A material loss control method based on data analysis

Abstract

The present invention relates to the technical field of material loss supervision and management, and specifically to a material loss control method based on data analysis, which first obtains the total amount of production materials, the construction period, and the production characteristic parameters of each production equipment, and then establishes multiple initial allocation vectors, and then optimizes the multiple initial allocation vectors according to a preset optimization algorithm to obtain the optimal allocation vector, and finally allocates the production materials to multiple production equipment for production based on the optimal allocation vector. Compared with the prior art, the present invention digitally represents the production scheduling problem by designing the initial allocation vector and the evaluation function, so that the present invention can be interpreted as a multi-objective optimization problem and solved through a preset optimization algorithm to find the best solution that can balance material loss and production time, and solves the problem of how to schedule production according to the loss rate to take into account material loss and production time, and ensure on-time delivery of products while minimizing loss costs.

Description

Technical Field

[0001] The present invention relates to the technical field of material loss supervision management, and in particular to a material loss control method based on data analysis. Background Art

[0002] Material loss control is a key link in manufacturing and supply chain management, and its importance cannot be ignored. Material loss not only affects the cost-effectiveness of the enterprise, but may also have a negative impact on product quality, production efficiency and customer satisfaction.

[0003] The causes of material loss are complex and varied. Among them, the equipment itself, such as equipment aging, wear, failure, etc., is an important factor leading to material loss. These factors are usually closely related to the service life and maintenance status of the equipment. As the equipment is used for a longer time, its performance will gradually decline, resulting in increased material loss.

[0004] In order to reduce losses, we can generally adopt the strategy of reducing the production volume of equipment with higher loss rates. By optimizing production plans and adjusting production processes, we can reduce the frequency of use of these equipment, thereby reducing losses. However, in practice, this strategy needs to find a balance between reducing losses and ensuring production efficiency. Because reducing the use of certain equipment may lead to an extension of the production cycle and affect the on-time delivery of products. Therefore, how to schedule production according to the loss rate to take into account material losses and production time, and ensure on-time delivery of products while minimizing loss costs, is a problem that people need to solve. Summary of the invention

[0005] The purpose of the present invention is to provide a material loss control method based on data analysis to solve the following technical problems:

[0006] How to schedule production based on the loss rate to take into account material loss and production time, and ensure on-time delivery of products while minimizing loss costs.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A material loss control method based on data analysis includes the following steps:

[0009] Obtain the total amount of production materials, construction duration, and production characteristic parameters of each production equipment, including material loss rate and material consumption rate;

[0010] Establish multiple initial allocation vectors according to the total amount of materials, the construction period and the number of production equipment, and each element value in the initial allocation vector is used to represent the allocation amount of the production material to each production equipment;

[0011] An evaluation function is established according to the construction period and production characteristic parameters. The evaluation function is used to calculate the excellence value of an initial allocation vector. The excellence value is used to indicate the quality of the allocation scheme represented by the initial allocation vector. The lower the material loss that can be achieved by the allocation scheme represented by the initial allocation vector and the shorter the production time, the better the initial allocation vector is.

[0012] Based on the evaluation function, multiple initial allocation vectors are optimized according to a preset optimization algorithm to obtain an optimal allocation vector;

[0013] Production materials are allocated to multiple production equipment for production based on the optimal allocation vector.

[0014] As a further solution of the present invention: multiple initial allocation vectors are established according to the total amount of materials, the construction period and the number of production equipment, including:

[0015] Based on the total amount of materials, construction duration and material consumption rate, calculate the solution space of the initial allocation vector;

[0016] Perform uniform distribution sampling in the solution space to obtain multiple first allocation vectors;

[0017] Performing a random adjustment on each first allocation vector to obtain a plurality of second allocation vectors;

[0018] The first allocation vector and the second allocation vector are used together as the initial allocation vector.

[0019] As a further solution of the present invention: the evaluation function is:

[0020] ;

[0021] Among them, F represents the excellent value of an initial allocation vector, x represents the allocation amount of a production equipment represented in the initial allocation vector, v represents the material consumption rate of the production equipment, rloss represents the material loss rate of the production equipment, C(x,v,rloss) represents the production loss cost of the production equipment calculated based on the allocation amount x, material consumption rate v and material loss rate rloss corresponding to the production equipment, T(x,v) represents the production time of the production equipment calculated based on the allocation amount x and material consumption rate v corresponding to the production equipment, ΣC(x,v,rloss) represents the sum of the production loss costs of each production equipment represented by the initial allocation vector, maxT(x,v) represents the maximum value of the production time of each production equipment represented by the initial allocation vector, w1 and w2 are different preset weight coefficients, and F0 is a preset hyperparameter.

[0022] As a further solution of the present invention: the production characteristic parameter also includes the yield rate of the production equipment; the specific expression for calculating the production loss cost is:

[0023] ;

[0024] Among them, rpass represents the yield rate of the production equipment, Closs(x,v,rloss) represents the material loss cost of the production equipment calculated based on the allocation amount x, material consumption rate v and material loss rate rloss corresponding to the production equipment, and Cpass(x,v,rpass) represents the defective product loss cost of the production equipment calculated based on the allocation amount x, material consumption rate v and yield rate rpass corresponding to the production equipment.

[0025] As a further solution of the present invention: the production characteristic parameters also include the loss rate growth coefficient of the production equipment; the specific expression for calculating the material loss cost is:

[0026] ;

[0027] Among them, eloss represents the loss rate growth coefficient of the production equipment, t is the time variable, and d is the integral operator.

[0028] As a further solution of the present invention: the production characteristic parameters also include the yield reduction coefficient of the production equipment; the specific expression for calculating the defective product loss cost is:

[0029] ;

[0030] Among them, epass represents the yield reduction coefficient of the production equipment, t is the time variable, and d is the integral operator.

[0031] As a further solution of the present invention: the specific expression for calculating the production time is:

[0032] ;

[0033] Among them, r is a random number between 0 and 1.

[0034] Beneficial effects of the present invention:

[0035] The present invention provides a material loss control method based on data analysis, which first obtains the total amount of production materials, the construction period and the production characteristic parameters of each production equipment, the production characteristic parameters include material loss rate and material consumption rate, and then establishes multiple initial allocation vectors according to the total amount of materials, the construction period and the number of production equipment, and then establishes an evaluation function according to the construction period and the production characteristic parameters, and then based on the evaluation function, optimizes multiple initial allocation vectors according to a preset optimization algorithm to obtain an optimal allocation vector, and finally allocates the production materials to multiple production equipment for production based on the optimal allocation vector. Among them, each element value in the initial allocation vector is used to characterize the allocation amount of the production material to each production equipment, and the evaluation function is used to calculate the excellent value of an initial allocation vector, and the excellent value is used to indicate the degree of pros and cons of the allocation scheme represented by the initial allocation vector, wherein the lower the material loss that can be achieved by the allocation scheme represented by an initial allocation vector, and the shorter the production time, the better the initial allocation vector. Compared with the prior art, the present invention digitally represents the production scheduling problem by designing an initial allocation vector and an evaluation function, and the representation method includes information such as the material loss rate and material consumption speed of different equipment. In this way, the present invention can be interpreted as a multi-objective optimization problem and solved through a preset optimization algorithm to find the best solution that can balance material loss and production time. It solves the problem of how to schedule production according to the loss rate to take into account material loss and production time, and ensure on-time delivery of products while minimizing loss costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present invention will be further described below in conjunction with the accompanying drawings.

[0037] Figure 1 It is a method flow chart of the material loss control method based on data analysis of the present invention;

[0038] Figure 2 yes Figure 1 Specific step diagram of step S102 in FIG. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] See also Figure 1 As shown, the present invention is a material loss control method based on data analysis, comprising the following steps:

[0041] S101, obtaining the total amount of production materials, the construction period, and the production characteristic parameters of each production equipment, where the production characteristic parameters include the material loss rate and the material consumption rate;

[0042] S102, establishing multiple initial allocation vectors according to the total amount of materials, the construction period, and the number of production equipment, wherein each element value in the initial allocation vector is used to represent the allocation amount of the production material to each production equipment;

[0043] S103, establishing an evaluation function according to the construction period and the production characteristic parameters, the evaluation function is used to calculate the excellence value of an initial allocation vector, the excellence value is used to indicate the excellence of the allocation scheme represented by the initial allocation vector, wherein the lower the material loss that can be achieved by the allocation scheme represented by the initial allocation vector and the shorter the production time, the better the initial allocation vector;

[0044] S104, based on the evaluation function, optimizing multiple initial allocation vectors according to a preset optimization algorithm to obtain an optimal allocation vector;

[0045] S105. Allocate production materials to multiple production equipment for production based on the optimal allocation vector.

[0046] Compared with the prior art, the present invention digitally represents the production scheduling problem by designing an initial allocation vector and an evaluation function, and the representation method includes information such as the material loss rate and material consumption speed of different equipment. In this way, the present invention can be interpreted as a multi-objective optimization problem and solved through a preset optimization algorithm to find the best solution that can balance material loss and production time. It solves the problem of how to schedule production according to the loss rate to take into account material loss and production time, and ensure on-time delivery of products while minimizing loss costs.

[0047] In the above process, the preset optimization algorithm can be any existing optimization algorithm such as genetic algorithm, particle swarm algorithm, etc. The evaluation function can be understood as a function similar to the fitness function in the genetic algorithm, which is used to evaluate the suitability of a solution (such as a chromosome in the genetic algorithm, an example in the particle swarm, and an initial allocation vector in the present invention) to screen it during the optimization process. Obviously, when establishing and optimizing the initial allocation vector, a series of constraints need to be followed. For example, in this embodiment, the amount of material represented by the sum of multiple element values ​​in the initial allocation vector needs to be equal to the total amount of material, and the actual production time corresponding to each initial allocation vector shall not exceed the duration of the construction period, etc. It can be understood that the optimization algorithm is a prior art that can be understood by those skilled in the art. Therefore, except for some improved technical features, other specific details in the process of optimizing multiple initial allocation vectors are not specifically described in this article, and it can be considered that these specific details are no different from the prior art.

[0048] Further, combined with Figure 2 As shown, in a preferred embodiment, the above step S102, establishing multiple initial allocation vectors according to the total amount of materials, the construction period and the number of production equipment, specifically includes:

[0049] S201, calculating the solution space of the initial allocation vector based on the total amount of materials, construction duration and material consumption rate;

[0050] S202, performing uniform distribution sampling in the solution space to obtain a plurality of first allocation vectors;

[0051] S203, performing a random adjustment on each first allocation vector to obtain a plurality of second allocation vectors;

[0052] S204: Use the first allocation vector and the second allocation vector together as an initial allocation vector.

[0053] In the above process, the solution space is the space where the initial allocation vector can take values. In some optimization algorithms, the determination of the initial allocation vector affects the convergence effect of the final optimization result, especially the particle swarm algorithm. Therefore, this embodiment first determines multiple first allocation vectors in the solution space by uniformly distributed sampling to ensure the balance of the initial allocation vector, and at the same time determines multiple second allocation vectors by random adjustment to increase randomness for the initial allocation vector. The combination of the two ensures the comprehensiveness of the initial allocation vector, thereby improving the accuracy of the final optimization result.

[0054] Furthermore, in a preferred embodiment, the above evaluation function is specifically:

[0055] ;

[0056] Among them, F represents the excellent value of an initial allocation vector, x represents the allocation amount of a production equipment represented in the initial allocation vector, v represents the material consumption rate of the production equipment, rloss represents the material loss rate of the production equipment, C(x,v,rloss) represents the production loss cost of the production equipment calculated based on the allocation amount x, material consumption rate v and material loss rate rloss corresponding to the production equipment, T(x,v) represents the production time of the production equipment calculated based on the allocation amount x and material consumption rate v corresponding to the production equipment, ΣC(x,v,rloss) represents the sum of the production loss costs of each production equipment represented by the initial allocation vector, maxT(x,v) represents the maximum value of the production time of each production equipment represented by the initial allocation vector, w1 and w2 are different preset weight coefficients, and F0 is a preset hyperparameter.

[0057] The significance of the above formula is to calculate the production loss cost and production time of the allocation scheme represented by an initial allocation vector respectively, and to comprehensively evaluate the pros and cons of an initial allocation scheme through these two dimensions. Only when the production loss cost and production time are both small, the initial allocation vector can achieve the maximum excellent value. Among them, the two preset weight coefficients can be flexibly adjusted according to specific needs, and the preset hyperparameters are used to control the size of the excellent value finally calculated to enhance the recognition.

[0058] It is understandable that the production loss cost in the above process can be represented by the material loss cost. In practice, the yield rate of different equipment is also different, and the number of defective products produced can also be regarded as part of the production loss cost. Therefore, when scheduling production, the yield rate should also be considered when calculating the production loss cost to obtain a more scientific and reasonable result. Therefore, the present invention also provides a preferred embodiment, in which the production characteristic parameters also include the yield rate of the production equipment; on this basis, the specific expression for calculating the production loss cost is:

[0059] ;

[0060] Among them, rpass represents the yield rate of the production equipment, Closs(x,v,rloss) represents the material loss cost of the production equipment calculated based on the allocation x, material consumption rate v and material loss rate rloss corresponding to the production equipment, and Cpass(x,v,rpass) represents the defective product loss cost of the production equipment calculated based on the allocation x, material consumption rate v and yield rate rpass corresponding to the production equipment. It can be understood that in practice, the weights of the two items in the above formula can be increased according to the specific situation (such as the specific values ​​of material loss and defective product cost) to obtain more accurate results.

[0061] In the above formula, the material loss cost can be directly obtained by multiplying the allocation amount of each production equipment by the material loss rate. In practice, production equipment generally needs to work 24 hours a day without interruption. At the same time, the production volume is generally of a larger order of magnitude, and the production period is also longer than usual. Under the above high-load working conditions, before the delivery date arrives, problems such as wear and tear of production equipment are very likely to be further aggravated, and the material loss rate of production equipment is very likely to increase further over time. Therefore, the present invention also provides a preferred embodiment, in which the production characteristic parameters also include the loss rate growth coefficient of the production equipment. On this basis, the specific expression for calculating the material loss cost is:

[0062] ;

[0063] Among them, eloss represents the loss rate growth coefficient of the production equipment, t is the time variable, and d is the integral operator.

[0064] The above formula directly uses the material loss amount to express the material loss cost. The most important thing is that when calculating the material loss cost, it takes into account the loss rate growth coefficient, so that the final calculated material loss cost is more in line with the actual situation.

[0065] Similarly, during the production process, the yield rate of the production equipment is also very likely to further decrease over time. Therefore, the present invention also provides a preferred embodiment, in which the production characteristic parameters also include a yield rate reduction coefficient of the production equipment; the specific expression for calculating the defective product loss cost is:

[0066] ;

[0067] Among them, epass represents the yield reduction coefficient of the production equipment, t is the time variable, and d is the integral operator.

[0068] The above formula directly uses the number of defective products to express the defective product loss cost. Most importantly, it takes into account the yield rate reduction coefficient when calculating the defective product loss cost, so that the final calculated defective product loss cost is more in line with the actual situation.

[0069] Furthermore, in a preferred embodiment, the specific expression for calculating the production time is:

[0070] ;

[0071] Among them, r is a random number between 0 and 1.

[0072] The above process is essentially to appropriately increase the item corresponding to the production time in the evaluation function. Because of the influence of personnel flow, production emergencies, etc. in practice, the production equipment cannot always operate in an ideal state, and the actual production time must be greater than the theoretically calculated time. Therefore, after calculating the theoretical production time of the production equipment through the allocation amount x and the material consumption rate v, this embodiment further corrects it through random numbers to make the final production time more reasonable and accurate.

[0073] The present invention provides a material loss control method based on data analysis, which first obtains the total amount of production materials, the construction period and the production characteristic parameters of each production equipment, the production characteristic parameters include material loss rate and material consumption rate, and then establishes multiple initial allocation vectors according to the total amount of materials, the construction period and the number of production equipment, and then establishes an evaluation function according to the construction period and the production characteristic parameters, and then based on the evaluation function, optimizes multiple initial allocation vectors according to a preset optimization algorithm to obtain an optimal allocation vector, and finally allocates the production materials to multiple production equipment for production based on the optimal allocation vector. Among them, each element value in the initial allocation vector is used to characterize the allocation amount of the production material to each production equipment, and the evaluation function is used to calculate the excellent value of an initial allocation vector, and the excellent value is used to indicate the degree of pros and cons of the allocation scheme represented by the initial allocation vector, wherein the lower the material loss that can be achieved by the allocation scheme represented by an initial allocation vector, and the shorter the production time, the better the initial allocation vector. Compared with the prior art, the present invention digitally represents the production scheduling problem by designing an initial allocation vector and an evaluation function, and the representation method includes information such as the material loss rate and material consumption speed of different equipment. In this way, the present invention can be interpreted as a multi-objective optimization problem and solved through a preset optimization algorithm to find the best solution that can balance material loss and production time. It solves the problem of how to schedule production according to the loss rate to take into account material loss and production time, and ensure on-time delivery of products while minimizing loss costs.

[0074] Working principle of the present invention:

[0075] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A material loss control method based on data analysis, characterized in that: The following steps are involved: Obtain the total amount of production materials, construction duration, and production characteristic parameters of each production equipment, including material loss rate and material consumption rate; Establish multiple initial allocation vectors according to the total amount of materials, the construction period and the number of production equipment, and each element value in the initial allocation vector is used to represent the allocation amount of the production material to each production equipment; An evaluation function is established according to the construction period and production characteristic parameters. The evaluation function is used to calculate the excellence value of an initial allocation vector. The excellence value is used to indicate the quality of the allocation scheme represented by the initial allocation vector. The lower the material loss that can be achieved by the allocation scheme represented by the initial allocation vector and the shorter the production time, the better the initial allocation vector is. Based on the evaluation function, multiple initial allocation vectors are optimized according to a preset optimization algorithm to obtain an optimal allocation vector; Allocate production materials to multiple production equipment for production based on the optimal allocation vector; The evaluation function is: ； Among them, F represents the excellent value of an initial allocation vector, x represents the allocation amount of a production equipment represented in the initial allocation vector, v represents the material consumption rate of the production equipment, rloss represents the material loss rate of the production equipment, C(x,v,rloss) represents the production loss cost of the production equipment calculated based on the allocation amount x, material consumption rate v and material loss rate rloss corresponding to the production equipment, T(x,v) represents the production time of the production equipment calculated based on the allocation amount x and material consumption rate v corresponding to the production equipment, ΣC(x,v,rloss) represents the sum of the production loss costs of each production equipment represented by the initial allocation vector, max(T(x,v)) represents the maximum value of the production time of each production equipment represented by the initial allocation vector, w1 and w2 are different preset weight coefficients, and F0 is a preset hyperparameter.

2. The material loss control method based on data analysis according to claim 1 is characterized in that: Establish multiple initial allocation vectors based on the total amount of materials, construction duration, and number of production equipment, including: Based on the total amount of materials, construction duration and material consumption rate, calculate the solution space of the initial allocation vector; Perform uniform distribution sampling in the solution space to obtain multiple first allocation vectors; Performing a random adjustment on each first allocation vector to obtain a plurality of second allocation vectors; The first allocation vector and the second allocation vector are used together as the initial allocation vector.

3. The material loss control method based on data analysis according to claim 1 is characterized in that: The production characteristic parameters also include the yield rate of production equipment; the specific expression for calculating the production loss cost is: ； Among them, rpass represents the yield rate of the production equipment, Closs(x,v,rloss) represents the material loss cost of the production equipment calculated based on the allocation amount x, material consumption rate v and material loss rate rloss corresponding to the production equipment, and Cpass(x,v,rpass) represents the defective product loss cost of the production equipment calculated based on the allocation amount x, material consumption rate v and yield rate rpass corresponding to the production equipment.

4. The material loss control method based on data analysis according to claim 3 is characterized in that: The production characteristic parameters also include the loss rate growth coefficient of production equipment; the specific expression for calculating the material loss cost is: ； Among them, eloss represents the loss rate growth coefficient of the production equipment, t is the time variable, and d is the integral operator.

5. The material loss control method based on data analysis according to claim 3 is characterized in that: The production characteristic parameters also include the yield reduction coefficient of the production equipment; the specific expression for calculating the defective product loss cost is: ； Among them, epass represents the yield reduction coefficient of the production equipment, t is the time variable, and d is the integral operator.

6. The material loss control method based on data analysis according to claim 1 is characterized in that: The specific expression for calculating production time is: ； Among them, r is a random number between 0 and 1.

Images