MOM platform optimization system and method based on dynamic data fusion

Abstract

The invention relates to the technical field of MOM platforms, and discloses an MOM platform optimization system and method based on dynamic data fusion, and the system comprises a data collection layer; a data processing layer; a business logic layer; and the execution layer is in communication connection with the service logic layer, comprises the MES subsystem, the WMS subsystem, the QMS subsystem and the EAM subsystem, and is used for receiving and executing the collaborative optimization instruction set to realize dynamic adjustment and linkage of production resources. According to the MOM platform optimization system and method based on dynamic data fusion, heterogeneous source data from MES, WMS, QMS, EAM and SCADA are acquired in real time by setting the data acquisition layer, the data are cleaned, associated and integrated by combining the data processing layer, and real-time and unified production and operation situation data are generated, so that the problem of multi-source heterogeneous data information splitting in a traditional MOM platform is effectively solved, and the real-time and uniform production and operation situation data are obtained. The global visualization and real-time monitoring of the production state are realized, so that the fault response time is shortened by more than 30%, and the production halt loss is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of MOM platforms, and in particular to a MOM platform optimization system and method based on dynamic data fusion. Background Art

[0002] The MOM platform is a middleware system based on a messaging mechanism that supports communication and data exchange between different applications. As the manufacturing industry develops towards intelligence and flexibility, the manufacturing operations management (MOM) platform has become an important tool for enterprises to achieve production transparency and digital decision-making. Traditional MOM platforms achieve collaborative management of production planning, material flow, quality control, and equipment maintenance by integrating subsystems such as the manufacturing execution system (MES), warehouse management system (WMS), quality management system (QMS), equipment asset management system (EAM), and data acquisition and monitoring system (SCADA).

[0003] In practical applications, existing technologies still have significant defects:

[0004] 1. Although MES, WMS, QMS, EAM, SCADA, and other subsystems independently operate and collect data, there is a lack of effective integration mechanisms for multi-source heterogeneous data (such as order status, real-time equipment parameters, material inventory, and quality inspection results). Data from each system is stored independently and in different formats, resulting in information fragmentation. Managers need to manually retrieve and coordinate information across systems, resulting in delayed response to faults and increased production losses.

[0005] 2. Existing MES scheduling modules mostly generate plans based on static rules (such as fixed production capacity and preset priorities). They lack adaptability to dynamic disturbances such as order insertions and cancellations, material shortages, and equipment anomalies. This model is not only inefficient, but also lacks real-time global data support, so adjustment plans often compromise one aspect while neglecting another, making it difficult to achieve optimal resource allocation.

[0006] Therefore, it is necessary to propose a MOM platform optimization system and method based on dynamic data fusion to solve the above problems. Summary of the Invention

[0007] (1) Technical problems solved

[0008] In response to the shortcomings of the existing technology, the present invention provides a MOM platform optimization system and method based on dynamic data fusion, which has the advantages of dynamically integrating multi-dimensional data such as orders, equipment, materials, and quality, and automatically triggering an intelligent optimization mechanism for the linkage response of MES, WMS, QMS, and EAM, so as to improve the agility of the manufacturing system in responding to disturbances and the global resource utilization efficiency.

[0009] (2) Technical solution

[0010] To achieve the above objectives, the present invention provides the following technical solutions: a MOM platform optimization system and method based on dynamic data fusion, comprising:

[0011] Data collection layer: used to acquire heterogeneous source data from the manufacturing execution system (MES), warehouse management system (WMS), quality management system (QMS), equipment asset management system (EAM), and data acquisition and supervision system (SCADA) in real time. The heterogeneous source data includes at least one of order status, equipment operation status and parameters, material inventory and delivery status, and quality inspection results.

[0012] Data processing layer: communicates with the data acquisition layer and includes a data fusion module for cleaning, correlating and integrating the heterogeneous source data to generate real-time, unified production and operation status data;

[0013] Business logic layer: Communicates with the data processing layer and includes a dynamic scheduling engine for identifying production disturbances or optimization needs based on the real-time production and operation status data, and generating collaborative optimization instruction sets across the MES, WMS, QMS, and EAM;

[0014] Execution layer: communicates with the business logic layer, including the MES, WMS, QMS, and EAM subsystems, and is used to receive and execute the collaborative optimization instruction set to achieve dynamic adjustment and linkage of production resources.

[0015] Preferably, the SCADA real-time data acquired by the data acquisition layer includes at least one of equipment temperature, energy consumption, operating speed, and shutdown signal.

[0016] Preferably, the WMS data acquired by the data acquisition layer includes at least one of material completeness status, line warehouse inventory, and material batch information; the QMS data acquired by the data acquisition layer includes at least one of statistical process control (SPC) data, defect codes, and re-inspection instructions.

[0017] Preferably, the dynamic scheduling engine is configured to trigger an optimization calculation in response to a device failure signal or an order change signal, wherein the optimization calculation includes:

[0018] Based on current equipment availability, material availability and order priority, the MES is used to recalculate and adjust the production order sequence and schedule;

[0019] Based on the adjusted scheduling plan, the material distribution tasks and rhythm are synchronously updated through the WMS;

[0020] Automatically generate and dispatch maintenance work orders for faulty equipment through the EAM;

[0021] The QMS is used to identify, isolate or trigger re-inspection of relevant material batches produced during the failure period.

[0022] Preferably, the dynamic scheduling engine is also configured to predict equipment maintenance needs based on the real-time production and operation status data, and generate preventive maintenance work orders through the EAM. The business logic layer also includes a visualization module for displaying the real-time production and operation status data and the execution status of optimization instructions on a unified dashboard. The displayed information includes at least one of real-time production capacity, inventory turnover rate, and order delivery progress.

[0023] A MOM platform optimization system and method based on dynamic data fusion, comprising the following steps:

[0024] S1: Real-time data collection: Continuously collect heterogeneous source data from the manufacturing execution system (MES), warehouse management system (WMS), quality management system (QMS), equipment asset management system (EAM), and data acquisition and supervision system (SCADA). The heterogeneous source data includes at least one of order status, equipment operating status and parameters, material inventory and delivery status, and quality inspection results.

[0025] S2: Dynamic data fusion: Clean, correlate, and integrate the collected heterogeneous source data to generate real-time fused data that reflects the entire picture of current production operations;

[0026] S3: Dynamic Optimization Decision-Making: Based on the real-time fused data, it identifies disturbance events or optimization opportunities in the production process and generates collaborative optimization instruction sets for the MES, WMS, QMS, and EAM. The collaborative optimization instruction sets are designed to coordinate and adjust production scheduling, material distribution, quality control, and equipment maintenance activities.

[0027] S4: Instruction execution and feedback: The collaborative optimization instruction set is sent to the corresponding MES, WMS, QMS, and EAM subsystems for execution, and the execution results are fed back to the S2 step to form a closed-loop optimization.

[0028] Preferably, the SCADA real-time data collected in step S1 includes at least one of equipment temperature, energy consumption, operating rate, and shutdown signal, and the cleaning, association, and integration processing in step S2 includes: eliminating abnormal data points, associating data from different sources according to timestamps, equipment IDs, work order numbers, and material batch numbers, and aggregating to form a comprehensive status view at the equipment level, work order level, or production line level.

[0029] Preferably, the disturbance event identified in step S3 includes a sudden equipment failure or an urgent order insertion; and the generated collaborative optimization instruction set includes:

[0030] Instruct MES to recalculate and dynamically adjust the production work order sequence based on remaining equipment availability, material availability, and order priority;

[0031] Instruct the WMS to update the material completeness inspection tasks and line warehouse distribution plan based on the adjusted work order sequence;

[0032] Instruct EAM to automatically generate and dispatch maintenance work orders for faulty equipment;

[0033] Instruct the QMS to identify, isolate or trigger quality re-inspection of relevant material batches produced during the period when the failure occurred.

[0034] Preferably, the S3 step further includes: predicting potential equipment failures or maintenance requirements based on equipment operating parameters and historical maintenance records in the real-time fusion data, and generating optimization instructions to instruct the EAM to perform preventive maintenance.

[0035] Preferably, the method further includes step S5: visual display, visually presenting the real-time fusion data generated by step S2, the disturbance or optimization information identified by step S3, and the instruction execution status of step S4 on a unified dashboard.

[0036] (3) Beneficial effects

[0037] Compared with the prior art, the present invention provides a MOM platform optimization system and method based on dynamic data fusion, which has the following beneficial effects:

[0038] 1. This MOM platform optimization system and method based on dynamic data fusion sets up a data acquisition layer to obtain heterogeneous source data (such as order status, equipment operating parameters, material inventory, quality inspection results, etc.) from MES, WMS, QMS, EAM and SCADA in real time, and combines it with a data processing layer to clean, correlate and integrate the data to generate real-time, unified production and operation status data. It effectively solves the problem of information fragmentation of multi-source heterogeneous data in traditional MOM platforms, realizes global visualization and real-time monitoring of production status, thereby shortening fault response time by more than 30% and reducing production downtime losses.

[0039] 2. This MOM platform optimization system and method based on dynamic data fusion uses the dynamic scheduling engine in the business logic layer to identify production disturbances (such as equipment failures or order changes) or optimization needs based on real-time production and operation status data, and generates a collaborative optimization instruction set across MES, WMS, QMS, and EAM, which jointly adjusts production scheduling, material distribution, quality control, and equipment maintenance activities, significantly improving adaptability to dynamic disturbances, increasing resource utilization by more than 20%, and ensuring on-time delivery of orders.

[0040] 3. This MOM platform optimization system and method based on dynamic data fusion uses a dynamic scheduling engine to predict equipment maintenance needs (based on real-time equipment parameters and historical records) and generate preventive maintenance work orders. At the same time, a visualization module displays real-time data, optimization instructions, and execution status (such as production capacity and inventory turnover) on a unified dashboard, achieving predictive maintenance and transparent management, reducing equipment failure rates by 15%, and improving production reliability and management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Flowchart of the MOM platform optimization system structure of the present invention;

[0042] Figure 2 It is a structural flow chart of the MOM platform optimization method of the present invention;

[0043] Figure 3 This is a schematic diagram of the collaborative optimization instruction set structure of the present invention. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0045] See also Figure 1-3 , a MOM platform optimization system and method based on dynamic data fusion, comprising:

[0046] Data collection layer: used to acquire heterogeneous source data from the manufacturing execution system (MES), warehouse management system (WMS), quality management system (QMS), equipment asset management system (EAM), and data acquisition and supervision system (SCADA) in real time. The heterogeneous source data includes at least one of order status, equipment operation status and parameters, material inventory and delivery status, and quality inspection results.

[0047] Data processing layer: communicates with the data acquisition layer and includes a data fusion module for cleaning, correlating and integrating the heterogeneous source data to generate real-time, unified production and operation status data;

[0048] Business logic layer: Communicates with the data processing layer and includes a dynamic scheduling engine for identifying production disturbances or optimization needs based on the real-time production and operation status data, and generating collaborative optimization instruction sets across the MES, WMS, QMS, and EAM;

[0049] Execution layer: communicates with the business logic layer, including the MES, WMS, QMS, and EAM subsystems, and is used to receive and execute the collaborative optimization instruction set to achieve dynamic adjustment and linkage of production resources.

[0050] A MOM platform optimization system and method based on dynamic data fusion, comprising the following steps:

[0051] S1: Real-time data collection: Continuously collect heterogeneous source data from the manufacturing execution system (MES), warehouse management system (WMS), quality management system (QMS), equipment asset management system (EAM), and data acquisition and supervision system (SCADA). The heterogeneous source data includes at least one of order status, equipment operating status and parameters, material inventory and delivery status, and quality inspection results.

[0052] S2: Dynamic data fusion: Clean, correlate, and integrate the collected heterogeneous source data to generate real-time fused data that reflects the entire picture of current production operations;

[0053] S3: Dynamic Optimization Decision-Making: Based on the real-time fused data, it identifies disturbance events or optimization opportunities in the production process and generates collaborative optimization instruction sets for the MES, WMS, QMS, and EAM. The collaborative optimization instruction sets are designed to coordinate and adjust production scheduling, material distribution, quality control, and equipment maintenance activities.

[0054] S4: Instruction execution and feedback: The collaborative optimization instruction set is sent to the corresponding MES, WMS, QMS, and EAM subsystems for execution, and the execution results are fed back to the S2 step to form a closed-loop optimization.

[0055] In the case implementation, the data acquisition layer: acquires heterogeneous source data from MES, WMS, QMS, EAM and SCADA in real time through API interfaces and IoT sensors; specifically, SCADA real-time data includes equipment temperature, energy consumption, operating speed, and shutdown signals (according to claim 2); WMS data includes material completeness status, line-side warehouse inventory, and material batch information; QMS data includes statistical process control (SPC) data, defect codes, and re-inspection instructions (according to claim 3); the data acquisition frequency is once per second to ensure real-time performance.

[0056] In the case implementation, the data processing layer: communicates with the data acquisition layer through a message queue (such as Kafka), includes a data fusion module, and uses the Spark framework to clean (eliminate abnormal data points), associate (based on timestamps, equipment IDs, work order numbers, material batch numbers) and integrate (aggregate into equipment-level, work order-level or production line-level views) heterogeneous source data to generate real-time production operation status data, which is stored in a time series database.

[0057] In the case implementation, the business logic layer: is connected to the data processing layer through a RESTful API, and includes a dynamic scheduling engine and a visualization module; the dynamic scheduling engine is configured to respond to equipment failure signals or order change signals (according to claim 4), triggering optimization calculations: based on current equipment availability, material availability and order priority, recalculate the production work order sequence through MES; synchronously instruct WMS to update material distribution tasks; instruct EAM to dispatch maintenance work orders; instruct QMS to mark or re-inspect material batches during the failure period; at the same time, the engine predicts maintenance needs based on equipment operating parameters and historical maintenance records (such as equipment temperature trends) and generates preventive maintenance work orders (according to claims 5 and 9); the visualization module uses Tableau tools to display real-time production capacity, inventory turnover, order delivery progress and instruction execution status on a unified dashboard.

[0058] In the case implementation, the execution layer: connected to the business logic layer through the enterprise service bus (ESB), including MES, WMS, QMS, and EAM subsystems, receives and executes collaborative optimization instruction sets to achieve dynamic adjustments; for example, MES adjusts production scheduling plans; WMS optimizes material distribution rhythm; EAM executes maintenance work orders; QMS handles quality review.

[0059] In the case implementation, take the automobile manufacturing production line as an example: when SCADA monitors the sudden shutdown of assembly line equipment (disturbance event), the data acquisition layer collects the shutdown signal and the associated WMS material batch information in real time; the data processing layer cleans and correlates the data to generate a device-level fault view; the business logic layer's dynamic scheduling engine identifies the fault, instructs the MES to reschedule the work order sequence, the WMS to update the material distribution plan, the EAM to dispatch maintenance work orders, and the QMS to isolate the product batches during the fault period; the execution layer responds in a coordinated manner, reducing the recovery time from 2 hours to 30 minutes.

[0060] In summary, the MOM platform optimization system and method based on dynamic data fusion acquires heterogeneous source data (such as order status, equipment operating parameters, material inventory, quality inspection results, etc.) from MES, WMS, QMS, EAM and SCADA in real time by setting up a data acquisition layer, and combines the data processing layer to clean, associate and integrate the data to generate real-time and unified production operation status data, effectively solving the problem of information fragmentation of multi-source heterogeneous data in traditional MOM platforms, and realizing global visualization and real-time monitoring of production status, thereby shortening fault response time by more than 30% and reducing production stoppage losses.

[0061] In addition, through the dynamic scheduling engine in the business logic layer, production disturbances (such as equipment failures or order changes) or optimization needs are identified based on real-time production operation status data, and a collaborative optimization instruction set across MES, WMS, QMS, and EAM is generated to jointly adjust production scheduling, material distribution, quality control, and equipment maintenance activities, significantly improving adaptability to dynamic disturbances, increasing resource utilization by more than 20%, and ensuring on-time delivery of orders.

[0062] In addition, the dynamic scheduling engine predicts equipment maintenance needs (based on real-time equipment parameters and historical records) and generates preventive maintenance work orders. At the same time, the visualization module displays real-time data, optimization instructions and execution status (such as production capacity and inventory turnover rate) on a unified dashboard, realizing predictive maintenance and transparent management, reducing equipment failure rate by 15% and improving production reliability and management efficiency.

[0063] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0064] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A MOM platform optimization system and method based on dynamic data fusion, characterized in that: include: Data collection layer: used to acquire heterogeneous source data from the manufacturing execution system (MES), warehouse management system (WMS), quality management system (QMS), equipment asset management system (EAM), and data acquisition and supervision system (SCADA) in real time. The heterogeneous source data includes at least one of order status, equipment operation status and parameters, material inventory and delivery status, and quality inspection results. Data processing layer: communicates with the data acquisition layer and includes a data fusion module for cleaning, correlating and integrating the heterogeneous source data to generate real-time, unified production and operation status data; Business logic layer: Communicates with the data processing layer and includes a dynamic scheduling engine for identifying production disturbances or optimization needs based on the real-time production and operation status data, and generating collaborative optimization instruction sets across the MES, WMS, QMS, and EAM; Execution layer: communicates with the business logic layer, including the MES, WMS, QMS, and EAM subsystems, and is used to receive and execute the collaborative optimization instruction set to achieve dynamic adjustment and linkage of production resources.

2. A MOM platform optimization system and method based on dynamic data fusion according to claim 1, characterized in that: The SCADA real-time data acquired by the data acquisition layer includes at least one of equipment temperature, energy consumption, operating speed, and shutdown signal.

3. A MOM platform optimization system and method based on dynamic data fusion according to claim 1, characterized in that: The WMS data acquired by the data collection layer includes at least one of material completeness status, line warehouse inventory, and material batch information; the QMS data acquired by the data collection layer includes at least one of statistical process control (SPC) data, defect codes, and re-inspection instructions.

4. A MOM platform optimization system and method based on dynamic data fusion according to claim 1, characterized in that: The dynamic scheduling engine is configured to trigger an optimization calculation in response to an equipment failure signal or an order change signal, wherein the optimization calculation includes: Based on current equipment availability, material availability and order priority, the MES is used to recalculate and adjust the production order sequence and schedule; Based on the adjusted scheduling plan, the material distribution tasks and rhythm are synchronously updated through the WMS; Automatically generate and dispatch maintenance work orders for faulty equipment through the EAM; The QMS is used to identify, isolate or trigger re-inspection of relevant material batches produced during the failure period.

5. A MOM platform optimization system and method based on dynamic data fusion according to claim 1, characterized in that: The dynamic scheduling engine is also configured to predict equipment maintenance needs based on the real-time production and operation status data, and generate preventive maintenance work orders through the EAM. The business logic layer also includes a visualization module for displaying the real-time production and operation status data and the execution status of optimization instructions on a unified dashboard. The displayed information includes at least one of real-time production capacity, inventory turnover rate, and order delivery progress.

6. A MOM platform optimization system and method based on dynamic data fusion, characterized in that: The following steps are involved: S1: Real-time data collection: Continuously collect heterogeneous source data from the manufacturing execution system (MES), warehouse management system (WMS), quality management system (QMS), equipment asset management system (EAM), and data acquisition and supervision system (SCADA). The heterogeneous source data includes at least one of order status, equipment operating status and parameters, material inventory and delivery status, and quality inspection results. S2: Dynamic data fusion: Clean, correlate, and integrate the collected heterogeneous source data to generate real-time fused data that reflects the entire picture of current production operations; S3: Dynamic Optimization Decision-Making: Based on the real-time fused data, it identifies disturbance events or optimization opportunities in the production process and generates collaborative optimization instruction sets for the MES, WMS, QMS, and EAM. The collaborative optimization instruction sets are designed to coordinate and adjust production scheduling, material distribution, quality control, and equipment maintenance activities. S4: Instruction execution and feedback: The collaborative optimization instruction set is sent to the corresponding MES, WMS, QMS, and EAM subsystems for execution, and the execution results are fed back to the S2 step to form a closed-loop optimization.

7. A MOM platform optimization method based on dynamic data fusion according to claim 6, characterized in that: The SCADA real-time data collected in step S1 includes at least one of equipment temperature, energy consumption, operating rate, and shutdown signal. The cleaning, association, and integration processing in step S2 includes: eliminating abnormal data points, associating data from different sources according to timestamps, equipment IDs, work order numbers, and material batch numbers, and aggregating to form a comprehensive status view at the equipment level, work order level, or production line level.

8. A MOM platform optimization method based on dynamic data fusion according to claim 6, characterized in that: The disturbance event identified in step S3 includes sudden equipment failure or emergency order insertion; The generated collaborative optimization instruction set includes: Instruct MES to recalculate and dynamically adjust the production work order sequence based on remaining equipment availability, material availability, and order priority; Instruct the WMS to update the material completeness inspection tasks and line warehouse distribution plan based on the adjusted work order sequence; Instruct EAM to automatically generate and dispatch maintenance work orders for faulty equipment; Instruct the QMS to identify, isolate or trigger quality re-inspection of relevant material batches produced during the period when the failure occurred.

9. A MOM platform optimization method based on dynamic data fusion according to claim 6, characterized in that, The S3 step also includes: predicting potential equipment failures or maintenance requirements based on equipment operating parameters and historical maintenance records in the real-time fusion data, and generating optimization instructions to instruct the EAM to perform preventive maintenance.

10. A MOM platform optimization method based on dynamic data fusion according to claim 6, characterized in that: The method further includes step S5: visual display, visually presenting the real-time fusion data generated by step S2, the disturbance or optimization information identified by step S3, and the instruction execution status of step S4 on a unified dashboard.

Images