Method for predicting material receiving progress of material supplying and taking plant container
By establishing a material receiving time prediction model in a uranium enrichment plant, the error problem caused by relying on manual experience to judge the material receiving time of containers was solved, and real-time prediction and efficient management of the material receiving progress of containers were realized.
Patent Information
- Application Number
- CN202511151157.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-18
- Publication Date
- 2025-12-16
AI Technical Summary
In existing technologies, the completion time of container receiving in uranium enrichment production units mainly relies on manual experience to judge, which is prone to error. This makes it impossible for managers to arrange receiving work in a timely manner, which may delay the plan and increase the workload.
A material receiving time prediction model is adopted. By establishing a linear regression model based on the relationship between container weight and material receiving time in the training sample set, the model parameters are optimized using the least squares method to predict the container material receiving completion time.
It enables real-time prediction of container receiving progress, reduces the amount of manual calculation for managers, improves work efficiency, and helps managers to arrange production plans in a timely manner.
Smart Images
Figure FT_1 
Figure FT_2
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of uranium enrichment, and particularly relates to a method for predicting container material receiving progress of a feed and take material workshop. BACKGROUND
[0002] In a uranium enrichment production unit, due to the particularity of nuclear material production, production personnel need to maintain the container feeding and receiving system of the uranium enrichment feed and take material workshop, regularly replace the containers after feeding is completed and the containers after receiving is completed, and timely replace to meet the production requirements.
[0003] At present, the container receiving completion time is mainly judged by manual experience, and there is an error condition. There is a lack of prompt method for reminding the management personnel to complete the receiving, which leads to the fact that the management personnel cannot arrange the receiving work in time, may delay the work originally completed in the white shift to the middle shift, and zero point completion, which increases the unnecessary work burden of the shift running personnel, and may delay the container receiving plan. SUMMARY
[0004] The application aims to provide a method for predicting container receiving progress of a feed and take material workshop to solve the problem that the container receiving completion time is mainly judged by manual experience in the prior art.
[0005] The technical scheme for achieving the purpose of the application is as follows:
[0006] The method for predicting container receiving progress of a feed and take material workshop provided by the application comprises the following steps:
[0007] Obtaining a receiving expected value of a target container;
[0008] Inputting the receiving expected value into a pre-obtained receiving time prediction model to obtain a predicted receiving time of the target container;
[0009] The receiving time prediction model is obtained according to a training sample set; the training sample set comprises a corresponding relationship between container weight and receiving time.
[0010] According to the current time and the predicted receiving time, the receiving completion time of the target container is determined.
[0011] Optionally, the receiving time prediction model is obtained through the following steps:
[0012] Obtaining the training sample set;
[0013] Substituting the training sample set into a pre-established corresponding relationship model between container weight and receiving time to perform model training, and obtaining the receiving time prediction model.
[0014] Optionally, the obtaining method of the training sample set is as follows:
[0015] The sampling period is 10 seconds, 360 groups of sampling data are obtained, and the container weight data samples in one hour are obtained; 720 groups of sampling data are obtained, and the container weight data samples in two hours are obtained.
[0016] Optionally, the number of groups of sampling data is changed to obtain container weight data samples in different time.
[0017] Optionally, the average value of the sampling data is counted, the abnormal sampling data is deleted, and the average value is used to replace the abnormal sampling data.
[0018] Optionally, the corresponding relationship model of the container weight and the material receiving time is a linear regression model, and the relationship between the container weight y and the material receiving time x is y=a+bx.
[0019] Optionally, the least square method is used to determine the coefficients a and b of the linear regression model, so that the error between the predicted value and the actual value is minimized.
[0020] Optionally, the error between the predicted value and the actual value is measured by the mean square error of the two.
[0021] The beneficial technical effects of the present application are:
[0022] The method for predicting the container material receiving progress of the supply and take material plant provided by the embodiment of the present application predicts the container material receiving completion time according to the real-time container material receiving rate, the material receiving expectation and the current time, helps the uranium enrichment plant managers to know the container material receiving completion time node in time and arrange the production plan, designs the container material receiving rate calculation module and the time prediction module, greatly reduces the artificial calculation amount of the managers and improves the work efficiency, realizes the real-time prediction of the container material receiving progress, and provides convenient guidance for the container material receiving work arrangement. BRIEF DESCRIPTION OF DRAWINGS
[0023] Figure 1 The method for predicting the container material receiving progress of the supply and take material plant provided by the embodiment of the present application is a flowchart;
[0024] Figure 2 The software interface schematic diagram of the method for predicting the container material receiving progress of the supply and take material plant provided by the embodiment of the present application. DETAILED DESCRIPTION
[0025] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the following described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments described in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.
[0026] The method for container receiving progress prediction provided by the embodiment of the present application predicts the container receiving completion time according to the real-time receiving rate of the container, the receiving expectation and the current time, helps the uranium enrichment plant manager to understand the container receiving completion time node in time and arrange the production plan; greatly reduces the artificial calculation amount of the manager and improves the work efficiency; realizes the real-time prediction of the container receiving progress and provides convenient guidance for the container receiving work arrangement.
[0027] Based on the above, in order to clearly and specifically describe the above advantages of the present application, the specific embodiments of the present application will be described in conjunction with the accompanying drawings.
[0028] Referring to Figure 1 The figure is a flowchart of the method for container receiving progress prediction provided by the embodiment of the present application.
[0029] The method for container receiving progress prediction provided by the embodiment of the present application comprises:
[0030] Obtaining the receiving expectation value of the target container;
[0031] Inputting the receiving expectation value into the pre-obtained receiving time prediction model to obtain the predicted receiving time of the target container;
[0032] The receiving time prediction model is obtained according to a training sample set; the training sample set comprises a corresponding relationship between the container weight and the receiving time;
[0033] According to the current time and the predicted receiving time, determining the receiving completion time of the target container.
[0034] In some possible implementation manners of the embodiment of the present application, the receiving time prediction model is obtained through the following steps:
[0035] Obtaining the training sample set;
[0036] Substituting the training sample set into a pre-established corresponding relationship model between the container weight and the receiving time to perform model training and obtain the receiving time prediction model.
[0037] In one example, the obtaining method of the training sample set is:
[0038] The sampling period is 10 seconds, 360 groups of sampling data are obtained, and the container weight data samples in one hour are obtained; 720 groups of sampling data are obtained, and the container weight data samples in two hours are obtained.
[0039] It can be understood that the number of groups of the sampling data is changed to obtain the container weight data samples in different time.
[0040] The average of the sampling data is counted, the abnormal sampling data is deleted, and the average value is used to replace the abnormal sampling data.
[0041] In another example, the corresponding relationship model of the container weight and the material receiving time is a linear regression model, and the relationship between the container weight y and the material receiving time x is y=a+bx.
[0042] In the embodiment of the application, the least square method is used to determine the coefficients a and b of the linear regression model, so that the error between the predicted value and the actual value is minimized.
[0043] Optionally, the error between the predicted value and the actual value is measured by the mean square error of the two.
[0044] It can be understood that the smaller the mean square error of the measured value and the actual value, the higher the model accuracy.
[0045] The method for predicting the container material receiving progress provided by the embodiment of the application predicts the container material receiving completion time according to the real-time container material receiving rate, the material receiving expectation and the current time, helps the uranium enrichment plant managers to know the container material receiving completion time node in time and arrange the production plan, designs the container material receiving rate calculation module and the time prediction module, greatly reduces the manual calculation amount of the managers and improves the work efficiency, realizes the real-time prediction of the container material receiving progress, and provides convenient guidance for the container material receiving work arrangement.
[0046] The above only describes the preferred embodiments of the patent and does not limit the patent. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the patent should be included in the protection scope of the patent.
[0047] It should be noted that, for the foregoing method embodiments, in order to facilitate description, they are all described as a series of action combinations, but those skilled in the art should know that the application is not limited by the action order described, because according to the application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the application.
[0048] The preferred embodiments of the application disclosed above are only used to illustrate the present application. The alternative embodiments do not describe all the details and do not limit the application to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the present application. The embodiments are selected and described in detail in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and utilize the present application.
Claims
1. A method for predicting the material receiving progress of containers in a material handling plant, characterized in that, The method includes: Obtain the expected material receiving value of the target container; The expected material receiving value is input into the pre-obtained material receiving time prediction model to obtain the expected material receiving time of the target container; The material receiving time prediction model is trained based on a training sample set; the training sample set includes the correspondence between container weight and material receiving time. The receiving completion time of the target container is determined based on the current time and the estimated receiving time.
2. The method for predicting the material receiving progress of containers in a material supply and unloading plant according to claim 1, characterized in that, The material receiving time prediction model is obtained through the following steps: Obtain the training sample set; The training sample set is substituted into a pre-established model of the correspondence between container weight and receiving time to train the model and obtain the receiving time prediction model.
3. The method for predicting the material receiving progress of containers in a material supply and unloading plant according to claim 2, characterized in that, The method for obtaining the training sample set is as follows: The sampling period is 10 seconds, and 360 sets of sampling data are obtained to obtain the container weight data sample for one hour; 720 sets of sampling data are obtained to obtain the container weight data sample for two hours.
4. The method for predicting the material receiving progress of containers in a material supply and unloading plant according to claim 3, characterized in that, By changing the number of groups of the sampled data, container weight data samples at different time periods are obtained.
5. A method for predicting the material receiving progress of containers in a material supply and unloading plant according to claim 2 or 3, characterized in that, Calculate the average value of the sampled data, delete the abnormal sampled data, and replace the abnormal sampled data with the average value.
6. The method for predicting the material receiving progress of containers in a material supply and unloading plant according to claim 2, characterized in that, The relationship between container weight and receiving time is a linear regression model, where the relationship between container weight y and receiving time x is y = a + bx.
7. The method for predicting the material receiving progress of containers in a material supply and unloading plant according to claim 6, characterized in that, The coefficients a and b of the linear regression model are determined using the least squares method to minimize the error between the predicted and actual values.
8. The method for predicting the material receiving progress of containers in a material supply and unloading plant according to claim 7, characterized in that, The error between the predicted and actual values is measured using the mean squared error of the two.