MES-based intelligent workshop sudden disruption handling system and method

Abstract

An MES-based intelligent workshop sudden disruption handling system and a method, relating to the technical field of MESs. The system comprises a data acquisition module, a real-time monitoring module and a production scheduling module. The data acquisition module is used for acquiring data information in a workshop; the real-time monitoring module comprises an identification unit and a prediction unit; the identification unit is used for monitoring a production process in the workshop in real time on the basis of the information of the data acquisition module; the prediction unit is used for predicting in advance potential anomalies and sudden disruptions in the intelligent workshop. The present application can combine multiple sets of data to cope with complex industrial environments, so as to avoid as much as possible the problems of possible blind spots in data collection or inaccurate data due to reasons such as sensor errors and data losses, has certain flexibility to obtain and predict anomalies and disruptions of intelligent workshops, and quickly and intelligently processes obtained information of the anomalies and disruptions to avoid losses caused by the sudden disruptions.

Description

A Smart Workshop Emergency Damage Handling System and Method Based on MES Technical Field

[0001] This invention relates to the field of MES technology, and more specifically, to an intelligent workshop emergency obstacle handling system and method based on MES. Background Technology

[0002] Intelligent workshop emergency obstacle handling systems are mainly used in fields that require high production management and real-time monitoring, such as electronics manufacturing, automobile manufacturing, pharmaceutical manufacturing, and food manufacturing. These fields usually have strict requirements for product quality and complex production processes, requiring real-time monitoring and scheduling to ensure production efficiency and product quality. The system can monitor the production process in real time, and when an obstacle occurs, it will issue an alarm in a timely manner and provide solutions to minimize production interruptions and losses.

[0003] However, in actual use, there may be blind spots in data collection, or the data may be inaccurate due to sensor errors, data loss, etc. Even the best system may not be able to predict and handle unknown or unconventional obstacles, requiring the system to have a certain degree of flexibility and creativity to cope with them. Moreover, in complex industrial environments, factors such as electromagnetic interference and equipment failure may affect the stability of the MES system.

[0004] Summary of the Invention

[0005] To address the issues that data collection may have blind spots or be inaccurate due to sensor errors or data loss during practical use, and that even the best systems may be unable to predict and handle unknown or unconventional obstacles, requiring systems to possess a certain degree of flexibility and creativity to cope with them, and that electromagnetic interference, equipment failure, and other factors may affect the stability of MES systems in complex industrial environments, this invention provides a smart workshop emergency obstacle handling system and method based on MES.

[0006] To achieve the above objectives, on the one hand, a smart workshop emergency obstacle handling system based on MES is proposed, including a data acquisition module, a real-time monitoring module, and a production scheduling module;

[0007] The data acquisition module is used to obtain data information within the workshop;

[0008] The real-time monitoring module includes an identification unit and a prediction unit. The identification unit is used to monitor the production process in the workshop in real time based on the information from the data acquisition module, and to determine in real time whether there are any abnormalities or obstacles. Specifically:

[0009] According to the formula The various anomaly scores of the smart workshop are calculated and obtained, where j represents the anomaly category (1,2,3), and Q...j Represents the j-th anomaly category, n j P1 represents the total number of monitoring parameters for the j-th anomaly category. ij P2 is the real-time monitoring value of the i-th monitoring parameter in the j-th anomaly category. ij P1 represents ij ωj is the pre-defined normal value for the i-th monitoring parameter in the j-th anomaly category. i The weight coefficient of the i-th monitoring parameter for the j-th anomaly category;

[0010] Pre-set thresholds (1, 2, 3) for each anomaly category, compare each anomaly score with its corresponding threshold, and determine that the anomaly category exists in the smart workshop if any anomaly score exceeds the corresponding threshold.

[0011] The prediction unit is used to predict potential anomalies and sudden obstacles in the smart workshop in advance;

[0012] The production scheduling module is used to dynamically schedule workshop production for rapid response based on the identification results of the real-time monitoring module.

[0013] Preferably, for the first anomaly category: the monitoring parameters for the first anomaly category are specifically fault, overload, and performance, and the weighting coefficients corresponding to the monitoring parameters for the first anomaly category are ω11, ω12, and ω13;

[0014] For the second anomaly category: The monitoring parameters for the second anomaly category are specifically production parameter deviations and process flow values, and the weighting coefficients corresponding to the monitoring parameters for the second anomaly category are ω21 and ω22;

[0015] For the third anomaly category: The monitoring parameters for the third anomaly category are raw material supply and logistics, and the weighting coefficients corresponding to the monitoring parameters for the third anomaly category are ω31 and ω32.

[0016] Preferably, the prediction unit specifically predicts equipment-related anomalies, production process anomalies, and resource and quality anomalies. For equipment-related anomaly prediction:

[0017] Obtain the average historical failure interval T of the equipment in the smart workshop. E The average standard deviation σ of historical failure intervals E ;

[0018] According to formula T E1 =T2+T E ±(k*σ E The predicted time T for the next equipment-related anomaly is calculated and obtained. E1 , where T2 is the current time and k is the preset confidence level coefficient.

[0019] Preferably, for predicting production process anomalies:

[0020] Obtain the historical average value D of the deviation of key production parameters of products in the smart workshop. E Sum of standard deviations D2;

[0021] According to the formula Obtain the predicted time T for the next production process anomaly. E2 , where T2 is the current time and β is the rate of change of deviation.

[0022] Preferably, for resource and quality anomaly prediction:

[0023] Obtain the daily consumption rate C of materials in the smart workshop. E ;

[0024] According to the formula Obtain the predicted time T of the next material shortage. E3 Where K2 is the current inventory and K1 is the safety stock;

[0025] Obtain the anomaly rate R of product quality in the smart workshop. E ;

[0026] According to the formula Obtain the time T during which quality defects occur in the next n products. E4 Where C1 is the current product quantity;

[0027] According to the formula The predicted time T for the next resource and quality anomaly is calculated and obtained. E5 ,in and This is a preset scaling factor.

[0028] Preferably, the real-time monitoring module further includes an environmental adjustment unit, which is used to adjust the results of the prediction unit by comprehensively considering the complex factors of the intelligent workshop, specifically:

[0029] The first adjustment factor A1, the second adjustment factor A2, and the third adjustment factor A3 are obtained.

[0030] According to the formula Tf1=T E1 (1+A1), Tf2=T E2 (1+A2) and Tf3=T E5 (1+A3) respectively calculate and obtain the predicted time Tf1 of the next equipment-related anomaly, the predicted time Tf2 of the next production process anomaly, and the predicted time Tf3 of the next resource and quality anomaly.

[0031] Preferably, the first adjustment factor A1, the second adjustment factor A2, and the third adjustment factor A3 are obtained in the following ways:

[0032] For the first adjustment factor A1: according to the formula The number of failures and total operating time are values ​​of the equipment in the smart workshop, and θ1 is a preset proportional coefficient.

[0033] For the second adjustment factor A2: According to the formula A2=(θ2*L), where L is the deviation rate of key parameters in the production process and θ2 is the preset proportional coefficient;

[0034] For the third adjustment factor A3: According to the formula A3=(θ3*(S1+S2)), where S1 is the supply chain disruption rate, S2 is the quality impact rate, and θ3 is the preset proportional coefficient.

[0035] Preferably, the production scheduling module includes a priority evaluation unit and a dynamic adjustment unit. The priority evaluation unit is used to prioritize anomaly categories, thereby facilitating subsequent obstacle response. Specifically:

[0036] Obtain the urgency index Z1 for the first abnormal category, the urgency index Z2 for the second abnormal category, and the urgency index Z3 for the third abnormal category;

[0037] According to the formula

[0038] as well as Obtain the priority values ​​H1, H2, and H3 for the first, second, and third anomaly categories, where... ε and ε are preset weighting coefficients, and U1, U2 and U3 are preset influence indices, respectively;

[0039] The priority values ​​H1, H2, and H3 are arranged in descending order and a signal is generated and transmitted to the dynamic adjustment unit.

[0040] Preferably, the urgency index Z1 of the first anomaly category, the urgency index Z2 of the second anomaly category, and the urgency index Z3 of the third anomaly category are obtained in the following ways:

[0041] According to the formula and The urgency index Z1 for the first anomaly category, the urgency index Z2 for the second anomaly category, and the urgency index Z3 for the third anomaly category are calculated and obtained respectively.

[0042] The specific working principle of the dynamic adjustment unit is as follows:

[0043] Equipment-related anomalies: Immediately inspect and maintain the equipment, and adjust the production plan to avoid problems at T. E1 Use the device during the specified time period;

[0044] Production process anomalies: Monitor the production line, at T E2 Previously, process parameters were adjusted or the production line was switched to a backup line;

[0045] Resource and quality anomalies: in T E5 Previously, key materials were replenished or quality control measures were adjusted.

[0046] On the other hand, this invention also proposes a method for handling sudden obstacles in a smart workshop based on MES, including the following steps:

[0047] Step 1: Obtain data information from within the workshop, and use this information to monitor the production process in real time, and determine in real time whether there are any abnormalities or obstacles;

[0048] Step Two: Anticipate potential anomalies and unexpected obstacles in the smart workshop;

[0049] Step 3: Dynamically schedule workshop production based on the identification results for rapid response.

[0050] Beneficial effects: It can combine multiple sets of data to deal with complex industrial environments, and avoid blind spots in data collection or inaccurate data due to sensor errors, data loss, etc. It can obtain predictions and intelligent workshop anomalies and obstacles with a certain degree of flexibility, and can quickly and intelligently process the information of anomalies and obstacles to avoid losses caused by sudden obstacles. Attached Figure Description

[0051] Figure 1 is a flowchart of the intelligent MES data analysis system of the present invention;

[0052] [Correction 14.08.2024 based on Rule 91] Figure 2 is a flowchart of the method of the present invention. Detailed Implementation

[0053] As shown in Figure 1, an intelligent workshop emergency obstacle handling system based on MES includes a data acquisition module, a real-time monitoring module, and a production scheduling module. It should be noted that it is mainly applied to fields that require high-level production management and real-time monitoring, such as electronics manufacturing, automobile manufacturing, pharmaceutical manufacturing, and food manufacturing. These fields usually have strict requirements for product quality and complex production processes, requiring real-time monitoring and scheduling to ensure production efficiency and product quality. The system can monitor the production process in real time, and when an obstacle occurs, it will promptly issue an alarm and provide a solution to minimize production interruptions and losses.

[0054] However, in actual use, there may be blind spots in data collection, or the data may be inaccurate due to sensor errors, data loss, etc. Even the best system may not be able to predict and handle unknown or unconventional obstacles, requiring the system to have a certain degree of flexibility and creativity to cope with them. Moreover, in complex industrial environments, factors such as electromagnetic interference and equipment failure may affect the stability of the MES system.

[0055] The data acquisition module is used to acquire data information within the workshop. It should be noted that, in this embodiment, the data information includes: equipment status data (including equipment operating status, efficiency, and fault information); production process data (involving output, production speed, and process parameters such as temperature and pressure); material tracking data (material consumption, inventory levels, and batch tracking information); quality monitoring data (product quality inspection results, defect records, and defective product statistics); personnel management data (employee attendance, work assignments, and skill information); energy and environmental data (energy consumption and workshop environmental conditions); maintenance and repair data (equipment maintenance cycles, repair records, and spare parts replacement); and order and production plan data (order details, production progress, and plan changes, acquired through various sensors).

[0056] The real-time monitoring module includes an identification unit and a prediction unit. The identification unit is used to monitor the production process in the workshop in real time based on the information from the data acquisition module, and to determine in real time whether there are any abnormalities or obstacles. Specifically:

[0057] According to the formula The various anomaly scores of the smart workshop are calculated and obtained, where j represents the anomaly category (1,2,3), and Q... j Represents the j-th anomaly category, n j P1 represents the total number of monitoring parameters for the j-th anomaly category. ij P2 is the real-time monitoring value of the i-th monitoring parameter in the j-th anomaly category. ij P1 represents ij ωj is the pre-defined normal value for the i-th monitoring parameter in the j-th anomaly category. i , is the weight coefficient of the i-th monitoring parameter of the j-th anomaly category; it should be noted that in this embodiment, there are three j, which are respectively equipment-related anomalies, production process anomalies and resource and quality anomalies, and the corresponding Q1 is the equipment-related anomaly score, Q2 is the production process anomaly, and Q3 is the resource and quality anomaly;

[0058] A threshold (1, 2, 3) is pre-set for each anomaly category. Each anomaly score is compared with its corresponding threshold. If any anomaly score exceeds the corresponding threshold, the intelligent workshop is determined to have that anomaly category. It should be noted that in this embodiment, the thresholds (1, 2, 3) for each anomaly category are also respectively the equipment-related anomaly threshold, the production process anomaly threshold, and the resource and quality anomaly threshold. If any anomaly score exceeds the corresponding threshold, the intelligent workshop is determined to have that anomaly. For example, if the equipment-related anomaly score Q1 is greater than the equipment-related anomaly threshold, the intelligent workshop is determined to have that type of anomaly.

[0059] The prediction unit is used to predict potential anomalies and sudden obstacles in the smart workshop in advance;

[0060] The production scheduling module is used to dynamically schedule workshop production based on the identification results of the real-time monitoring module. It should be noted that by implementing a buffer management strategy, the impact of production fluctuations and data inaccuracies is reduced.

[0061] As an optional embodiment: For the first anomaly category: The monitoring parameters for the first anomaly category are specifically fault, overload, and performance, and the weighting coefficients corresponding to the monitoring parameters for the first anomaly category are ω11, ω12, and ω13; It should be noted that in this embodiment, the specific values ​​for fault, overload, and performance can be:

[0062] Install fault indicator lights in the smart workshop and obtain the status or status code of the fault indicator lights through a data acquisition module;

[0063] If the fault indicator light is on or the status code indicates a fault, the fault value is 1; otherwise, the fault value is 0.

[0064] Overload is obtained by monitoring the real-time power of equipment in the workshop using sensors.

[0065] The performance is evaluated based on the staff's comprehensive historical data and the historical maintenance information of the equipment in the workshop, and is specifically any integer from 1 to 10; it should also be noted that in this embodiment, the values ​​of ω11, ω12 and ω13 can be 0.293, 0.093 and 0.613, respectively;

[0066] For the second anomaly category: the monitoring parameters for the second anomaly category are specifically production parameter deviation and process flow value, and the weighting coefficients corresponding to the monitoring parameters for the second anomaly category are ω21 and ω22; it should be noted that, in this embodiment, the values ​​of production parameter deviation and process flow value can be:

[0067] Data is collected for each key production parameter (such as temperature, pressure, speed, etc.), a threshold is set for each parameter, the deviation of each parameter from the threshold is calculated, and the deviation is collectively marked as the production parameter deviation; the process flow value is evaluated by staff in conjunction with historical data, and is any integer from 1 to 10; it should also be noted that the values ​​of ω21 and ω22 can be 0.299 and 0.701, respectively.

[0068] For the third anomaly category: the monitoring parameters for the third anomaly category are specifically raw material supply and logistics, and the corresponding weighting coefficients for the monitoring parameters of the third anomaly category are ω31 and ω32. It should be noted that in this embodiment, both raw material supply and logistics are evaluated by staff in conjunction with historical data, specifically any integer from 1 to 10; it should also be noted that the values ​​of ω31 and ω32 can be 0.402 and 0.598, respectively.

[0069] As an optional embodiment: the prediction unit specifically predicts equipment-related anomalies, production process anomalies, and resource and quality anomalies. For equipment-related anomaly prediction:

[0070] Obtain the average historical failure interval T of the equipment in the smart workshop. E The average standard deviation σ of historical failure intervals E ;

[0071] According to formula T E1 =T2+T E ±(k*σ E The predicted time T for the next equipment-related anomaly is calculated and obtained. E1 Where T2 is the current time and k is the preset confidence level coefficient; it should be noted that in this embodiment, the value of k is 1.023 (k=1 corresponds to a 68% confidence interval).

[0072] As an optional implementation: for production process anomaly prediction:

[0073] Obtain the historical average value D of the deviation of key production parameters of products in the smart workshop. E The standard deviation D2; It should be noted that, in this embodiment, the deviation of key production parameters is: data of each key production parameter (such as temperature, pressure, speed, etc.) are collected, a threshold is set for each parameter, the deviation of each parameter from the threshold is calculated, and the deviation is collectively marked as the production parameter deviation;

[0074] According to the formula Obtain the predicted time T for the next production process anomaly. E2Where T2 is the current time and β is the rate of change of deviation. It should be noted that β refers to the rate at which the deviation changes over time, which can be calculated based on historical data. It is an indicator for measuring the speed of deviation in the production process, and in this embodiment, it can be 1.203.

[0075] As an optional implementation: for resource and quality anomaly prediction:

[0076] Obtain the daily consumption rate C of materials in the smart workshop. E It should be noted that in this embodiment, for each material, the average consumption over a certain period of time (usually a working day) is calculated, which can be done by dividing the total consumption during the period by the number of days.

[0077] According to the formula Obtain the predicted time T of the next material shortage. E3 Where K2 is the current inventory and K1 is the safety stock;

[0078] Obtain the anomaly rate R of product quality in the smart workshop. E It should be noted that, in this embodiment, the quality defect rate can be calculated by dividing the number of defective products by the total number of products.

[0079] According to the formula Obtain the time T during which quality defects occur in the next n products. E4 Where C1 is the current product quantity;

[0080] According to the formula The predicted time T for the next resource and quality anomaly is calculated and obtained. E5 ,in and This is a preset scaling factor. It should be noted that, in this embodiment, and The value can be 0.228 or 0.762.

[0081] As an optional embodiment: the real-time monitoring module further includes an environmental adjustment unit, which is used to adjust the results of the prediction unit by comprehensively considering the complex factors of the smart workshop. Specifically: it should be noted that in a complex industrial environment, factors such as electromagnetic interference and equipment failure may affect the stability of the MES system. This technical solution calculates a more stable judgment result by combining the interference of multiple factors in the judgment process.

[0082] The first adjustment factor A1, the second adjustment factor A2, and the third adjustment factor A3 are obtained. It should be noted that, in this embodiment, the first adjustment factor A1, the second adjustment factor A2, and the third adjustment factor A3 are adjustment factors for equipment-related anomalies, reflecting the impact of electromagnetic interference and equipment failure on equipment stability; adjustment factors for production process anomalies, reflecting the impact of environmental factors on production process control; and adjustment factors for resource and quality anomalies, reflecting the uncertainty of supply chain and quality control.

[0083] According to the formula Tf1=T E1 (1+A1), Tf2=T E2 (1+A2) and Tf3=T E5 (1+A3) Calculate and obtain the adjusted predicted time Tf1 for the next equipment-related anomaly, Tf2 for the next production process anomaly, and Tf3 for the next resource and quality anomaly. It should be noted that the above method allows for the consideration of complex industrial environmental factors such as electromagnetic interference and equipment failure in the MES system, thereby more accurately predicting the actual occurrence time of anomalies.

[0084] As an optional embodiment, the specific methods for obtaining the first adjustment factor A1, the second adjustment factor A2, and the third adjustment factor A3 are as follows:

[0085] For the first adjustment factor A1: according to the formula The number of failures and total running time are values ​​of the equipment in the smart workshop, and θ1 is a preset proportional coefficient. It should be noted that in this embodiment, θ1 reflects the degree of impact of failures on production, and in this embodiment, the value can be 0.291.

[0086] For the second adjustment factor A2: according to the formula A2=(θ2*L), where L is the deviation rate of key parameters in the production process, and θ2 is the preset proportional coefficient; it should be noted that in this embodiment, θ1 is the degree of influence of the environment on production, and in this embodiment, the value can be 0.028; it should also be noted that in this embodiment, the deviation rate of key parameters can be obtained by dividing the total number of historical deviations by the number of measurements and then multiplying by 100%, where the total number of deviations refers to the number of times the key parameter exceeds the threshold:

[0087] For the third adjustment factor A3: According to the formula A3=(θ3*(S1+S2)), where S1 is the supply chain disruption rate, S2 is the quality impact rate, and θ3 is a preset proportional coefficient. It should be noted that in this embodiment, S1 (supply chain disruption rate) and S2 (quality impact rate) are obtained as follows: Supply chain disruption is defined as a supplier failing to deliver on time or materials failing to meet quality standards; The number of disruptions is recorded: within a certain time period (e.g., one month or one year), the total number of all supply chain disruption events is recorded; the supply chain disruption rate can be calculated by dividing the number of disruptions by the total time period considered (days, weeks, months, etc.); quality anomalies are defined: the criteria for quality anomalies are determined, such as products failing quality inspection or customer returns; the number of non-conforming products is recorded: within a certain time period, the number of all products identified as non-conforming is recorded; total production volume is recorded: simultaneously, the total number of products produced within the same time period is recorded; the quality anomaly rate can be calculated by dividing the number of non-conforming products by the total production volume.

[0088] As an optional embodiment: the production scheduling module includes a priority evaluation unit and a dynamic adjustment unit. The priority evaluation unit is used to prioritize anomaly categories, thereby facilitating subsequent obstacle response, specifically:

[0089] Obtain the urgency index Z1 for the first abnormal category, the urgency index Z2 for the second abnormal category, and the urgency index Z3 for the third abnormal category;

[0090] According to the formula

[0091] as well as Obtain the priority values ​​H1, H2, and H3 for the first, second, and third anomaly categories, where... ε and ε are preset weighting coefficients, and U1, U2, and U3 are preset influence indices, respectively. It should be noted that in this embodiment, the first, second, and third anomaly categories are equipment-related anomalies, production process anomalies, and resource and quality anomalies, respectively. It should also be noted that... The values ​​of ε can be 0.402 and 0.598, and the values ​​of U1, U2 and U3 can be 0.102, 0.129 and 0.117;

[0092] The priority values ​​H1, H2, and H3 are arranged in descending order and a signal is generated and transmitted to the dynamic adjustment unit.

[0093] As an optional embodiment, the urgency index Z1 of the first anomaly category, the urgency index Z2 of the second anomaly category, and the urgency index Z3 of the third anomaly category are obtained in the following ways:

[0094] According to the formula and The urgency indices Z1 for the first anomaly category, Z2 for the second anomaly category, and Z3 for the third anomaly category are calculated and obtained respectively. It should be noted that in this embodiment, the urgency index reflects the proximity of the anomaly's occurrence time; the closer the times, the higher the urgency.

[0095] The specific working principle of the dynamic adjustment unit is as follows:

[0096] Equipment-related anomalies: Immediately inspect and maintain the equipment, and adjust the production plan to avoid problems at T. E1 Use the device during the specified time period;

[0097] Production process anomalies: Monitor the production line, at T E2 Previously, process parameters were adjusted or the process was switched to a backup production line.

[0098] Resource and quality anomalies: in T E5 Previously, key materials were replenished or quality control measures were adjusted. It should be noted that through this priority-based response strategy, the smart factory can effectively handle and respond to various abnormal situations, ensuring production continuity and efficiency.

[0099] On the other hand, this invention also proposes a method for handling sudden obstacles in a smart workshop based on MES, including the following steps:

[0100] Step 1: Obtain data information from within the workshop, and use this information to monitor the production process in real time, and determine in real time whether there are any abnormalities or obstacles;

[0101] Step Two: Anticipate potential anomalies and unexpected obstacles in the smart workshop;

[0102] Step 3: Dynamically schedule workshop production based on the identification results for rapid response.

[0103] Working principle: It can combine multiple sets of data to deal with complex industrial environments, and avoid blind spots in data collection or inaccurate data due to sensor errors, data loss, etc. It can obtain predictions and intelligent workshop anomalies and obstacles with a certain degree of flexibility, and quickly perform intelligent processing after obtaining information on anomalies and obstacles to avoid losses caused by sudden obstacles.

[0104] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of this template.

Claims

1. An MES-based intelligent workshop sudden obstacle processing system, characterized in that, The system comprises a data acquisition module, a real-time monitoring module and a production scheduling module. The data acquisition module is configured to acquire data information in the workshop. The real-time monitoring module comprises an identification unit and a prediction unit. According to the formula The abnormal scores of the intelligent workshop are calculated, where j represents an abnormal category (1, 2, 3), Q j represents the jth abnormal category, n j is the total number of monitoring parameters of the jth abnormal category, P1 ij is a real-time monitoring value of the ith monitoring parameter in the jth abnormal category, P2 ij represents P1 ij is a preset normal value of the ith monitoring parameter in the jth abnormal category, ωj i is a weight coefficient of the ith monitoring parameter in the jth abnormal category; The identification unit is configured to monitor the production process in the workshop in real time according to the information of the data acquisition module, and to determine whether there is an abnormality or an obstacle in real time. The prediction unit is configured to predict potential abnormalities and sudden obstacles in the smart workshop in advance. The production scheduling module is configured to dynamically schedule the production of the workshop according to the identification result of the real-time monitoring module. 2.The MES-based intelligent workshop sudden obstacle processing system according to claim 1, wherein, For the first abnormality category, the first abnormality category monitoring parameter is specifically fault, overload and performance, and the weight coefficient corresponding to the first abnormality category monitoring parameter is ω11, ω12 and ω13. For the second abnormality category, the second abnormality category monitoring parameter is specifically production parameter deviation and process flow value, and the weight coefficient corresponding to the second abnormality category monitoring parameter is ω21 and ω22. For the third abnormality category, the third abnormality category monitoring parameter is specifically raw material supply and logistics, and the weight coefficient corresponding to the third abnormality category monitoring parameter is ω31 and ω32. 3.The MES-based intelligent workshop sudden obstacle processing system according to claim 1, wherein, The prediction unit specifically predicts equipment-related abnormalities, production process abnormalities and resource and quality abnormalities. Obtaining the average value T of the historical failure interval time of the equipment in the smart workshop E and the average value standard deviation σ of the historical failure interval time E ; According to the formula T E1 = T2 + T E ± (k * σ E ) to obtain the predicted time T E1 of the next device-related anomaly, where T2 is the current time, and k is a preset confidence level coefficient.

4. The MES-based intelligent workshop sudden obstacle processing system according to claim 3, characterized in that, For the production process abnormality prediction: obtaining a historical average value D of a deviation of a key production parameter of a smart factory product E and a standard deviation D2; According to the formula obtaining a predicted time T for the next production process anomaly E2 where T2 is the current time and β is a bias change rate value.

5. The MES-based intelligent workshop sudden obstacle processing system according to claim 4, characterized in that, For the resource and quality abnormality prediction: Obtaining the daily consumption rate C of the smart plant materials E ; According to the formula Obtaining a predicted time T of the next material shortage E3 where K2 is the current inventory and K1 is the safety stock; An abnormality rate R of a product quality of a smart workshop is acquired E ; According to the formula Obtaining the time T of quality abnormality occurrence in the next n products E4 wherein C1 is the current product quantity; According to the formula The predicted time T of the next resource and quality anomaly is calculated E5 wherein and The preset proportion coefficient is θ.

6. The MES-based intelligent workshop sudden obstacle processing system according to claim 5, characterized in that, The real-time monitoring module further comprises an environment adjustment unit. The first adjustment factor A1, the second adjustment factor A2 and the third adjustment factor A3 are obtained. According to the formula Tf1=T E1 (1+A1), Tf2=T E2 (1+A2), and Tf3=T E5 (1+A3), respectively, to obtain the adjusted prediction time of the next equipment-related anomaly Tf1, the next production process anomaly Tf2, and the next resource and quality anomaly Tf3.

7. The MES-based intelligent workshop sudden obstacle processing system according to claim 6, characterized in that, The first adjustment factor A1, the second adjustment factor A2 and the third adjustment factor A3 are obtained as follows: For the first adjustment factor A1 : according to the formula The fault frequency and the total running time are values of the equipment in the smart workshop, and θ1 is a preset proportion coefficient. For the second adjustment factor A2, according to the formula A2=(θ2*L), wherein L is the deviation rate of the key parameter in the production process, and θ2 is a preset proportion coefficient. For the third adjustment factor A3, according to the formula A3=(θ3*(S1+S2)), wherein S1 is the supply chain interruption rate, S2 is the quality influence rate, and θ3 is a preset proportion coefficient.

8. The MES-based intelligent workshop sudden obstacle processing system according to claim 1, characterized in that, The production scheduling module comprises a priority evaluation unit and a dynamic adjustment unit. The priority evaluation unit is configured to evaluate the priority of the abnormality category, which is conducive to subsequent obstacle response. The first abnormality category emergency index Z1, the second abnormality category emergency index Z2 and the third abnormality category emergency index Z3 are obtained. According to the formula and The priority values H1, H2 and H3 of the first, second and third abnormality categories are obtained, wherein ε is a preset weight coefficient, U1, U2 and U3 are preset influence indexes, respectively. The priority values H1, H2 and H3 are arranged in descending order, and a signal is transmitted to the dynamic adjustment unit.

9. The MES-based intelligent workshop sudden obstacle processing system according to claim 8, characterized in that, The specific acquisition manners of the emergency index Z1 of the first abnormality category, the emergency index Z2 of the second abnormality category, and the emergency index Z3 of the third abnormality category are as follows: According to the formula and The emergency index Z1 of the first abnormality category, the emergency index Z2 of the second abnormality category, and the emergency index Z3 of the third abnormality category are respectively calculated and acquired; The specific working manner of the dynamic adjustment unit is as follows: Equipment related anomalies: immediate equipment check and maintenance, adjust production plan to avoid using the equipment during the T E1 time period; Production process anomalies: Monitor the production line, at T E2 Previously, process parameters were adjusted or the production line was switched to a backup line; Resource and quality abnormalities: Before T E5 supplement critical materials or adjust quality control measures. 10.A method for handling an unexpected obstacle in an MES-based smart workshop, characterized in that, The specific working manner of the dynamic adjustment unit is as follows: Step one: data information in the workshop is acquired, the production process in the workshop is monitored in real time according to the information, and it is judged in real time whether there is an abnormality and an obstacle; Step two: potential abnormalities and sudden obstacles of the intelligent workshop are predicted in advance; Step three: dynamic scheduling of the workshop production is performed according to the identification result to respond quickly.

Images