Distributed intelligent production scheduling decision-making system based on cloud computing

Abstract

The invention relates to the technical field of production scheduling of manufacturing workshops, in particular to a distributed intelligent production scheduling decision-making system based on cloud computing. The system is composed of a cloud computing platform, a data acquisition module, a data processing module, an intelligent production scheduling engine and a distributed execution control module. The problems of performance bottleneck, data acquisition limitation, lack of flexibility and adaptability of a production scheduling scheme and the like in a traditional production scheduling system are solved, intelligent distribution and scheduling of production tasks can be realized through fusion application of advanced technologies such as cloud computing, big data and artificial intelligence, the production efficiency and the product quality are improved, and the production cost is reduced. And greater economic benefits and social benefits are created for enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of production scheduling in a manufacturing workshop, and in particular to a distributed intelligent production scheduling decision system based on cloud computing. Background Art

[0002] With the rapid development of the manufacturing industry and increasingly fierce market competition, workshop production scheduling has become one of the key factors restricting enterprise production efficiency, cost control and market competitiveness. Traditional production scheduling methods mainly rely on manual experience and simple calculation tools, which are difficult to cope with the complex and changeable production environment and rapidly changing customer needs in modern manufacturing. Therefore, a distributed intelligent scheduling decision system based on cloud computing to realize intelligent, automated and efficient scheduling of production tasks is of great significance to improving production efficiency, reducing production costs and improving product quality.

[0003] Workshop production scheduling is a typical combinatorial optimization problem, involving the allocation of production tasks, resource scheduling, time arrangement and other aspects. Traditional methods often rely on manual experience for production scheduling, which is not only inefficient but also prone to errors, leading to problems such as extended production cycle, waste of resources, and unstable product quality. There are mainly the following limitations:

[0004] (1) Excessive manual intervention: Traditional production scheduling relies on manual experience and judgment, requiring schedulers to make real-time scheduling based on the actual situation at the production site. However, with the expansion of production scale and the increase in production complexity, manual scheduling is not only inefficient, but also prone to misjudgment and omissions, resulting in poor execution of production plans.

[0005] (2) Lack of real-time data support: Traditional production scheduling methods often rely on paper records or simple spreadsheets to record production data. These data are not only not updated in a timely manner, but are also prone to errors. The lack of real-time and accurate production data support makes it difficult to make scientific and reasonable production scheduling decisions.

[0006] (3) Difficulty in coping with complex environments: In modern manufacturing, the production environment is complex and changeable, involving the collaborative operations of multiple machines, equipment, and personnel. Traditional production scheduling methods are difficult to effectively deal with the various uncertainties and conflicts in such a complex environment, which leads to problems in the execution of production plans.

[0007] (4) Low resource utilization: Traditional production scheduling methods often fail to fully utilize existing resources, resulting in idleness and waste of resources such as machines, equipment, and personnel. This not only increases production costs, but also reduces the market competitiveness of enterprises. Summary of the invention

[0008] The present invention proposes a distributed intelligent production scheduling decision-making system based on cloud computing, which solves the problems of performance bottlenecks, data collection limitations, lack of flexibility and adaptability of production scheduling plans, etc. in traditional production scheduling systems. Through the integrated application of advanced technologies such as cloud computing, big data, and artificial intelligence, it can realize the intelligent allocation and scheduling of production tasks, improve production efficiency and product quality, and create greater economic and social benefits for enterprises.

[0009] The technical solution adopted by the present invention is: a distributed intelligent production scheduling decision system based on cloud computing, which is composed of a cloud computing platform, a data acquisition module, a data processing module, an intelligent production scheduling engine, and a distributed execution control module.

[0010] The cloud computing platform is used to provide computing resources, storage resources and network resources, and supports distributed computing and data exchange;

[0011] The data acquisition module is connected to various sensors, actuators and information systems on the production line to collect production data, order information and resource status in real time;

[0012] The data processing module is set up on the cloud computing platform to clean, integrate and pre-process the collected data to generate a data set that can be used for decision analysis;

[0013] The intelligent production scheduling engine uses optimization algorithms and machine learning models to automatically generate efficient and flexible production scheduling solutions based on processed data, realizing intelligent allocation and scheduling of production tasks;

[0014] The distributed execution control module sends control instructions to each execution unit of the production line according to the scheduling plan generated by the intelligent production scheduling engine, so as to realize the distributed execution and monitoring of production tasks.

[0015] As a further improvement of the present invention, the cloud computing platform supports elastic expansion and can dynamically adjust computing resources, storage resources and network resources according to load changes of production tasks, ensuring that the system can still operate stably under high concurrency and large data volumes; the cloud computing platform has built-in security mechanisms and data backup strategies, and ensures data security and privacy protection through data encryption and access control.

[0016] As a further improvement of the present invention, the data acquisition module can capture data from multiple sources of the production line in real time and accurately, including data from temperature sensors, pressure sensors, flow sensors, and order, inventory, and personnel status data in the ERP (Enterprise Resource Planning) information system and the MES (Manufacturing Execution System) information system.

[0017] As a further improvement of the present invention, the data collected by the data acquisition module is securely and efficiently transmitted to the cloud computing platform through standard interface protocols, including MQTT, OPC UA, and HTTP.

[0018] As a further improvement of the present invention, missing value filling, outlier detection and processing, and data type conversion technology are used in the data cleaning process to ensure data quality and improve the accuracy of subsequent decision analysis; in the data integration process, data from different data sources and in different formats are unified to form a structured data set, which is convenient for the intelligent production scheduling engine to perform efficient analysis.

[0019] As a further improvement of the present invention, the intelligent production scheduling engine is composed of a task decomposition subunit, a resource allocation subunit, a time optimization subunit, and a conflict resolution subunit.

[0020] The task decomposition subunit is responsible for breaking down complex production tasks into multiple manageable subtasks, so that each subtask can be executed independently and are interrelated;

[0021] The resource allocation subunit allocates the most appropriate resources, including machines, manpower, and materials, to each subtask according to the actual capacity and resource status of the production line;

[0022] The time optimization subunit optimizes the execution order and time of each subtask to minimize the production cycle and improve production efficiency;

[0023] The conflict resolution subunit handles possible resource conflicts and task conflicts in a complex manner to ensure smooth execution of the production plan.

[0024] As a further improvement of the present invention, the intelligent production scheduling engine adopts a variety of optimization algorithms, including genetic algorithms, simulated annealing algorithms, and particle swarm optimization algorithms, combined with machine learning models, including neural networks and decision trees, to deeply mine and analyze production data to find the optimal production scheduling solution.

[0025] As a further improvement of the present invention, the distributed execution control module adopts a microservice architecture to split the control logic into multiple independent service units. Each service unit is responsible for controlling a part of the execution units on the production line, including machines, conveyor belts, and robots, to achieve efficient and flexible collaborative operations; each service unit can receive scheduling instructions generated by the intelligent scheduling engine in real time, and accurately control the operation of the corresponding execution unit according to the instruction content, including starting, stopping, and adjusting parameters; at the same time, the service units exchange information through a lightweight communication protocol to ensure the coordinated operation of the entire production line.

[0026] As a further improvement of the present invention, the distributed execution control module has a real-time monitoring function and a feedback adjustment mechanism, which can collect the operating status data of each execution unit on the production line in real time, including the machine's operating speed, fault conditions, and material consumption, and promptly feed back these data to the intelligent production scheduling engine; the intelligent production scheduling engine can adjust the production scheduling plan in time based on these feedback data, optimize resource allocation, reduce waste and delays in the production process, and improve production efficiency and product quality.

[0027] Beneficial effects of the present invention: (1) Improving production efficiency: The present invention can dynamically adjust the production plan according to the actual situation of the production line and order requirements in real time through the automated scheduling and optimization algorithm of the intelligent production scheduling engine, thereby ensuring rapid response and efficient execution of production tasks, reducing production cycles, and improving production efficiency.

[0028] (2) Optimizing resource allocation: The system of the present invention can collect production data, order information and resource status in real time, and allocate the most appropriate resources to production tasks through intelligent analysis and optimization algorithms, thereby reducing idleness and waste of resources and improving resource utilization.

[0029] (3) Enhanced flexibility and adaptability: The intelligent production scheduling engine of the present invention can cope with various uncertainties and conflicts in the production process, and ensure the smooth execution of the production plan by adjusting and optimizing the production scheduling plan in real time; at the same time, it supports a variety of optimization algorithms and machine learning models, and can continuously learn and optimize to improve the flexibility and adaptability of the system.

[0030] (4) Improving product quality: The present invention can reduce errors and defective products in the production process and improve product quality and customer satisfaction by real-time monitoring of the operating status of each execution unit on the production line and timely feedback to adjust the production schedule.

[0031] (5) Reducing production costs: The present invention can significantly reduce the production costs of enterprises and improve economic benefits by improving production efficiency and resource utilization, reducing waste and delays. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a system block diagram of a distributed intelligent production scheduling decision system based on cloud computing in the present invention. DETAILED DESCRIPTION

[0033] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] The present invention provides a distributed intelligent production scheduling decision system based on cloud computing, which consists of a cloud computing platform, a data acquisition module, a data processing module, an intelligent production scheduling engine, and a distributed execution control module. The cloud computing platform is used to provide computing resources, storage resources and network resources, and supports distributed computing and data exchange; the data acquisition module is connected to various sensors, actuators and information systems on the production line, and collects production data, order information, and resource status in real time; the data processing module is arranged on the cloud computing platform, cleans, integrates and pre-processes the collected data, and generates a data set that can be used for decision analysis; the intelligent production scheduling engine adopts optimization algorithms and machine learning models, and automatically generates efficient and flexible production scheduling plans based on processed data, so as to realize intelligent allocation and scheduling of production tasks; the distributed execution control module sends control instructions to each execution unit of the production line according to the scheduling plan generated by the intelligent production scheduling engine, so as to realize distributed execution and monitoring of production tasks.

[0035] The cloud computing platform described in the present invention supports elastic expansion, and can dynamically adjust computing resources, storage resources and network resources according to load changes of production tasks, ensuring that the system can still operate stably under high concurrency and large data volumes; the cloud computing platform has built-in security mechanisms and data backup strategies, and ensures data security and privacy protection through data encryption and access control.

[0036] The data acquisition module of the present invention can capture data from multiple sources of the production line in real time and accurately, including data from temperature sensors, pressure sensors, flow sensors, and order, inventory, and personnel status data in the ERP (Enterprise Resource Planning) information system and the MES (Manufacturing Execution System) information system. The data collected by the data acquisition module is safely and efficiently transmitted to the cloud computing platform through standard interface protocols, including MQTT, OPC UA, and HTTP.

[0037] In the data cleaning process described in the present invention, missing value filling, outlier detection and processing, and data type conversion technology are used to ensure data quality and improve the accuracy of subsequent decision-making analysis; in the data integration process, data from different data sources and in different formats are unified to form a structured data set, which is convenient for the intelligent production scheduling engine to perform efficient analysis.

[0038] The intelligent production scheduling engine described in the present invention is composed of a task decomposition subunit, a resource allocation subunit, a time optimization subunit, and a conflict resolution subunit. The task decomposition subunit is responsible for breaking down complex production tasks into multiple manageable subtasks so that each subtask can be executed independently and are interrelated; the resource allocation subunit allocates the most appropriate resources, including machines, manpower, and materials, to each subtask according to the actual capacity and resource status of the production line; the time optimization subunit optimizes the execution order and time of each subtask to minimize the production cycle and improve production efficiency; the conflict resolution subunit handles possible resource conflicts and task conflicts in a complex manner to ensure the smooth execution of the production plan. The intelligent production scheduling engine uses a variety of optimization algorithms, including genetic algorithms, simulated annealing algorithms, and particle swarm optimization algorithms, combined with machine learning models, including neural networks and decision trees, to deeply mine and analyze production data to find the optimal production scheduling solution.

[0039] The distributed execution control module described in the present invention adopts a microservice architecture, splitting the control logic into multiple independent service units, each service unit is responsible for controlling a part of the execution units on the production line, including machines, conveyor belts, and manipulators, to achieve efficient and flexible collaborative operations; each service unit can receive the scheduling instructions generated by the intelligent production scheduling engine in real time, and accurately control the operation of the corresponding execution unit according to the content of the instructions, including starting, stopping, and adjusting parameters; at the same time, each service unit exchanges information through a lightweight communication protocol to ensure the coordinated operation of the entire production line. The distributed execution control module has a real-time monitoring function and a feedback adjustment mechanism, which can collect the operating status data of each execution unit on the production line in real time, including the machine's operating speed, fault conditions, and material consumption, and feed back these data to the intelligent production scheduling engine in a timely manner; the intelligent production scheduling engine can adjust the production scheduling plan in a timely manner based on these feedback data, optimize resource allocation, reduce waste and delays in the production process, and improve production efficiency and product quality.

[0040] Embodiment 1:

[0041] In this embodiment, it is assumed that a certain automobile manufacturer faces urgent delivery requirements for multiple production orders, and at the same time, the machines and human resources on the production line are limited, and production tasks need to be arranged efficiently and accurately. Therefore, a distributed intelligent production scheduling decision system based on cloud computing is introduced in the present invention.

[0042] First, the data acquisition module collects real-time production data such as temperature, pressure, flow, and order, inventory, and personnel status information in the ERP and MES systems through various sensors and information systems on the production line. These data are safely and efficiently transmitted to the cloud computing platform through the MQTT protocol.

[0043] On the cloud computing platform, the data processing module cleans, integrates and preprocesses the received data. Missing values ​​are filled through reasonable prediction models, abnormal values ​​are removed or corrected after detection and processing, and data types are uniformly converted to ensure that data quality meets the needs of decision analysis. The processed data is organized into a structured data set for use by the intelligent production scheduling engine.

[0044] After the intelligent production scheduling engine receives the data set, the task decomposition subunit first breaks down the complex production task into multiple subtasks, such as stamping, welding, painting, and assembly. Then, the resource allocation subunit allocates the most suitable machines, manpower, and materials to each subtask based on the actual capacity and resource status of the production line. The time optimization subunit further optimizes the execution order and time of each subtask to minimize the production cycle and improve production efficiency. During the allocation process, the conflict resolution subunit is responsible for handling possible resource conflicts and task conflicts to ensure the smooth execution of the production plan.

[0045] The intelligent production scheduling engine uses genetic algorithms and neural network models to deeply mine and analyze production data, taking into account multiple factors such as order priority, machine load, and material supply, to generate an efficient and flexible production scheduling plan. The plan is sent to the distributed execution control module, which splits the control logic into multiple independent service units based on the microservice architecture, and controls different execution units on the production line respectively.

[0046] Each service unit receives scheduling instructions in real time and accurately controls the operation of the corresponding execution unit. At the same time, they exchange information through lightweight communication protocols to ensure the coordinated operation of the entire production line. During the execution process, the distributed execution control module monitors the operating status of each execution unit on the production line in real time and feeds back the data to the intelligent production scheduling engine in a timely manner. The intelligent production scheduling engine adjusts the production scheduling plan based on the feedback data, optimizes resource allocation, and reduces waste and delays.

[0047] Through the implementation of the present invention, the automobile manufacturer has successfully dealt with various uncertainties and conflicts in the production process, improved production efficiency and product quality, and reduced production costs. At the same time, the flexibility and adaptability of the system have also been significantly improved, providing strong support for the sustainable development of the enterprise.

[0048] Embodiment 2:

[0049] In this embodiment, consider the scenario of an electronic manufacturing enterprise, which focuses on the production of high-precision electronic components and faces the challenge of small batch and multi-variety production. Due to the particularity of the products and the diversity of customer needs, it is necessary to respond quickly to market changes and flexibly adjust the production plan. Therefore, a distributed intelligent production scheduling decision system based on cloud computing is introduced in the present invention.

[0050] First, the data acquisition module collects various data related to the production of electronic components through various sensors and information systems on the production line, including environmental parameters such as temperature, humidity, cleanliness, and order details, material inventory, employee skills, etc. in the ERP and MES systems. These data are securely transmitted to the cloud computing platform through the OPC UA protocol to ensure the real-time and security of data transmission.

[0051] On the cloud computing platform, the data processing module performs more sophisticated cleaning and integration of data in view of the particularity of electronic component production. In particular, sensitive algorithms are used to detect and process tiny outliers to ensure the accuracy of production data. At the same time, customized preprocessing of data is performed according to the production process requirements of electronic components to meet the analysis needs of the intelligent production scheduling engine.

[0052] After receiving the processed data set, the intelligent production scheduling engine combines the characteristics of electronic component production to perform a more detailed breakdown of the production tasks. For example, the production process is subdivided into multiple subtasks such as cleaning, photolithography, etching, and packaging, and the dependencies and constraints between different subtasks are taken into account. In the resource allocation stage, in addition to considering the allocation of machines, manpower, and materials, special attention is also paid to the control of the production environment, such as the use and management of clean rooms.

[0053] When optimizing production schedules, the time optimization subunit fully considers the periodicity and volatility of electronic component production, and achieves the balance of the production line and maximizes efficiency by adjusting the production rhythm and batch size. At the same time, the conflict resolution subunit has developed more flexible solutions for possible resource conflicts and task conflicts, such as temporarily adjusting production plans and borrowing external resources.

[0054] In the implementation of the distributed execution control module, special attention is paid to the coordination and cooperation between the service units. Through lightweight communication protocols and real-time data sharing mechanisms, each service unit can quickly respond to changes in the production line and make corresponding adjustments. At the same time, the real-time monitoring function ensures that any abnormalities in the production process can be discovered and handled in a timely manner, thereby ensuring the stable operation of the production line.

[0055] Through the implementation of the present invention, the electronic manufacturing enterprise successfully solved the scheduling problem in small-batch and multi-variety production, improved production efficiency and product quality, and shortened the order delivery cycle. At the same time, the intelligence and automation level of the system have also been significantly improved, providing strong support for the transformation and upgrading of the enterprise and the improvement of its market competitiveness.

[0056] In summary, the distributed intelligent production scheduling decision-making system based on cloud computing of the present invention realizes the intelligent allocation and scheduling of production tasks through the integrated application of advanced technologies such as cloud computing, big data, and artificial intelligence, improves production efficiency and product quality, reduces production costs, and creates greater economic and social benefits for enterprises.

[0057] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed intelligent production scheduling decision system based on cloud computing, characterized by: It consists of cloud computing platform, data collection module, data processing module, intelligent production scheduling engine and distributed execution control module. The cloud computing platform is used to provide computing resources, storage resources and network resources, and supports distributed computing and data exchange; The data acquisition module is connected to various sensors, actuators and information systems on the production line to collect production data, order information and resource status in real time; The data processing module is set up on the cloud computing platform to clean, integrate and pre-process the collected data to generate a data set that can be used for decision analysis; The intelligent production scheduling engine uses optimization algorithms and machine learning models to automatically generate efficient and flexible production scheduling solutions based on processed data, realizing intelligent allocation and scheduling of production tasks; The distributed execution control module sends control instructions to each execution unit of the production line according to the scheduling plan generated by the intelligent production scheduling engine, so as to realize the distributed execution and monitoring of production tasks.

2. According to the distributed intelligent production scheduling decision system based on cloud computing in claim 1, it is characterized by: The cloud computing platform supports elastic expansion and can dynamically adjust computing resources, storage resources and network resources according to load changes of production tasks, ensuring that the system can still operate stably under high concurrency and large data volumes; the cloud computing platform has built-in security mechanisms and data backup strategies, and ensures data security and privacy protection through data encryption and access control.

3. The distributed intelligent production scheduling decision system based on cloud computing according to claim 1 is characterized by: The data acquisition module can capture data from multiple sources of the production line in real time and accurately, including data from temperature sensors, pressure sensors, flow sensors, and order, inventory, and personnel status data in the ERP (Enterprise Resource Planning) information system and MES (Manufacturing Execution System) information system.

4. The distributed intelligent production scheduling decision system based on cloud computing according to claim 3 is characterized by: The data collected by the data acquisition module is securely and efficiently transmitted to the cloud computing platform through standard interface protocols, including MQTT, OPC UA, and HTTP.

5. The distributed intelligent production scheduling decision system based on cloud computing according to claim 1 is characterized by: The data cleaning process uses missing value filling, outlier detection and processing, and data type conversion technology to ensure data quality and improve the accuracy of subsequent decision analysis; During the data integration process, data from different data sources and in different formats are processed in a unified manner to form a structured data set, which is convenient for the intelligent production scheduling engine to perform efficient analysis.

6. The distributed intelligent production scheduling decision system based on cloud computing according to claim 1 is characterized by: The intelligent production scheduling engine consists of a task decomposition subunit, a resource allocation subunit, a time optimization subunit, and a conflict resolution subunit. The task decomposition subunit is responsible for breaking down complex production tasks into multiple manageable subtasks, so that each subtask can be executed independently and are interrelated; The resource allocation subunit allocates the most appropriate resources, including machines, manpower, and materials, to each subtask according to the actual capacity and resource status of the production line; The time optimization subunit optimizes the execution order and time of each subtask to minimize the production cycle and improve production efficiency; The conflict resolution subunit handles possible resource conflicts and task conflicts in a complex manner to ensure smooth execution of the production plan.

7. The distributed intelligent production scheduling decision system based on cloud computing according to claim 6 is characterized by: The intelligent production scheduling engine uses a variety of optimization algorithms, including genetic algorithms, simulated annealing algorithms, and particle swarm optimization algorithms, combined with machine learning models, including neural networks and decision trees, to deeply mine and analyze production data to find the optimal production scheduling solution.

8. The distributed intelligent production scheduling decision system based on cloud computing according to claim 1 is characterized by: The distributed execution control module adopts a microservice architecture, splitting the control logic into multiple independent service units. Each service unit is responsible for controlling a part of the execution units on the production line, including machines, conveyor belts, and robots, to achieve efficient and flexible collaborative operations. Each service unit can receive scheduling instructions generated by the intelligent production scheduling engine in real time, and accurately control the operation of the corresponding execution unit according to the content of the instructions, including starting, stopping, and adjusting parameters. At the same time, each service unit exchanges information through a lightweight communication protocol to ensure the coordinated operation of the entire production line.

9. The distributed intelligent production scheduling decision system based on cloud computing according to claim 8, characterized in that: The distributed execution control module has real-time monitoring function and feedback adjustment mechanism, which can collect the operation status data of each execution unit on the production line in real time, including the machine's operation speed, fault conditions, and material consumption, and feed back these data to the intelligent production scheduling engine in a timely manner; Based on these feedback data, the intelligent scheduling engine can adjust the production schedule in a timely manner, optimize resource allocation, reduce waste and delays in the production process, and improve production efficiency and product quality.

Images