Method for predicting installation time of air duct, operation control device and production system

By constructing a working time prediction model and using the backpropagation neural network model, the problem of difficult to control the production cycle and progress during the air duct assembly process is solved, and accurate prediction of the air duct installation working time and improvement of production efficiency are achieved.

CN119067241APending Publication Date: 2024-12-03HEFEI MIDEA REFRIGERATOR CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310631654.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the process of air duct assembly of home appliance products, it is difficult for the existing technology to accurately control the production cycle and production progress, resulting in the accumulation of materials and finished products, increasing production costs and reducing efficiency.

Method used

By obtaining historical installation data of the air duct, filtering key link data, building a working-time prediction model, using the backpropagation neural network model to perform working-time prediction, reducing dependence on human experience, providing accurate installation-time prediction data, and optimizing production plans.

Benefits of technology

Accurate prediction of air duct installation working hours is achieved, production costs are reduced, production efficiency and progress control capabilities are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067241A_ABST
    Figure CN119067241A_ABST
Patent Text Reader

Abstract

The invention provides a prediction method, an operation control device and a production system.The prediction method comprises the steps that historical installation data of an air duct are obtained, and the historical installation data comprise installation link data of a plurality of installation links; key link data having key influences on the air duct installation working hours are screened out from the multiple pieces of installation link data; constructing a man-hour prediction model according to the key link data; acquiring current installation data of the air duct; inputting the current installation data into the man-hour prediction model to obtain the predicted installation man-hour of the air duct; according to the technical scheme provided by the embodiment of the invention, the installation time required in the air duct installation process can be accurately predicted, effective reference data can be provided for organizing a production plan of a production line, and the production efficiency can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for predicting the man-hours for installing an air duct, an operation control device and a production system. Background Art

[0002] At present, assembly production lines play an important role in the manufacturing industry. They can organically combine multiple workstations and seamlessly complete each process in the production process, thereby effectively reducing production costs. With the continuous development and updating of home appliances, production lines for assembling home appliances have also been widely used. For large-scale manufacturing plans, there are complex and changeable assembly processes. For example, for the duct assembly plan in refrigerator manufacturing, duct assembly often includes multiple processes such as material preparation, duct installation, and finished product distribution. At the same time, the duct installation process often involves many different installation processes, and there is great uncertainty in time control. The production line manufacturing process in the relevant technology usually relies on the management of production line professionals, mainly based on personal experience to specify production plans and scheduling methods. This method lacks scientific analysis and cannot accurately control the production cycle. It is easy to have a large amount of materials and finished products piled up, which greatly increases production costs. At the same time, it is difficult to accurately control the production progress and reduce production efficiency. Summary of the invention

[0003] The purpose of the present invention is to solve at least one of the technical problems existing in the prior art, and to provide a method for predicting the work time of air duct installation, an operation control device and a production system, which can accurately predict the installation work time required for the air duct installation process, and can provide effective reference data for organizing the production plan of the production line, which is conducive to improving production efficiency.

[0004] In a first aspect, an embodiment of the present invention provides a method for predicting the man-hours for air duct installation, comprising:

[0005] Acquire historical installation data of the air duct, wherein the historical installation data includes installation link data of multiple installation links;

[0006] Filter out the key link data that has a key impact on the man-hours of the air duct installation from the plurality of installation link data;

[0007] Constructing a man-hour prediction model based on the key link data;

[0008] Obtaining current installation data of the air duct;

[0009] The current installation data is input into the man-hour prediction model to obtain the predicted installation man-hour of the air duct.

[0010] The method for predicting the installation man-hours of the air duct provided in accordance with the embodiment of the present invention has at least the following beneficial effects: by acquiring the historical installation data of the air duct, the historical installation status of the air duct can be reflected, the historical installation data includes the installation link data of multiple installation links in the air duct installation process, and by screening out the key link data that have a key impact on the installation man-hours of the air duct from the multiple installation link data, the complex historical installation data can be simplified, and at the same time, it is convenient to analyze the main installation links that affect the installation man-hours of the air duct, and construct a man-hour prediction model based on the key link data, which can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the man-hour prediction model, and the predicted installation man-hours of the air duct can be obtained by inputting the current installation data of the air duct into the man-hour prediction model, which can accurately predict the installation man-hours required for the air duct installation process, reduce the dependence on human experience in the manufacturing process, and greatly reduce costs. The predicted installation man-hours of the air duct can provide effective reference data for organizing the production plan of the production line, facilitate more accurate control of the production cycle, and effectively manage the production progress, which is conducive to improving production efficiency.

[0011] The above-mentioned method for predicting the man-hours for air duct installation also includes:

[0012] Predicting the man-hours of each installation link of the air duct according to the current installation data and the man-hour prediction model to obtain a plurality of predicted man-hours;

[0013] Determine a first influence of the predicted link working time on the predicted installation working time;

[0014] The predicted link man-hours with the highest first impact are determined as key link man-hours, and a target installation link corresponding to the key link man-hours is determined.

[0015] In this embodiment, by inputting the current installation data into the work time prediction model, the work time prediction model can realize the prediction of the work time of each installation link of the air duct, so as to obtain the predicted link work time corresponding to each installation link, and by determining the first influence degree of each predicted link work time on the predicted installation work time, the predicted link work time with the highest first influence degree is determined as the key link work time. The key link work time has the greatest impact on the predicted installation work time. According to the key link work time, the corresponding target installation link can be determined. The target installation link can be understood as the most redundant installation link in the air duct installation process. By analyzing the target installation link, it is convenient to optimize the process for the target installation link, so as to design a better process plan, which is conducive to improving the efficiency of air duct installation.

[0016] In the above-mentioned method for predicting the man-hours for air duct installation, there are multiple key link data, and the key link data having a key impact on the man-hours for air duct installation is screened out from the multiple installation link data, including:

[0017] Calculating the second influence of each of the installation link data on the air duct installation man-hours;

[0018] Sort the plurality of installation link data from high to low according to the second influence degree to obtain an influence link data sequence;

[0019] The first N installation link data are selected from the influencing link data sequence as key link data, wherein N is a natural number greater than 1.

[0020] In this embodiment, by calculating the second influence degree of each installation link data on the air duct installation time, the influence of each installation link data on the air duct installation time can be determined, and by sorting multiple installation link data from high to low according to the second influence degree, an influence link data sequence can be obtained, and by filtering out the first N installation link data in the influence link data sequence, multiple key link data that have a key influence on the air duct installation time can be obtained. In addition, by first sorting multiple installation link data according to the second influence degree, it is convenient to quickly filter out key link data, thereby greatly improving the search efficiency.

[0021] In the above-mentioned method for predicting the man-hours for air duct installation, the step of calculating the second influence of the data of each installation link on the man-hours for air duct installation includes:

[0022] Using mathematical modeling methods to perform multiple regression analysis on the data of multiple installation links and generate a target regression equation;

[0023] The second influence of each installation link data on the air duct installation man-hour is calculated according to the target regression equation.

[0024] In this embodiment, by using a mathematical modeling method to perform multivariate regression analysis on multiple installation link data, the influence of each installation link data on the air duct installation time can be effectively analyzed. The target regression equation constructed based on multiple installation link data of the air duct can be used to explain the relationship between the installation link data and the air duct installation time. According to the target regression equation, the second influence degree of each installation link data on the air duct installation time can be calculated, which is convenient for the subsequent screening of key link data that have a key impact on the air duct installation time.

[0025] In the above-mentioned method for predicting the man-hours for air duct installation, the installation link data includes the specification data of the air duct sub-components required for the installation link, and the multivariate regression analysis is performed on the plurality of the installation link data to generate the target regression equation, including:

[0026] Constructing a function formula for describing the relationship between the air duct installation time and the specification data;

[0027] The function formula is fitted and analyzed using a regression analysis method to obtain a target regression equation.

[0028] In this embodiment, since there may be certain differences in the air duct sub-components required for different installation links, and the specification data of different air duct sub-components will affect the working hours required for the installation link, by adopting a mathematical modeling method to construct a function formula for describing the relationship between the air duct installation working hours and the specification data of the air duct sub-components, it is possible to fully reflect the influence of the data of each installation link on the air duct installation working hours, and adopt a regression analysis method to fit the function formula so that the function formula reaches the best fitting relationship, thereby obtaining the target regression equation, which is convenient for the subsequent calculation of the second influence of the data of each installation link on the air duct installation working hours, which is beneficial to improving the accuracy of the data of the key links, and further can achieve more effective prediction of the air duct installation working hours.

[0029] In the above-mentioned method for predicting the man-hours for duct installation, there are multiple key link data, and the man-hour prediction model is constructed according to the key link data, including:

[0030] Constructing a back-propagation neural network model, and inputting a plurality of the key link data into the back-propagation neural network model;

[0031] The back propagation neural network model is iteratively trained according to the multiple key link data to obtain a trained man-hour prediction model.

[0032] In this embodiment, an error back propagation algorithm is used to obtain a man-hour prediction model. First, a back propagation neural network model is constructed, and multiple key link data are input into the back propagation neural network model. Since these key link data have a key impact on the man-hour of air duct installation, the back propagation neural network model is iteratively trained according to multiple key link data until the back propagation neural network model reaches a convergence state. Then, a man-hour prediction model can be obtained. The man-hour prediction model can accurately predict the man-hour required for the air duct installation process. It should be noted that the back propagation neural network model has the characteristics of strong nonlinear mapping ability and good robustness. The man-hour prediction model is obtained by training the back propagation neural network model, which can effectively improve the prediction accuracy and reliability of the man-hour prediction model. When the current installation data of any air duct is input into the man-hour prediction model, a highly accurate predicted installation man-hour can be output.

[0033] The above-mentioned method for predicting the man-hours for air duct installation also includes:

[0034] Acquire air duct verification data, wherein the air duct verification data includes actual installation man-hours;

[0035] In the process of iteratively training the back propagation neural network model, obtaining the difference between the predicted installation time output by the back propagation neural network model and the actual installation time;

[0036] The back propagation neural network model is modified according to the difference so that the difference is within a preset accuracy range.

[0037] In this embodiment, during the iterative training of the back propagation neural network model, the air duct verification data can be used to verify the training effect of the back propagation neural network model. By obtaining the predicted installation hours output by the back propagation neural network model and comparing the preset installation hours with the actual installation hours in the air duct verification data, the difference between the predicted installation hours and the actual installation hours can be obtained. The difference can reflect the training effect of the back propagation neural network model. The back propagation neural network model is continuously corrected according to the difference so that the difference is within the preset accuracy range, so that the back propagation neural network model can reach a convergence state, which is conducive to ensuring the prediction accuracy of the hour prediction model.

[0038] In the above-mentioned method for predicting the man-hours for air duct installation, the step of correcting the back propagation neural network model according to the difference degree includes:

[0039] When the difference is outside the preset accuracy range, an error fitting method is used to correct the back propagation neural network model.

[0040] In this embodiment, when the difference is outside the preset accuracy range, it means that the back propagation neural network model has not been trained, that is, the prediction accuracy of the current back propagation neural network model does not meet the requirements temporarily. Then, the error fitting method is used to correct the back propagation neural network model, which can improve the generalization ability of the model, so that the difference is within the preset accuracy range.

[0041] In the above-mentioned method for predicting the man-hours for air duct installation, the step of inputting the plurality of key link data into the back propagation neural network model includes:

[0042] Normalizing the working hours corresponding to the data of each key link to obtain a plurality of working hour characteristic data;

[0043] A plurality of the working hour feature data are input into the back propagation neural network model to train the back propagation neural network model according to the working hour feature data.

[0044] In this embodiment, after obtaining multiple key link data, the working hours corresponding to each key link data are normalized to obtain multiple working hour feature data. Normalization can make data processing more convenient. At the same time, the working hour feature data can better reflect the impact of each key link data on the duct installation working hours. By inputting multiple working hour feature data into the back propagation neural network model, and iteratively training the back propagation neural network model according to the working hour feature data to obtain a working hour prediction model, the prediction accuracy of the working hour prediction model for the duct installation working hours can be improved.

[0045] In a second aspect, an embodiment of the present invention provides an operation control device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the prediction method as described in the embodiment of the first aspect above.

[0046] The operation control device provided according to the embodiment of the present invention has at least the following beneficial effects: by acquiring the historical installation data of the air duct, the historical installation status of the air duct can be reflected, and the historical installation data includes the installation link data of multiple installation links in the air duct installation process, and by screening out the key link data that has a key impact on the air duct installation man-hours from the multiple installation link data, the complex historical installation data can be simplified, and at the same time, it is convenient to analyze the main installation links that affect the air duct installation man-hours, and construct a man-hour prediction model based on the key link data, which can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the man-hour prediction model, and the predicted installation man-hours of the air duct can be obtained by inputting the current installation data of the air duct into the man-hour prediction model, which can accurately predict the installation man-hours required for the air duct installation process, reduce the dependence on human experience in the manufacturing process, and greatly reduce costs. The predicted installation man-hours of the air duct can provide effective reference data for organizing the production plan of the production line, which is convenient for more accurate control of the production cycle, and can effectively manage the production progress, which is conducive to improving production efficiency.

[0047] In a third aspect, an embodiment of the present invention provides a production system, comprising an operation control device as described in the embodiment of the second aspect above.

[0048] The production system provided according to the embodiment of the present invention has at least the following beneficial effects: by acquiring the historical installation data of the air duct, the historical installation status of the air duct can be reflected, and the historical installation data includes the installation link data of multiple installation links in the air duct installation process, and by screening out the key link data that has a key impact on the air duct installation man-hours from the multiple installation link data, the complex historical installation data can be simplified, and at the same time, it is convenient to analyze the main installation links that affect the air duct installation man-hours, and construct a man-hour prediction model based on the key link data, which can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the man-hour prediction model, and the predicted installation man-hours of the air duct can be obtained by inputting the current installation data of the air duct into the man-hour prediction model, which can accurately predict the installation man-hours required for the air duct installation process, reduce the dependence on human experience in the manufacturing process, and greatly reduce costs. The predicted installation man-hours of the air duct can provide effective reference data for organizing the production plan of the production line, facilitate more accurate control of the production cycle, and can effectively manage the production progress, which is conducive to improving production efficiency.

[0049] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the prediction method described in the embodiment of the first aspect above.

[0050] The computer-readable storage medium provided in accordance with the embodiment of the present invention has at least the following beneficial effects: by acquiring the historical installation data of the air duct, the historical installation status of the air duct can be reflected, the historical installation data includes the installation link data of multiple installation links in the air duct installation process, and by screening out the key link data that has a key impact on the air duct installation man-hours from the multiple installation link data, the complex historical installation data can be simplified, and at the same time, it is convenient to analyze the main installation links that affect the air duct installation man-hours, and construct a man-hour prediction model based on the key link data, which can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the man-hour prediction model, and the predicted installation man-hours of the air duct can be obtained by inputting the current installation data of the air duct into the man-hour prediction model, which can accurately predict the installation man-hours required for the air duct installation process, reduce the dependence on human experience in the manufacturing process, and greatly reduce costs. The predicted installation man-hours of the air duct can provide effective reference data for organizing the production plan of the production line, facilitate more accurate control of the production cycle, and can effectively manage the production progress, which is conducive to improving production efficiency.

[0051] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present invention is further described below in conjunction with the accompanying drawings and embodiments;

[0053] Figure 1 It is a flow chart of the method for predicting the man-hours for air duct installation provided in the first embodiment of the present invention.

[0054] Figure 2 Schematic diagram of the working hours distribution of the air duct assembly process provided by the second embodiment of the present invention;

[0055] Figure 3 is a flow chart of a method for predicting the man-hours for air duct installation provided in Embodiment 3 of the present invention;

[0056] Figure 4 is a flow chart of a method for predicting the man-hours for air duct installation provided by a fourth embodiment of the present invention;

[0057] Figure 5 is a flow chart of a method for predicting the man-hours for air duct installation provided in Embodiment 5 of the present invention;

[0058] Figure 6 is a flow chart of a method for predicting the man-hours for air duct installation provided in Embodiment 6 of the present invention;

[0059] Figure 7 is a flow chart of a method for predicting the man-hours for air duct installation provided in Embodiment 7 of the present invention;

[0060] Figure 8 is a flow chart of a method for predicting the man-hours for air duct installation provided in Embodiment 8 of the present invention;

[0061] Fig. 9 is a flow chart of a method for predicting the man-hours for air duct installation provided in Embodiment 9 of the present invention;

[0062] Fig.10 is a specific implementation flow chart of the method for predicting the man-hours for air duct installation provided in the tenth embodiment of the present invention;

[0063] Fig.11 It is a structural diagram of the operation control device provided in the eleventh embodiment of the present invention. DETAILED DESCRIPTION

[0064] This section will describe in detail the specific embodiments of the present invention. The preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the accompanying drawings is to supplement the description of the text part of the specification with graphics, so that people can intuitively and vividly understand each technical feature and the overall technical solution of the present invention, but it cannot be understood as a limitation on the scope of protection of the present invention.

[0065] It should be understood that in the description of the embodiments of the present invention, if there is a description of "first", "second", etc., it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features. "At least one" means one or more, "more than" means more than two, greater than, less than, exceeding, etc. are understood to not include the number itself, above, below, within, etc. are understood to include the number itself, and "several" means one or more, unless otherwise clearly and specifically limited. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. It can be understood that A and / or B can represent the situation where A exists alone, A and B exist at the same time, or B exists alone. Among them, A and B can be singular or plural.

[0066] In addition, unless otherwise clearly specified and limited, the term "connected / connected" should be understood in a broad sense, for example, it can be a fixed connection or a movable connection, a detachable connection or a non-detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or can communicate with each other; it can be directly connected or indirectly connected through an intermediate medium. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order from that in the flowchart. It should be noted that the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0067] The assembly line plays an important role in the manufacturing industry. It can organically combine multiple workstations and seamlessly complete each process in the production process, thereby effectively reducing production costs. With the continuous development and updating of home appliances, production lines for assembling home appliances have also been widely used. For large-scale manufacturing plans, there are complex and changeable assembly processes. For example, for the duct assembly plan in refrigerator manufacturing, duct assembly often includes multiple processes such as material preparation, duct installation, and finished product distribution. At the same time, the duct installation process often involves many different installation processes, and there is great uncertainty in time control. The production line manufacturing process in the relevant technology usually relies on the management of production line professionals, mainly based on personal experience to specify production plans and scheduling methods. This method lacks scientific analysis and cannot accurately control the production cycle. It is easy to have a large amount of materials and finished products piled up, which greatly increases production costs. At the same time, it is difficult to accurately control the production progress and reduce production efficiency.

[0068] Based on the above situation, an embodiment of the present invention proposes a method for predicting the installation time of the air duct, an operation control device, a production system and a computer-readable storage medium. The predicted installation time of the air duct can be obtained by inputting the current installation data of the air duct into the time prediction model. The installation time required for the air duct installation process can be accurately predicted, which reduces the dependence on human experience in the manufacturing process and greatly reduces costs. The predicted installation time of the air duct can provide effective reference data for organizing the production plan of the production line, which is convenient for more accurate control of the production cycle, and can effectively manage the production progress, which is conducive to improving production efficiency.

[0069] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0070] like Figure 1 As shown, the embodiment of the first aspect of the present invention provides a method for predicting the man-hours for air duct installation, including but not limited to steps S110 to S150:

[0071] Step S110: Acquire historical installation data of the air duct, wherein the historical installation data includes installation link data of multiple installation links;

[0072] It should be noted that the air duct installation process refers to the process of assembling and processing various materials of the air duct and finally combining them into a complete finished product. This process often involves many different installation processes, and usually requires the cooperation of multiple installation links to complete. It is understandable that the air duct installation process can be composed of multiple installation links. By obtaining the historical installation data of the air duct, that is, retrieving the historical original data, the historical installation data of the air duct includes the installation link data of multiple installation links in the air duct installation process, and each installation link has an impact on the air duct installation process.

[0073] In one embodiment, the air duct installation may be an air duct installation of a refrigerator, or an air duct installation of an air conditioning system.

[0074] Step S120: Filter out key link data that have a key impact on the man-hours of air duct installation from multiple installation link data;

[0075] The installation link data can reflect the man-hours of the corresponding installation links. The installation link data of different installation links have certain differences in their impact on the duct installation man-hours of the duct installation process. By obtaining the installation link data of multiple installation links of the duct, the impact of different installation link data on the duct installation man-hours can be analyzed, and the key link data that have a key impact on the duct installation man-hours can be screened out, which is convenient for analyzing the main installation links that affect the duct installation man-hours. For example, if the installation link data of installation link A has a key impact on the duct installation man-hours, it can be considered that installation link A has a greater impact on the duct installation process, which may be that the man-hours required to complete installation link A are longer, or that in the process of completing installation link A, it will have a greater impact on other installation links.

[0076] Step S130: constructing a man-hour prediction model based on key link data;

[0077] It should be noted that the man-hour prediction model is used to predict the installation man-hours required to complete the air duct installation process. By screening out the key link data that have a key impact on the air duct installation man-hours and building a man-hour prediction model based on the key link data, that is, using the key link data as sample data for modeling, it can simplify the modeling workload and effectively improve the modeling efficiency. At the same time, it can improve the prediction accuracy of the man-hour prediction model and ensure the reliability of the model.

[0078] Step S140: obtaining current installation data of the air duct;

[0079] Step S150: input the current installation data into the man-hour prediction model to obtain the predicted installation man-hour of the air duct.

[0080] Since there are many different types of finished products for air ducts, the installation data required for each air duct installation process may be different. By inputting the current installation data of the air duct into the labor time prediction model, the predicted installation labor time of the air duct can be obtained, that is, the installation labor time required to complete the air duct installation process can be predicted, which can facilitate the organization of production plans. For example, material preparation can be carried out in advance and finished product distribution can be reasonably arranged, so as to reduce material inventory costs and finished product distribution costs.

[0081] The method for predicting the installation man-hours of the duct provided in the above-mentioned first aspect embodiment can reflect the historical installation status of the duct by acquiring the historical installation data of the duct. The historical installation data includes the installation link data of multiple installation links in the duct installation process. By screening out the key link data that have a key impact on the installation man-hours of the duct from the multiple installation link data, the complex historical installation data can be simplified, and it is also convenient to analyze the main installation links that affect the installation man-hours of the duct. Constructing a man-hour prediction model based on the key link data can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the man-hour prediction model. The predicted installation man-hours of the duct can be obtained by inputting the current installation data of the duct into the man-hour prediction model, and the installation man-hours required for the duct installation process can be accurately predicted, which reduces the dependence on human experience in the manufacturing process and greatly reduces costs. The predicted installation man-hours of the duct can provide effective reference data for organizing the production plan of the production line, which is convenient for more accurate control of the production cycle, and can effectively manage the production progress, which is conducive to improving production efficiency.

[0082] It should be noted that the input data of the man-hour prediction model comes from the production line, which can realize the man-hour prediction of complex installation problems of the production line, and can provide production managers with more accurate man-hour data, so that production managers can prepare materials in advance and reasonably arrange the distribution of finished products. It can effectively reduce the accumulation of materials and finished products, provide better guidance for cost budgeting, and is conducive to the scientific management and control of production progress, greatly improving production efficiency. In addition, it is also possible to combine the predicted installation man-hour of the air duct, design a reasonable improvement plan for the air duct installation process, optimize the input allocation of each installation link, and improve the efficiency of air duct installation.

[0083] In one embodiment, the installation link data includes the man-hours required for the installation link, so as to better analyze the impact of the corresponding installation link on the man-hours for the air duct installation.

[0084] like Figure 2 As shown, in one embodiment, taking the duct assembly plan in refrigerator manufacturing as an example, the duct assembly process of the refrigerator consists of a material preparation process, a duct installation process and a finished product distribution process. The duct installation process consists of installation links such as workpiece organization, equipment selection, batch sorting, installation process, information recording and uploading, among which there are multiple installation processes. It should be noted that the installation link can be understood as a process that one (or a group of workers) continuously completes on several duct sub-components at a work site. For example, installation link A is the workpiece organization process, installation link B is the tape processing process (including installation processes such as sticking tape and tearing tape), and installation link C is the sponge strip processing (such as the installation process of sticking sponge strips). The duct installation process has many installation links, which consume the most man-hours and are the most uncontrollable in the entire duct assembly plan. Among them, Figure 2The time domain T in is the man-hours required for the duct installation process. The uncertainty of the duct installation process is the root cause of the material inventory risk and finished product distribution problems, and it is easy to have a large amount of material and finished product inventory pile up. The man-hour prediction model can accurately obtain the predicted installation man-hours of the duct, which is convenient for realizing the precise control of the duct installation process, which is conducive to improving the intelligence of the production line. At the same time, the entire duct assembly plan can be reasonably planned, such as preparing materials in advance and reasonably arranging the distribution of finished products, which can effectively reduce production costs.

[0085] In one embodiment, a commonly used artificial intelligence algorithm may be used to construct a working time prediction model, such as a back propagation (BP) neural network algorithm, a support vector machine (SVM) algorithm, etc., which is not specifically limited in the embodiment of the present invention.

[0086] like Figure 3 As shown, in the above-mentioned method for predicting the man-hours for air duct installation, it also includes but is not limited to steps S210 to S230:

[0087] Step S210: predicting the man-hours of each installation link of the air duct according to the current installation data and the man-hour prediction model, and obtaining the man-hours of multiple predicted links;

[0088] Step S220: determining the first influence of the man-hours of each predicted link on the predicted installation man-hours;

[0089] Step S230: Determine the predicted link man-hours with the highest first impact as the key link man-hours, and determine the target installation link corresponding to the key link man-hours.

[0090] In this embodiment, by inputting the current installation data into the work time prediction model, the work time prediction model can realize the prediction of the work time of each installation link of the air duct, so as to obtain the predicted link work time corresponding to each installation link, and by determining the first influence degree of each predicted link work time on the predicted installation work time, the influence of each installation link on the air duct installation process can be analyzed, and the predicted link work time with the highest first influence degree is determined as the key link work time, and the key link work time has the greatest influence on the predicted installation work time. According to the key link work time, the corresponding target installation link can be determined, and the target installation link can be understood as the most redundant installation link in the air duct installation process. By analyzing the target installation link, it is convenient to optimize the process for the target installation link, so as to design a better process plan, which is conducive to improving the efficiency of air duct installation.

[0091] In one embodiment, all predicted link working hours can be sorted from high to low. The predicted link working hours ranked at the front can be considered to have the highest first impact on the predicted installation working hours, and can be determined as key link working hours. The key link working hours occupy the largest proportion in the predicted installation working hours. By determining the target installation link corresponding to the key link working hours, the target installation link can be optimized to shorten the working hours required for the target installation link, thereby better shortening the working hours required for the air duct installation process.

[0092] In one embodiment, the predicted installation man-hours may be obtained by accumulating the predicted link man-hours corresponding to all installation links.

[0093] like Figure 4 As shown, in the above-mentioned method for predicting the duct installation time, there are multiple key link data. In step S120, the key link data that has a key impact on the duct installation time is screened out from the multiple installation link data, including but not limited to steps S310 to S330:

[0094] Step S310: Calculate the second influence of each installation link data on the air duct installation time;

[0095] Step S320: sorting the plurality of installation link data from high to low according to the second influence degree to obtain an influence link data sequence;

[0096] Step S330: Filter out the first N installation link data in the influencing link data sequence as key link data, where N is a natural number greater than 1.

[0097] In this embodiment, the historical installation data includes installation link data of multiple installation links. By calculating the second influence degree of each installation link data on the air duct installation working hours, the influence of each installation link data on the air duct installation working hours can be determined. By sorting the multiple installation link data from high to low according to the second influence degree, an influence link data sequence can be obtained. It can be understood that the influence link data sequence can reflect the influence degree of each installation link data on the air duct installation working hours. By screening out the first N installation link data in the influence link data sequence, multiple key link data that have a key influence on the air duct installation working hours can be obtained. By first sorting the multiple installation link data according to the second influence degree, it is convenient to quickly screen out the key link data, which greatly improves the search efficiency. In addition, constructing a working hour prediction model based on multiple key link data can not only simplify the modeling workload, but also ensure the representativeness of the modeling data, which is conducive to ensuring the prediction accuracy of the working hour prediction model.

[0098] In one embodiment, there are ten key link data. The second influence degree of each installation link data on the air duct installation time is calculated, and then the multiple installation link data are sorted from high to low according to the second influence degree to obtain an influence link data sequence. Then, the first ten installation link data in the influence link data sequence are screened out as key link data. It can be understood that by screening out ten key link data, ten key installation links can be determined, which is convenient for analyzing the main installation links that affect the air duct installation time.

[0099] like Figure 5 As shown, in the above-mentioned method for predicting the air duct installation time, the second influence degree of each installation link data on the air duct installation time is calculated in step S310, including but not limited to steps S410 and S420:

[0100] Step S410: using a mathematical modeling method to perform a multivariate regression analysis on the data of multiple installation links and generate a target regression equation;

[0101] Step S420: Calculate the second influence of each installation link data on the air duct installation time according to the target regression equation.

[0102] In this embodiment, by using a mathematical modeling method to perform multivariate regression analysis on multiple installation link data, the influence of each installation link data on the air duct installation working hours can be effectively analyzed. The target regression equation constructed based on multiple installation link data of the air duct can be used to explain the relationship between the installation link data and the air duct installation working hours. According to the target regression equation, the second influence of each installation link data on the air duct installation working hours can be calculated, which is convenient for the subsequent screening of key link data that have a key impact on the air duct installation working hours. It can be understood that the use of mathematical modeling methods can efficiently screen out modeling data for constructing a working hour prediction model, which can not only greatly simplify the modeling workload, but also ensure the reliability of the working hour prediction model.

[0103] It can be understood that the target regression equation belongs to a fixed effect econometric model. In one embodiment, the second influence degree can be determined by verifying the significance level of the air duct installation man-hours of the data of each installation link.

[0104] like Figure 6 As shown, in the above-mentioned method for predicting the man-hours for air duct installation, the installation link data includes the specification data of the air duct sub-components required for the installation link. In step S410, multiple regression analysis is performed on multiple installation link data and a target regression equation is generated, including but not limited to steps S510 and S520:

[0105] Step S510: constructing a function formula for describing the relationship between the air duct installation man-hours and specification data;

[0106] Step S520: Use a regression analysis method to perform fitting analysis on the function formula to obtain a target regression equation.

[0107] In this embodiment, since there may be certain differences in the air duct sub-components required for different installation links, and the specification data of different air duct sub-components will affect the working hours required for the installation link, by adopting a mathematical modeling method to construct a function formula for describing the relationship between the air duct installation working hours and the specification data of the air duct sub-components, it is possible to fully reflect the influence of the data of each installation link on the air duct installation working hours, and adopt a regression analysis method to fit the function formula so that the function formula reaches the best fitting relationship, thereby obtaining the target regression equation, which is convenient for the subsequent calculation of the second influence of the data of each installation link on the air duct installation working hours, which is beneficial to improving the accuracy of the data of the key links, and further can achieve more effective prediction of the air duct installation working hours.

[0108] In one embodiment, the specification data of the air duct sub-components may include but are not limited to data such as length, width, height, volume, bottom area, and sub-component category. The specification data of the air duct sub-components may be used as the independent variable of the function formula, and the air duct installation man-hour may be used as the dependent variable of the function formula. By continuously fitting and analyzing the function formula, the regression coefficient of each independent variable may be determined, and the regression coefficient may be verified. When it is determined that the verification passes, the regression coefficient may be substituted into the function formula to obtain the target regression equation.

[0109] Specifically, the target regression equation can be expressed by the following formula:

[0110] ST i =β0+β1*Length i +β2*Width i +β3*Highth i +β4*Volume i +β5*BA i +β6*FE i ;

[0111] Among them, ST i represents the man-hours for duct installation; β0 is a constant term; Length i Indicates length; Width i Indicates width; Height i Indicates height; Volume i Indicates volume, Volume i =Length i *Width i *Highth i BA i represents the bottom area;

[0112] BAi =Length i *Width i ; FE i represents the fixed effects used to control different sub-component categories; β1, β2, β3, β4, β5, and β6 represent regression coefficients.

[0113] like Figure 7 As shown, in the above-mentioned method for predicting the man-hours for air duct installation, there are multiple key link data. In step S130, a man-hour prediction model is constructed according to the key link data, including but not limited to steps S610 and S620:

[0114] Step S610: construct a back propagation neural network model, and input multiple key link data into the back propagation neural network model;

[0115] Step S620: iteratively train the back propagation neural network model according to multiple key link data to obtain a trained man-hour prediction model.

[0116] In this embodiment, an error back propagation algorithm is used to obtain a man-hour prediction model. First, a back propagation neural network model is constructed, and multiple key link data are input into the back propagation neural network model. Since these key link data have a key impact on the man-hour of air duct installation, the back propagation neural network model is iteratively trained according to multiple key link data until the back propagation neural network model reaches a convergence state. Then, a man-hour prediction model can be obtained. The man-hour prediction model can accurately predict the man-hour required for the air duct installation process. It should be noted that the back propagation neural network model has the characteristics of strong nonlinear mapping ability and good robustness. The man-hour prediction model is obtained by training the back propagation neural network model, which can effectively improve the prediction accuracy and reliability of the man-hour prediction model. When the current installation data of any air duct is input into the man-hour prediction model, a highly accurate predicted installation man-hour can be output.

[0117] like Figure 8 As shown, in the above-mentioned method for predicting the man-hours for air duct installation, it also includes but is not limited to steps S710 to S730:

[0118] Step S710: Acquire air duct verification data, wherein the air duct verification data includes actual installation man-hours;

[0119] Step S720: in the process of iteratively training the back propagation neural network model, obtaining the difference between the predicted installation time output by the back propagation neural network model and the actual installation time;

[0120] Step S730: modifying the back propagation neural network model according to the difference so that the difference is within a preset accuracy range.

[0121] In this embodiment, during the iterative training of the back propagation neural network model, the air duct verification data can be used to verify the training effect of the back propagation neural network model. By obtaining the predicted installation hours output by the back propagation neural network model and comparing the preset installation hours with the actual installation hours in the air duct verification data, the difference between the predicted installation hours and the actual installation hours can be obtained. The difference can reflect the training effect of the back propagation neural network model. The back propagation neural network model is continuously corrected according to the difference so that the difference is within the preset accuracy range, so that the back propagation neural network model can reach a convergence state, which is conducive to ensuring the prediction accuracy of the hour prediction model.

[0122] In the above-mentioned method for predicting the man-hours for air duct installation, the back propagation neural network model is corrected according to the difference in step S730, including the following steps:

[0123] When the difference is outside the preset accuracy range, the back propagation neural network model is corrected using the error fitting method.

[0124] In this embodiment, the difference between the predicted installation time output by the back propagation neural network model and the actual installation time is obtained, and it is determined whether the difference is within the preset accuracy range. When the difference is outside the preset accuracy range, it means that the back propagation neural network model has not been trained, that is, the prediction accuracy of the current back propagation neural network model does not meet the requirements temporarily. In this case, the back propagation neural network model is corrected by an error fitting method, which can improve the generalization ability of the model, so that the difference is within the preset accuracy range.

[0125] like Fig. 9 As shown, in the above-mentioned method for predicting the man-hours for air duct installation, in step S610, multiple key link data are input into the back propagation neural network model, including but not limited to steps S810 and S820:

[0126] Step S810: normalizing the working hours corresponding to the data of each key link to obtain a plurality of working hours characteristic data;

[0127] Step S820: Input a plurality of working hour feature data into the back propagation neural network model to train the back propagation neural network model according to the working hour feature data.

[0128] In this embodiment, after obtaining multiple key link data, the working hours corresponding to each key link data are normalized to obtain multiple working hour feature data. Normalization can make data processing more convenient. At the same time, the working hour feature data can better reflect the impact of each key link data on the duct installation working hours. By inputting multiple working hour feature data into the back propagation neural network model, and iteratively training the back propagation neural network model according to the working hour feature data to obtain a working hour prediction model, the prediction accuracy of the working hour prediction model for the duct installation working hours can be improved.

[0129] like Fig.10 As shown, in order to more clearly explain the method for predicting the man-hours for installing the air duct of the present invention, a specific embodiment will be used for further introduction. Taking the air duct installation process of a refrigerator as an example, the specific implementation process of the method for predicting the man-hours for installing the air duct of the present invention is as follows:

[0130] First, the air duct of a certain model of refrigerator is selected as the research object, and the original data set of the air duct in the historical installation process is obtained. The original data set may include historical installation data of multiple different finished product types, and the historical installation data includes installation link data of multiple installation links, and the installation link data includes specification data and working hours of air duct sub-components required for the installation link; mathematical modeling is performed on a historical installation data, and a function formula is constructed to describe the relationship between the air duct installation working hours and the specification data of the air duct sub-components, and the function formula is continuously fitted and analyzed to obtain a target regression equation, and the target regression equation is used to screen out the top ten key link data with a high degree of influence on the air duct installation working hours from multiple installation link data; then the working hours corresponding to these key link data are normalized to obtain multiple working hour characteristic data, and these working hour characteristic data are used as Sample data for training the BP neural network model, that is, converting key link data into sample data; iteratively training the BP neural network model through sample data, during which the training effect of the BP neural network model can be verified using air duct verification data to determine whether the prediction accuracy of the BP neural network model meets the requirements. If it does not meet the requirements, the BP neural network model is corrected until the prediction accuracy meets the requirements, and a working time prediction model is obtained; by inputting the current installation data of the air duct to be installed into the working time prediction model, the predicted installation working time of the air duct can be output, and the target installation link with the greatest impact on the air duct installation process can be determined; production managers can plan material preparation and finished product distribution based on the predicted installation working time, and can also optimize the process for this key installation link, which is conducive to greatly improving the efficiency of air duct installation.

[0131] It should be noted that the method for predicting the man-hours for air duct installation provided in the embodiment of the present invention can be applied to a terminal, or can be software running in the terminal. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the software can be an application for implementing the method for predicting the man-hours for air duct installation, etc., but is not limited to the above forms.

[0132] like Fig.11 As shown, the second aspect of the present invention provides an operation control device 1100, including a memory 1110, a processor 1120, and a computer program stored in the memory 1110 and executable on the processor 1120; the processor 1120 and the memory 1110 can be connected via a bus or other means. Fig.11 The example of bus connection is shown in FIG. 1 , and the processor 1120 executes the above computer program to implement the prediction method of the first aspect embodiment as described above, for example, to implement the above described Figure 1 Steps S110 to S150 of the method, Figure 3 Steps S210 to S230 of the method, Figure 4 Steps S310 to S330 of the method, Figure 5 Steps S410 and S420 of the method, Figure 6 Steps S510 and S520 of the method, Figure 7 Steps S610 and S620 of the method, Figure 8 Steps S710 to S730 of the method, Fig. 9 Method steps S810 and S820, and Fig.10 Method steps in. By obtaining the historical installation data of the air duct, the historical installation situation of the air duct can be reflected. The historical installation data includes the installation link data of multiple installation links in the air duct installation process. By screening out the key link data that have a key impact on the air duct installation time from the multiple installation link data, the complex historical installation data can be simplified, and it is convenient to analyze the main installation links that affect the air duct installation time. The time prediction model is constructed according to the key link data, which can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the time prediction model. The predicted installation time of the air duct can be obtained by inputting the current installation data of the air duct into the time prediction model, which can accurately predict the installation time required for the air duct installation process, reduce the dependence on human experience in the manufacturing process, and greatly reduce costs. The predicted installation time of the air duct can provide effective reference data for the production plan of the organization production line, which is convenient for more accurate control of the production cycle, and can effectively control the production progress, which is conducive to improving production efficiency.

[0133] A third aspect of the present invention provides a production system, comprising the operation control device of the second aspect of the present invention.

[0134] In this embodiment, by acquiring the historical installation data of the air duct, the historical installation status of the air duct can be reflected. The historical installation data includes the installation link data of multiple installation links in the air duct installation process. By screening out the key link data that have a key impact on the air duct installation working hours from the multiple installation link data, the complex historical installation data can be simplified, and at the same time, it is convenient to analyze the main installation links that affect the air duct installation working hours. Constructing a working hour prediction model based on the key link data can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the working hour prediction model. The predicted installation working hours of the air duct can be obtained by inputting the current installation data of the air duct into the working hour prediction model, and the installation working hours required for the air duct installation process can be accurately predicted, which reduces the dependence on human experience in the manufacturing process and greatly reduces costs. The predicted installation working hours of the air duct can provide effective reference data for organizing the production plan of the production line, which is convenient for more accurate control of the production cycle, and can effectively manage the production progress, which is conducive to improving production efficiency.

[0135] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions can be used to enable a computer to execute the prediction method of the first aspect of the present invention, for example, to execute the above-described Figure 1 Steps S110 to S150 of the method, Figure 3 Steps S210 to S230 of the method, Figure 4 Steps S310 to S330 of the method, Figure 5 Steps S410 and S420 of the method, Figure 6 Steps S510 and S520 of the method, Figure 7 Steps S610 and S620 of the method, Figure 8 Steps S710 to S730 of the method, Fig. 9 Method steps S810 and S820, and Fig.10Method steps in. By obtaining the historical installation data of the air duct, the historical installation situation of the air duct can be reflected. The historical installation data includes the installation link data of multiple installation links in the air duct installation process. By screening out the key link data that have a key impact on the air duct installation time from the multiple installation link data, the complex historical installation data can be simplified, and it is convenient to analyze the main installation links that affect the air duct installation time. The time prediction model is constructed according to the key link data, which can not only simplify the modeling workload, but also effectively improve the prediction accuracy of the time prediction model. The predicted installation time of the air duct can be obtained by inputting the current installation data of the air duct into the time prediction model, which can accurately predict the installation time required for the air duct installation process, reduce the dependence on human experience in the manufacturing process, and greatly reduce costs. The predicted installation time of the air duct can provide effective reference data for the production plan of the organization production line, which is convenient for more accurate control of the production cycle, and can effectively control the production progress, which is conducive to improving production efficiency.

[0136] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed methods above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium or a non-transitory medium and a communication medium or a temporary medium. As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk DVD or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0137] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present invention.

Claims

1. A method for predicting the man-hours for air duct installation, characterized in that: include: Acquire historical installation data of the air duct, wherein the historical installation data includes installation link data of multiple installation links; Filter out the key link data that has a key impact on the man-hours of the air duct installation from the plurality of installation link data; Constructing a man-hour prediction model based on the key link data; Obtaining current installation data of the air duct; The current installation data is input into the man-hour prediction model to obtain the predicted installation man-hour of the air duct.

2. The prediction method according to claim 1, characterized in that: Also includes: Predicting the man-hours of each installation link of the air duct according to the current installation data and the man-hour prediction model to obtain a plurality of predicted man-hours; Determine a first influence of the predicted link working time on the predicted installation working time; The predicted link man-hours with the highest first impact are determined as key link man-hours, and a target installation link corresponding to the key link man-hours is determined.

3. The prediction method according to claim 1, characterized in that: There are multiple key link data, and the key link data having a key impact on the air duct installation time is screened out from the multiple installation link data, including: Calculating the second influence of each of the installation link data on the air duct installation man-hours; Sort the plurality of installation link data from high to low according to the second influence degree to obtain an influence link data sequence; The first N installation link data are selected from the influencing link data sequence as key link data, wherein N is a natural number greater than 1.

4. The prediction method according to claim 3, characterized in that: The calculating of the second influence of each of the installation link data on the air duct installation man-hours includes: Using mathematical modeling methods to perform multiple regression analysis on the data of multiple installation links and generate a target regression equation; The second influence of each installation link data on the air duct installation man-hour is calculated according to the target regression equation.

5. The prediction method according to claim 4, characterized in that: The installation link data includes specification data of air duct sub-components required for the installation link, and the multivariate regression analysis is performed on a plurality of the installation link data to generate a target regression equation, including: Constructing a function formula for describing the relationship between the air duct installation time and the specification data; The function formula is fitted and analyzed using a regression analysis method to obtain a target regression equation.

6. The prediction method according to claim 1, characterized in that: There are multiple key link data, and the man-hour prediction model is constructed according to the key link data, including: Constructing a back-propagation neural network model, and inputting a plurality of the key link data into the back-propagation neural network model; The back propagation neural network model is iteratively trained according to the multiple key link data to obtain a trained man-hour prediction model.

7. The prediction method according to claim 6, characterized in that: Also includes: Acquire air duct verification data, wherein the air duct verification data includes actual installation man-hours; In the process of iteratively training the back propagation neural network model, obtaining the difference between the predicted installation time output by the back propagation neural network model and the actual installation time; The back propagation neural network model is modified according to the difference so that the difference is within a preset accuracy range.

8. The prediction method according to claim 7, characterized in that: The step of correcting the back propagation neural network model according to the difference comprises: When the difference is outside the preset accuracy range, an error fitting method is used to correct the back propagation neural network model.

9. The prediction method according to claim 6, characterized in that: The step of inputting the plurality of key link data into the back propagation neural network model comprises: Normalizing the working hours corresponding to the data of each key link to obtain a plurality of working hour characteristic data; A plurality of the working hour feature data are input into the back propagation neural network model to train the back propagation neural network model according to the working hour feature data.

10. An operation control device, characterized in that: The system comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the prediction method according to any one of claims 1 to 9.

11. A production system, characterized in that: Includes the operation control device as claimed in claim 10.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the prediction method according to any one of claims 1 to 9.