Intelligent control method and system for coffee cup production process

Abstract

The invention relates to the technical field of production control, and particularly discloses an intelligent control method and system for a coffee cup production process, and the method comprises the steps: determining the parameter range of production equipment, randomly selecting a parameter from the parameter range of each production equipment, combining the parameters, and carrying out the circulation execution, thereby obtaining a preset number of production schemes; for each production scheme, generating a control instruction based on the production scheme, sending the control instruction to production equipment, and synchronously obtaining product quality parameters; and selecting the optimal production scheme as the production scheme of the next production cycle according to the product quality parameters. According to the method, one production parameter is selected in each production parameter range, the production parameters are combined to obtain multiple production schemes, iterative optimization is performed on the production schemes based on the product quality, finally, a better scheme under the current environment condition is obtained, and the flexibility is extremely high.

Description

Technical Field

[0001] The present invention relates to the technical field of production control, and in particular to an intelligent control method and system for a coffee cup production process. Background Art

[0002] The unmanned intelligent coffee cup production process is an innovative production model that combines automation, intelligence and traditional ceramic production processes. Through the unmanned production line, using intelligent equipment, sensors, robots and other technologies, the efficient and precise production of coffee cups can be achieved, while reducing manual intervention and improving production efficiency and product quality.

[0003] There are multiple production equipment in the production line, including intelligent batching system, automatic molding equipment, automatic drying equipment and automatic glaze spraying system, etc. These production equipment all work under preset parameters; in actual applications, the production parameters of different production equipment are actually a range, and under different environmental conditions, the optimal production parameters are different. The production parameters in the existing technical solutions are fixed parameters, which are difficult to adjust according to environmental conditions and lack flexibility; how to improve the fit between production parameters and the actual environment is the technical problem that the technical solution of the present invention wants to solve. Summary of the invention

[0004] The object of the present invention is to provide a method and system for intelligently controlling a coffee cup production process, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for intelligently controlling a coffee cup production process, the method comprising:

[0007] Query the production equipment of coffee cups, query the product yield of each production equipment during the damage period in the maintenance record table, and calculate the production weight of each production equipment based on the product yield;

[0008] Determine the parameter range of the production equipment based on the production weight, randomly select a parameter from the parameter range of each production equipment and combine them, execute them cyclically, and obtain a preset number of production plans;

[0009] For each production plan, control instructions are generated based on the production plan and sent to the production equipment to synchronously obtain product quality parameters;

[0010] Select the best production plan based on product quality parameters as the production plan for the next production cycle;

[0011] Among them, when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the simulation software, the preset number is two orders of magnitude; when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the test assembly line, the preset number is in the single digit.

[0012] As a further solution of the present invention: the step of querying the production equipment of the coffee cups, querying the product yield of each production equipment during the damage period in the maintenance record table, and calculating the production weight of each production equipment according to the product yield includes:

[0013] Check the production equipment of coffee cups;

[0014] Locate the damage period of each production equipment in the maintenance record table and query the product yield simultaneously; when the production of the product is stopped, the product yield is zero;

[0015] The production weight of the production equipment is determined according to the product yield; the relationship between the production weight and the product yield is an exponential function relationship.

[0016] As a further solution of the present invention: the step of determining the parameter range of the production equipment based on the production weight, randomly selecting a parameter from the parameter range of each production equipment and combining them, and executing them cyclically to obtain a preset number of production plans includes:

[0017] Query the standard production parameters of each production equipment;

[0018] Determine the floating ratio according to the production weight, and determine the parameter range according to the floating ratio and the standard production parameter; the floating ratio is inversely proportional to the production weight;

[0019] A parameter is randomly selected from the parameter range of each production equipment, and the selected parameters are combined according to the order of the production equipment to obtain a production plan;

[0020] Execute in a loop and record the total number of production plans. When the total number reaches the preset number, output all the obtained production plans.

[0021] Among them, the process of determining the floating ratio is:.

[0022] As a further solution of the present invention: for each production plan, the step of generating a control instruction based on the production plan, sending the control instruction to the production equipment, and synchronously acquiring the product quality parameters includes:

[0023] For each production plan, query the production parameters of each production equipment in the production plan;

[0024] Generate control instructions based on the production parameters and send them to the production equipment;

[0025] Obtain a product image of an output product of a production device, input the product image into a trained convolutional recognition model, and obtain an abnormality type and abnormality level;

[0026] The product quality score is determined according to the abnormality type and abnormality level as a product quality parameter.

[0027] As a further solution of the present invention: the step of selecting the optimal production plan according to the product quality parameters as the production plan for the next production cycle includes:

[0028] Select the current optimal production plan based on product quality parameters and simultaneously update the global optimal production plan;

[0029] Determine adjustment vectors of other production plans based on the current optimal production plan and the global optimal production plan;

[0030] Update all production plans based on the adjustment vector;

[0031] The loop is executed iteratively, and when the preset number of iterations is reached, the global optimal production plan is output as the production plan for the next production cycle.

[0032] As a further solution of the present invention: the process of updating all production plans based on the adjustment vector is:

[0033] x i (t+1)=x i (t)+v i (t+1);

[0034] v i (t+1)=ω·v i (t)+c 1 ·r 1 ·(p i -x i (t))+c 2 ·r 2 ·(g(t)-x i (t));

[0035] In the formula, x i (t+1) represents the production plan of the i-th production plan after the (t+1)th iteration, x i (t) represents the production plan of the i-th production plan after the t-th iteration, v i (t+1) represents the adjustment vector of the i-th production plan at the (t+1)th iteration, v i (t) represents the adjustment vector of the i-th production plan at the t-th iteration, ω is the preset inertia weight, c1 and c 2 is the preset acceleration constant, r 1 and r 2 is a preset random number, the selection range is (0,1); p i is the optimal production plan of the ith production plan in the historical iteration process, that is, the current optimal production plan; g(t) represents the optimal plan of all production plans at the tth iteration, that is, the global optimal production plan.

[0036] The technical solution of the present invention also provides an intelligent control system for coffee cup production process, the system comprising:

[0037] The production weight calculation module is used to query the production equipment of coffee cups, query the product yield of each production equipment during the damage period in the maintenance record table, and calculate the production weight of each production equipment according to the product yield;

[0038] The production plan generation module is used to determine the parameter range of the production equipment based on the production weight, randomly select a parameter from the parameter range of each production equipment and combine them, execute them cyclically, and obtain a preset number of production plans;

[0039] A quality parameter acquisition module is used to generate control instructions based on each production plan, send them to the production equipment, and synchronously acquire product quality parameters;

[0040] The production plan update module is used to select the optimal production plan according to product quality parameters as the production plan for the next production cycle;

[0041] Among them, when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the simulation software, the preset number is two orders of magnitude; when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the test assembly line, the preset number is in the single digit.

[0042] As a further solution of the present invention: the production weight calculation module includes:

[0043] Equipment query unit, used to query the production equipment of coffee cups;

[0044] The product yield query unit is used to locate the damage period of each production equipment in the maintenance record table and simultaneously query the product yield; when the production of the product is stopped, the product yield is zero;

[0045] A calculation execution unit is used to determine the production weight of the production equipment according to the product yield; the relationship between the production weight and the product yield is an exponential function relationship.

[0046] As a further solution of the present invention: the production plan generation module includes:

[0047] Standard parameter query unit, used to query the standard production parameters of each production equipment;

[0048] A floating parameter calculation unit, used to determine a floating ratio according to the production weight, and to determine a parameter range according to the floating ratio and a standard production parameter; the floating ratio is inversely proportional to the production weight;

[0049] A parameter combination unit is used to randomly select a parameter in the parameter range of each production equipment, and combine the selected parameters according to the order of the production equipment to obtain a production plan;

[0050] A plan output unit is used to execute cyclically and record the total number of production plans. When the total number reaches a preset number, all the obtained production plans are output;

[0051] Among them, the process of determining the floating ratio is:.

[0052] As a further solution of the present invention: the quality parameter acquisition module includes:

[0053] A production parameter query unit, used for querying the production parameters of each production equipment in each production plan;

[0054] An instruction sending unit, used to generate a control instruction based on the production parameters and send it to the production equipment;

[0055] A recognition unit, used to obtain a product image of an output product of a production device, input the product image into a trained convolutional recognition model, and obtain an abnormality type and abnormality level;

[0056] The score generating unit is used to determine the product quality score according to the abnormality type and abnormality level as a product quality parameter.

[0057] Compared with the prior art, the beneficial effects of the present invention are: the present invention determines a production parameter range for each production equipment, selects a production parameter within each production parameter range and combines the production parameters to obtain multiple production plans, obtains the product quality corresponding to different production plans, iteratively optimizes the production plan based on the product quality, and finally obtains the best plan under the current environmental conditions, which is extremely flexible. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0059] Figure 1 This is a flowchart of the intelligent control method for the coffee cup production process.

[0060] Figure 2 This is a block diagram of the first sub-process of the intelligent control method for the coffee cup production process.

[0061] Figure 3 This is a second sub-process flowchart of the intelligent control method for the coffee cup production process.

[0062] Figure 4 This is the third sub-process flowchart of the intelligent control method for coffee cup production process.

[0063] Figure 5 This is the fourth sub-process flowchart of the intelligent control method for the coffee cup production process.

[0064] Figure 6 This is a structural block diagram of the intelligent control system for the coffee cup production process. DETAILED DESCRIPTION

[0065] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] Figure 1 : is a flowchart of an intelligent control method for a coffee cup production process. In an embodiment of the present invention, an intelligent control method for a coffee cup production process is provided. The method comprises:

[0067] Step S100: query the production equipment of the coffee cups, query the product yield of each production equipment during the damage period in the maintenance record table, and calculate the production weight of each production equipment according to the product yield;

[0068] The existing coffee cup production process is an intelligent production process, involving multiple intelligent production equipment; problems may occasionally occur during the use of the production equipment, and the production equipment needs to be inspected. Some of these production equipment are necessary equipment, and some are non-essential equipment; the product yield of each production equipment during the damage period is queried in the maintenance record table. The higher the product yield, the less important the production equipment is. Even if it is in a maintenance state, the production process can still proceed, and the corresponding production weight is lower; the production weight is used to characterize the importance of the production equipment in the production process.

[0069] Step S200: Determine the parameter range of the production equipment based on the production weight, randomly select a parameter from the parameter range of each production equipment and combine them, execute in a loop, and obtain a preset number of production plans;

[0070] A parameter range is determined based on the production weight, and the production equipment selects parameters within the parameter range to carry out production activities; after the parameter range of each production equipment is set, a parameter is randomly selected from the parameter range of each production equipment and combined, and the execution is repeated to obtain a preset number of production plans.

[0071] Step S300: for each production plan, generate a control instruction based on the production plan, send it to the production equipment, and synchronously obtain product quality parameters;

[0072] For each production plan generated, the parameters of each production equipment in the production plan are read, and control instructions are generated based on the parameters, which actually affect the amount of resources invested and the accuracy of the production equipment; after the production plan is put into use, the product is simultaneously tested to obtain product quality parameters; the product quality parameters are used to characterize the quality of the products output by the production equipment.

[0073] Among them, when for each production plan, a control instruction is generated based on the production plan, sent to the production equipment, and the product quality parameters are obtained simultaneously, this step is completed by the simulation software, the preset number can be more, such as two orders of magnitude, that is, hundreds of production plans, and the best plan is selected from hundreds of production plans; when for each production plan, a control instruction is generated based on the production plan, sent to the production equipment, and the product quality parameters are obtained simultaneously, this step is completed by the test assembly line, the preset number is in the single digit; on the contrary, if the actual scenario is used for testing, the test cycle will be very long. At this time, only a limited number of production plans can be tested to determine the optimal plan.

[0074] Step S400: selecting the best production plan according to the product quality parameters as the production plan for the next production cycle;

[0075] Using product quality parameters as evaluation indicators, various production plans are evaluated for their pros and cons, and the best production plan is selected as the production plan for the next production cycle.

[0076] Figure 2 This is a flowchart of the first sub-process of the intelligent control method for the coffee cup production process. The steps of querying the production equipment of the coffee cup, querying the product yield of each production equipment during the damage period in the maintenance record table, and calculating the production weight of each production equipment according to the product yield include:

[0077] Step S101: Query the production equipment of coffee cups;

[0078] Step S102: Locate the damage period of each production equipment in the maintenance record table, and simultaneously query the product yield; wherein, when the production of the product is stopped, the product yield is zero;

[0079] Step S103: determining the production weight of the production equipment according to the product yield; the relationship between the production weight and the product yield is an exponential function relationship.

[0080] In an example of the technical solution of the present invention, the process of determining the production weight is described. The production equipment of the coffee cups is queried, the damage period of each production equipment is located in the maintenance record table, and the product yield of the product in the corresponding period is queried simultaneously. When a certain production equipment is in the damage period, if the product stops production, it means that the importance of the production equipment is extremely high. At this time, the product yield is set to zero.

[0081] It is worth mentioning that the present application also takes into account the situation where two production equipment are damaged at the same time. It may be the product of the two product yields, or it may be directly zero. Therefore, it is also necessary to locate the situation of common damage in the maintenance record table. If the two production equipment are not damaged together, then the two production equipment are regarded as independent equipment. For a certain production equipment, when it and other production equipment are damaged together, the minimum value of its own product yield and the product yield of other production equipment is used as the final product yield, that is, the extreme case is selected.

[0082] Figure 3 This is a second sub-flow chart of the coffee cup production process intelligent control method. The step of determining the parameter range of the production equipment based on the production weight, randomly selecting a parameter from the parameter range of each production equipment and combining them, and executing them cyclically to obtain a preset number of production plans includes:

[0083] Step S201: querying the standard production parameters of each production equipment;

[0084] Step S202: determining a floating ratio according to the production weight, and determining a parameter range according to the floating ratio and the standard production parameter; the floating ratio is inversely proportional to the production weight;

[0085] Step S203: randomly selecting a parameter in the parameter range of each production equipment, combining the selected parameters according to the order of the production equipment, and obtaining a production plan;

[0086] Step S204: loop execution and record the total number of production plans, and when the total number reaches a preset number, output all the obtained production plans;

[0087] In an example of the technical solution of the present invention, the process of generating a production plan is described. First, the standard production parameters of each production equipment are queried. This is factory data and can be directly read. On this basis, the floating ratio is determined according to the production weight. The larger the production weight, the more important the production equipment, and the smaller the range determined according to the floating ratio. Then, a parameter is randomly selected from the parameter range of each production equipment, and the selected parameters are combined according to the order of the production equipment to obtain a production plan. Finally, the selection process is executed in a loop for multiple times. When the total number of production plans reaches a preset number, all the obtained production plans are output.

[0088] Figure 4 The third sub-flow chart of the intelligent control method for the coffee cup production process is as follows. For each production plan, the steps of generating a control instruction based on the production plan, sending the control instruction to the production equipment, and synchronously acquiring the product quality parameters include:

[0089] Step S301: for each production plan, query the production parameters of each production equipment in the production plan;

[0090] Step S302: Generate a control instruction based on the production parameters and send it to the production equipment;

[0091] Step S303: obtaining a product image of an output product of the production equipment, inputting the product image into a trained convolutional recognition model, and obtaining an abnormality type and abnormality level;

[0092] Step S304: Determine a product quality score according to the abnormality type and abnormality level as a product quality parameter.

[0093] For each production plan, the production parameters of each production equipment in the production plan are queried, and the production parameters are converted into control instructions and sent to the production equipment; when the production equipment receives the control instructions, it starts working. At this time, the product image of the output product of the production equipment is obtained, and the product image is input into the trained convolution recognition model to obtain the abnormality type and abnormality level; the abnormality type indicates which abnormalities have occurred in the product, and the abnormality level indicates the degree of the abnormality; finally, the product quality score is determined according to the abnormality type and abnormality level as the product quality parameter.

[0094] It is worth mentioning that the calculation process of the product quality score is to determine a basic score for each abnormality type, determine the multiple by the abnormality level, multiply the multiple by the basic score, and then add them up to get the product quality score.

[0095] Figure 5 This is a fourth sub-flow chart of the intelligent control method for the coffee cup production process. The step of selecting the optimal production plan according to the product quality parameters as the production plan for the next production cycle includes:

[0096] Step S401: Select the current optimal production plan according to the product quality parameters, and simultaneously update the global optimal production plan;

[0097] Step S402: determining adjustment vectors of other production plans based on the current optimal production plan and the global optimal production plan;

[0098] Step S403: updating all production plans based on the adjustment vector;

[0099] Step S404: The loop is iterated and when the preset number of iterations is reached, the global optimal production plan is output as the production plan for the next production cycle.

[0100] In the technical solution of the present invention, the selection process of the production plan is specifically limited, and a particle swarm iteration algorithm is adopted. The product quality parameter is used to characterize the quality of the product. According to the product quality parameter, the best production plan under the current number of iterations can be determined, which is called the current optimal production plan. On this basis, it is also necessary to record the optimal production plan at each iteration in real time as the global optimal production plan; all production plans are adjusted according to the current optimal production plan and the global optimal production plan, and the adjustment method adopts an adjustment vector, and all production plans are updated based on the adjustment vector; after multiple iterations, all production plans will approach the optimal production plan. In the process of approaching the optimal production plan, a large number of new and better plans will be generated (because each time it approaches the optimal production plan). These plans greatly increase the number of samples, and the current optimal production plan and the global optimal production plan will also be updated. After a sufficient number of iterations, the global optimal production plan is output. At this time, the global optimal production plan is close enough to the theoretical optimal production plan.

[0101] Specifically, the process of updating all production plans based on the adjustment vector is:

[0102] x i (t+1)=x i (t)+v i (t+1);

[0103] v i (t+1)=ω·v i (t)+c 1 ·r 1 ·(p i -x i (t))+c 2 ·r 2 ·(g(t)-x i (t));

[0104] In the formula, x i(t+1) represents the production plan of the i-th production plan after the (t+1)th iteration, x i (t) represents the production plan of the i-th production plan after the t-th iteration, v i (t+1) represents the adjustment vector of the i-th production plan at the (t+1)th iteration, v i (t) represents the adjustment vector of the i-th production plan at the t-th iteration, ω is the preset inertia weight, c 1 and c 2 is the preset acceleration constant, r 1 and r 2 is a preset random number, the selection range is (0,1); p i is the optimal production plan of the ith production plan in the historical iteration process, that is, the current optimal production plan; g(t) represents the optimal plan of all production plans at the tth iteration, that is, the global optimal production plan.

[0105] The meaning of the above content is that each time a new iteration is performed, an adjustment vector is determined based on the previous iteration result, and the production plan is composed of x i (t) indicates that it is an array whose dimension is the same as the total number of production equipment, and the value of each element is a production parameter of the production equipment; regarding the adjustment vector, it is affected by the previous adjustment vector, the current optimal production plan, and the global optimal production plan.

[0106] Figure 6 : is a structural block diagram of a coffee cup production process intelligent control system. In an embodiment of the present invention, a coffee cup production process intelligent control system is provided. The system 10 includes:

[0107] The production weight calculation module 11 is used to query the production equipment of the coffee cups, query the product yield of each production equipment during the damage period in the maintenance record table, and calculate the production weight of each production equipment according to the product yield;

[0108] The production plan generation module 12 is used to determine the parameter range of the production equipment based on the production weight, randomly select a parameter from the parameter range of each production equipment and combine them, execute them cyclically, and obtain a preset number of production plans;

[0109] The quality parameter acquisition module 13 is used to generate a control instruction based on each production plan, send it to the production equipment, and synchronously acquire the product quality parameters;

[0110] The production plan updating module 14 is used to select the best production plan according to the product quality parameters as the production plan for the next production cycle;

[0111] Among them, when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the simulation software, the preset number is two orders of magnitude; when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the test assembly line, the preset number is in the single digit.

[0112] Furthermore, the production weight calculation module 11 includes:

[0113] Equipment query unit, used to query the production equipment of coffee cups;

[0114] The product yield query unit is used to locate the damage period of each production equipment in the maintenance record table and simultaneously query the product yield; when the production of the product is stopped, the product yield is zero;

[0115] A calculation execution unit is used to determine the production weight of the production equipment according to the product yield; the relationship between the production weight and the product yield is an exponential function relationship.

[0116] Specifically, the production plan generating module 12 includes:

[0117] Standard parameter query unit, used to query the standard production parameters of each production equipment;

[0118] A floating parameter calculation unit, used to determine a floating ratio according to the production weight, and to determine a parameter range according to the floating ratio and a standard production parameter; the floating ratio is inversely proportional to the production weight;

[0119] A parameter combination unit is used to randomly select a parameter in the parameter range of each production equipment, and combine the selected parameters according to the order of the production equipment to obtain a production plan;

[0120] A plan output unit is used to execute cyclically and record the total number of production plans. When the total number reaches a preset number, all the obtained production plans are output;

[0121] Among them, the process of determining the floating ratio is:.

[0122] In addition, the quality parameter acquisition module 13 includes:

[0123] A production parameter query unit, used for querying the production parameters of each production equipment in each production plan;

[0124] An instruction sending unit, used to generate a control instruction based on the production parameters and send it to the production equipment;

[0125] A recognition unit, used to obtain a product image of an output product of a production device, input the product image into a trained convolutional recognition model, and obtain an abnormality type and abnormality level;

[0126] The score generating unit is used to determine the product quality score according to the abnormality type and abnormality level as a product quality parameter.

[0127] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A coffee cup production process intelligent control method, characterized in that: The method comprises: Query the production equipment of coffee cups, query the product yield of each production equipment during the damage period in the maintenance record table, and calculate the production weight of each production equipment based on the product yield; Determine the parameter range of the production equipment based on the production weight, randomly select a parameter from the parameter range of each production equipment and combine them, execute them cyclically, and obtain a preset number of production plans; For each production plan, control instructions are generated based on the production plan and sent to the production equipment to synchronously obtain product quality parameters; Select the best production plan based on product quality parameters as the production plan for the next production cycle; Among them, when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the simulation software, the preset number is two orders of magnitude; when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the test assembly line, the preset number is in the single digit.

2. The intelligent control method for coffee cup production process according to claim 1, characterized in that: The steps of querying the production equipment of the coffee cups, querying the product yield of each production equipment during the damage period in the maintenance record table, and calculating the production weight of each production equipment according to the product yield include: Check the production equipment of coffee cups; Locate the damage period of each production equipment in the maintenance record table and query the product yield simultaneously; when the production of the product is stopped, the product yield is zero; The production weight of the production equipment is determined according to the product yield; the relationship between the production weight and the product yield is an exponential function relationship.

3. The intelligent control method for coffee cup production process according to claim 1, characterized in that: The step of determining the parameter range of the production equipment based on the production weight, randomly selecting a parameter from the parameter range of each production equipment and combining them, and executing them cyclically to obtain a preset number of production plans includes: Query the standard production parameters of each production equipment; Determine the floating ratio according to the production weight, and determine the parameter range according to the floating ratio and the standard production parameter; the floating ratio is inversely proportional to the production weight; A parameter is randomly selected from the parameter range of each production equipment, and the selected parameters are combined according to the order of the production equipment to obtain a production plan; The loop is executed and the total number of production plans is recorded. When the total number reaches the preset number, all the obtained production plans are output.

4. The intelligent control method for coffee cup production process according to claim 1, characterized in that: The step of generating a control instruction based on the production plan for each production plan, sending the control instruction to the production equipment, and synchronously acquiring the product quality parameters includes: For each production plan, query the production parameters of each production equipment in the production plan; Generate control instructions based on the production parameters and send them to the production equipment; Obtain a product image of an output product of a production device, input the product image into a trained convolutional recognition model, and obtain an abnormality type and abnormality level; The product quality score is determined according to the abnormality type and abnormality level as a product quality parameter.

5. The intelligent control method for coffee cup production process according to claim 1, characterized in that: The step of selecting the optimal production plan according to the product quality parameters as the production plan for the next production cycle includes: Select the current optimal production plan based on product quality parameters and simultaneously update the global optimal production plan; Determine adjustment vectors of other production plans based on the current optimal production plan and the global optimal production plan; Update all production plans based on the adjustment vector; The loop is executed iteratively, and when the preset number of iterations is reached, the global optimal production plan is output as the production plan for the next production cycle.

6. The intelligent control method for coffee cup production process according to claim 5, characterized in that: The process of updating all production plans based on the adjustment vector is as follows: x i (t+1)=x i (t)+v i (t+1); v i (t+1)=ω·v i (t)+c1·r1·(p i -x i (t))+c2·r2·(g(t)-x i (t)); In the formula, x i (t+1) represents the production plan of the i-th production plan after the (t+1)th iteration, x i (t) represents the production plan of the i-th production plan after the t-th iteration, v i (t+1) represents the adjustment vector of the i-th production plan at the (t+1)th iteration, v i (t) represents the adjustment vector of the ith production plan at the tth iteration, ω is the preset inertia weight, c1 and c2 are the preset acceleration constants, r1 and r2 are the preset random numbers, and the selection range is (0, 1); p i is the optimal production plan of the ith production plan in the historical iteration process, that is, the current optimal production plan; g(t) represents the optimal plan of all production plans at the tth iteration, that is, the global optimal production plan.

7. An intelligent control system for coffee cup production process, characterized in that: The system comprises: The production weight calculation module is used to query the production equipment of coffee cups, query the product yield of each production equipment during the damage period in the maintenance record table, and calculate the production weight of each production equipment according to the product yield; A production plan generation module is used to determine the parameter range of production equipment based on production weights, randomly select a parameter from the parameter range of each production equipment and combine them, execute them cyclically, and obtain a preset number of production plans; A quality parameter acquisition module is used to generate control instructions based on each production plan, send them to the production equipment, and synchronously acquire product quality parameters; The production plan update module is used to select the optimal production plan according to product quality parameters as the production plan for the next production cycle; Among them, when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the simulation software, the preset number is two orders of magnitude; when for each production plan, the step of generating control instructions based on the production plan, sending them to the production equipment, and synchronously obtaining product quality parameters is completed by the test assembly line, the preset number is in the single digit.

8. The intelligent control system for coffee cup production process according to claim 7, characterized in that: The production weight calculation module includes: Equipment query unit, used to query the production equipment of coffee cups; The product yield query unit is used to locate the damage period of each production equipment in the maintenance record table and query the product yield simultaneously; when the production of the product is stopped, the product yield is zero; A calculation execution unit is used to determine the production weight of the production equipment according to the product yield; the relationship between the production weight and the product yield is an exponential function relationship.

9. The intelligent control system for coffee cup production process according to claim 7, characterized in that: The production plan generation module includes: Standard parameter query unit, used to query the standard production parameters of each production equipment; A floating parameter calculation unit, used to determine a floating ratio according to the production weight, and to determine a parameter range according to the floating ratio and a standard production parameter; the floating ratio is inversely proportional to the production weight; A parameter combination unit is used to randomly select a parameter in the parameter range of each production equipment, and combine the selected parameters according to the order of the production equipment to obtain a production plan; A plan output unit is used to execute cyclically and record the total number of production plans. When the total number reaches a preset number, all the obtained production plans are output; Among them, the process of determining the floating ratio is:.

10. The intelligent control system for coffee cup production process according to claim 7, characterized in that: The quality parameter acquisition module includes: A production parameter query unit, used for querying the production parameters of each production equipment in each production plan; An instruction sending unit, used to generate a control instruction based on the production parameters and send it to the production equipment; A recognition unit, used to obtain a product image of an output product of a production device, input the product image into a trained convolutional recognition model, and obtain an abnormality type and abnormality level; The score generating unit is used to determine the product quality score according to the abnormality type and abnormality level as a product quality parameter.

Images