A cuckoo-particle swarm-based intelligent machine tool man-machine interface layout optimization method

Abstract

This invention proposes a layout optimization method for the human-machine interface of intelligent machine tools based on a cuckoo-particle swarm optimization approach, belonging to the field of equipment interface ergonomics design. It includes determining the module importance of the intelligent machine tool human-machine interface, classifying visual perception intensity levels, constructing a layout optimization model, solving the layout optimization model, and evaluating the optimization effect. Based on the human-machine interaction task and the operator's cognitive characteristics, the ergonomic optimization design method for the intelligent machine tool human-machine interface is systematically studied. Furthermore, a solution method based on a cuckoo-particle swarm optimization hybrid intelligent algorithm is proposed, introducing a particle swarm optimization algorithm with inertial weight W into the cuckoo search algorithm to solve the problems of slow convergence and easy getting trapped in local optima in the later stages of the algorithm. Its beneficial effects are: obtaining an optimized layout scheme for the human-machine interface of CNC machine tools, improving the comfort and interaction efficiency of the human-machine interaction process of intelligent CNC machine tools, and providing good support for the optimization design of the human-machine interface of CNC machine tools.

Description

Technical Field

[0001] This invention relates to a method for optimizing the layout of a human-machine interface for intelligent machine tools based on cuckoo-particle swarm optimization, belonging to the field of equipment interface ergonomic design. Background Technology

[0002] In the wave of technological innovation in global manufacturing, intelligent manufacturing has become the mainstream trend in technological innovation in recent years. CNC machine tools, as a core competitive advantage in the field of intelligent manufacturing, have seen their intelligent development become a focal point of competition among nations. During the operation of intelligent machine tools, due to the large amount of feedback data, precise operation by the user is required to ensure machining quality. Therefore, the role of human-machine interaction in the operation of intelligent machine tools is self-evident. As the medium for information interaction between the machine tool and the operator, the simplicity and efficiency of the human-machine interface are primary factors in its design. The increasing functionality of the intelligent machine tool human-machine interface leads to increased complexity. To ensure user efficiency and reduce fatigue, comprehensive monitoring and real-time control of the intelligent machine tool should be achieved. Therefore, the optimized design of the intelligent machine tool human-machine interface is particularly important.

[0003] Users of intelligent machine tools have shifted from traditional operators to observers and decision-makers. This role change increases the cognitive demands on users, leading to increased cognitive load and workload, and consequently, low human-machine interaction efficiency. Existing research on human-machine interface optimization mainly focuses on information interface layout optimization and spatial layout optimization, achieving some success. However, considering the complexity of intelligent machine tool operation and multi-dimensional interactive information, especially the high integration and complexity of industrial control systems, existing human-machine interface layout optimization methods are insufficient to meet the multi-level, multi-functional, and multi-objective human-machine interaction requirements. The following problems remain to be solved:

[0004] (1) At present, the layout model of intelligent machine tool human-machine interface is optimized based on the experience of mechanical engineers. It is difficult to systematically take into account the viewing frequency, relevance and operation sequence of each functional module of the interface. The evaluation of each functional module is highly subjective, which makes it difficult for the current human-machine interface layout to meet the user's needs to improve work efficiency and enhance operation stability.

[0005] (2) Existing intelligent machine tool human-machine interface optimization methods are limited to meeting the basic functional requirements of the system, ignoring the operator's visual perception and the overall importance of each module in the interface. This makes it difficult to meet the complex cognitive requirements of human-machine interaction, such as multiple information and multiple processes, making it difficult for the operator to quickly and accurately obtain key parameter information, which in turn affects the operator's real-time control and creates safety hazards.

[0006] (3) When solving the layout optimization model of the human-machine interface of intelligent machine tools, the traditional optimization algorithm is prone to getting stuck in local optima and low solution quality due to improper setting of the importance of module parameter information. Summary of the Invention

[0007] This invention aims to provide a method for optimizing the layout of a human-machine interface for intelligent machine tools based on a cuckoo-particle swarm optimization approach, offering a better strategy for optimizing the design of human-machine interfaces for intelligent machine tools. The method includes the following steps:

[0008] S1. The importance of the intelligent machine tool human-machine interface module is determined.

[0009] S2. Classification of visual perception intensity levels for human-machine interfaces of intelligent machine tools.

[0010] S3, Construction of an optimized layout model for the human-machine interface of intelligent machine tools.

[0011] S4. Solving the layout optimization model of the human-machine interface for intelligent machine tools based on the cuckoo-particle swarm optimization algorithm.

[0012] Evaluation of the optimization effect of human-machine interface of S5 intelligent machine tool.

[0013] Furthermore, the specific method for optimizing the layout of the human-machine interface of the intelligent machine tool based on the cuckoo-particle swarm optimization is as follows:

[0014] (1) Analysis of the cognitive characteristics of human-machine interface of intelligent machine tool based on cognitive psychology

[0015] Analyzing user characteristics during the human-machine interaction process of intelligent CNC machine tools and determining the operator's cognitive characteristics of the intelligent machine tool human-machine interface, and incorporating these characteristics into the optimized design of the human-machine interface, can ultimately reduce user cognitive fatigue, increase operator comfort, enhance satisfaction with the human-machine interface layout, and improve work efficiency. Based on relevant theories of cognitive psychology, a user cognitive characteristic model of the intelligent machine tool human-machine interface is constructed, and user cognitive characteristics are analyzed in detail.

[0016] 1) Establish an interactive characteristic model for intelligent machine tools

[0017] Based on the differences between the interaction mode of current intelligent CNC systems and traditional complex systems, an interaction characteristic model of intelligent CNC systems is constructed.

[0018] 2) Establish a user cognitive characteristic model for the human-machine interface of intelligent machine tools.

[0019] To address the problem that the human-machine interface of intelligent CNC machine tools has a complex collection of multiple information, parameters, and encoded information, which makes it difficult for users to quickly locate the required task information, a user cognitive characteristic analysis is conducted to construct a user cognitive characteristic model for the human-machine interface of intelligent CNC machine tools.

[0020] (2) Module division of intelligent machine tool human-machine interface considering cognitive characteristics

[0021] The human-machine interface information of intelligent CNC machine tools is modularly decomposed. Based on the correlation of parameter information, the human-machine interface is divided into modules of different sizes. Each functional module in the human-machine interface is encoded using integer numbers from 1 to 20. There are no situations where functional modules should be arranged adjacently or should be avoided. The decomposed modules are then rearranged and optimized.

[0022] (3) Evaluation index system for the importance of human-machine interface module of intelligent machine tool

[0023] 1) Questionnaire content design for interface importance evaluation indicators

[0024] A total of 24 questions were asked and a questionnaire was distributed, focusing on the perception, memory, layout, inter-module relationships, attention resource allocation, and response speed of the human-machine interface of intelligent CNC machine tools.

[0025] 2) Questionnaire survey and data analysis

[0026] First, the reliability of the results was analyzed using SPSS software (a data processing and analysis software). Then, factor analysis was performed on the questionnaire for evaluating the importance of the human-machine interface module of intelligent machine tools, taking into account the cognitive characteristics of users.

[0027] 3) Construct an evaluation system for the importance of interface modules.

[0028] (4) A method for determining the importance of interface modules based on AHP-DEMATAL (Analytic Hierarchy Process - Decision Experiment and Evaluation Laboratory Method).

[0029] 1) First, create a hierarchical structure and use a 9-point scale to perform pairwise comparisons of the identified factors, constructing a pairwise comparison matrix. Determine the normalized weights of the identified factors and form a normalized weight vector. Based on the normalized vector, sort the factors according to their weights and complete the consistency test of the evaluation, where N is the order of the matrix.

[0030]

[0031]

[0032] 2) The creation of the direct relationship matrix involves experts performing pairwise comparisons of the identified parameters to determine the degree of influence of each parameter on the other parameters.

[0033] Construct the direct relation average matrix

[0034]

[0035] 3) Create a standardized direct relation matrix, and then multiply the direct relation matrix by the factor F to obtain an n*n normalized direct relation matrix.

[0036]

[0037] Z = F * A

[0038] 4) Calculation of the total relation matrix: The total relation matrix represents the total relation between all identified parameter pairs.

[0039] T = Z + Z 2 +Z 3 +Z h =Z(IZ) -1 (IZ) h

[0040]

[0041] T = Z(IZ) -1

[0042] 5) Determining the row and column sums and centrality of the overall relation matrix.

[0043]

[0044]

[0045] P = R + C

[0046] 6) Determine the weight of the comprehensive index: Let ω be the weight of the j-th evaluation index at the i-th level. je

[0047]

[0048] 7)ω j Let be the comprehensive weight value of the j-th indicator, which is equal to the product of the indicator's own weight and the weights of each level within its dimension.

[0049] ω j =ω j1 ω j2 ω j3

[0050] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S2 specifically involves the following method:

[0051] Reasonably allocate user attention resources, analyze the distribution of human eye gaze, clarify the user's visual perception intensity level and classify it reasonably, and integrate the visual perception intensity level with the modular division results of the intelligent CNC machine tool human-machine interface to determine the field of view distribution of each module area of ​​the intelligent CNC machine tool human-machine interface.

[0052] (1) Horizontal and vertical field of vision

[0053] When users read the human-machine interface of an intelligent CNC machine tool, they need to coordinate with the movement of their eyes to do so smoothly. By combining the horizontal and vertical field of vision of the human eye, the range of visual perception intensity of the user can be obtained.

[0054] (2) Distribution of visual perception areas

[0055] This paper analyzes the visual perception during the human-machine interface interaction process of intelligent CNC machine tools based on the View Cones and VisualFields modules in JACK (an ergonomic simulation software).

[0056] (3) Classification of interface visual perception intensity levels

[0057] Construct a modular interface for the human-machine interaction of intelligent CNC machine tools based on the intensity level of the visual perception area.

[0058] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S3 specifically involves the following method:

[0059] (1) Problem Description: Based on the layout optimization principles of the human-machine interface of intelligent CNC machine tools and related ergonomic principles, and combined with the visual perception intensity level of the parameter information of different module areas of the human-machine interface, the importance, relevance, operation sequence and viewing frequency of each module area in the human-machine interface are quantitatively analyzed. The modules with higher importance, relevance and viewing frequency are arranged in areas with higher visual perception intensity level. Attention is also paid to the logical degree between the operation relationships of each area. The goal is to maximize the overall intensity of the total importance of each module area in each visual perception intensity area. A layout optimization model of the human-machine interface of intelligent CNC machine tools based on visual perception intensity is constructed.

[0060] (2) Assumptions: This paper makes the following assumptions for the optimization of the layout of the human-machine interface of intelligent CNC machine tools: the size, quantity and internal composition of all module areas of the human-machine interface of intelligent CNC machine tools remain unchanged, there is no overlap between the module areas, and the layout range of the areas is within the boundary of the human-machine interface.

[0061] (3) Variable Definition: The main variables of the intelligent CNC machine tool human-machine interface layout optimization model are as follows:

[0062] W – Total importance, where W = ω + f + 0

[0063] K—Visual perception intensity level of different module areas, K ij Let be the intensity level of the i-th module region in the j-th visual perception region.

[0064] X — The number of units occupied by different levels of visual perception intensity module regions, X ij This represents the number of units occupied by the i-th module region within the j-th visual perception region.

[0065] U—The level of visual perception intensity in the region where the centroid of the module area is located. ij Let be the intensity level of the i-th module region in the j-th visual perception region.

[0066] n — Number of human-computer interaction interface module areas

[0067] m — Number of visual perception intensity levels in the human-computer interaction interface

[0068] Z – Overall Strength of Human-Computer Interface Layout Optimization

[0069] S – Total number of human-computer interaction interface units

[0070] The optimized layout model of the human-machine interface for intelligent CNC machine tools can be represented as:

[0071]

[0072] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S4 specifically involves the following method:

[0073] Step 1: Initialize relevant parameters, such as population size N;

[0074] Step 2: Set the perturbation iteration threshold T0, and set the upper and lower boundaries of the variables b and a, etc.

[0075] x = a + rand(1,D)*(ba)

[0076] Step 3: Calculate the fitness value of all nest sites in the population, and record the best nest site and its fitness value;

[0077] Step 4: Calculate the fitness value of the updated nest location and compare it with the fitness value of the nest location before the update, and retain the best nest location and its fitness value;

[0078]

[0079]

[0080]

[0081]

[0082]

[0083] Step 5: For each nest, discard it, calculate the fitness value of the nest location after discarding it, and compare it with the fitness value of the nest location before discarding it.

[0084]

[0085]

[0086] Step 6: For each nest, perform mutation, calculate the fitness value of the mutated nest location and compare it with the fitness value of the nest location before mutation;

[0087]

[0088] Step 7: Record the optimal nest location and its fitness value for each iteration. If T > T0, then perturb the nest and retain the optimal location of the population.

[0089] x best (t+1)=x best (t)+N(0,1)*(x i (t)-x j (t))

[0090] Step 8: Determine if the termination condition (maximum number of iterations) is met. If yes, output the optimal solution; otherwise, go to Step 3.

[0091] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S5 specifically involves the following method:

[0092] (1) Determination of the subjective and objective weighting of the evaluation of human-machine interface of intelligent machine tools

[0093] 1) Determining subjective weights using the BWM method (best-worst method)

[0094]

[0095]

[0096] 2) CRITIC method (objective weighting method) to determine objective weights

[0097] First, construct the initial decision matrix, where x kj The evaluation value of the plan

[0098] X = [x kj ] m×t

[0099]

[0100] Standardized initialization of the decision matrix:

[0101]

[0102] Information content D in the j attribute j :

[0103]

[0104] in The standard deviation of the j-th attribute is given by the formula:

[0105]

[0106] Where p jl The correlation coefficient between attributes j and l is expressed as:

[0107]

[0108] The target weights are represented as (λ1,λ2,…,λ) t ):

[0109]

[0110] 3) Obtain the combined weights based on the minimum total deviation method

[0111] The core of the minimum total deviation method is to minimize the deviation between the evaluation vector corresponding to the combined weights and the evaluation vector corresponding to the original weights, thereby obtaining the optimal weight model.

[0112]

[0113] (2) Evaluation method for human-machine interface of intelligent machine tool based on normal fuzzy numbers

[0114] Based on the combined weights, calculate the average value x for each attribute. j and standard deviation τ j

[0115]

[0116]

[0117] Construct the standard value matrix

[0118]

[0119] Constructing a composite decision matrix

[0120]

[0121] The scheme index is calculated from the standard value matrix Z.

[0122]

[0123]

[0124]

[0125] The beneficial effects of this invention are: it provides an optimized layout scheme for the human-machine interface of CNC machine tools, improving the comfort and efficiency of the human-machine interaction process in intelligent CNC machine tools. It also provides excellent support for the optimized design of the human-machine interface for CNC machine tools. Attached Figure Description

[0126] Figure 1 This is the numbering result of the human-machine interface of the intelligent CNC machine tool of this invention.

[0127] Figure 2 This is the interactive characteristic model of the intelligent numerical control system of the present invention.

[0128] Figure 3 This invention relates to a user cognitive characteristic model of the human-machine interface for intelligent machine tools.

[0129] Figure 4 This is the modular processing result of the intelligent CNC machine tool human-machine interface of the present invention.

[0130] Figure 5(a) and 5(b) It refers to the horizontal and vertical field of view, where Figure 5(a) shows the horizontal field of view and Figure 5(b) shows the vertical field of view.

[0131] Figure 6 It is a distribution map of the user's visual perception area.

[0132] Figure 7 It is the intensity level of the visual perception area of ​​the human-computer interaction interface.

[0133] Figure 8 It is a cuckoo-particle swarm hybrid intelligent algorithm process.

[0134] Figure 9 This is the result of the algorithm comparison.

[0135] Figure 10 This is the effect of the optimized layout scheme.

[0136] Figure 11 This is an image from an eye-tracking experiment conducted on a participant.

[0137] Figure 12 This is a comparison chart of the first gaze time before and after interface optimization.

[0138] Figure 13 This is a comparison chart of sustained gaze time before and after interface optimization.

[0139] Figure 14 This is the heatmap of the original human-computer interface design.

[0140] Figure 15 This is a heatmap of the optimized human-computer interface solution. Detailed Implementation

[0141] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. However, it should be understood that the embodiments are used to explain the present invention and are not intended to limit the present invention.

[0142] This embodiment provides a method for optimizing the layout of a human-machine interface for intelligent machine tools based on the cuckoo-particle swarm optimization approach, comprising the following steps:

[0143] S1. The importance of the intelligent machine tool human-machine interface module is determined.

[0144] S2. Classification of visual perception intensity levels for human-machine interfaces of intelligent machine tools.

[0145] S3, Construction of an optimized layout model for the human-machine interface of intelligent machine tools.

[0146] S4. Solving the layout optimization model of the human-machine interface for intelligent machine tools based on the cuckoo-particle swarm optimization algorithm.

[0147] Evaluation of the optimization effect of human-machine interface of S5 intelligent machine tool.

[0148] Furthermore, the specific method for optimizing the layout of the human-machine interface of the intelligent machine tool based on the cuckoo-particle swarm optimization is as follows:

[0149] (1) Analysis of the cognitive characteristics of human-machine interface of intelligent machine tool based on cognitive psychology

[0150] Analyzing user characteristics during the human-machine interaction process of intelligent CNC machine tools and determining the operator's cognitive characteristics of the intelligent machine tool human-machine interface, and incorporating these characteristics into the optimized design of the human-machine interface, can ultimately reduce user cognitive fatigue, increase operator comfort, enhance satisfaction with the human-machine interface layout, and improve work efficiency. Based on relevant theories of cognitive psychology, a user cognitive characteristic model of the intelligent machine tool human-machine interface is constructed, and user cognitive characteristics are analyzed in detail.

[0151] 1) Establish an interactive characteristic model for intelligent machine tools

[0152] Based on the differences between the interaction mode of current intelligent CNC systems and traditional complex systems, an interaction characteristic model of intelligent CNC systems is constructed.

[0153] 2) Establish a user cognitive characteristic model for the human-machine interface of intelligent machine tools.

[0154] To address the problem that the human-machine interface of intelligent CNC machine tools has a complex collection of multiple information, parameters, and encoded information, which makes it difficult for users to quickly locate the required task information, a user cognitive characteristic analysis is conducted to construct a user cognitive characteristic model for the human-machine interface of intelligent CNC machine tools.

[0155] (2) Module division of intelligent machine tool human-machine interface considering cognitive characteristics

[0156] The human-machine interface information of intelligent CNC machine tools is modularly decomposed. Based on the correlation of parameter information, the human-machine interface is divided into modules of different sizes. Each functional module in the human-machine interface is encoded using integer numbers from 1 to 20. There are no situations where functional modules should be arranged adjacently or should be avoided. The decomposed modules are then rearranged and optimized.

[0157] (3) Evaluation index system for the importance of human-machine interface module of intelligent machine tool

[0158] 1) Questionnaire content design for interface importance evaluation indicators

[0159] A total of 24 questions were asked and a questionnaire was distributed, focusing on the perception, memory, layout, inter-module relationships, attention resource allocation, and response speed of the human-machine interface of intelligent CNC machine tools.

[0160] 2) Questionnaire survey and data analysis

[0161] First, the reliability of the results was analyzed using SPSS software. Then, factor analysis was performed on the questionnaire for evaluating the importance of the human-machine interface module of intelligent machine tools, taking into account the cognitive characteristics of users.

[0162] 3) Construct an evaluation system for the importance of interface modules.

[0163] (4) A method for determining the importance of interface modules based on AHP-DEMATAL

[0164] 1) First, create a hierarchical structure and use a 9-point scale to perform pairwise comparisons of the identified factors, constructing a pairwise comparison matrix. Determine the normalized weights of the identified factors and form a normalized weight vector. Based on the normalized vector, sort the factors according to their weights and complete the consistency test of the evaluation, where N is the order of the matrix.

[0165]

[0166]

[0167] 2) The creation of the direct relationship matrix involves experts performing pairwise comparisons of the identified parameters to determine the degree of influence of each parameter on the other parameters.

[0168] Construct the direct relation average matrix

[0169]

[0170] 3) Create a standardized direct relation matrix, and then multiply the direct relation matrix by the factor F to obtain an n*n normalized direct relation matrix.

[0171]

[0172] Z = F * A

[0173] 4) Calculation of the total relation matrix: The total relation matrix represents the total relation between all identified parameter pairs.

[0174] T = Z + Z 2 +Z 3 +Z h =Z(IZ) -1 (IZ) h

[0175]

[0176] T = Z(IZ) -1

[0177] 5) Determining the row and column sums and centrality of the overall relation matrix.

[0178]

[0179]

[0180] P = R + C

[0181] 6) Determine the weight of the comprehensive index: Let ω be the weight of the j-th evaluation index at the i-th level. je

[0182]

[0183] 7)ω j Let be the comprehensive weight value of the j-th indicator, which is equal to the product of the indicator's own weight and the weights of each level within its dimension.

[0184] ω j =ω j1 ω j2 ω j3

[0185] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S2 specifically involves the following method:

[0186] Reasonably allocate user attention resources, analyze the distribution of human eye gaze, clarify the user's visual perception intensity level and classify it reasonably, and integrate the visual perception intensity level with the modular division results of the intelligent CNC machine tool human-machine interface to determine the field of view distribution of each module area of ​​the intelligent CNC machine tool human-machine interface.

[0187] (1) Horizontal and vertical field of vision

[0188] When users read the human-machine interface of an intelligent CNC machine tool, they need to coordinate with the movement of their eyes to do so smoothly. By combining the horizontal and vertical field of vision of the human eye, the range of visual perception intensity of the user can be obtained.

[0189] (2) Distribution of visual perception areas

[0190] This paper analyzes the visual perception during the interaction process of the human-machine interface of intelligent CNC machine tools based on the View Cones and Visual Fields modules in JACK.

[0191] (3) Classification of interface visual perception intensity levels

[0192] Construct a modular interface for the human-machine interaction of intelligent CNC machine tools based on the intensity level of the visual perception area.

[0193] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S3 specifically involves the following method:

[0194] (1) Problem Description: Based on the layout optimization principles of the human-machine interface of intelligent CNC machine tools and related ergonomic principles, and combined with the visual perception intensity level of the parameter information of different module areas of the human-machine interface, the importance, relevance, operation sequence and viewing frequency of each module area in the human-machine interface are quantitatively analyzed. The modules with higher importance, relevance and viewing frequency are arranged in areas with higher visual perception intensity level. Attention is also paid to the logical degree between the operation relationships of each area. The goal is to maximize the overall intensity of the total importance of each module area in each visual perception intensity area. A layout optimization model of the human-machine interface of intelligent CNC machine tools based on visual perception intensity is constructed.

[0195] (2) Assumptions: This paper makes the following assumptions for the optimization of the layout of the human-machine interface of intelligent CNC machine tools: the size, quantity and internal composition of all module areas of the human-machine interface of intelligent CNC machine tools remain unchanged, there is no overlap between the module areas, and the layout range of the areas is within the boundary of the human-machine interface.

[0196] (3) Variable Definition: The main variables of the intelligent CNC machine tool human-machine interface layout optimization model are as follows:

[0197] W – Total importance, where W = ω + f + 0

[0198] K—Visual perception intensity level of different module areas, K ij Let be the intensity level of the i-th module region in the j-th visual perception region.

[0199] X — The number of units occupied by different levels of visual perception intensity module regions, X ij This represents the number of units occupied by the i-th module region within the j-th visual perception region.

[0200] U—The level of visual perception intensity in the region where the centroid of the module area is located. ij Let be the intensity level of the i-th module region in the j-th visual perception region.

[0201] n — Number of human-computer interaction interface module areas

[0202] m — Number of visual perception intensity levels in the human-computer interaction interface

[0203] Z – Overall Strength of Human-Computer Interface Layout Optimization

[0204] S – Total number of human-computer interaction interface units

[0205] The optimized layout model of the human-machine interface for intelligent CNC machine tools can be represented as:

[0206]

[0207] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S4 specifically involves the following method:

[0208] Step 1: Initialize relevant parameters, such as population size N;

[0209] Step 2: Set the perturbation iteration threshold T0, and set the upper and lower boundaries of the variables b and a, etc.

[0210] x = a + rand(1,D)*(ba)

[0211] Step 3: Calculate the fitness value of all nest sites in the population, and record the best nest site and its fitness value;

[0212] Step 4: Calculate the fitness value of the updated nest location and compare it with the fitness value of the nest location before the update, and retain the best nest location and its fitness value;

[0213]

[0214]

[0215]

[0216]

[0217]

[0218] Step 5: For each nest, discard it, calculate the fitness value of the nest location after discarding it, and compare it with the fitness value of the nest location before discarding it.

[0219]

[0220]

[0221] Step 6: For each nest, perform mutation, calculate the fitness value of the mutated nest location and compare it with the fitness value of the nest location before mutation;

[0222]

[0223] Step 7: Record the optimal nest location and its fitness value for each iteration. If T > T0, then perturb the nest and retain the optimal location of the population.

[0224] x best (t+1)=x best (t)+N(0,1)*(x i (t)-x j (t))

[0225] Step 8: Determine if the termination condition (maximum number of iterations) is met. If yes, output the optimal solution; otherwise, go to Step 3.

[0226] Furthermore, in the method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization, step S5 specifically involves the following method:

[0227] (1) Determination of the subjective and objective weighting of the evaluation of human-machine interface of intelligent machine tools

[0228] 1) Determining subjective weights using the BWM method

[0229]

[0230]

[0231] 2) CRITIC method for determining objective weights

[0232] First, construct the initial decision matrix, where x kj The evaluation value of the plan

[0233] X = [x kj ] m×t

[0234]

[0235] Standardized initialization of the decision matrix:

[0236]

[0237] Information content D in the j attribute j :

[0238]

[0239] in The standard deviation of the j-th attribute is given by the formula:

[0240]

[0241] Where p jl The correlation coefficient between attributes j and l is expressed as:

[0242]

[0243] The target weights are represented as (λ1,λ2,…,λ) t ):

[0244]

[0245] 3) Obtain the combined weights based on the minimum total deviation method

[0246] The core of the minimum total deviation method is to minimize the deviation between the evaluation vector corresponding to the combined weights and the evaluation vector corresponding to the original weights, thereby obtaining the optimal weight model.

[0247]

[0248] (2) Evaluation method for human-machine interface of intelligent machine tool based on normal fuzzy numbers

[0249] Based on the combined weights, calculate the average value x for each attribute. j and standard deviation τ j

[0250]

[0251]

[0252] Construct the standard value matrix

[0253]

[0254] Constructing a composite decision matrix

[0255]

[0256] The scheme index is calculated from the standard value matrix Z.

[0257]

[0258]

[0259]

[0260] See Figure 1 This is the result of the interface function division in this embodiment of the invention. According to step S1, in this embodiment, eight experts use a 9-point scale to compare the importance evaluation indicators of each module of the human-machine interface of the i5M4 series intelligent CNC machine tool in pairs. Based on this, a pairwise comparison matrix, a direct relationship matrix of the evaluation indicators of each module, and a normalized direct relationship matrix are constructed to determine the overall relationship matrix of the module importance evaluation indicators.

[0261] After obtaining the row, column, and centrality of the importance evaluation indicators for each module of the intelligent machine tool human-machine interface, the final (M1~M) is determined. 20 ) module importance ω jThe values ​​are (0.3621, 0.2876, 0.2016, 0.2354, 0.2431, 0.2274, 0.2018, 0.2207, 0.2230, 0.1994, 0.2107, 0.2413, 0.2406, 0.2618, 0.2747, 0.2571, 0.3114, 0.3052, 0.2133, 0.2023).

[0262] See Figure 2 This is the interactive characteristic model of the intelligent CNC system of the present invention. According to step S1, this example is guided by user needs and fully considers the user's usage needs to help the user quickly achieve the operation purpose. Based on the difference between the current interactive mode of the intelligent CNC system and the traditional complex system, the interactive characteristic model of the intelligent CNC system is constructed.

[0263] See Figure 3 This invention provides a user cognitive characteristic model for the human-machine interface of an intelligent machine tool. According to step S1, this example analyzes the user cognitive characteristics of the information content of the human-machine interface of an intelligent CNC machine tool and constructs a user cognitive characteristic model for the human-machine interface of an intelligent CNC machine tool.

[0264] See Figure 4 This is the modular processing result of the intelligent CNC machine tool human-machine interface of the present invention. According to step S1, this example makes reasonable module division of the intelligent CNC machine tool human-machine interface based on the cognitive characteristic analysis results. According to the correlation of parameter information, the human-machine interface is divided into module interfaces of different sizes, which are divided into 20 regular functional modules of different sizes. The functional modules in the human-machine interface are encoded using integer numbers from 1 to 20.

[0265] According to step S1, this embodiment asks a total of 24 questions and distributes a questionnaire based on the perception, memory, layout, inter-module relationships, attention resource allocation, and reaction speed of the human-machine interface of intelligent CNC machine tools. A seven-level Likert scale is established, and the questionnaire is scored in seven ranges from 1 to 7. The questionnaire was distributed to workers at Shenyang Machine Tool Plant and teachers and students engaged in machine tool research and human factors engineering research. The questionnaire evaluated the importance of the current human-machine interface modules of intelligent CNC machine tools. A total of 50 questionnaires were distributed and all 50 questionnaires were returned.

[0266] According to step S1, this embodiment uses SPSS software to perform credibility analysis, data analysis, and approximate chi-square value analysis in Bartlett's test values. It also performs variance interpretation analysis on the interface importance evaluation questionnaire. Based on the component extraction method, the specific rotational load sum of squares can be obtained. By combining the factor analysis results and the rotational load sum of squares with the previous cognitive characteristic analysis results of the intelligent machine tool human-machine interface, the five types of factors can be expressed as subsystem importance, display design degree, error prevention design degree, overall system importance, and safety coding status, represented by C1, C2, C3, C4, and C5, respectively.

[0267] Table 1. Factor Analysis Results

[0268]

[0269]

[0270] According to step S2, this embodiment comprehensively constructs an evaluation index system for the importance of the human-machine interface module of intelligent machine tools in the form of a three-level evaluation index, as shown in Table 2.

[0271] Table 2. Evaluation Index System for the Importance of Human-Machine Interface Modules in Intelligent Machine Tools

[0272]

[0273] See Figure 5(a) and 5(b) According to step S2, this embodiment analyzes the user's visual perception range based on the View Cones and VisualFields modules in JACK, and exports the user's field of view distribution map. The user's field of view distribution map is then divided into visual perception intensity levels. These levels are combined with the modular division results of the intelligent CNC machine tool human-machine interface to construct a modular interface based on the visual perception intensity levels.

[0274] See Figure 8 According to step S4, the present invention provides a method for solving the layout of a human-machine interface for intelligent machine tools based on cuckoo-particle swarm optimization, including the following steps:

[0275] Step 1: Initialize relevant parameters, such as population size N;

[0276] Step 2: Set the perturbation iteration threshold T0, and set the upper and lower boundaries of the variables b and a, etc.

[0277] x = a + rand(1,D)*(ba)

[0278] Step 3: Calculate the fitness value of all nest sites in the population, and record the best nest site and its fitness value;

[0279] Step 4: Calculate the fitness value of the updated nest location and compare it with the fitness value of the nest location before the update, and retain the best nest location and its fitness value;

[0280]

[0281]

[0282]

[0283]

[0284]

[0285] Step 5: For each nest, discard it, calculate the fitness value of the nest location after discarding it, and compare it with the fitness value of the nest location before discarding it.

[0286]

[0287]

[0288] Step 6: For each nest, perform mutation, calculate the fitness value of the mutated nest location and compare it with the fitness value of the nest location before mutation;

[0289]

[0290] Step 7: Record the optimal nest location and its fitness value for each iteration. If T > T0, then perturb the nest and retain the optimal location of the population.

[0291] x best (t+1)=x best (t)+N(0,1)*(x i (t)-x j (t))

[0292] Step 8: Determine if the termination condition (maximum number of iterations) is met. If yes, output the optimal solution; otherwise, go to Step 3.

[0293] After preparing the data for the parameters of each module area within the human-machine interface of the intelligent CNC machine tool, the algorithm statements were written in Matlab based on the cuckoo-particle swarm hybrid intelligent algorithm. Assume the total number of iterations is 200, the swarm size is 150, the inertia factor ω = 0.7, and the probability p of discovering a cuckoo egg is... a=0.25. After optimization calculation, the optimal layout scheme value was obtained as 872, and the original layout scheme was solved to obtain a layout value of 746. In order to further determine the improvement of the solution quality of the cuckoo-particle swarm hybrid intelligent algorithm in solving the layout optimization model of the human-machine interface of intelligent CNC machine tools, this invention simultaneously uses the artificial fish swarm algorithm and the particle swarm algorithm to solve the same model, and the resulting solution quality comparison result is shown in the figure. Figure 9 As shown.

[0294] Table 3 Optimized Human-Machine Interface Layout Scheme for Intelligent Machine Tools

[0295]

[0296]

[0297] See Figure 10 The optimized layout scheme was visualized by adjusting the position of the main display screen downwards, placing more of its area within the highest visual perception zone (I). The spindle scaling control module was positioned in the middle right of the human-machine interface, avoiding the need for users to repeatedly look down and bend over to observe and rotate buttons. This overall optimization improves user attention allocation during interaction and reduces cognitive fatigue during the visual encoding and decoding process in the human-machine interface of intelligent CNC machine tools.

[0298] To further ensure the effectiveness of the optimized human-machine interface for intelligent CNC machine tools, an eye-tracking experiment was conducted to verify the results using physiological data of the operator's eye movements before and after optimization. The experiment used a Tobii X2-60 eye tracker, along with a dongle and signal storage device. Eye movement data was collected using the ErgoLAB V2.0 human-machine environment testing platform to quantify and clarify the user's attention allocation, determining whether the optimized human-machine interface for intelligent CNC machine tools effectively reduced cognitive efficiency, improved operational comfort, and enhanced user experience. The specific eye tracker used in this experiment is as follows: Figure 11 As shown.

[0299] See Figure 12 , 13 Tables 4 and 5 show the comparison results of the first gaze time and the continuous gaze time before and after the layout optimization of the human-machine interface of the intelligent machine tool in this embodiment.

[0300] Table 4 First gaze time before and after interface optimization

[0301]

[0302] Table 5. Continuous gaze time before and after interface optimization

[0303]

[0304] The comparison of first fixation time shows that experienced operators experienced a reduction of 0.22 seconds in average first fixation time, while trainee operators experienced a reduction of 0.44 seconds. This indicates that the optimized human-computer interface can effectively shorten the time it takes for users to recognize interface information, thereby improving interaction efficiency. A two-way ANOVA was then conducted based on the above results, as shown in Table 6.

[0305] Table 6. Results of the two-way ANOVA on first fixation time.

[0306]

[0307] Note: R² = 0.986 (adjusted R² = 0.973)

[0308] The comparison of sustained gaze time shows that experienced operators experienced a reduction of 0.28 seconds in average sustained gaze time, while trainee operators experienced a reduction of 0.51 seconds. This indicates that the optimized human-computer interface can improve the time users spend searching for information and is more in line with users' visual cognitive characteristics. A two-way ANOVA was then conducted based on the above, and the results are shown in Table 7.

[0309] Table 7 Results of Two-Way Analysis of Variance on Continuous Gazing Time

[0310]

[0311] Note: R² = 0.983 (adjusted R² = 0.961)

[0312] See Figure 14 , 15 From the optimized heatmap, the optimized interface has more concentrated hotspots and deeper red areas compared to the original interface. The heatmap is also relatively hotter, indicating that the operator's gaze is more focused, which is conducive to the operator concentrating on handling the task.

[0313] In summary, the optimization of the human-machine interface for intelligent CNC machine tools has yielded positive and effective results. While effectively improving user comfort, user experience, safety, and efficiency, it did not sacrifice human-machine interaction efficiency and, to some extent, reduced operation time and alleviated operator cognitive fatigue.

[0314] The above description represents preferred embodiments of the present invention and is not intended to limit the invention. Those skilled in the art can still modify the above technical solutions or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing the layout of a human-machine interface for intelligent machine tools based on cuckoo-particle swarm optimization, characterized in that, Includes the following steps: S1. The importance of the intelligent machine tool human-machine interface module is determined. S2. Classification of visual perception intensity levels for human-machine interfaces of intelligent machine tools. S3, Construction of an optimized layout model for the human-machine interface of intelligent machine tools. S4. Solving the layout optimization model of the human-machine interface for intelligent machine tools based on the cuckoo-particle swarm optimization algorithm. Evaluation of the optimization effect of the human-machine interface of S5 intelligent machine tools The specific method for step S3 is as follows: (1) Problem Description: Based on the layout optimization principles of the human-machine interface of intelligent CNC machine tools and related ergonomic principles, and combined with the visual perception intensity levels of the parameter information of different module areas of the human-machine interface, this paper quantitatively analyzes the importance, relevance, operation sequence and viewing frequency of each module area in the human-machine interface. It ensures that modules with higher importance, relevance and viewing frequency are placed in areas with higher visual perception intensity levels, and pays attention to the logical degree between the operation relationships of each area. With the goal of maximizing the overall intensity of the total importance of each module area in each visual perception intensity area, a layout optimization model for the human-machine interface of intelligent CNC machine tools based on visual perception intensity is constructed. (2) Assumptions: This paper makes the following assumptions regarding the layout optimization of the human-machine interface of intelligent CNC machine tools: the size, quantity, and internal composition of all module areas of the human-machine interface of intelligent CNC machine tools remain unchanged; there is no overlap between the module areas; and the layout range of the areas is within the boundary of the human-machine interface. (3) Variable definition: The main variables of the intelligent CNC machine tool human-machine interface layout optimization model are as follows: W —Overall importance, of which K—— Visual perception intensity levels in different module areas For the first i The module area in the first j Intensity levels of each visual perception region X —The number of units occupied by different levels of visual perception intensity module regions, For the first i The module area in the first j The number of units occupied within a visual perception region. U —The level of visual perception intensity in the region where the centroid of the module area is located. For the first i The module area in the first j Intensity levels of each visual perception region n —Number of human-computer interaction interface module areas m —Number of visual perception intensity levels in human-computer interaction interfaces Z —Comprehensive strength of human-computer interface layout optimization S —Total number of human-computer interaction interface units The optimized layout model of the human-machine interface for intelligent CNC machine tools can be represented as: 。 2. The method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization as described in claim 1, characterized in that, The specific method for step S1 is as follows: (1) Analysis of the cognitive characteristics of human-machine interface of intelligent machine tool based on cognitive psychology Analyzing user characteristics during the human-machine interaction process of intelligent CNC machine tools, determining the operator's cognitive characteristics of the intelligent machine tool human-machine interface, and incorporating these characteristics into the optimized design of the human-machine interface can ultimately reduce user cognitive fatigue, increase operator comfort, enhance satisfaction with the layout of the human-machine interface, and improve work efficiency. Based on relevant theories of cognitive psychology, we analyze user characteristics and construct a cognitive characteristic model of users in the human-machine interface of intelligent machine tools, and analyze user cognitive characteristics in detail. 1) Establish an interactive characteristic model for intelligent machine tools Based on the differences between the interaction mode of current intelligent numerical control systems and traditional complex systems, an interaction characteristic model of intelligent numerical control systems is constructed. 2) Establish a user cognitive characteristic model for the human-machine interface of intelligent machine tools; To address the problem that the human-machine interface of intelligent CNC machine tools has a complex collection of multiple information, parameters, and information encoding content, which makes it difficult for users to quickly locate the required task information, a user cognitive characteristic analysis is conducted to construct a user cognitive characteristic model of the human-machine interface of intelligent CNC machine tools. (2) Module division of intelligent machine tool human-machine interface considering cognitive characteristics The human-machine interface information of intelligent CNC machine tools is modularly decomposed. Based on the correlation of parameter information, the human-machine interface is divided into modules of different sizes. Integer numbers from 1 to 20 are used to encode each functional module in the human-machine interface. There should be no adjacent or avoidable adjacent arrangement between functional modules. The decomposed modules are then rearranged and optimized. (3) Evaluation index system for the importance of human-machine interface module of intelligent machine tool 1) Questionnaire content design based on interface importance evaluation indicators A total of 24 questions were asked and a questionnaire was distributed, focusing on the perception, memory, layout, inter-module relationships, attention resource allocation, and response speed of the human-machine interface of intelligent CNC machine tools. 2) Questionnaire survey and data analysis First, the reliability of the results was analyzed using SPSS software. Then, factor analysis was performed on the questionnaire for evaluating the importance of the human-machine interface module of intelligent machine tools, taking into account the cognitive characteristics of users. 3) Construct an evaluation system for the importance of interface modules; (4) A method for determining the importance of interface modules based on AHP-DEMATAL 1) First, create a hierarchical structure, use a 9-point scale to perform pairwise comparisons on the identified factors, construct a pairwise comparison matrix, determine the normalized weights of the identified factors and form a normalized weight vector, sort the factors according to their weights based on the normalized vector, and complete the consistency test of the evaluation, where N is the order of the matrix. 2) Creating a direct relationship matrix involves experts performing pairwise comparisons of the identified parameters to determine the degree of influence of each parameter on the others. Construct the direct relation average matrix 3) Create the standardized direct relation matrix, and then multiply the direct relation matrix by the factor F to obtain... Normalized direct relation matrix, 4) Calculation of the overall relational matrix: The overall relational matrix represents the total relational relationship between all identified parameter pairs. 5) Determining the row and column sums and centrality of the overall relation matrix. 6) Determine the weights of the comprehensive indicators: Let the weight of the first indicator be... i The first level j The weights of each evaluation indicator are: 7) For the first j The comprehensive weight value of an indicator is equal to the product of the indicator's own weight and the weights of each level within its dimension. 。 3. The method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization as described in claim 1, characterized in that, The specific method for step S2 is as follows: This process involves allocating user attention resources, analyzing the distribution of human eye gaze, identifying and rationally classifying the user's visual perception intensity levels, and integrating these levels with the modular division results of the intelligent CNC machine tool's human-machine interface to determine the visual field distribution of each module area within the interface. (1) Horizontal and vertical field of vision When users read the human-machine interface of an intelligent CNC machine tool, they need to coordinate with the movement of their eyes to proceed smoothly. By combining the horizontal and vertical visual field of the human eye, the range of visual perception intensity for the user can be obtained. (2) Distribution of visual perception areas This paper analyzes the visual perception during the human-machine interface interaction process of intelligent CNC machine tools based on the View Cones and Visual Fields modules in JACK. (3) Classification of visual perception intensity levels of the interface Construct a modular interface for the human-machine interaction of intelligent CNC machine tools based on the intensity level of the visual perception area.

4. The method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization as described in claim 1, characterized in that, The specific method for step S4 is as follows: Step 1: Initialize relevant parameters: population size N; Step 2: Set the perturbation iteration threshold Set the upper and lower boundaries of the variable, b and a; Step 3: Calculate the fitness value of all nest sites in the population, and record the best nest site and its fitness value; Step 4: Calculate the fitness value of the updated nest location and compare it with the fitness value of the nest location before the update, and retain the best nest location and its fitness value; Step 5: For each nest, discard it, calculate the fitness value of the nest location after discarding it, and compare it with the fitness value of the nest location before discarding it. Step 6: For each nest, perform mutation, calculate the fitness value of the mutated nest location and compare it with the fitness value of the nest location before mutation; Step 7: Record the optimal nest location and its fitness value for each iteration. The nests will be disturbed while preserving the optimal location for the population. Step 8: Determine if the termination condition (maximum number of iterations) is met. If yes, output the optimal solution; otherwise, go to Step 3.

5. The method for optimizing the layout of the human-machine interface of an intelligent machine tool based on cuckoo-particle swarm optimization as described in claim 1, characterized in that, The specific method for step S5 is as follows: (1) Determination of the subjective and objective weighting of the evaluation of the human-machine interface of intelligent machine tools 1) Determining Subjective Weights using the BWM Method Building the BWM model: 2) CRITIC method for determining objective weights First, construct the initial decision matrix, where The evaluation value of the plan Standardized initialization of the decision matrix: j Information content in attributes : in For the first j The standard deviation of each attribute is shown in the formula: in For attributes j The correlation coefficient between l and is expressed as: The target weight is expressed as : 3) Obtain the combined weights based on the minimum total deviation method The core of the minimum total deviation method is to minimize the deviation between the evaluation vector corresponding to the combined weights and the evaluation vector corresponding to the original weights, thereby obtaining the optimal weight model. (2) Evaluation method of human-machine interface of intelligent machine tool based on normal fuzzy number Calculate the average value of each attribute based on the combined weights. and standard deviation Construct the standard value matrix Constructing a composite decision matrix The scheme index is calculated from the standard value matrix Z. 。

Images