109] According to the personnel operation capability status set, the personnel suitability score is calculated using the following formula:

[0110] ;

[0111] in, is the fitness score of the i-th operator, is the skill proficiency level of the i-th operator in the target process, is the total continuous working time of the i-th operator in the current cycle, is the cumulative error number of the i-th operator in the current cycle, is the number of tasks assigned to the i-th operator in the current scheduling period;

[0112] Based on the personnel suitability score, all candidate operators are sorted in descending order, and the personnel with the highest personnel suitability score are selected in order of process matching priority for scheduling and allocation to generate a personnel scheduling execution plan.

[0113] Specifically, based on the "personnel real-time status evaluation value set" obtained in the previous step, which includes each candidate operator's skill level for a specific target process category, historical performance (completion efficiency and error rate), and recent working time, the system first extracts or converts the specific parameters required for the subsequent fitness calculation for each operator. The first item is the "skill proficiency level". This value is directly taken from the "Skill Level" for the current target process category recorded in the "Personnel Real-time Status Assessment Value" and converted from the original descriptive level (such as L1, L2, L3, L4) to a preset numerical score. This numerical system is jointly formulated by the Human Resources Department and the Production Technology Department. For example, L1 corresponds to 10 points, L2 corresponds to 20 points, L3 corresponds to 30 points, and L4 corresponds to 40 points. The score interval reflects the weight of the ability difference between each level. The second item is the "total continuous working time". This data is also obtained from the "Accumulated Working Hours" included in the "Personnel Real-time Status Assessment Value" or the summary analysis of the "Recent Continuous Working Time Period". It accurately records the actual total working time of the operator in the current shift or a preset fatigue monitoring period (for example, the last 4 hours) without effective rest (effective rest standard, as defined above, is more than 30 consecutive minutes) in hours. The third item is the "Number of currently assigned tasks" This data is not directly stored in the "personnel instant status assessment value". Instead, the system needs to query the real-time task scheduling dashboard or database of the manufacturing execution system (MES) based on the operator number in real time, and count the total number of process tasks that have been clearly assigned to the operator and have a status of "to be started" or "in progress" as of the current moment. The "current scheduling cycle" here usually refers to the remaining time of the current shift or a fixed shorter planning time domain in the future (for example, the next 4 hours). Through the above extraction and query, a record containing the above three core data is generated for each candidate operator, which together form a set of personnel operation capability status.

[0114] formula: The benefit of the formula is that it constructs a quantitative model for comprehensively evaluating the adaptability of operators to specific process tasks, which not only positively incentivizes high skill levels ( ), and also introduces nonlinear penalty terms to reasonably consider the operator's immediate state, specifically: using the natural logarithm function To deal with the continuous working time, the negative impact of fatigue on fitness increases with the working time, but the growth rate gradually slows down, which is more in line with the actual physiological characteristics of fatigue accumulation, avoiding the problem of excessive sensitivity to short-term overtime or insufficient punishment for overlong work caused by linear punishment. At the same time, for historical errors ( ) and the current task load ( ) considerations, through the square root function and As the denominator, it smooths the impact of errors and moderately adjusts the impact of individual errors when multi-tasking is in progress, making the scoring more robust and providing practical guidance. Ultimately, it helps the system make the best personnel assignment decisions among a large number of qualified operators based on four dimensions: skills, fatigue, historical performance, and current load.

[0115] parameter The steps for obtaining are as follows: it represents the quantitative value of the skill proficiency level of the i-th operator corresponding to the target process. This value comes from the quantified skill level recorded for each operator in the previous step "forming a set of personnel operation capability status". The original skill level (such as L1 to L4) is converted into a numerical value according to the internal position skill and salary level correspondence table of the enterprise. The correspondence table is jointly formulated by the Human Resources Department and the Production Engineering Department. For example, L1 (junior operator) is scored as 10 points, L2 (intermediate operator, able to work independently) is scored as 20 points, L3 (senior operator, able to handle complex problems and guide others) is scored as 30 points, and L4 (technician level, able to perform process improvements and fault diagnosis) is scored as 40 points. This scoring system is adjusted every two years as the enterprise skill certification system is updated. For example, if operator Zhang San's certified skill level for the current target process "precision grinding 03B" is L3, then its corresponding ;

[0116] parameter The steps for obtaining are as follows: , which represents the total continuous working time of the i-th operator in the current evaluation period (for example, from the start of this shift to the current moment), in hours. This data is also extracted from the operator's continuous working time recorded in the previous step "Forming the personnel operation capability status set", which is calculated by analyzing the operator's task sign-in and sign-out records in the MES system and the defined effective rest time (for example, a rest time of more than 30 minutes is considered to be an interruption of continuous operation). For example, operator Zhang San has worked for a total of 3.5 hours since he started working, and the longest continuous rest time during this period is 15 minutes (which does not meet the effective rest standard). Then his Hour;

[0117] parameter The steps for obtaining are as follows: it represents the cumulative number of error processes (i.e., the number of processes that resulted in product scrapping or required significant rework) that were confirmed to be directly caused by the i-th operator's operation during the past specified evaluation period (for example, the past four consecutive full working weeks. This period is set by the quality management department based on product complexity and production rhythm to ensure that there is a sufficient sample size to reflect the actual error level). This data is obtained by querying the "operator-related NCR (non-conformity report) record database" of the quality management system and summarizing it by operator number. For example, in the past four weeks, among the processes responsible for operator Zhang San, there was one process that had a quality problem that required scrapping due to his operational error. Then ;

[0118] parameter The steps for obtaining are as follows: it represents the number of tasks that have been assigned and not yet completed to the i-th operator when the current scheduling instruction is issued. These tasks include tasks that are being executed and tasks that have been included in the current shift work queue waiting to be executed. This data is obtained by real-time querying the MES system. For example, when evaluating whether to assign a new task to operator Zhang San, it is found that there are already two tasks in his name in the "in progress" or "pending" status, then .

[0119] Calculation process: Take operator Zhang San (code i=1) as an example, substitute the obtained parameter values ​​for calculation: , Hour, , Substituting the parameters into the formula, we get 11.403.

[0120] The result shows that the operator Zhang San (i=1) has a personnel suitability score of It is approximately 11.403, which is a comprehensive dimensionless score. The higher the score, the better the operator's comprehensive adaptability to the target process at the current moment. This score of 11.403 specifically reflects that Zhang San's higher skill proficiency (30 points) is reduced under the influence of fatigue after a certain continuous working time (3.5 hours), and the negative impact of his recent cumulative error (1 time) and current task load (2 items) are deducted. This score will serve as the core basis for horizontal comparison and preferential ranking among multiple candidate operators. For example, if another operator Li Si's score is 10.5, then without considering other priority rules, Zhang San will be considered for assignment of the task before Li Si.

[0121] The personnel suitability score calculated for each candidate operator in the previous step for the specific target process , the system firstly combines all these candidate operators and their corresponding Ratings are organized into a list and strictly followed The operators in the list are sorted in descending order from high to low scores to form a priority queue. For example, if there are three candidate operators A, B, and C, their scores are , , , then the queues after sorting may be A, C, and B (if the scores are the same, they can be sorted by secondary keys such as employee numbers, or maintain the original relative order). Then, the system refers to a preset "process matching priority table" to determine the order of scheduling and allocation. The table is formulated by the production planning department based on factors such as the urgency of the order, customer importance, material scarcity, or the dependency relationship of subsequent processes, and is updated regularly. For example, the table stipulates that "expedited order process" has the highest priority, followed by "bottleneck equipment process", and then "ordinary order process". The system processes the target processes that need to be assigned operators in this priority order. For the target process with the highest priority currently being processed, the system selects the top of the queue (i.e., the operator at the top of the queue) from the candidate operator queue that has been sorted in descending order of fitness score. The operator with the highest score (the highest score) and current status of "available" (i.e., not selected by a previous higher-priority process or having reached the upper limit of working hours for the day) is bound to the target process and its selected alternative equipment to form a specific personnel allocation instruction. For example, if operator A has the highest score and is available for the current process P1, A is assigned to P1. Then, when the system processes the next-priority process P2, it will select from the remaining available candidates with the highest adaptation scores. This selection and allocation process will continue until all target processes that need to be scheduled have been successfully matched with operators, or there are no suitable available operators. All these successful matches (process-equipment-operator) are combined to generate the final personnel scheduling execution plan.

[0122] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An artificial intelligence-driven intelligent manufacturing system scheduling method, characterized in that: The following steps are involved: Real-time monitoring of order status parameters in the manufacturing execution system, identification of equipment failure shutdown signals or order insertion signals, extraction of associated equipment codes and current work order numbers, and establishment of core disturbance information pairs; Based on the core disturbance information pair, the expected completion time of the affected process in the current production activity of the intelligent manufacturing system is evaluated to obtain an expected delay value for a single process. Based on the expected delay value for a single process and combined with the original planned completion time of all affected processes, the delay amount of the overall plan is calculated to determine the scheduling adjustment time window; According to the resource changes reflected by the scheduling adjustment time window and the core disturbance information, the processing capacity and material supply cycle of the alternative equipment associated with the affected process are retrieved to obtain a set of available alternative resource parameters. Based on the set of available alternative resource parameters and in comparison with the production efficiency index, a resource combination is selected for replacement to form a preliminary scheduling operation instruction to cope with the disturbance; Based on the preliminary scheduling instructions for responding to the disturbance, the continuous operation time and skill proficiency of the target process operators are obtained to obtain the personnel's real-time status evaluation value. Based on the personnel's real-time status evaluation value, personnel allocation is optimized to generate a personnel scheduling execution plan; The steps for obtaining the core disturbance information pair are: Collect order status parameters in real time, analyze and judge the equipment failure shutdown signal and order insertion signal in the order status parameters respectively, and extract the equipment failure shutdown signal and order insertion signal; Based on the equipment failure shutdown signal and the order insertion signal, the corresponding equipment code and the current work order number are retrieved, and an association relationship between the equipment failure shutdown signal and the equipment code, and an association relationship between the order insertion signal and the current work order number are respectively established to form association mapping information; Based on the association mapping information, the device code and the current work order number are combined and matched, and the code data and the work order data are bound in the form of a key-value pair to form a core disturbance information pair.

2. The artificial intelligence-driven intelligent manufacturing system scheduling method according to claim 1, characterized in that: The steps for obtaining the estimated delay value of a single process are: Based on the core disturbance information pair, the affected process numbers in the current production activity are located, and the planned completion time, unit standard working hours, resource start time, and resource recovery time of each affected process are extracted to form a set of production scheduling parameters for the affected processes; According to the affected process scheduling parameter set, the difference between the resource recovery available time and the actual resource start time is calculated to obtain the resource available delay length, and the affected process schedule offset data group is generated; Based on the affected process progress deviation data group, a single process estimated delay value is calculated.

3. The artificial intelligence-driven intelligent manufacturing system scheduling method according to claim 1, characterized in that: The steps for obtaining the scheduling adjustment time window are: Based on the estimated delay value of the single process, the delay values ​​of all affected processes are aggregated in order of process numbers, and each delay value is matched one-to-one with the original planned completion time of the corresponding process to generate a comparison table of affected process plans; According to the affected process plan comparison table, the affected processes are sorted by their original planned completion time, the delay value corresponding to the process with the latest planned completion time is extracted, and the delay value is added to the original planned completion time to obtain the maximum delay time point of the overall plan; Based on the maximum delay time point of the overall plan, the time difference between the end time of the current global production scheduling cycle of the intelligent manufacturing system and the maximum delay time point of the overall plan is compared to determine whether the scheduling adjustment requirement duration exceeds the acceptable range and obtain the scheduling adjustment time window.

4. The artificial intelligence-driven intelligent manufacturing system scheduling method according to claim 1, characterized in that: The steps for obtaining the available alternative resource parameter set are: Based on the equipment code and current work order number identified in the scheduling adjustment time window and the core disturbance information, query the associated equipment resource database and order resource mapping table in the intelligent manufacturing system, extract the equipment configuration records and original material call records associated with the affected process, and generate an affected process resource binding information set; Based on the affected process resource binding information set, search the equipment capability database for equipment items with the same process characteristics as the bound equipment, screen the equipment processing capability parameters with available idle time periods within the scheduling adjustment time window, and simultaneously search the corresponding material supply time intervals in the material supply plan table to generate a list of candidate resource capability and material supply cycle combinations; Based on the list of candidate resource capabilities and material supply cycle combinations, identify combinations with processing capability equivalence, time cycle matching, and scheduling compatibility, screen the equipment processing capabilities and material supply cycles that meet the replaceable conditions within the time window, and obtain a set of available alternative resource parameters.

5. The artificial intelligence-driven intelligent manufacturing system scheduling method according to claim 1, characterized in that: The steps for obtaining the preliminary scheduling operation instructions for dealing with disturbances are as follows: Based on the available alternative resource parameter set, the unit processing output, unit operation time, scheduling adjustment time window length and material supply cycle length corresponding to each resource combination are extracted to construct standardized resource combination index items to form a resource combination performance index set; Calculating the efficiency matching value of the resource combination according to the resource combination performance indicator set; Based on the efficiency matching values ​​of the resource combinations, the resource combinations are sorted from high to low according to their efficiency matching values, and resource combinations with efficiency matching values ​​greater than the average production efficiency threshold are selected to form preliminary scheduling operation instructions to cope with disturbances.

6. The artificial intelligence-driven intelligent manufacturing system scheduling method according to claim 1, characterized in that: The steps for obtaining the personnel's immediate status evaluation value are as follows: Based on the preliminary scheduling instructions for coping with the disturbance, the target process information corresponding to each scheduling instruction is extracted, the operator number bound to the process is matched, the operator task record database is queried, the continuous working time period of each operator in the current cycle is obtained, and the target process operator working time information set is generated; Based on the target process operator's working time information set, combined with the operator's training record file and performance evaluation form, the skill level, completion efficiency and error rate of each operator in the corresponding process category are extracted to generate the operator's real-time status evaluation value.

7. The artificial intelligence driven intelligent manufacturing system scheduling method according to claim 1, characterized in that: The steps for obtaining the personnel scheduling execution plan are: Based on the personnel's real-time status evaluation value, extract each operator's skill proficiency level, total continuous operation time, and number of currently assigned tasks to form a personnel operation capability status set; Calculating a personnel suitability score based on the personnel operational capability status set; Based on the personnel suitability score, all candidate operators are sorted in descending order, and the personnel with the highest personnel suitability score are selected in order of process matching priority for scheduling and allocation to generate a personnel scheduling execution plan.

Images