Mechanical automation scheduling test method and system

Abstract

The invention relates to the technical field of mechanical automation, in particular to a mechanical automation scheduling test method and system, and the method comprises the following steps: S1, simulating a dynamic working condition; s2, acquiring and processing multi-modal data; s3, reinforcement learning optimization scheduling; s4, virtual-real fusion verification; according to the method, the performance of the mechanical equipment under various actual production conditions is comprehensively and truly tested by constructing the high-simulation simulation working condition, the problem of inaccurate test results caused by single working condition or unreal simulation of a traditional test method is avoided, a more reliable basis is provided for formulating a scheduling scheme, and the test efficiency is improved. According to optimization suggestions provided by the data acquisition and analysis module, the scheduling scheme optimization module can automatically generate and screen out an optimal scheduling scheme, so that the production efficiency is effectively improved, the equipment energy consumption is reduced, the equipment failure is reduced, and the stability and reliability of the whole production system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical automation, and in particular to a mechanical automation scheduling test method and system. Background Art

[0002] In modern industrial production, the degree of mechanical automation continues to increase, with various types of machinery working collaboratively to complete complex production tasks. However, current automated machinery scheduling faces numerous challenges. Traditional scheduling testing methods often rely on manual experience for setup and judgment, lacking systematicity and precision. For example, in production line scheduling testing, human judgment is susceptible to subjective factors in key aspects such as equipment startup sequence, operating speed adjustment, and task allocation, resulting in inaccurate and unreliable test results. Furthermore, existing testing systems struggle to fully simulate the complex operating conditions found in actual production and fail to accurately reflect the performance of machinery under varying loads and operating times. This makes machinery prone to failures after production, leading to low production efficiency and even impacting the stability of the entire production process. Furthermore, traditional testing methods and systems also suffer from shortcomings in data collection and analysis, making it difficult to obtain critical equipment operation data in a timely and accurate manner, making it difficult to effectively optimize and improve scheduling plans. Therefore, a method and system for testing automated machinery scheduling is proposed. Summary of the Invention

[0003] In view of this, the present invention provides a mechanical automation scheduling test method and system to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0004] The technical solution of the present invention is implemented as follows: a mechanical automation scheduling test method, comprising the following steps:

[0005] S1, dynamic working condition simulation;

[0006] S2, multimodal data acquisition and processing;

[0007] S3, reinforcement learning optimization scheduling;

[0008] S4. Virtual-reality fusion verification.

[0009] Further preferably, S1 utilizes a pressure sensor to monitor in real time the weight of materials grasped or pushed by a robotic arm or other device, simulating changes in load borne by the machine during actual production. When a weight change is detected, the pressure sensor transmits a signal to the servo motor control system. Based on the received signal, the servo motor precisely adjusts its output torque, thereby dynamically regulating the robotic arm's load, allowing it to flexibly vary within a range of 0-100% of the rated load. A fault injection system is specifically designed to test the mechanical automation scheduling system's ability to respond to equipment failures. This system can simulate various common faults at any point during the test process through control circuits. Based on an in-depth analysis of the company's historical order data, data mining and statistical methods are used to develop an order flow generator. This generator can simulate a dynamic task queue based on information such as the temporal distribution of historical orders, product type combinations, and order urgency. This includes complex scenarios such as the sudden insertion of urgent orders during normal production and the rescheduling of existing orders.

[0010] Further preferably, in said S2, various types of sensors are widely deployed on the mechanical equipment to comprehensively collect the equipment operation status data. Since the data collection frequency and time base of different types of sensors may be different, in order to make the collected data consistent and comparable, precise clock synchronization technology is used to synchronize the clocks of each sensor with the central clock. During the data collection process, an accurate timestamp is given to each data sample, and then the data collected by different sensors are aligned along the time axis through an algorithm, and feature extraction is performed on the collected multimodal data to construct an equipment health status assessment matrix.

[0011] Further preferably, in said S3, with the goal of minimizing the production cycle, balancing the equipment load and improving production efficiency, a deep reinforcement learning algorithm is used to generate a dynamic scheduling plan. During the operation of the machine, the control parameters of the equipment are adjusted online using an adaptive control algorithm based on the data collected in real time, and a fault tree knowledge base is established to organize and store various possible equipment failures and their corresponding causes and solutions. When the multimodal data acquisition and processing module detects an abnormal equipment operating status, the system quickly matches and searches in the fault tree knowledge base to determine the fault type and possible causes, and then automatically triggers the backup scheduling plan according to the pre-set fault response strategy.

[0012] Further preferably, in S4, 3D modeling technology is used to construct an accurate virtual model of the mechanical equipment based on its actual size, structure, and movement mode, namely a digital twin model. This model not only has the same appearance and geometry as the physical equipment, but also simulates the equipment's operation process and physical characteristics, allowing different scheduling plans to be rehearsed and evaluated in a virtual environment. By simulating the production process and calculating various performance indicators, a visual interactive interface is provided to the user, allowing the user to monitor and analyze the test process.

[0013] A mechanical automation scheduling test system includes the following modules: a simulated working condition construction module, a test execution module, a data acquisition and analysis module, and a scheduling scheme optimization module.

[0014] Further preferably, the simulated working condition construction module converts various factors in actual production into quantifiable parameters by establishing a mathematical model, uses computer simulation technology to generate corresponding working condition data according to the set parameters, and transmits these data to the subsequent test execution module to provide a real and reliable simulation environment for the test.

[0015] Further preferably, the test execution module establishes a communication connection with the control system of the mechanical equipment, sends control instructions to drive the equipment to operate, adopts sensor technology to collect the status parameters of the equipment in real time, and uses the data transmission protocol to transmit the collected data quickly and accurately to the data acquisition and analysis module.

[0016] Further preferably, the data acquisition and analysis module utilizes hardware devices such as data acquisition cards to collect data transmitted by sensors, and performs analog-to-digital conversion, and adopts machine learning algorithms to classify and cluster the data, to mine the potential patterns and features in the data, and to achieve accurate judgment and optimization of equipment status and scheduling effects by establishing equipment failure prediction models and scheduling scheme evaluation models.

[0017] Further preferably, the scheduling scheme optimization module optimizes and searches the parameters of the scheduling scheme based on an optimization algorithm, such as a genetic algorithm, a particle swarm optimization algorithm, etc., evaluates the pros and cons of the schemes by simulating the operation of the equipment under different schemes, and finally determines the optimal scheduling scheme.

[0018] The embodiment of the present invention adopts the above technical solution, which has the following advantages:

[0019] 1. The present invention constructs highly simulated working conditions to comprehensively and realistically test the performance of mechanical equipment under various actual production conditions, avoiding the problem of inaccurate test results caused by the traditional testing method due to the single working condition or unrealistic simulation, and provides a more reliable basis for the formulation of scheduling plans. By using the optimization suggestions provided by the data acquisition and analysis module, the scheduling plan optimization module can automatically generate and screen the best scheduling plan, effectively improve production efficiency, reduce equipment energy consumption, reduce equipment failures, and enhance the stability and reliability of the entire production system.

[0020] 2. The data acquisition and analysis module of the present invention uses advanced algorithms to analyze equipment operation data, which can identify potential equipment failure risks in advance, provide early warning for equipment maintenance, facilitate timely repair measures, avoid the impact of sudden equipment failures on production, and reduce maintenance costs. The entire testing process is automated, reducing manual intervention, improving test efficiency and consistency, while also reducing labor costs and errors caused by human factors, which is in line with the development trend of modern industrial automation.

[0021] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 It is a system module diagram of the present invention;

[0024] Figure 2 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0025] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0026] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0027] like Figure 1-2As shown, an embodiment of the present invention provides a mechanical automation scheduling test method, comprising the following steps:

[0028] S1, dynamic working condition simulation;

[0029] S2, multimodal data acquisition and processing;

[0030] S3, reinforcement learning optimization scheduling;

[0031] S4. Virtual-reality fusion verification.

[0032] In one embodiment, S1 simulates the load variations experienced by machinery in actual production by using pressure sensors to monitor in real time the weight of materials being grasped or pushed by a robotic arm or other device. When a weight change is detected, the pressure sensor transmits a signal to the servo motor control system. Based on the received signal, the servo motor precisely adjusts its output torque, dynamically adjusting the robotic arm's load, allowing it to flexibly vary between 0% and 100% of its rated load. A fault injection system is designed to test the automated mechanical scheduling system's ability to respond to equipment failures. This system can simulate various common faults at any point during the testing process through control circuits. Based on an in-depth analysis of the company's historical order data, data mining and statistical methods are used to develop an order flow generator. This generator simulates a dynamic task queue based on historical order time distribution patterns, product type combinations, and order urgency. This includes complex scenarios such as the sudden insertion of urgent orders during normal production and the rescheduling of existing orders.

[0033] In one embodiment, in S2, various types of sensors are widely deployed on mechanical equipment to comprehensively collect equipment operation status data. Since the data collection frequency and time base of different types of sensors may be different, in order to make the collected data consistent and comparable, precise clock synchronization technology is used to synchronize the clocks of each sensor with the central clock. During the data collection process, an accurate timestamp is added to each data sample, and then the data collected by different sensors are aligned along the time axis through an algorithm, and feature extraction is performed on the collected multimodal data to construct an equipment health status assessment matrix.

[0034] In one embodiment, in S3, with the goal of minimizing the production cycle, balancing equipment load, and improving production efficiency, a deep reinforcement learning algorithm is used to generate a dynamic scheduling plan. During the operation of the machine, the control parameters of the equipment are adjusted online using an adaptive control algorithm based on the real-time collected data, and a fault tree knowledge base is established to organize and store various possible equipment failures and their corresponding causes and solutions. When the multimodal data acquisition and processing module detects an abnormal equipment operating status, the system quickly matches and searches in the fault tree knowledge base to determine the fault type and possible causes, and then automatically triggers the backup scheduling plan based on the pre-set fault response strategy.

[0035] In one embodiment, S4 utilizes 3D modeling technology to construct a precise virtual model of the mechanical equipment, known as a digital twin, based on its actual size, structure, and motion. This model not only has the same appearance and geometry as the physical equipment but also simulates the equipment's operational processes and physical characteristics, allowing for previewing and evaluating different scheduling scenarios in a virtual environment. By simulating the production process and calculating various performance indicators, a visual interactive interface is provided for users to easily monitor and analyze the testing process.

[0036] A mechanical automation scheduling test system includes the following modules: a simulated working condition construction module, a test execution module, a data acquisition and analysis module, and a scheduling scheme optimization module.

[0037] In one embodiment, the simulation working condition construction module converts various factors in actual production into quantifiable parameters by establishing a mathematical model, uses computer simulation technology to generate corresponding working condition data according to the set parameters, and transmits this data to the subsequent test execution module to provide a real and reliable simulation environment for the test.

[0038] In one embodiment, the test execution module establishes a communication connection with the control system of the mechanical equipment, sends control instructions to drive the equipment to operate, adopts sensor technology to collect the status parameters of the equipment in real time, and uses the data transmission protocol to quickly and accurately transmit the collected data to the data acquisition and analysis module.

[0039] In one embodiment, the data acquisition and analysis module uses hardware devices such as data acquisition cards to collect data transmitted by sensors and performs analog-to-digital conversion. It uses machine learning algorithms to classify and cluster the data, explore potential patterns and features in the data, and establish equipment failure prediction models and scheduling plan evaluation models to achieve accurate judgment and optimization of equipment status and scheduling effects.

[0040] In one embodiment, the scheduling scheme optimization module optimizes and searches the parameters of the scheduling scheme based on an optimization algorithm, such as a genetic algorithm, a particle swarm optimization algorithm, etc., evaluates the pros and cons of the schemes by simulating the operation of the equipment under different schemes, and finally determines the optimal scheduling scheme.

[0041] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various modifications and substitutions within the technical scope disclosed in the present invention, and such modifications and substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A mechanical automation scheduling test method, characterized by: The following steps are involved: S1, dynamic working condition simulation; S2, multimodal data acquisition and processing; S3, reinforcement learning optimization scheduling; S4. Virtual-reality fusion verification.

2. A mechanical automation scheduling test method according to claim 1, characterized in that: S1 simulates the load variations experienced by machinery in actual production, utilizing pressure sensors to monitor in real time the weight of materials being grasped or pushed by robotic arms and other equipment. When a weight change is detected, the pressure sensor transmits a signal to the servo motor control system. Based on this signal, the servo motor precisely adjusts its output torque, dynamically adjusting the robotic arm's load, allowing it to flexibly vary between 0% and 100% of its rated load. A fault injection system was specifically designed to test the automated mechanical scheduling system's ability to respond to equipment failures. This system simulates various common faults at any point during the test process through control circuitry. Based on an in-depth analysis of the company's historical order data, data mining and statistical methods were used to develop an order flow generator. This generator simulates a dynamic task queue based on historical order data, including temporal distribution patterns, product type mix, and order urgency. This includes complex scenarios such as the sudden insertion of urgent orders into the normal production process and the rescheduling of existing orders.

3. The method for testing a mechanical automation scheduling system according to claim 1, wherein: In S2, various types of sensors are widely deployed on mechanical equipment to comprehensively collect equipment operation status data. Since the data collection frequency and time base of different types of sensors may be different, in order to make the collected data consistent and comparable, precise clock synchronization technology is used to synchronize the clocks of each sensor with the central clock. During the data collection process, an accurate timestamp is given to each data sample, and then the data collected by different sensors are aligned along the time axis through an algorithm, and feature extraction is performed on the collected multimodal data to construct an equipment health status assessment matrix.

4. A mechanical automation scheduling test method according to claim 1, characterized in that: In the S3, with the goal of minimizing the production cycle, balancing equipment loads, and improving production efficiency, a deep reinforcement learning algorithm is used to generate a dynamic scheduling plan. During the operation of the machine, the control parameters of the equipment are adjusted online using an adaptive control algorithm based on the real-time collected data, and a fault tree knowledge base is established to organize and store various possible equipment failures and their corresponding causes and solutions. When the multimodal data acquisition and processing module detects an abnormal equipment operating status, the system quickly matches and searches in the fault tree knowledge base to determine the fault type and possible causes, and then automatically triggers the backup scheduling plan based on the pre-set fault response strategy.

5. The method for testing mechanical automation scheduling according to claim 1, characterized in that: In S4, 3D modeling technology is used to construct a precise virtual model of the mechanical equipment, known as a digital twin, based on its actual size, structure, and motion. This model not only has the same appearance and geometry as the physical equipment but also simulates the equipment's operational processes and physical characteristics. This allows for the preview and evaluation of different scheduling scenarios in a virtual environment. By simulating the production process and calculating various performance indicators, a visual interactive interface is provided for users to monitor and analyze the testing process.

6. A mechanical automation scheduling test system, equipped with a mechanical automation scheduling test method according to any one of claims 1 to 5, characterized in that: It includes the following modules: simulation condition construction module, test execution module, data acquisition and analysis module and scheduling plan optimization module.

7. A mechanical automation scheduling test system according to claim 6, characterized in that: The simulated working condition construction module converts various factors in actual production into quantifiable parameters by establishing a mathematical model, uses computer simulation technology to generate corresponding working condition data according to the set parameters, and transmits this data to the subsequent test execution module, providing a real and reliable simulation environment for testing.

8. The mechanical automation scheduling test system according to claim 6, characterized in that: The test execution module establishes a communication connection with the control system of the mechanical equipment, sends control instructions to drive the equipment to operate, adopts sensor technology to collect the status parameters of the equipment in real time, and uses the data transmission protocol to quickly and accurately transmit the collected data to the data acquisition and analysis module.

9. The mechanical automation scheduling test system according to claim 6, characterized in that: The data acquisition and analysis module uses hardware devices such as data acquisition cards to collect data transmitted by sensors and performs analog-to-digital conversion. It uses machine learning algorithms to classify and cluster the data, explore potential patterns and features in the data, and establish equipment failure prediction models and scheduling plan evaluation models to achieve accurate judgment and optimization of equipment status and scheduling effects.

10. The mechanical automation scheduling test system according to claim 6, characterized in that: The scheduling scheme optimization module optimizes and searches for parameters of the scheduling scheme based on optimization algorithms, such as genetic algorithms and particle swarm optimization algorithms, and evaluates the pros and cons of the schemes by simulating the operation of equipment under different schemes, and finally determines the optimal scheduling scheme.

Images