Production control method, system and equipment for intelligent mold

Abstract

The invention relates to the technical field of mold production control, and discloses a production control method, system and equipment for an intelligent mold. The method comprises the steps of collecting mold production parameters through a multi-dimensional sensor, and performing feature extraction and classification arrangement to obtain a feature data set; screening and matching the material performance indexes according to the feature data set to generate a matching parameter matrix; constructing a processing path based on the parameter matrix to obtain an intelligent processing path set; processing error values are collected to form compensation vectors; performing temperature field division according to the compensation vector to obtain a process parameter group; a quality evaluation system is established through key point data acquisition and testing. By establishing a complete data processing logic chain, the intelligent control of the whole process from parameter acquisition, material proportioning, processing control to quality evaluation is realized, and the accuracy and reliability of the mold production process are improved.

Description

Technical Field

[0001] The present application relates to the field of mold production control, and in particular to a production control method, system and equipment for intelligent molds. Background Art

[0002] In the field of intelligent manufacturing, the production control method of molds plays a key role in product quality. Existing mold production control methods are mainly studied from the aspects of process parameter setting, processing path planning, error compensation, etc. In the production process, processing parameters are collected through sensors, and data analysis and processing are performed using numerical calculation methods to achieve monitoring and control of the mold processing process. At the same time, the existing technology also combines the research results of heat treatment process control, assembly quality evaluation, etc. to form a relatively complete mold production control system.

[0003] However, the existing mold production control methods have problems such as incomplete data processing logic and insufficient connection between various processes. Specifically, the lack of systematic production parameter collection leads to inaccurate data feature extraction; insufficient correlation analysis between material performance indicators and processing parameters affects the control effect of processing accuracy; and the lack of effective data transmission mechanism between heat treatment process parameters and assembly quality assessment results in insufficient continuity of quality control. These problems seriously restrict the level of intelligence in the mold production process. Summary of the invention

[0004] The present application provides a production control method, system and equipment for intelligent molds, which are used to achieve intelligent control of the entire process from parameter acquisition, material ratio, processing control to quality assessment by establishing a complete data processing logic chain, thereby improving the accuracy and reliability of the mold production process.

[0005] In the first aspect, the present application provides a production control method for an intelligent mold, and the production control method for the intelligent mold includes: collecting mold production parameters through a multidimensional sensor, extracting features and classifying the production parameters to obtain a mold production feature data set; based on the mold production feature data set, performing layered screening and combination matching on mold material performance indicators to generate a mold material ratio parameter matrix; based on the mold material ratio parameter matrix, constructing a processing coordinate sequence through preset processing trajectory rules, and obtaining an intelligent processing path set through trajectory optimization calculation; based on the intelligent processing path set, real-time collection and cumulative calculation of error deviation values ​​in the mold processing process to form a mold error compensation vector; based on the mold error compensation vector, gradient division and regional mapping of the heat treatment temperature field distribution to obtain a heat treatment process parameter group; based on the heat treatment process parameter group, a mold quality evaluation index system is established through key point data collection and performance testing during the assembly process.

[0006] In a second aspect, the present application provides a production control system for an intelligent mold, the production control system for the intelligent mold comprising:

[0007] An acquisition module is used to acquire mold production parameters through a multi-dimensional sensor, perform feature extraction and classification on the production parameters, and obtain a mold production feature data set;

[0008] A screening module, used to perform hierarchical screening and combination matching of mold material performance indicators according to the mold production feature data set, and generate a mold material ratio parameter matrix;

[0009] A construction module is used to construct a processing coordinate sequence based on the mold material ratio parameter matrix through a preset processing trajectory rule, and obtain an intelligent processing path set through trajectory optimization calculation;

[0010] A calculation module, used for collecting and accumulating the error deviation values ​​in the mold processing process in real time according to the intelligent processing path set, and forming a mold error compensation vector;

[0011] A mapping module, used to perform gradient division and area mapping on the heat treatment temperature field distribution according to the mold error compensation vector, and obtain a heat treatment process parameter group;

[0012] The test module is used to establish a mold quality evaluation index system based on the heat treatment process parameter group through key point data collection and performance testing during the assembly process.

[0013] The third aspect of the present application provides a computer device, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor and the memory communicate via a bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned intelligent mold production control method are performed.

[0014] In the technical solution provided by this application, by collecting die production parameters through multi-dimensional sensors, real-time monitoring and feature extraction of key parameters such as temperature, pressure, and vibration are achieved. Based on the die production feature data set, hierarchical screening and combined matching of material performance indicators are carried out, and the corresponding relationship between material performance and processing requirements is established, forming a scientific material ratio parameter matrix; by constructing a processing coordinate sequence according to the preset rules of the processing trajectory and obtaining an intelligent processing path set through trajectory optimization calculation, the accuracy of the processing process is improved; the error deviation values during the die processing process are collected and cumulatively calculated in real time, forming an accurate die error compensation vector, effectively controlling the processing error; according to the die error compensation vector, the heat treatment temperature field distribution is divided into gradients and regionally mapped, obtaining a reasonable heat treatment process parameter group, ensuring the heat treatment quality; through data collection and performance testing at key points during the assembly process, a complete die quality evaluation index system is established, realizing the comprehensiveness of quality control, and significantly improving the intelligent level and control accuracy of the die production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a schematic diagram of an embodiment of the production control method of the intelligent die in the embodiment of this application;

[0017] Figure 2 It is a schematic diagram of the assembly monitoring point sequence in the embodiment of this application;

[0018] Figure 3 It is a schematic diagram of an embodiment of the production control system of the intelligent die in the embodiment of this application;

[0019] Figure 4 It is a schematic diagram of the structure of the computer device in the embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] Embodiments of the present application provide a production control method, system and device for an intelligent mold. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the production control method of the intelligent mold in the embodiment of the present application includes:

[0022] Step S101, collecting mold production parameters through a multi-dimensional sensor, extracting and classifying the production parameters, and obtaining a mold production feature data set;

[0023] Step S102: According to the mold production feature data set, the mold material performance indicators are screened and matched in layers to generate a mold material ratio parameter matrix;

[0024] Step S103, based on the mold material ratio parameter matrix, a processing coordinate sequence is constructed through a preset processing trajectory rule, and an intelligent processing path set is obtained through trajectory optimization calculation;

[0025] Step S104: based on the intelligent processing path set, the error deviation values ​​in the mold processing process are collected and accumulated in real time to form a mold error compensation vector;

[0026] Step S105, performing gradient division and area mapping on the heat treatment temperature field distribution according to the mold error compensation vector to obtain a heat treatment process parameter group;

[0027] Step S106: Based on the heat treatment process parameter group, a mold quality evaluation index system is established through key point data collection and performance testing during the assembly process.

[0028] It is understandable that the execution subject of the present application may be a production control system of the intelligent mold, or a terminal or a server, which is not limited here. The present application embodiment is described by taking the server as the execution subject as an example.

[0029] Specifically, the multidimensional sensor acquisition stage involves the acquisition of temperature parameters, pressure parameters, and vibration parameters. The data collected by the sensor is marked by time series to form an original data matrix, which contains the characteristics of each physical quantity changing over time. When the data is segmented, the continuous data stream is divided according to a fixed sampling period, and each data segment obtains the periodic characteristic value through discrete sampling, and these characteristic values ​​constitute the frequency domain data sequence. The data in the frequency domain data sequence is classified according to the physical quantity category, and each type of data is numerically statistically operated to obtain the distribution characteristics of this type of data, including the central tendency and discrete degree of the data, so as to obtain the parameter statistical results. The parameter statistical results are divided into numerical intervals, and the change characteristic coefficients are obtained by combining data fluctuation analysis. These coefficients reflect the dynamic change law of the data, thereby constructing the parameter characteristic vector. The parameter characteristic vector eliminates the dimension effect through standardization transformation, and the converted data forms a normalized parameter set. The principal component extraction is performed on the normalized parameter set, and the mold production characteristic data set is obtained through data dimensionality reduction analysis. For the obtained mold production characteristic data set, the mechanical strength, heat treatment parameters, and material hardness data are analyzed and separated to generate a performance parameter sequence. Each indicator in the performance parameter sequence is quantified through numerical calculation to form a quantitative indicator array. The data in the quantitative indicator array is used to determine the priority relationship of each indicator through hierarchical calculation to construct a hierarchical weight sequence. The hierarchical weight sequence is used to perform data matching calculation with the material ratio coefficient, and the ratio scheme set is obtained through combined calculation. The ratio scheme set is verified by data, and the performance matching degree is evaluated through cross-validation to construct a verification data set. After multiple rounds of data analysis and screening of the verification data set, the mold material ratio parameter matrix is ​​obtained.

[0030] The data of the mold material ratio parameter matrix is ​​divided by spatial coordinates to form a processing point sequence and construct an initial trajectory data group. The initial trajectory data group is arranged in the processing order, and the path connection relationship is determined by continuity calculation to form a trajectory connection matrix. The trajectory connection matrix is ​​numerically operated to calculate the path length parameters and generate a trajectory cost sequence. The trajectory cost sequence is processed by path planning and trajectory smoothing to obtain a smooth path array and construct an optimized trajectory set. The optimized trajectory set is subjected to kinematic analysis, and a motion parameter group is obtained by speed planning to form a processing strategy matrix. The processing strategy matrix is ​​integrated to obtain an intelligent processing path set. The intelligent processing path set is used to monitor the position deviation during the processing process, and the coordinate points collected in real time constitute the deviation monitoring data group. The deviation monitoring data group is compared and calculated with the set coordinate value to obtain the position deviation amount and form an initial error sequence. The initial error sequence is subjected to time series analysis and cumulative calculation to obtain the error change trend and generate an error cumulative array. The error cumulative array obtains the error distribution characteristics through data analysis and constructs the error feature matrix. The error feature matrix is ​​converted into a compensation parameter group through spatial mapping to form a compensation strategy sequence. The compensation strategy sequence obtains the mold error compensation vector through data integration and vector operation.

[0031] The mold error compensation vector is decomposed into a temperature distribution point set according to the spatial distribution relationship to form a temperature field monitoring sequence. The temperature field monitoring sequence is numerically segmented, the temperature gradient is calculated to obtain the heat distribution characteristics, and the thermal distribution matrix is ​​constructed. The thermal distribution matrix is ​​divided into regions, the temperature change law is calculated, and the temperature change array is generated. The temperature change array is subjected to correlation analysis, the temperature field coupling relationship is calculated, and the temperature control parameter set is formed. The temperature control parameter set is subjected to process analysis, the heating strategy sequence is calculated, and the heat treatment control matrix is ​​constructed. The heat treatment control matrix is ​​converted through process parameter conversion to obtain the heat treatment process parameter group. The assembly sequence information is extracted from the heat treatment process parameter group, and the process parameter requirements are integrated to form an assembly monitoring point sequence. The monitoring point sequence is used to collect assembly process data, and the data is calibrated in combination with the physical quantity measurement standard to construct the assembly data matrix. The numerical distribution law in the assembly data matrix is ​​used to divide the key indicators of performance evaluation and generate the performance analysis benchmark group. The performance analysis benchmark group is combined with the assembly accuracy requirements to derive the interaction between various indicators and obtain the performance evaluation parameter set. The performance evaluation parameter set is used to set the evaluation criteria, and a comprehensive analysis is performed in combination with the assembly process specifications to form a quality assessment data group. The index system is constructed based on the quality assessment data group, and the mold quality evaluation index system is obtained by combining assembly accuracy and performance.

[0032] In the embodiment of the present application, mold production parameters are collected by multidimensional sensors, and real-time monitoring and feature extraction of key parameters such as temperature, pressure, and vibration are achieved. Based on the mold production feature data set, material performance indicators are hierarchically screened and combined to match, a correspondence between material performance and processing requirements is established, and a scientific material ratio parameter matrix is ​​formed; a processing coordinate sequence is constructed through preset rules of the processing trajectory, and an intelligent processing path set is obtained through trajectory optimization calculation, thereby improving the accuracy of the processing process; the error deviation values ​​in the mold processing process are collected and accumulated in real time to form an accurate mold error compensation vector, which effectively controls the processing error; according to the mold error compensation vector, the heat treatment temperature field distribution is gradient divided and regionally mapped, and a reasonable heat treatment process parameter group is obtained to ensure the quality of heat treatment; through key point data collection and performance testing of the assembly process, a complete mold quality evaluation index system is established, which realizes the comprehensiveness of quality control and significantly improves the intelligence level and control accuracy of the mold production process.

[0033] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0034] (1) Collecting temperature parameters, pressure parameters, and vibration parameters through multi-dimensional sensors, marking the temperature parameters, pressure parameters, and vibration parameters in time series, and generating a raw data matrix;

[0035] (2) The original data matrix is ​​segmented according to the sampling period, and the periodic eigenvalues ​​are obtained through discrete sampling to form a frequency domain data sequence;

[0036] (3) Classify the physical quantities of the frequency domain data sequence, obtain the numerical distribution characteristics through numerical statistical operations, and obtain parameter statistical results;

[0037] (4) Divide the parameter statistical results into numerical intervals, obtain the change characteristic coefficient through data fluctuation analysis, and construct the parameter characteristic vector;

[0038] (5) Perform data standardization conversion on the parameter feature vector and obtain a normalized parameter set through linear transformation;

[0039] (6) Principal components are extracted from the normalized parameter set, and the mold production feature data set is obtained through data dimensionality reduction analysis.

[0040] Specifically, a multidimensional sensor network is used for data collection. The multidimensional sensor network includes temperature sensors, pressure sensors and vibration sensors, which monitor the key physical parameters in the mold production process respectively. The temperature sensor collects the temperature data of each key point in the mold processing process, the pressure sensor collects the pressure change data in the processing process, and the vibration sensor collects the vibration signals of the processing equipment and the mold. The various types of data collected are marked according to the time series, and each data point is accompanied by the corresponding timestamp information to form an original data matrix containing multidimensional physical quantity information. The original data matrix is ​​segmented according to a fixed sampling period, and the selection of the sampling period is determined based on the characteristics of the mold processing technology. In each sampling period, the continuous data is discretized and the eigenvalues ​​in the time period are extracted. The eigenvalues ​​include statistical characteristics such as the average value, maximum value, and minimum value of each physical quantity in the sampling period, and these eigenvalues ​​constitute the frequency domain data sequence. The frequency domain data sequence reflects the periodic characteristics of each physical quantity changing over time.

[0041] The data in the frequency domain data sequence are classified into physical quantities, and the temperature data, pressure data, and vibration data are classified separately. Numerical statistical operations are performed on each type of data, and statistical parameters such as the mean, variance, and standard deviation of the data are calculated to obtain the numerical distribution characteristics of each type of physical quantity. The numerical distribution characteristics reflect the change law and distribution of each physical quantity, and these characteristics are combined to form parameter statistical results.

[0042] The statistical data is divided into several intervals according to the numerical value. The data in each interval is subjected to fluctuation analysis, and the rate of change and fluctuation amplitude of the data are calculated to obtain the variation characteristic coefficient. The variation characteristic coefficient describes the variation characteristics of the data in different intervals, and these coefficients are combined to form the parameter characteristic vector. The mathematical expression of this process is:

[0043]

[0044] Among them, V ij is the component of the eigenvector, λ k is the interval weight coefficient, is the fluctuation coefficient of the i-th physical quantity in the j-th interval, μ i is the scale factor of the physical quantity i, σ j is the standard deviation of interval j, γ ij is the correction coefficient, and n is the number of intervals. The parameter feature vector is subjected to data standardization transformation to eliminate the dimensional differences between different physical quantities. The data is mapped to a uniform numerical interval through linear transformation to obtain a normalized parameter set. The data in the normalized parameter set have the same numerical range and comparability.

[0045] The principal components of the normalized parameter set are extracted, the correlation between the parameters is analyzed, and the main influencing factors are identified. Through data dimensionality reduction analysis, data redundancy is reduced, the most representative characteristic parameters are extracted, and the mold production characteristic data set is obtained.

[0046] For example, during the processing, multi-dimensional sensors continuously collect data. The temperature sensor collects the surface temperature of the mold, and the data shows that the temperature changes periodically with the processing time. The pressure sensor records the processing pressure, and the data shows the stage characteristics corresponding to the processing procedure. The vibration sensor collects the vibration signal of the equipment, and the data reflects the stability changes during the processing. After these raw data are marked by time series, a data matrix containing information such as time, temperature, pressure, and vibration is formed. The data is segmented according to a sampling period of 10 seconds, and the characteristic values ​​of each time period are extracted to form a frequency domain sequence. The frequency domain sequence is classified and statistically analyzed by physical quantities to obtain the distribution characteristics of each parameter. Through numerical interval division and fluctuation analysis, the change characteristic coefficient is calculated and the characteristic vector is constructed. The characteristic vector is standardized and subjected to principal component analysis to obtain a data set reflecting the key characteristics of the mold production process.

[0047] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0048] (1) Analyze the mold production feature data set, separate the mechanical strength, heat treatment parameters, and material hardness data, and generate a performance parameter sequence;

[0049] (2) Classify and organize the performance parameter sequence through numerical calculation, quantify different indicators, and form a quantitative indicator array;

[0050] (3) Perform hierarchical operations on the quantitative indicator array, obtain the indicator priority through weight allocation, and construct a hierarchical weight sequence;

[0051] (4) Data matching is performed between the stratified weight sequence and the material ratio coefficient, and a ratio scheme set is obtained through combined calculation;

[0052] (5) Perform data verification on the ratio scheme set, obtain the performance matching degree through cross-validation, and construct a verification data set;

[0053] (6) Perform multiple rounds of data analysis on the verification data group and obtain the mold material ratio parameter matrix through data screening.

[0054] Specifically, the mold production feature data set is analyzed and processed. The mold production feature data set contains multiple indicator data such as mechanical strength, heat treatment parameters, and material hardness. During the analysis of the data set, three types of key data are separated: mechanical strength data reflects the mold's anti-deformation ability and load-bearing capacity, heat treatment parameter data includes process parameters such as temperature and insulation time, and material hardness data reflects the mold surface wear resistance and service life characteristics. These separated data are reorganized according to physical properties to form a performance parameter sequence.

[0055] Perform numerical calculations and classification on the performance parameter sequence to convert different types of indicator data into comparable quantitative values. The quantification process involves the following mathematical expressions:

[0056]

[0057] Among them, Q ij represents the jth quantitative value of the i-th indicator, β m is the quantization coefficient, is the original data value, ψ i is the normalization factor, θ j is the correction coefficient, and p is the parameter dimension. Through this operation, we can get the quantitative index array.

[0058] Perform hierarchical operations on the quantitative indicator array to calculate the weight of each indicator. The calculation formula is:

[0059]

[0060] Among them, W rs is the weight value of the sth indicator in the rth layer, δ n is the level coefficient, is the index correlation, ω r is the level factor, τ s is the adjustment coefficient, and q is the number of levels. This gives us a hierarchical weight sequence.

[0061] Match and calculate the stratified weight sequence and material ratio coefficient:

[0062]

[0063] Among them, M gh is the hth ratio value of the gth material, ρ k is the matching coefficient, is the weight contribution value, ∈ g is the material factor, κ his the balance coefficient, and t is the number of matching parameters. The matching scheme set is obtained by calculation. Data verification is performed on the matching scheme set, and the performance matching degree of each matching scheme is evaluated by cross-validation method. During the cross-validation process, the matching scheme is compared with the performance requirements, the matching score is calculated, and the matching is screened according to the matching degree to construct a verification data set.

[0064] We conduct multiple rounds of data analysis on the validation data set and conduct a comprehensive evaluation of various performance indicators. The analysis process includes reliability analysis, stability analysis and consistency analysis. Through data screening, we determine the optimal ratio scheme and generate a mold material ratio parameter matrix.

[0065] For example: extract various types of data from the mold production feature data set. Mechanical strength data includes parameters such as tensile strength and yield strength, heat treatment parameters include process parameters such as quenching temperature and tempering temperature, and material hardness data includes indicators such as surface hardness and core hardness. These data are converted into numerical values ​​of unified dimensions through quantization processing to form a quantitative indicator array. Then, the importance of each indicator is determined through hierarchical analysis, and a weight system is constructed to obtain a hierarchical weight sequence. The weight sequence is combined with the material ratio coefficient to generate multiple groups of ratio schemes. These schemes are cross-validated to evaluate whether their performance indicators meet the requirements, and the schemes with high matching degree are selected to enter the verification data group. Finally, through multiple rounds of analysis and screening, the optimal material ratio parameters are determined to form a ratio parameter matrix.

[0066] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0067] (1) Perform data analysis on the mold material ratio parameter matrix, obtain the processing point sequence through spatial coordinate division, and construct the initial trajectory data set;

[0068] (2) Arranging the initial trajectory data set according to the processing order, obtaining the path connection relationship through continuity calculation, and forming a trajectory connection matrix;

[0069] (3) Perform numerical operations on the trajectory connection matrix, obtain the distance parameter set through path length calculation, and generate the trajectory cost sequence;

[0070] (4) Perform path planning based on the trajectory cost sequence, obtain a smooth path array through trajectory smoothing, and construct an optimized trajectory set;

[0071] (5) Perform kinematic analysis on the optimized trajectory set, obtain the motion parameter group through speed planning, and form a processing strategy matrix;

[0072] (6) The processing strategy matrix is ​​integrated and the intelligent processing path set is obtained through trajectory combination.

[0073] Specifically, the processing trajectory planning stage performs data analysis on the mold material ratio parameter matrix. The matrix contains material distribution information and processing requirements, and this information is converted into specific processing points through the spatial coordinate system. The three-dimensional space is divided into grid units, each unit corresponds to a processing point, forming a processing point sequence. The processing point sequence contains the spatial coordinate value and processing parameter information of each point, and this information combination constitutes the initial trajectory data group. The point information in the initial trajectory data group needs to be reasonably sorted according to the processing technology requirements. Each point contains three coordinate values ​​of X, Y, and Z and the corresponding processing parameters. By analyzing the spatial relationship between adjacent points, the connection cost between points is calculated, including distance cost, direction change cost, and process constraint cost. The calculation expression of this connection relationship is:

[0074]

[0075] Among them, D xy is the cost of connecting point x to point y, α i is the connection weight coefficient, is the spatial distance value, ν x is the starting factor, π y is the end point coefficient, and u is the number of connection parameters. The calculation results form the trajectory connection matrix.

[0076] According to the connection relationship in the trajectory connection matrix, the path length is quantitatively calculated:

[0077]

[0078] Among them, L ab is the comprehensive length value of path segment ab, σ j is the path characteristic coefficient, is the path parameter value, μ a is the starting segment factor, λ b is the termination coefficient, and v is the number of path features. The distance parameter set is obtained by calculation, and then the trajectory cost sequence is generated.

[0079] Mathematical expression of trajectory smoothing based on trajectory cost sequence:

[0080]

[0081] Among them, S cd is the smoothness value of the smooth path segment cd, β k is the smoothing coefficient, is the curvature parameter, θ c is the path starting factor, is the path end coefficient, w is the number of smoothing parameters. The calculation results constitute the optimized trajectory set.

[0082] For example: for a complex curved surface mold, the processing area information is extracted from the material ratio parameter matrix, and the surface is divided into grid units, with the center point of each unit as the processing point. These points form an initial trajectory data set according to the spatial position relationship. Then the connection relationship between adjacent points is analyzed, and the factors such as spatial distance, processing direction change and process constraints are considered to calculate the connection cost and form a connection matrix. Based on the connection matrix, the length and process cost of each possible path are calculated to generate a cost sequence. The path is smoothed to eliminate sharp turns and discontinuous points to obtain a smooth path. Finally, according to the machine tool performance and process requirements, the feed speed and processing parameters of each path segment are planned to form a complete processing path set.

[0083] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0084] (1) Monitor the intelligent machining path set in sections, obtain real-time coordinate points through position sensing, and construct a deviation monitoring data set;

[0085] (2) Compare the deviation monitoring data set with the set coordinate value, calculate the position deviation through the difference, and form the initial error sequence;

[0086] (3) Perform time series analysis on the initial error sequence, obtain the error change trend through cumulative calculation, and generate an error accumulation array;

[0087] (4) Perform data analysis based on the error accumulation array, obtain error distribution characteristics through statistical operations, and construct an error characteristic matrix;

[0088] (5) Perform spatial mapping on the error characteristic matrix, obtain the compensation parameter group through coordinate transformation, and form a compensation strategy sequence;

[0089] (6) The compensation strategy sequence is integrated and the mold error compensation vector is obtained through vector operation.

[0090] Specifically, the error compensation process divides the intelligent processing path set into several path segments, and key monitoring points are set for each path segment. The real-time coordinates of these monitoring points are collected by position sensors to obtain the actual processing position data of each point. The collected coordinate data are arranged in time sequence and spatial position to establish a deviation monitoring data group containing the position information of the monitoring points. The deviation monitoring data group stores the position information of the actual processing process, which needs to be compared and analyzed with the set coordinate values ​​in the theoretical processing path. The difference operation is performed on the actual coordinates and the set coordinates of each monitoring point, and the position deviation in the three directions of X, Y, and Z is calculated. The calculated deviation values ​​are arranged in time sequence to form an initial error sequence that describes the change of position error during the processing process.

[0091] Perform time series analysis on the initial sequence of errors to study the law of error change over time. By accumulating the error values ​​in continuous time periods, the cumulative change trend of the error is obtained. This accumulation process reflects the evolution law of the error during the processing, and the generated error accumulation array contains the time correlation information of the error. Data analysis is performed based on the error accumulation array, and the distribution law of the error is described by calculating the statistical parameters such as the mean, standard deviation, and peak value of the error. These statistical characteristics reflect the overall performance and local characteristics of the error during the processing process, and constitute the error characteristic matrix. The mathematical expression of the error characteristic matrix is:

[0092]

[0093] Among them, C ij is the compensation matrix element, ξ p is the mapping coefficient, is the error characteristic value, ω i is the spatial factor, φ j is the transformation coefficient, and r is the characteristic dimension. The compensation parameter group is obtained through this calculation, and then the compensation strategy sequence is formed. The data in the compensation strategy sequence is integrated, and the compensation amounts in each direction are combined into a unified compensation vector using the vector operation method. This process takes into account the directionality and correlation of the error and obtains the mold error compensation vector.

[0094] For example, when processing a complex curved surface mold, the processing path is divided into multiple path segments, and monitoring points are set on each path segment. The coordinate data of these points are collected in real time by position sensors to form a monitoring data group. The actual coordinates are compared with the set coordinates to calculate the position deviation of each point. These deviation data are analyzed in time series to study the trend of error changes over time and obtain the error accumulation array. The distribution characteristics of the error are determined through statistical analysis, and the error characteristic matrix is ​​established. The error characteristics are converted into compensation parameters and compensation strategies are formulated. Finally, a complete error compensation vector is obtained through vector operation to guide subsequent processing compensation.

[0095] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0096] (1) Decomposing the mold error compensation vector according to the spatial distribution relationship, performing temperature correspondence transformation on the coordinate data sequence, and obtaining the initial temperature distribution sequence;

[0097] (2) Based on the temperature fluctuations in the initial temperature distribution sequence, a temperature difference calculation formula is constructed from the perspective of spatial distribution to form a temperature gradient matrix;

[0098] (3) Through characteristic analysis of the temperature gradient matrix, the temperature correlation between different regions is established to generate a regional coupling data set;

[0099] (4) Calculate the heat transfer relationship of each region based on the regional coupling data group, and obtain the temperature fluctuation characteristic value by combining the material thermophysical property parameters;

[0100] (5) The heat treatment temperature rise law is derived through the temperature fluctuation characteristic value, and the process curve is constructed in combination with the time series to form a thermal process control sequence;

[0101] (6) The thermal process control sequence is associated with the heat treatment process parameters, and the parameters are matched according to the processing requirements to obtain a heat treatment process parameter group.

[0102] Specifically, the heat treatment process performs spatial decomposition processing on the mold error compensation vector. The compensation vector in the three-dimensional space is decomposed into components in the three directions of X, Y, and Z, and each component corresponds to a coordinate data sequence. According to the principles of thermodynamics, these coordinate data are converted into corresponding temperature values, and the corresponding relationship between spatial position and temperature is established to form an initial temperature distribution sequence.

[0103] According to the temperature variation law in the initial temperature distribution sequence, a temperature difference calculation model is constructed. The calculation expression of the temperature gradient is:

[0104]

[0105] Among them, G mn is the temperature gradient from point m to point n, ψ i is the temperature weight coefficient, is the spatial distance function, η m is the starting temperature factor, ξ n is the termination temperature coefficient, h is the temperature characteristic dimension, and the temperature gradient matrix is ​​obtained by calculation.

[0106] Perform characteristic analysis on the temperature gradient matrix and calculate the temperature correlation between regions:

[0107]

[0108] Among them, R pq is the temperature correlation between regions p and q, ν j is the area coefficient, is the temperature gradient characteristic value, σ p is the temperature characteristic factor of region p, ρ q is the temperature characteristic coefficient of region q, and k is the number of associated characteristics. The calculation results form a regional coupling data set.

[0109] Compute heat transfer relations based on a zone-coupled data set:

[0110]

[0111] Among them, H st is the heat transfer value from area s to t, is the heat transfer coefficient, is the temperature difference, ω s is the thermal conductivity of the material, φ t is the heat capacity coefficient, and m is the number of heat transfer characteristics. The temperature fluctuation characteristic value is obtained by calculation. Based on the temperature fluctuation characteristic value, the time law of temperature change is analyzed. According to the requirements of the heat treatment process, the temperature change characteristics are matched with the time axis, and a process curve containing parameters such as heating rate, holding time, cooling rate, etc. is constructed to form a thermal process control sequence.

[0112] The thermal process control sequence needs to match the specific heat treatment process requirements. According to the physical properties of the mold material and the heat treatment target, set the control parameters of each process stage, including heating temperature, holding time, cooling method, etc., to generate a complete heat treatment process parameter group.

[0113] For example: convert the error compensation vector into temperature distribution data, and establish the corresponding relationship between the spatial position and the initial temperature. Then analyze the temperature difference between adjacent areas, calculate the temperature gradient, and form the temperature field distribution characteristics. By studying the temperature correlation between different areas, determine the direction and intensity of heat transfer. Based on the law of heat transfer, combined with the thermal conductivity, specific heat capacity and other parameters of the mold material, calculate the temperature change characteristics. According to these characteristics, formulate a heating curve and determine the process parameters of each stage, such as quenching temperature range, tempering temperature range, etc. Finally, integrate these parameters into a complete process parameter group to guide the actual heat treatment process.

[0114] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0115] (1) Extract assembly sequence information from the heat treatment process parameter group, integrate the parameter requirements of each process, and form an assembly monitoring point sequence;

[0116] (2) Collect assembly process data according to the assembly monitoring point sequence, calibrate the data in combination with the physical quantity measurement standard, and construct an assembly data matrix;

[0117] (3) Divide the key performance evaluation indicators according to the numerical distribution law in the assembly data matrix and generate a performance analysis benchmark group;

[0118] (4) Combine the performance analysis benchmark set with the assembly accuracy requirements, derive the interactions among various indicators, and obtain the performance evaluation parameter set;

[0119] (5) Setting evaluation criteria based on the performance evaluation parameter set and conducting comprehensive analysis in combination with the assembly process specifications to form a quality assessment data set;

[0120] (6) An index system is constructed around the quality assessment data group, and a mold quality assessment index system is obtained by combining assembly accuracy and performance.

[0121] Specifically, the mold quality assessment stage extracts key information from the heat treatment process parameter group. This information includes the order of assembly processes, parameter requirements of each process, and quality control points. By parsing the process information in the parameter group, the key monitoring point layout of the assembly process is established, and each monitoring point corresponds to a specific assembly process and quality requirements. The process parameter requirements are matched with the monitoring point positions to form a complete assembly monitoring point sequence. Figure 2 As shown, it is a schematic diagram of the assembly monitoring point sequence in the embodiment of the present application, and the figure shows a front view of the mold, including: a bottom plate, left and right side modules, an intermediate cavity area, and a guide system on both sides (the dotted line indicates the blocked part). The monitoring points are arranged as follows: monitoring point 1 and monitoring point 2 are located in the guide systems on both sides for monitoring the guide accuracy; monitoring point 3 is located in the center of the mold surface for monitoring the mold accuracy; monitoring point 4 and monitoring point 5 are located in the core pulling mechanism for monitoring the synchronicity of core pulling; monitoring point 6 is located in the cooling system for monitoring the sealing of the waterway. The black dots in the figure indicate the positions of the monitoring points. Data collection is performed according to the assembly monitoring point sequence, and each monitoring point records multiple physical quantity parameters. These physical quantities include key indicators such as dimensional error, form and position tolerance, and assembly clearance. The collected raw data needs to be calibrated according to the measurement standard to eliminate the measurement system error and ensure the accuracy and comparability of the data. The calibrated data is matrixed according to the monitoring point position and the physical quantity type to construct an assembly data matrix.

[0122] Conduct regularity analysis on the assembly data matrix to study the distribution characteristics and correlation between different physical quantities. Identify key performance indicators through data clustering methods, which directly reflect the assembly quality and functional characteristics of the mold. Classify and organize the identified key indicators, establish benchmark standards for performance evaluation, and generate performance analysis benchmark groups. Compare and analyze the performance analysis benchmark groups with assembly accuracy requirements. Assembly accuracy requirements include specific indicators at multiple levels such as dimensional accuracy, shape and position accuracy, and fit accuracy. Through correlation analysis methods, study the influence and constraint relationships between various indicators, establish the action mechanism between indicators, and obtain the performance evaluation parameter set.

[0123] Construct an evaluation criterion system based on the performance evaluation parameter set. The evaluation criteria take into account various specific requirements in the assembly process specifications, including assembly process requirements, quality inspection standards, and acceptance specifications. Through comprehensive analysis methods, the parameter set is matched with the process specification requirements to determine the evaluation criteria for each indicator, forming a quality assessment data set. A complete evaluation index system is established around the quality assessment data set. This system organically combines the assembly accuracy indicators and performance indicators to construct a multi-level evaluation structure. The evaluation index system covers all aspects of the mold assembly quality, including geometric accuracy, assembly performance, functional characteristics, etc., forming a mold quality evaluation index system.

[0124] For example: Extract assembly information from the heat treatment process parameter set, and clarify the assembly sequence and process requirements of key components such as cavity components, core pulling mechanisms, and cooling systems. Set monitoring points in each assembly process, and the monitoring points cover key positions such as cavity mating surfaces, guiding and positioning structures, and cooling waterway interfaces. Collect data during the assembly process, including parameters such as the flatness of the mating surface, the fit clearance between the guide pillars and bushings, and the waterway tightness. After calibration, these data form a data matrix, and through analysis, the key indicators affecting the mold quality are determined, such as mold closing accuracy, core pulling synchronization, and cooling uniformity. Combining these indicators with the assembly accuracy standards, the correlation relationships between the indicators are established, forming an evaluation system including quantitative and qualitative evaluation criteria.

[0125] In a specific embodiment, the process of performing the step of extracting the assembly sequence information from the heat treatment process parameter set may specifically include the following steps:

[0126] (1) Analyze the heat treatment process parameter set according to the process type, separate the temperature parameters and the assembly point data to obtain the initial assembly information sequence;

[0127] (2) Perform time sequence sorting on the initial assembly information sequence, and combine the correlation relationships between the assembly processes to form a process connection data set;

[0128] (3) Perform parameter matching on the process connection data set, extract the key operation parameters of each process, and construct a process parameter set;

[0129] (4) Locate the assembly requirements in the process parameter set in space, determine the distribution of monitoring points according to the position relationship, and generate a monitoring reference matrix;

[0130] (5) Perform data normalization processing on the monitoring reference matrix, establish the correlation rules between the monitoring points, and obtain the monitoring layout sequence;

[0131] (6) Perform data merging around the monitoring layout sequence, integrate the monitoring requirements of each process, and obtain the assembly monitoring point sequence.

[0132] Specifically, the heat treatment process parameter group is analyzed. The heat treatment process parameter group contains two types of key information: temperature parameters and assembly point data. The temperature parameters record the process requirements of each process, such as the heat treatment temperature and holding time, while the assembly point data contains spatial information such as assembly position and assembly sequence. Through data separation processing, these two types of information are extracted and reorganized to form an initial assembly information sequence containing basic information of the assembly process. To perform time sequence processing on the initial assembly information sequence, it is necessary to consider the sequence relationship and logical dependency between the assembly processes. By analyzing the correlation between assembly processes, a sequential chain of process execution is established. The correlation between processes is reflected in many aspects: the adjacent relationship in physical space, the dependency relationship in functional realization, and the constraint relationship in assembly operation. These correlation relationships are digitized and arranged in chronological order to form a process connection data group.

[0133] Carry out parameter matching analysis on the process connection data group, focusing on extracting the key operating parameters in each process. Key operating parameters include specific numerical requirements such as assembly force, positioning accuracy, and tightening torque. By classifying and correlating these parameters, the interrelated parameters are organized together to construct a complete process parameter set. Each set of parameters in the process parameter set corresponds to a specific assembly operation. Convert the assembly requirements in the process parameter set into spatial positioning information. According to the three-dimensional structural characteristics of the mold, determine the key position points that need to be monitored. The distribution of these monitoring points needs to consider the assembly accuracy requirements, detection feasibility, and data representativeness. Through spatial coordinate transformation, the assembly requirements are mapped to specific monitoring positions to generate a monitoring reference matrix containing the spatial distribution information of the monitoring points.

[0134] The monitoring reference matrix is ​​processed for data normalization to unify the dimensions and scales of different types of monitoring data. By analyzing the spatial relationship and functional association between monitoring points, the data transmission rules between monitoring points are established. These rules describe the mutual influence and constraint relationship between the data of different monitoring points, and a standardized monitoring point sequence is obtained based on this. Data integration is performed around the monitoring point sequence, and the monitoring requirements of each process are matched with the location of the monitoring points. The integration process needs to consider the comprehensiveness and economy of monitoring to ensure that key parts are effectively monitored. Through data association analysis, the monitoring points in similar positions are merged and optimized to obtain the optimized assembly monitoring point sequence.

[0135] Taking a smart mold assembly process as an example, the heat treatment process parameter group contains temperature parameters such as cavity heat treatment temperature and tempering time, as well as assembly information such as cavity assembly position and guide component installation order. After separating this information, the initial assembly sequence is obtained. By analyzing the assembly sequence, it is found that the installation of the guide component must be completed before the cavity assembly, and the installation of the cooling system needs to be carried out after the cavity assembly is completed, thus forming a process connection relationship. In each process, key parameters are extracted, such as the matching clearance of the guide component, the mold closing accuracy of the cavity, and the sealing requirements of the cooling water channel, to construct a process parameter set. According to these parameter requirements, monitoring points are set at the matching surface of the guide component, the mold closing surface of the cavity, the water channel interface, and other locations. The spatial distribution of these monitoring points is optimized, and the association rules between the monitoring points are established to form a complete monitoring point layout plan.

[0136] The above describes the production control method of the intelligent mold in the embodiment of the present application. The following describes the production control system of the intelligent mold in the embodiment of the present application. Figure 3 In the embodiment of the present application, an embodiment of the production control system of the intelligent mold includes:

[0137] The acquisition module 201 is used to acquire mold production parameters through a multi-dimensional sensor, extract features of the production parameters, and classify and sort them to obtain a mold production feature data set;

[0138] A screening module 202 is used to perform hierarchical screening and combination matching on the mold material performance indicators according to the mold production characteristic data set to generate a mold material ratio parameter matrix;

[0139] A construction module 203 is used to construct a processing coordinate sequence based on the mold material ratio parameter matrix and a preset processing trajectory rule, and obtain an intelligent processing path set through trajectory optimization calculation;

[0140] A calculation module 204 is used to collect and accumulate error deviation values ​​in the mold processing process in real time according to the intelligent processing path set to form a mold error compensation vector;

[0141] A mapping module 205 is used to perform gradient division and area mapping on the heat treatment temperature field distribution according to the mold error compensation vector to obtain a heat treatment process parameter group;

[0142] The testing module 206 is used to establish a mold quality evaluation index system based on the heat treatment process parameter group through key point data collection and performance testing during the assembly process.

[0143] Through the coordinated cooperation of the above-mentioned components, the mold production parameters are collected through multi-dimensional sensors, and the real-time monitoring and feature extraction of key parameters such as temperature, pressure, and vibration are realized. Based on the mold production feature data set, the material performance indicators are hierarchically screened and combined, and the corresponding relationship between material performance and processing requirements is established, forming a scientific material ratio parameter matrix; the processing coordinate sequence is constructed through the preset rules of the processing trajectory, and the intelligent processing path set is obtained through trajectory optimization calculation, which improves the accuracy of the processing process; the error deviation value in the mold processing process is collected and accumulated in real time, forming an accurate mold error compensation vector, which effectively controls the processing error; according to the mold error compensation vector, the heat treatment temperature field distribution is gradient divided and regionally mapped, and a reasonable heat treatment process parameter group is obtained to ensure the quality of heat treatment; through the key point data collection and performance testing of the assembly process, a complete mold quality evaluation index system is established, the comprehensiveness of quality control is achieved, and the intelligence level and control accuracy of the mold production process are significantly improved.

[0144] Based on the same technical concept, the embodiment of the present application also provides an electronic device. Figure 4 As shown, it is a schematic diagram of the structure of the electronic device 300 provided in the embodiment of the present application, including a processor 301, a memory 302, and a bus 303. Among them, the memory 302 is used to store execution instructions, including a memory 3021 and an external memory 3022; the memory 3021 here is also called an internal memory, which is used to temporarily store the operation data in the processor 301, and the data exchanged with the external memory 3022 such as a hard disk. The processor 301 exchanges data with the external memory 3022 through the memory 3021. When the computer device 300 is running, the processor 301 communicates with the memory 302 through the bus 303.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0146] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0147] As described above, the above embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. A production control method for an intelligent mold, characterized in that: The production control method of the intelligent mold includes: Collect mold production parameters through multi-dimensional sensors, extract features and classify the production parameters to obtain a mold production feature data set; According to the mold production characteristic data set, the mold material performance indicators are screened and matched in layers to generate a mold material ratio parameter matrix; Based on the mold material ratio parameter matrix, a processing coordinate sequence is constructed through a preset processing trajectory rule, and an intelligent processing path set is obtained through trajectory optimization calculation; According to the intelligent processing path set, the error deviation value in the mold processing process is collected and accumulated in real time to form a mold error compensation vector; According to the mold error compensation vector, gradient division and area mapping are performed on the heat treatment temperature field distribution to obtain a heat treatment process parameter group; Based on the heat treatment process parameter group, a mold quality evaluation index system is established through key point data collection and performance testing during the assembly process.

2. The production control method of the intelligent mold according to claim 1, characterized in that: The mold production parameters are collected by multi-dimensional sensors, and the production parameters are feature extracted and classified to obtain a mold production feature data set, including: The temperature parameters, pressure parameters and vibration parameters are collected by the multidimensional sensor, and the temperature parameters, pressure parameters and vibration parameters are marked in time series to generate a raw data matrix; The original data matrix is ​​segmented according to the sampling period, and the periodic eigenvalues ​​are obtained by discrete sampling to form a frequency domain data sequence; Performing physical quantity classification on the frequency domain data sequence, obtaining numerical distribution characteristics through numerical statistical operations, and acquiring parameter statistical results; Divide the parameter statistical results into numerical intervals, obtain the change characteristic coefficient through data fluctuation analysis, and construct the parameter characteristic vector; Performing data standardization conversion on the parameter feature vector to obtain a normalized parameter set through linear transformation; Principal components are extracted from the normalized parameter set, and the mold production feature data set is obtained through data dimensionality reduction analysis.

3. The production control method of the intelligent mold according to claim 1, characterized in that: The method of performing hierarchical screening and combination matching on the mold material performance indicators according to the mold production characteristic data set to generate a mold material ratio parameter matrix includes: Analyzing the mold production feature data set, separating the mechanical strength, heat treatment parameters, and material hardness data, and generating a performance parameter sequence; Classify and sort the performance parameter sequence through numerical calculation, quantify different indicators, and form a quantitative indicator array; Performing hierarchical operations on the quantitative indicator array, obtaining indicator priorities through weight allocation, and constructing a hierarchical weight sequence; Performing data matching on the hierarchical weight sequence and the material ratio coefficient, and obtaining a ratio scheme set by combined calculation; Performing data verification on the ratio scheme set, obtaining performance matching through cross-validation, and constructing a verification data set; Multiple rounds of data analysis are performed on the verification data set, and the mold material ratio parameter matrix is ​​obtained through data screening.

4. The production control method of the intelligent mold according to claim 1, characterized in that: Based on the mold material ratio parameter matrix, a processing coordinate sequence is constructed through a preset processing trajectory rule, and an intelligent processing path set is obtained through trajectory optimization calculation, including: Performing data analysis on the mold material ratio parameter matrix, obtaining a processing point sequence through spatial coordinate division, and constructing an initial trajectory data set; Arranging the initial trajectory data set according to the processing order, obtaining the path connection relationship through continuity calculation, and forming a trajectory connection matrix; Numerical operations are performed on the trajectory connection matrix, a distance parameter set is obtained by path length calculation, and a trajectory cost sequence is generated; Perform path planning based on the trajectory cost sequence, obtain a smooth path array through trajectory smoothing, and construct an optimized trajectory set; Performing kinematic analysis on the optimized trajectory set, obtaining a motion parameter group through speed planning, and forming a machining strategy matrix; The processing strategy matrix is ​​data integrated, and the intelligent processing path set is obtained through trajectory combination.

5. The production control method of the intelligent mold according to claim 1, characterized in that: According to the intelligent processing path set, the error deviation value in the mold processing process is collected and accumulated in real time to form a mold error compensation vector, including: The intelligent processing path set is monitored in sections, real-time coordinate points are acquired through position sensing, and a deviation monitoring data set is constructed; Comparing the deviation monitoring data set with the set coordinate value, obtaining the position deviation amount by difference calculation, and forming an initial error sequence; Performing a time series analysis on the initial error sequence, obtaining the error variation trend through cumulative calculation, and generating an error accumulation array; Perform data analysis based on the error accumulation array, obtain error distribution characteristics through statistical operations, and construct an error characteristic matrix; Performing spatial mapping on the error characteristic matrix, obtaining a compensation parameter group through coordinate transformation, and forming a compensation strategy sequence; The compensation strategy sequence is data integrated, and the mold error compensation vector is obtained through vector operation.

6. The production control method of the intelligent mold according to claim 1, characterized in that: The step of performing gradient division and area mapping on the heat treatment temperature field distribution according to the mold error compensation vector to obtain a heat treatment process parameter group includes: Decomposing the mold error compensation vector according to the spatial distribution relationship, performing temperature correspondence conversion on the coordinate data sequence, and obtaining an initial temperature distribution sequence; According to the temperature fluctuation in the initial temperature distribution sequence, a temperature difference calculation formula is constructed from the perspective of spatial distribution to form a temperature gradient matrix; By analyzing the characteristics of the temperature gradient matrix, establishing the temperature correlation between different regions and generating a regional coupling data set; Calculate the heat transfer relationship of each region according to the regional coupling data group, and obtain the temperature fluctuation characteristic value in combination with the material thermophysical property parameters; The temperature rise rule of heat treatment is deduced through the temperature fluctuation characteristic value, and the process curve is constructed in combination with the time series to form a thermal process control sequence; The thermal process control sequence is associated with the thermal treatment process parameters, and the parameters are matched according to the processing requirements to obtain the thermal treatment process parameter group.

7. The production control method of the intelligent mold according to claim 1, characterized in that: Based on the heat treatment process parameter group, a mold quality evaluation index system is established through key point data collection and performance testing during the assembly process, including: Extract assembly sequence information from the heat treatment process parameter group, integrate the parameter requirements of each process step, and form an assembly monitoring point sequence; Collect assembly process data according to the assembly monitoring point sequence, calibrate the data in combination with the physical quantity measurement standard, and construct an assembly data matrix; According to the numerical distribution law in the assembly data matrix, key performance evaluation indicators are divided to generate a performance analysis benchmark group; Combining the performance analysis benchmark group with the assembly accuracy requirements, deriving the interaction between various indicators, and obtaining a performance evaluation parameter set; Setting evaluation criteria based on the performance evaluation parameter set, and conducting comprehensive analysis in combination with assembly process specifications to form a quality evaluation data set; An index system is constructed around the quality assessment data set, and the mold quality assessment index system is obtained by combining assembly accuracy and performance.

8. The production control method of the intelligent mold according to claim 7, characterized in that: The step of extracting assembly sequence information from the heat treatment process parameter group and integrating the parameter requirements of each process step to form an assembly monitoring point sequence includes: Parsing the heat treatment process parameter group according to the process type, separating the temperature parameters and the assembly point data, and obtaining an initial assembly information sequence; The initial assembly information sequence is sorted in time sequence, and the association relationship between assembly processes is combined to form a process connection data group; Perform parameter matching on the process connection data group, extract key operating parameters of each process, and construct a process parameter set; Positioning the assembly requirements in the process parameter set in space, determining the distribution of monitoring points according to the positional relationship, and generating a monitoring reference matrix; Performing data normalization processing on the monitoring reference matrix, establishing association rules between monitoring points, and obtaining a monitoring point sequence; Data merging is performed around the monitoring point sequence, and the monitoring requirements of each process are integrated to obtain the assembly monitoring point sequence.

9. A production control system for an intelligent mold, used to implement the production control method for an intelligent mold as claimed in any one of claims 1 to 8, characterized in that: The production control system of the intelligent mold includes: An acquisition module is used to acquire mold production parameters through a multi-dimensional sensor, perform feature extraction and classification on the production parameters, and obtain a mold production feature data set; A screening module, used to perform hierarchical screening and combination matching of mold material performance indicators according to the mold production feature data set, and generate a mold material ratio parameter matrix; A construction module is used to construct a processing coordinate sequence based on the mold material ratio parameter matrix through a preset processing trajectory rule, and obtain an intelligent processing path set through trajectory optimization calculation; A calculation module, used for collecting and accumulating the error deviation values ​​in the mold processing process in real time according to the intelligent processing path set, and forming a mold error compensation vector; A mapping module, used to perform gradient division and area mapping on the heat treatment temperature field distribution according to the mold error compensation vector, and obtain a heat treatment process parameter group; The test module is used to establish a mold quality evaluation index system based on the heat treatment process parameter group through key point data collection and performance testing during the assembly process.

10. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the production control method of the intelligent mold as described in any one of claims 1 to 8 are performed.

Images