High-precision product manufacturing environment intelligent management and control method based on artificial intelligence

By using AI-based pollutant monitoring and ant colony algorithm to optimize cleaning paths, the problem of untimely pollutant treatment in high-precision product manufacturing environments has been solved, improving cleaning efficiency and equipment utilization, and ensuring a high standard of cleanliness in the production environment.

CN119005466AInactive Publication Date: 2024-11-22CHONGQING VOCATIONAL & TECH COLLEGE OF IND & TRADE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411091173.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing technologies cannot respond promptly to ground pollution in high-precision product manufacturing environments and lack intelligent cleaning scheduling, resulting in unsatisfactory cleaning efficiency and effectiveness, which affects product quality and production efficiency.

Method used

Using an artificial intelligence-based approach, pollutant information is monitored in real time to generate cleaning priorities. An improved ant colony algorithm is used to plan the optimal path for cleaning equipment, and the cleaning route is optimized by updating the pheromone. In combination with a BP neural network, the type and area of ​​pollutants are analyzed to optimize the operation route and scheduling of cleaning equipment.

Benefits of technology

It enables timely treatment of pollutants, improves cleaning efficiency, reduces resource consumption, extends equipment life, reduces product defects, and optimizes the cleanliness of the production environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005466A_ABST
    Figure CN119005466A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent cleaning, in particular to a high-precision product manufacturing environment intelligent control method based on artificial intelligence, and the method comprises the steps: monitoring the pollutant information of a target region, and generating the cleaning priority of each pollutant according to the type and area of the pollutants; establishing a factory road network model; establishing a plurality of pollutant models according to the category and area of each pollutant, and inserting the pollutant models into the factory road network model according to the position of each pollutant; establishing a cleaning equipment model, and according to the initial position of the cleaning equipment model and the position of each pollutant, inserting the cleaning equipment model into the factory road network model for simulation motion; and performing optimal path planning in the factory road network model by adopting an improved ant colony algorithm. By the adoption of the scheme, pollution can be treated in time through intelligent cleaning scheduling, meanwhile, the cleaning efficiency is improved, resource consumption is reduced, the manufacturing environment of high-precision products is optimized, and the product quality can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent cleaning technology, and in particular to an intelligent management and control method for a high-precision product manufacturing environment based on artificial intelligence. Background Art

[0002] In the manufacturing process of high-precision products, the cleanliness of the environment is crucial to the quality of the final product. For example, in the electronics industry, pharmaceutical industry, and precision machining, trace amounts of dust or pollutants may cause product defects or even the scrapping of an entire batch of products. Therefore, these industries have extremely strict requirements for the cleanliness of the manufacturing environment.

[0003] At present, in order to control the cleanliness of the manufacturing environment, factories usually take the following measures: using electrostatic adsorption devices to reduce floating dust in the air; strictly disinfecting personnel and materials entering the factory area; cleaning the floor according to a fixed schedule, etc. These measures can maintain the cleanliness of the environment to a certain extent, but they have some significant shortcomings.

[0004] First, although the electrostatic adsorption device can reduce floating dust in the air, it is powerless against dust and pollutants that have settled on the ground. Secondly, disinfection before entering the site can reduce external pollution sources, but it cannot deal with pollution generated within the factory. Furthermore, the fixed-time cleaning plan may not be able to clean up sudden pollution incidents in time, causing pollutants to exist in the production environment for a long time. In addition, existing cleaning methods often lack flexibility and intelligence. Cleaning work is usually carried out according to a preset schedule, rather than adjusted according to the actual pollution situation. This means that in some key areas, product quality may be affected due to untimely cleaning, while in other areas, there may be excessive cleaning, resulting in a waste of resources.

[0005] In summary, the existing technology has many deficiencies in the cleanliness control of high-precision product manufacturing environments, including the inability to respond to ground contamination in a timely manner, lack of intelligent cleaning scheduling, and unsatisfactory cleaning efficiency and results. These problems have seriously affected the production efficiency and quality of high-precision products, and a new intelligent management and control method is urgently needed to solve these deficiencies. Summary of the invention

[0006] The present invention provides an intelligent management and control method for a high-precision product manufacturing environment based on artificial intelligence, which can achieve timely treatment of pollution through intelligent cleaning scheduling, while improving cleaning efficiency, reducing resource consumption, and optimizing the manufacturing environment of high-precision products, which is conducive to improving product quality.

[0007] In order to achieve the above objectives, this application provides the following technical solutions:

[0008] The intelligent control method of high-precision product manufacturing environment based on artificial intelligence includes the following contents:

[0009] Monitoring pollutant information in the target area, the pollutant information including the type, location and area of ​​each pollutant; and generating a cleaning priority for each pollutant according to the type and area of ​​the pollutant;

[0010] Obtaining road network information of the target area and establishing a factory road network model; establishing several pollutant models according to the type and area of ​​each pollutant, and inserting the pollutant models into the factory road network model according to the location of each pollutant;

[0011] Establish a cleaning equipment model, and insert the cleaning equipment model into the factory road network model to simulate movement according to the initial position of the cleaning equipment model and the position of each pollutant;

[0012] The improved ant colony algorithm is used to plan the optimal path of the cleaning equipment model in the factory road network model, and the parameters of the ant colony algorithm are initialized to set the initial number of ants in the ant colony, the initial concentration of pheromones, and the pheromone volatilization rate.

[0013] According to the cleaning priority of each pollutant, a heuristic function and a node selection function are constructed;

[0014] After all ants have completed a path, the path with the highest pheromone concentration is selected as the optimal cleaning path.

[0015] Furthermore, it also includes: obtaining the remaining battery life T of the cleaning equipment model x , and analyze the total time required to clean up each pollutant based on its type and area c ;

[0016] Calculate the estimated time T of the optimized trajectory of the cleaning equipment model y :

[0017]

[0018] Where v is the moving speed of the cleaning equipment model, d a , i is the distance between the initial position a of the cleaning equipment model and the position i of the pollutant, d i , j is the distance between the pollutant position i and the pollutant position j, n means there are n pollutants in total, corresponding to n pollutant positions, d n-1 , a It represents the distance that the cleaning equipment model returns to the initial position a after cleaning all pollutants;

[0019] The heuristic function is:

[0020]

[0021] Where η ij is the inspiration of the ant from position i to position j, Priority(j) is the cleaning priority of the pollutant corresponding to position j, d ij is the distance from position i to position j.

[0022] Further, the node selection function is:

[0023]

[0024] In the formula, is the probability that ant k chooses position j from position i, τ ij is the pheromone concentration between paths ij, α is the parameter that controls the relative importance of pheromone concentration, β is the parameter that controls the relative importance of heuristic, is the set of locations that ant k can choose to go to at location i.

[0025] Furthermore, it also includes: constructing a pheromone update function:

[0026]

[0027] In the formula, τ ij (d+1) is the updated pheromone concentration, ρ is the pheromone volatility, τ ij (d) is the pheromone concentration before updating, is the pheromone concentration increased by ant k from position i to position j in d iterations, m is the total number of ants, Q is the fixed increase in pheromone concentration, C is the number of workers within the preset distance on the path from position i to position j in the cleaning equipment model, γ c The factors that influence the obstacles of cleaning equipment model for individual workers;

[0028] After all ants have completed a path, the pheromone concentration on each path is updated according to the pheromone update function, and the path with the highest pheromone concentration is selected as the optimal cleaning path.

[0029] Furthermore, according to the type and area of ​​the pollutants, the cleaning priority of each pollutant is generated respectively, including:

[0030] Calling a pre-stored comparison table, wherein the comparison table records the categories of several pollutants and the corresponding cleaning urgency of each category of pollutants;

[0031] According to the type of pollutants, refer to the comparison table to analyze the urgency of cleaning the pollutants;

[0032] The cleaning urgency is adjusted according to the area of ​​the pollutants, and the cleaning priority of each pollutant is generated according to the cleaning urgency of each pollutant.

[0033] Furthermore, according to the type and area of ​​the pollutants, the cleaning priority of each pollutant is generated respectively, including:

[0034] Through artificial intelligence, the cleaning priority of each pollutant is analyzed and generated according to the type and area of ​​pollutants. The type and area of ​​pollutants are used as the input of the input layer, and the cleaning priority of pollutants is used as the output of the output layer.

[0035] The principle and advantage of the present invention are: in this scheme, the pollutant information of the target area is monitored in real time, so as to quickly identify and locate the pollutants, and the cleaning equipment is dispatched in time to perform local or comprehensive cleaning work, which significantly reduces the residence time of the pollutants in the production environment, thereby maintaining a high standard of production environment cleanliness, which is conducive to reducing the defect rate of products caused by environmental pollution and improving product quality. In order to ensure that stains with higher urgency are treated first, the cleaning priority of each pollutant is analyzed according to the type and area of ​​the pollutant, so as to reasonably plan the operation route of the intelligent cleaning equipment according to the cleaning priority of each pollutant, and at the same time reduce the interference of the intelligent cleaning equipment to the worker's operating area during operation, so as to keep the environment clean without hindering the normal operation of the production line. In addition, in terms of optimizing the operating time and frequency of the cleaning equipment, by optimizing the cleaning route and scheduling strategy, the operating time and frequency of the cleaning equipment are reduced, thereby saving energy and reducing equipment wear, extending the service life of the equipment, and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The present invention is a flowchart of an embodiment of the method for intelligent management and control of high-precision product manufacturing environment based on artificial intelligence. DETAILED DESCRIPTION

[0037] The following is further described in detail through specific implementation methods:

[0038] Embodiment 1:

[0039] Embodiment 1 is basically as attached Figure 1 As shown:

[0040] The intelligent control method of high-precision product manufacturing environment based on artificial intelligence includes the following steps:

[0041] S1. Monitor the pollutant information in the target area. In this embodiment, the target area is the product manufacturing area, specifically the ground of the product manufacturing area. In other embodiments of the present application, pollutants at other locations can also be identified and corresponding cleaning equipment can be used. The pollutant information includes the category, location, and area of each pollutant. After identifying that there are pollutants in the target area, according to the category and area of the pollutants, the cleaning priorities of each pollutant are generated respectively.

[0042] Specifically, it includes:

[0043] Obtain the image data of the target area; according to the image data, identify whether there are pollutants in the target area. If so, extract the features of the pollutants, and compare the extracted feature data with the feature data of each pollutant in the pre-stored pollutant feature library to further confirm the category of the pollutants; and according to the image data, analyze the location and area of the pollutants.

[0044] Call the pre-stored comparison table. The comparison table records the categories of several pollutants and the cleaning urgency corresponding to each category of pollutants. According to the category of the pollutants, refer to the comparison table to analyze the cleaning urgency of the pollutants; and according to the area of the pollutants, adjust the cleaning urgency, and generate the cleaning priorities of each pollutant according to the cleaning urgency of each pollutant. In this embodiment, the cleaning urgency of pollutants is divided into 8 levels from low to high, namely level 1, level 2... level 8. Each pollutant is set with a preset emergency area threshold. Analyze the ratio of the area of the pollutant to the preset emergency area threshold, and adjust the cleaning urgency according to the ratio. The cleaning urgency corresponding to each pollutant is inversely proportional to the corresponding preset emergency area threshold. Specifically, if the ratio is greater than a, the cleaning urgency is increased by one level; if the ratio is greater than b, the cleaning urgency is increased by two levels; if the ratio is greater than c, the cleaning urgency is increased by three levels, where a < b < c. If the adjusted cleaning urgency is greater than level 8, it is recorded as level 8, so as to ensure that stains with higher urgency can be processed preferentially. Sort each pollutant according to the corresponding cleaning urgency, and determine its cleaning priority according to the sorting order. The higher the cleaning urgency, the higher the cleaning priority. If there are pollutants with equal cleaning urgency, it is determined that the pollutant with a larger area has a higher cleaning priority.

[0045] S2. Obtain the road network information of the target area and establish a factory road network model; according to the category and area of each pollutant, establish several pollutant models, and insert the pollutant models into the factory road network model according to the location of each pollutant. In this embodiment, the worker information of the target area is also obtained, and a worker model is established, and the worker model is inserted into the factory road network model according to the movement behavior of the corresponding worker in the historical worker information.

[0046] S3, establish a cleaning equipment model, and insert the cleaning equipment model into the factory road network model to simulate movement according to the initial position of the cleaning equipment model and the position of each pollutant; specifically, the cleaning equipment model starts from the initial position, passes through the position of each pollutant to clean the corresponding pollutant, and after traversing all pollutants, returns to the initial position to wait. In this embodiment, since the pollutants on the ground are analyzed and cleaned, an intelligent sweeping robot is used.

[0047] S4, using the improved ant colony algorithm to perform optimal path planning for the cleaning equipment model in the factory road network model, initialize the ant colony algorithm parameters, set the initial number of ants in the ant colony, the initial pheromone concentration and the pheromone volatilization rate; in this embodiment, the initial number of ants is 1000, and the initial pheromone concentration between all nodes is 0.2, and the pheromone volatilization rate is 60%.

[0048] S5, constructing a heuristic function and a node selection function according to the cleaning priority of each pollutant.

[0049] First, obtain the remaining battery life T of the cleaning equipment model x , and analyze the total time required to clean up each pollutant based on its type and area c ;

[0050] Calculate the estimated time T of the optimized trajectory of the cleaning equipment model y :

[0051]

[0052] Where v is the moving speed of the cleaning equipment model, d a , i is the distance between the initial position a of the cleaning equipment model and the position i of the pollutant, d i , j is the distance between the pollutant position i and the pollutant position j, n means there are n pollutants in total, corresponding to n pollutant positions, d n-1 , a It represents the distance that the cleaning equipment model returns to the initial position a after completing the cleaning of all pollutants.

[0053] When generating the heuristic function, it is necessary to ensure that the estimated time of the optimized trajectory is less than the remaining battery life of the cleaning device model to prevent it from failing to complete the cleaning task or failing to return to the initial position for charging after completing the cleaning task. The heuristic function is:

[0054]

[0055] Where η ijis the inspiration of the ant from position i to position j, Priority(j) is the cleaning priority of the pollutant corresponding to position j, d ij is the distance from position i to position j.

[0056] The node selection function is:

[0057]

[0058] In the formula, is the probability that ant k chooses position j from position i, τ ij is the pheromone concentration between paths ij, α is the parameter that controls the relative importance of pheromone concentration, β is the parameter that controls the relative importance of heuristic, is the set of locations that ant k can choose to go to at location i.

[0059] S6, for each ant, starting from the (0,0,0) node, that is, the initial position, the node selection function is executed cyclically to select nodes until the number of nodes meets the boundary conditions. The nodes selected by the ants are connected to form a path. After all ants have completed the path once, the path with the highest pheromone concentration is selected as the optimal cleaning path.

[0060] Specifically, it also includes constructing a pheromone update function:

[0061]

[0062] In the formula, τ ij (d+1) is the updated pheromone concentration, ρ is the pheromone volatility, τ ij (d) is the pheromone concentration before updating, is the pheromone concentration increased by ant k from position i to position j in d iterations, m is the total number of ants, Q is the fixed increase in pheromone concentration, C is the number of workers within the preset distance on the path from position i to position j in the cleaning equipment model, γ c Factors that influence the hindrance of a single worker to the cleaning equipment model.

[0063] After all ants have completed a path, the pheromone concentration on each path is updated according to the pheromone update function, and the path with the highest pheromone concentration is selected as the optimal cleaning path.

[0064] Embodiment 2:

[0065] The basic principle of Example 2 is the same as that of Example 1, with the difference being that in Example 2, the cleaning priority of each pollutant is generated according to the category and area of ​​the pollutant, including: analyzing and generating the cleaning priority of each pollutant according to the category and area of ​​the pollutant by means of artificial intelligence, taking the category and area of ​​the pollutant as the input of the input layer, and taking the cleaning priority of the pollutant as the output of the output layer.

[0066] Specifically, a three-layer BP neural network model is first constructed, including an input layer, a hidden layer, and an output layer. In this embodiment, the type and area of ​​pollutants are used as the input of the input layer, so the input layer has 2 nodes, and the output is the cleaning priority of the pollutants, so there is a total of 1 node; for the hidden layer, this embodiment uses the following formula to determine the number of hidden layer nodes: Where l is the number of nodes in the hidden layer, n is the number of nodes in the input layer, m is the number of nodes in the output layer, and a is a number between 1 and 10. In this embodiment, it is 5, so there are 7 nodes in the hidden layer. BP neural network usually uses Sigmoid differentiable function and linear function as the excitation function of the network. In this embodiment, the S-type tangent function tansig is selected as the excitation function of the hidden layer neurons. The prediction model selects the S-type logarithmic function tansig as the excitation function of the output layer neurons.

[0067] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent control method for high-precision product manufacturing environment based on artificial intelligence, characterized by: Includes the following: Monitoring pollutant information in the target area, the pollutant information including the type, location and area of ​​each pollutant; and generating a cleaning priority for each pollutant according to the type and area of ​​the pollutant; Obtaining road network information of the target area and establishing a factory road network model; establishing several pollutant models according to the type and area of ​​each pollutant, and inserting the pollutant models into the factory road network model according to the location of each pollutant; Establish a cleaning equipment model, and insert the cleaning equipment model into the factory road network model to simulate movement according to the initial position of the cleaning equipment model and the position of each pollutant; The improved ant colony algorithm is used to plan the optimal path of the cleaning equipment model in the factory road network model, and the parameters of the ant colony algorithm are initialized to set the initial number of ants in the ant colony, the initial concentration of pheromones, and the pheromone volatilization rate. According to the cleaning priority of each pollutant, a heuristic function and a node selection function are constructed; After all ants have completed a path, the path with the highest pheromone concentration is selected as the optimal cleaning path.

2. The method for intelligent management and control of high-precision product manufacturing environment based on artificial intelligence according to claim 1 is characterized in that: Also includes: Get the remaining battery life T of the cleaning equipment model x , and analyze the total time required to clean up each pollutant based on its type and area c ; Calculate the estimated time T of the optimized trajectory of the cleaning equipment model y : Where v is the moving speed of the cleaning equipment model, d a , i is the distance between the initial position a of the cleaning equipment model and the position i of the pollutant, d i , j is the distance between the pollutant position i and the pollutant position j, n means there are n pollutants in total, corresponding to n pollutant positions, d n-1 , a It represents the distance that the cleaning equipment model returns to the initial position a after cleaning all pollutants; The heuristic function is: Where η ij is the inspiration of the ant from position i to position j, Priority(j) is the cleaning priority of the pollutant corresponding to position j, d ij is the distance from position i to position j.

3. The method for intelligent management and control of high-precision product manufacturing environment based on artificial intelligence according to claim 2 is characterized in that: The node selection function is: In the formula, is the probability that ant k chooses position j from position i, τ ij is the pheromone concentration between paths ij, α is the parameter that controls the relative importance of pheromone concentration, β is the parameter that controls the relative importance of heuristic, is the set of locations that ant k can choose to go to at location i.

4. The method for intelligent management and control of high-precision product manufacturing environment based on artificial intelligence according to claim 1 is characterized in that: Also includes: Construct the pheromone update function: In the formula, τ ij (d+1) is the updated pheromone concentration, ρ is the pheromone volatility, τ ij (d) is the pheromone concentration before updating, is the pheromone concentration increased by ant k from position i to position j in d iterations, m is the total number of ants, Q is the fixed increase in pheromone concentration, C is the number of workers within the preset distance on the path from position i to position j in the cleaning equipment model, γ c The factors that influence the obstacles of cleaning equipment model for individual workers; After all ants have completed a path, the pheromone concentration on each path is updated according to the pheromone update function, and the path with the highest pheromone concentration is selected as the optimal cleaning path.

5. The method for intelligent management and control of high-precision product manufacturing environment based on artificial intelligence according to claim 1 is characterized in that: According to the type and area of ​​the pollutants, the cleaning priority of each pollutant is generated respectively, including: Calling a pre-stored comparison table, wherein the comparison table records the categories of several pollutants and the corresponding cleaning urgency of each category of pollutants; According to the type of pollutants, refer to the comparison table to analyze the urgency of cleaning the pollutants; The cleaning urgency is adjusted according to the area of ​​the pollutants, and the cleaning priority of each pollutant is generated according to the cleaning urgency of each pollutant.

6. The method for intelligent management and control of high-precision product manufacturing environment based on artificial intelligence according to claim 1 is characterized in that: According to the type and area of ​​the pollutants, the cleaning priority of each pollutant is generated respectively, including: Through artificial intelligence, the cleaning priority of each pollutant is analyzed and generated according to the type and area of ​​pollutants. The type and area of ​​pollutants are used as the input of the input layer, and the cleaning priority of pollutants is used as the output of the output layer.