Circuit board processing automation control method and system

Abstract

The invention relates to the technical field of industrial automatic control and intelligent manufacturing, and discloses an automatic control method and system for circuit board processing. According to the method, initial operation parameters of equipment are collected and subjected to time sequence analysis, and an operation parameter set is constructed; simulating mutual influence among parameters based on a genetic algorithm, determining weight distribution, and generating an equipment coordination demand vector; performing hierarchical processing and feature separation on the data exceeding the threshold value, and determining a production limitation constraint group; similar cases in the historical control instruction database are matched, and an adjustment scheme is generated and optimized; a final control instruction is obtained through key variable conflict solution and production line feedback signal deviation calibration; and distributing an execution signal based on the instruction, collecting and correcting an update parameter, and realizing intelligent closed-loop control of the circuit board processing process. According to the invention, the automation level, the production efficiency and the product quality consistency of circuit board processing are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of industrial automation control and intelligent manufacturing technology, and in particular to an automated control method and system for a circuit board processing production line. Background Technology

[0002] Currently, in the electronics manufacturing industry, the level of automation in circuit board processing is constantly improving, while the requirements for control precision, response speed, and multi-device collaboration capabilities in production lines are increasing. As one of the key technologies supporting modern manufacturing, industrial control systems play a crucial role in process control and information interaction during circuit board processing. How to achieve high-efficiency and high-consistency processing capabilities through advanced industrial control systems has become a key focus of the industry.

[0003] In existing technologies, control systems typically collect operating parameters of production line equipment and issue control commands to the processing equipment based on fixed logic or rule models to achieve basic automation control. For example, some industrial control systems rely on static production models to independently control each processing unit (such as drilling, mounting, and soldering). Some systems use simple speed matching, cycle time control, or threshold judgment methods to coordinate the processing rhythm of multiple devices to avoid mutual blockage or processing delays. However, with the increase in the number of devices, the complexity of production line structures, and the increasing demands for real-time performance, existing technologies are gradually revealing their limitations. Especially in circuit board processing scenarios that require the coordinated operation of multiple devices, the operating parameters of each device within the production line are diverse and change rapidly, and there are multiple coupling constraints between different devices, such as processing speed, step sequence, and process windows. If the control system cannot perform multi-dimensional analysis of this real-time data, it will be difficult to generate optimal commands that match the current production environment.

[0004] Therefore, existing technologies suffer from poor coordination between devices. Summary of the Invention

[0005] This invention proposes an automated control method and system for circuit board processing to solve the problem of low coordination in existing manufacturing processes.

[0006] In a first aspect, to solve the above-mentioned technical problems, the present invention provides an automated control method for circuit board processing, comprising: The initial operating parameters of the acquisition device are collected, and time series analysis is performed on the initial operating parameters to obtain a set of operating parameters. Based on the set of operating parameters, a genetic algorithm is used to simulate and iteratively calculate the mutual influence relationship between the parameters, determine the weight distribution result of the parameter influence, and generate the equipment coordination demand vector according to the weight distribution result. The data portion of the coordination demand vector that exceeds the preset coordination threshold is processed in layers to obtain a layered dataset. Feature separation is performed on the layered dataset, and the separated features are segmented into regions to determine the boundary constraint range after segmentation. Production restriction constraint groups are determined based on the boundary constraint range. For the production constraint group, similar cases are obtained from a preset historical control instruction database. Based on the similar cases, a weighted fusion is used to generate a preliminary adjustment scheme. The preliminary adjustment scheme is then compared and verified for consistency to obtain an optimized control instruction. Key variables are extracted from the optimized control instructions. If there is a conflict between the key variables, a genetic algorithm is iteratively applied to resolve the conflict and determine the conflict-free control instructions. Obtain the feedback signal from the current production line, and use the feedback signal to calibrate the deviation of the conflict-free control command to obtain the final control command; Based on the final control command, execution signals are distributed to the production line equipment, and the updated operating parameters after the signal execution are collected and compared with the preset operating parameter thresholds to determine the parameter deviation range. The updated operating parameters are corrected based on the parameter deviation range to obtain the final operating parameter control scheme.

[0007] In a second aspect, the present invention provides an automated control system for circuit board processing, comprising: The data acquisition module is used to collect the initial operating parameters of the equipment, perform time series analysis on the initial operating parameters, and obtain a set of operating parameters. The coordination requirement determination module is used to simulate and iteratively calculate the mutual influence relationship between the parameters based on the set of operating parameters using a genetic algorithm, determine the weight distribution result of the parameter influence, and generate the coordination requirement vector of the equipment based on the weight distribution result. The constraint group generation module is used to perform hierarchical processing on the data portion of the coordination demand vector that exceeds the preset coordination threshold to obtain a hierarchical dataset, perform feature separation on the hierarchical dataset, perform region segmentation on the separated features and determine the boundary constraint range after segmentation, and determine the production restriction constraint group based on the boundary constraint range. The instruction optimization module is used to obtain similar cases from a preset historical control instruction database for the production constraint group, generate a preliminary adjustment scheme by weighted fusion based on the similar cases, and perform consistency comparison and verification on the preliminary adjustment scheme to obtain optimized control instructions. The conflict resolution module is used to extract key variables from the optimized control instructions. If there is a conflict between the key variables, a genetic algorithm is iteratively applied to resolve the conflict and determine the conflict-free control instructions. The instruction calibration module is used to acquire the feedback signal of the current production line, and use the feedback signal to calibrate the deviation of the conflict-free control instruction to obtain the final control instruction. The execution monitoring module is used to distribute execution signals to production line equipment based on the final control command, collect updated operating parameters after signal execution and compare them with preset operating parameter thresholds to determine the parameter deviation range; The final correction module is used to correct the updated operating parameters according to the parameter deviation range to obtain the final operating parameter control scheme.

[0008] Compared with the prior art, the present invention has the following advantages: (1) This invention achieves real-time correlation analysis of the operating status between equipment through time series analysis, parameter correlation modeling and genetic algorithm weight optimization, enabling the control system to dynamically adjust instructions according to the processing environment, improve the coordination capability of multiple equipment, avoid cycle time conflict and equipment waiting, and effectively improve the coordination between equipment.

[0009] (2) This invention introduces a historical instruction database and a weighted case fusion mechanism, which can automatically generate optimized instructions based on production constraints, and further improve the reliability of instructions through consistency comparison and conflict resolution, so that the control strategy has learning and adaptive capabilities.

[0010] (3) The present invention uses the feedback signal deviation calibration and final parameter correction mechanism to dynamically compensate for the error in the execution process, so that the control system can continuously optimize the control command according to the actual state of the production line, thereby improving the processing accuracy and operation stability.

[0011] (4) The present invention constitutes a complete process from parameter acquisition, feature separation, constraint generation, instruction optimization to conflict resolution and final calibration. It can handle multi-variable coupling, high-dimensional parameter changes and complex process windows, and provide an scalable control framework for highly automated and highly flexible circuit board production lines. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating an embodiment of the automated control method for circuit board processing provided by the present invention; Figure 2 This is a schematic diagram of an embodiment of the automated control system for circuit board processing provided by the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0014] Reference Figure 1 The first embodiment of the present invention provides an automated control method for circuit board processing, including steps S11 to S18: S11, Collect the initial operating parameters of the equipment, perform time series analysis on the initial operating parameters, and obtain a set of operating parameters; S12, based on the set of operating parameters, a genetic algorithm is used to simulate and iteratively calculate the mutual influence relationship between the parameters, determine the weight distribution result of the parameter influence, and generate the equipment coordination demand vector according to the weight distribution result; S13, perform hierarchical processing on the data portion of the coordination demand vector that exceeds the preset coordination threshold to obtain a hierarchical dataset, perform feature separation on the hierarchical dataset, perform region segmentation on the separated features and determine the boundary constraint range after segmentation, and determine the production restriction constraint group based on the boundary constraint range. S14, for the production constraint group, obtain similar cases from the preset historical control instruction database, generate a preliminary adjustment scheme by weighted fusion based on the similar cases, and perform consistency comparison and verification on the preliminary adjustment scheme to obtain optimized control instructions; S15, extract key variables from the optimized control instructions. If there is a conflict between the key variables, iteratively apply a genetic algorithm to resolve the conflict and determine the conflict-free control instructions. S16, Obtain the feedback signal of the current production line, and use the feedback signal to perform deviation calibration on the conflict-free control command to obtain the final control command; S17, based on the final control command, distribute execution signals to the production line equipment, collect the updated operating parameters after the signal execution and compare them with the preset operating parameter thresholds to determine the parameter deviation range; S18, The updated operating parameters are corrected according to the parameter deviation range to obtain the final operating parameter control scheme.

[0015] In step S11, the initial operating parameters of the device are collected, and time series analysis is performed on the initial operating parameters to obtain a set of operating parameters, including: The initial operating parameters of the equipment are collected through a sensor network; The initial operating parameters are denoised and segmented to obtain a preliminarily organized parameter dataset; The parameter dataset is decomposed into time series to extract trend and periodic components. Feature values ​​are calculated for the trend and periodic components to determine key parameters of the equipment's operating status. The key parameters are then integrated to obtain a set of operating parameters.

[0016] Specifically, initial operating parameters are collected through a sensor network deployed at key locations on the production line equipment. This sensor network includes various types of sensors, such as vibration sensors, temperature sensors, current sensors, and pressure sensors, which monitor the mechanical, thermal, electrical, and process conditions of the equipment, respectively. Each sensor collects data synchronously according to a preset sampling frequency; for example, the vibration sensor sampling frequency is set to 100Hz, the temperature sensor sampling frequency to 1Hz, and the current sensor sampling frequency to 100Hz. The collected raw signal data is transmitted to the monitoring system via a data acquisition card, forming initial operating parameters that include timestamps, sensor identifiers, and parameter values.

[0017] A moving average filtering method is used to denoise the collected initial operating parameters, eliminating the influence of environmental interference and sensor noise. The sliding window length is set to one-tenth of the sampling frequency. The data points within the window are arithmetically averaged, and the average value replaces the original value at the window's center point. The sliding window moves forward sequentially until the entire data sequence has been processed. After denoising, the parameter data is segmented, dividing the continuous time series into data segments of fixed duration. This segmentation is performed according to the device's operating cycle or a fixed time interval, typically set to 1 minute or the duration of one complete operating cycle. Each data segment contains all sampling points within that time period, with no overlap or only partial overlap between segments (overlap rate typically set to 10-20%), forming a pre-processed parameter dataset.

[0018] An additive decomposition model is used to process the parameter dataset, splitting the original signal into three parts: trend component, periodic component, and residual component. The trend component is extracted using a moving average method, calculating the average value of each data segment over a longer time window (e.g., 10 minutes), reflecting the long-term trend of the parameter over time. The periodic component is extracted by identifying repetitive patterns in the trend-removed signal, determining the period length using autocorrelation analysis, and then averaging the data within each period to obtain a standard periodic waveform. The residual component is the remaining part after subtracting the trend and periodic components from the original signal, mainly containing random fluctuations and irregular changes. For the trend component, the rate of change, initial value, and final value are calculated. The rate of change is obtained by dividing the difference between the first and last values ​​of the trend component by the time span, reflecting the rate of increase or decrease of the parameter. For the periodic component, the frequency, amplitude, and stability of the period are calculated; these characteristic values ​​reflect the regularity and stability of the equipment operation.

[0019] Based on the calculated feature values, key parameters of the equipment's operating status are determined, including the trend slope, period frequency, period amplitude, and root mean square value of the residual components of various sensor signals. The key parameters of each sensor are categorized and organized according to sensor type and parameter type, forming a structured set of operating parameters. This set of operating parameters includes the current value, trend, statistical characteristics, and corresponding timestamp information of each key parameter, providing a data foundation for subsequent anomaly detection and status assessment.

[0020] In step S12, based on the set of operating parameters, a genetic algorithm is used to simulate and iteratively calculate the mutual influence relationships between the parameters to determine the weight distribution results of the parameter influences. Based on the weight distribution results, a coordination demand vector for the equipment is generated, including: The set of operating parameters is standardized to obtain a set of standard parameters; For the set of standard parameters, calculate the correlation strength between each parameter, construct a mutual influence matrix between parameters based on the correlation strength, and calculate and determine the preliminary weight set of the parameter influence based on the mutual influence matrix; If the weight value of at least one parameter in the preliminary weight set exceeds the preset weight optimization threshold, a genetic algorithm is used to iteratively simulate and optimize the preliminary weight set to obtain the optimized weight distribution result. Based on the weight distribution results, the current deviation of each parameter is multiplied by the corresponding optimization weight to generate the coordination requirement vector of the equipment.

[0021] Specifically, based on the set of operating parameters obtained in step S11, the Z-score standardization method is used to process various parameters to obtain a set of standard parameters.

[0022] For a standard set of parameters, a mutual influence matrix is ​​constructed. Specifically, the Pearson correlation coefficient is first used to calculate the linear correlation between any two parameters. Then, an N×N mutual influence matrix is ​​constructed, where N is the number of parameters, and the element in the i-th row and j-th column is the Pearson correlation coefficient between the i-th and j-th parameters. The diagonal elements of the matrix are all 1s (parameters are perfectly correlated with themselves), and the matrix is ​​symmetric.

[0023] Based on the correlation strength of each parameter in the mutual influence matrix, a preliminary set of parameter influence weights is calculated. These preliminary weights are obtained by summing the absolute values ​​of the correlation coefficients of each parameter in the corresponding row of the matrix. After calculation, normalization is performed so that the sum of all parameter weights equals 1, resulting in the preliminary weight set.

[0024] The weights of each parameter in the initial weight set are compared with preset weight optimization thresholds. These weight optimization thresholds are empirically set to a range of 0.15-0.30, specifically determined based on statistical analysis of historical operating data, typically using the 10th and 90th quantiles of the parameter weight distribution to avoid excessively high weights for a single parameter that could cause the system to become overly sensitive to that parameter. If the initial weight of a parameter exceeds the upper bound of 0.30 or falls below the lower bound of 0.15, then that weight is deemed to require optimization.

[0025] A genetic algorithm is used to iteratively simulate and optimize the initial weight set. The genetic algorithm includes steps such as population initialization, fitness evaluation, selection, crossover, and mutation. The initial weight set is used as the initial individuals, and several mutated individuals are randomly generated to form the initial population, typically set to 50-100 individuals. A fitness function is defined to evaluate the quality of each individual. This fitness function comprehensively considers the balance of the weight distribution and the consistency between the weights and the correlation coefficient. The calculation method is as follows: the smaller the weight variance, the higher the matching degree between the weights and the correlation coefficient. Specifically, the weight variance is first subtracted from 1 to obtain the weight variance index. The matching degree index is quantified by first vectorizing the weight sequence and the correlation coefficient sequence, then calculating their cosine similarity, and finally fusing the two indices through linear weighting to obtain the fitness. For example, the weights are set to [0.5, 0.5], which can be dynamically adjusted according to parameter sensitivity.

[0026] Individuals in the population are selected based on their fitness scores, with those possessing higher fitness retained as parents. A crossover operation is performed on the parents, randomly selecting two individuals and swapping their weight vectors at the crossover point to generate new offspring. A mutation operation is then performed on the offspring, randomly adjusting the weight values ​​of individual parameters with a certain probability (usually set to 5-10%). This selection, crossover, and mutation process is repeated for multiple generations (usually 50-100 generations) until the population gradually converges to the optimal solution. The individual with the highest fitness in the final population is selected as the optimized weight distribution. The current deviation of each parameter is multiplied by its corresponding optimized weight to obtain the coordination demand vector. The current deviation of a parameter is calculated by comparing its current standardized value with its historical normal range. The historical normal range typically uses the mean of historical data ± two standard deviations as the upper and lower bounds; a larger deviation indicates a higher degree of abnormality for the parameter.

[0027] For example, the set of operating parameters containing 9 key parameters obtained in step S11 is standardized using Z-score to form a standard parameter set. A 9×9 mutual influence matrix is ​​constructed, and the Pearson correlation coefficient between the vibration trend slope and the temperature trend slope is calculated to be 0.72, indicating a strong positive correlation. Preliminary weights are calculated based on the mutual influence matrix, and it is found that the preliminary weight of the vibration trend slope is 0.125 (below the lower threshold of 0.15), and the preliminary weight of the current cycle amplitude is 0.35 (exceeding the upper threshold of 0.30).

[0028] A genetic algorithm was used for optimization, with a population size of 60 individuals, 80 generations, and a mutation probability of 8%. After iterative optimization, the following weight distribution was obtained: vibration trend slope weight 0.18, temperature trend slope weight 0.16, current cycle amplitude weight 0.28, and other parameter weights ranging from 0.02 to 0.11. A coordination requirement vector was calculated based on the optimized weights and the current parameter deviation. The vector component ranking showed that the coordination requirement component for vibration trend slope was 0.103 (highest priority), followed by temperature trend slope at 0.08 (second highest priority), guiding operators to prioritize checking vibration-related mechanical components.

[0029] In step S13, the data portion of the coordination demand vector exceeding a preset coordination threshold is processed into a hierarchical dataset. Feature separation is performed on the hierarchical dataset, and the separated features are used for region segmentation to determine the boundary constraint range after segmentation. Based on the boundary constraint range, a production restriction constraint group is determined, including: The data portion of the coordination demand vector that exceeds a preset coordination threshold is processed in layers to obtain a layered dataset. For the hierarchical dataset, feature separation is performed on dynamic environmental variables to determine the set of separated variable features; If at least one feature value in the variable feature set exceeds the preset feature threshold range, then the variable feature set is segmented into regions to obtain the segmented boundary constraint range. Based on the boundary constraint range, constraint integration is used to combine and map the production constraints to obtain a production constraint set.

[0030] Specifically, based on the coordination demand vector obtained in step S12, the data portion in the vector whose values ​​exceed a preset coordination threshold is extracted. The preset coordination threshold is set according to the normal operating range of the equipment, typically determined by adding or subtracting the mean and twice the standard deviation as the upper and lower limits for threshold determination. The data exceeding the threshold are stratified according to risk level. The K-means clustering method is used to divide the data into three levels: high-risk, medium-risk, and low-risk. The high-risk level contains data with the largest deviation from the threshold, the medium-risk level contains data with a moderate degree of deviation, and the low-risk level contains data with a small degree of deviation but still exceeding the threshold, forming a stratified dataset.

[0031] For the hierarchical dataset, dynamic environmental variables related to equipment operation are extracted and feature separation is performed. These dynamic environmental variables include parameters across multiple dimensions such as ambient temperature, ambient humidity, equipment runtime, equipment load rate, energy consumption level, and production cycle time. Principal component analysis (PCA) is used to reduce the dimensionality of these variables and extract features. The top principal components with a cumulative variance contribution rate of over 85% are selected as the separated variable features, thus determining the set of separated variable features.

[0032] Each feature value in the variable feature set is compared with a preset feature threshold range. The feature threshold range is determined based on the statistical distribution of historical data, typically using the mean ± two standard deviations as the upper and lower bounds of the normal range. If a feature value exceeds the upper bound or falls below the lower bound, it is determined to be an anomalous feature, requiring region segmentation. The variable feature set containing anomalous features is segmented into regions using a support vector machine classifier to delineate the boundaries of the feature space, obtaining the segmented boundary constraint range. This boundary constraint range defines the allowable intervals for normal operation in each feature dimension.

[0033] It should be noted that the Support Vector Machine (SVM) classifier uses the RBF kernel parameters, and the training process includes two key steps: dataset construction and parameter optimization. For dataset construction, the equipment operation records for the most recent 6 months are extracted from the historical operation database. Records marked as "normal" are selected as positive samples, and records marked as "abnormal" or "faulty" are selected as negative samples. The training and test sets are divided in a 7:3 ratio to ensure sufficient sample diversity in the training set. The feature data in the training set are standardized to eliminate the influence of different feature units. For parameter optimization, a grid search method is used to jointly optimize the penalty coefficient C and the kernel function parameter γ. The candidate value range for C is set to [0.1, 1, 10, 100], and the candidate value range for γ is set to [0.001, 0.01, 0.1, 1], forming 16 parameter combinations. Five-fold cross-validation is performed on each parameter combination. The training set is divided into 5 subsets, and 4 subsets are used alternately to train the model, while the remaining subset is used to validate the performance. The average accuracy of the 5 validations is calculated. The parameter combination that yields the highest cross-validation accuracy is selected as the optimal parameter.

[0034] Based on the segmented boundary constraint ranges, production constraints are combined and mapped. These constraints include multiple constraints such as equipment load limits, energy consumption limits, production cycle time requirements, and permissible environmental temperature and humidity ranges. The boundary constraint ranges of each feature dimension are converted into corresponding production constraints; for example, the boundary constraint of the temperature feature is converted into the adjustment range of the workshop temperature control system, and the boundary constraint of the load feature is converted into the load limit for equipment task allocation. A linear programming method is used to optimize the combination of multiple constraints. First, an objective function is constructed, with the optimization objective being minimizing equipment operating deviation and energy consumption. The objective function has the form: min(w1×b1) 2 +w2×b2 2 +w3×b3 2 The equation is as follows: b1, b2, and b3 represent load deviation, energy consumption deviation, and cycle time deviation, respectively. During calculation, Z-score standardization is first performed to eliminate dimensional differences. w1, w2, and w3 are weighting coefficients set based on the influence of each deviation factor on the total deviation, typically set to 0.4, 0.3, and 0.3, respectively. Next, a set of constraint inequalities is established, including: equipment load rate ≤ upper boundary constraint limit, ambient temperature ≥ lower boundary constraint limit and ≤ upper boundary constraint limit, energy consumption level ≤ energy consumption limit, and production cycle time ≥ minimum cycle time requirement. Simultaneously, variable value range constraints are added to ensure that each parameter is within the physical feasible region. The simplex method is used to solve the linear programming problem, iteratively calculating the optimal solution in the feasible solution space that minimizes the objective function. During the solution process, if conflicts between constraints lead to an infeasible solution, secondary constraints are relaxed sequentially according to constraint priority (safety constraints > quality constraints > efficiency constraints) until a feasible solution is obtained.

[0035] The parameter values ​​of the optimal solution in the feasible solutions are used as the specific values ​​of the production constraint set. The production constraint set clarifies the load range, energy consumption limit, and environmental condition requirements that each piece of equipment should follow under the current operating state, providing a constraint basis for subsequent scheduling decisions.

[0036] For example, for the coordination demand vector (containing 9 components, with values ​​ranging from 0.006 to 0.103), the median is calculated to be 0.033, and the preset coordination threshold is 0.05. Data exceeding the threshold are extracted: vibration trend slope 0.103, temperature trend slope 0.08, and current cycle amplitude 0.056. K-means clustering is used to divide the data into: a high-risk layer containing the vibration trend slope (0.103), a medium-risk layer containing the temperature trend slope (0.08), and a low-risk layer containing the current cycle amplitude (0.056).

[0037] Dynamic environmental variables were extracted: ambient temperature 28℃, humidity 65%, equipment operating time 120 hours, load rate 88%, and energy consumption 1.2kW. Principal component analysis was used, and the cumulative variance contribution rate of the first two principal components reached 90%. The eigenvalue of the first principal component, 2.1, exceeded the upper bound of 1.8, and the eigenvalue of the second principal component, 1.5, exceeded the upper bound of 1.2.

[0038] A support vector machine classifier was used for region segmentation, and the boundary constraints were determined as follows: temperature not exceeding 26℃, load rate not exceeding 75%, maintenance and inspection every 100 hours of operation, and energy consumption not exceeding 1.0kW. A linear programming method was used to integrate the constraints, resulting in the following production constraint set: equipment load rate reduced to 70%, workshop temperature control system adjusted to 25℃, task allocation adjusted to 92 pieces per hour, and energy consumption limit set at 0.95kW.

[0039] In step S14, for the production constraint group, similar cases are obtained from a preset historical control instruction database. Based on the similar cases, a weighted fusion is used to generate a preliminary adjustment scheme. The preliminary adjustment scheme is then subjected to consistency comparison and verification to obtain optimized control instructions, including: From a preset historical control instruction database, obtain case data related to the production constraint group, calculate the similarity between the case data and the production constraint group, and filter similar cases based on the similarity. For the aforementioned similar cases, dynamic weights are calculated for the environmental variables of the case data to obtain dynamic weight combinations; If at least one value in the dynamic weight combination exceeds the preset weight threshold range, then the similar cases are weighted and fused based on the dynamic weight combination to obtain a preliminary adjustment scheme. The initial adjustment scheme is compared and verified for consistency to obtain optimized control instructions.

[0040] Specifically, case data related to the production constraint group obtained in step S13 is retrieved from a pre-established historical control instruction database. The retrieval process first performs a coarse screening based on key constraints in the production constraint group, extracting candidate cases from the database that meet the following conditions: the equipment type is consistent with the current equipment, the constraint type matches, and the historical execution effect rating is "good" or "excellent." After the coarse screening, approximately 200-300 candidate cases are selected from over 5,000 historical records in the database. The historical control instruction database stores various equipment anomalies that have occurred in past production and their corresponding adjustment measures. Each case record includes constraints (load rate, temperature, energy consumption, etc.), environmental variables (runtime, task priority, equipment status, etc.), adjustment instructions (load adjustment range, temperature adjustment range, task redistribution scheme, etc.), and execution effects (adjusted equipment status, changes in production efficiency, etc.). This is achieved through continuous collection of production line operation data, manual annotation of anomaly cases, and regular optimization and updates.

[0041] The similarity between the current production constraint group and each case in the database is calculated using the cosine similarity method for quantitative evaluation. Specifically, the constraint values ​​of the current constraint group (load rate 70%, temperature 25℃, energy consumption 0.95kW, etc.) and the constraint values ​​of historical cases are first Z-score standardized to form vectors. The dot product of the two vectors is then divided by the product of the magnitudes of the vectors to obtain the similarity score. The calculated similarities are ranked, and the top 5-10 cases with the highest similarity are selected as similar cases.

[0042] For the selected similar cases, environmental variable data are extracted for each case, including parameters such as ambient temperature, ambient humidity, equipment runtime, task priority, and equipment health (calculated based on historical failure rate and real-time diagnostic data). The entropy weight method is used to calculate the weight of each environmental variable. First, the data for each environmental variable is standardized. Then, the information entropy of each variable is calculated. The information entropy is obtained by the negative sum of the products of the proportion of each data point and its logarithm. The entropy weight is obtained by subtracting the information entropy from 1 and then normalizing. The environmental variables of each similar case are weighted according to the calculated entropy weights to form a dynamic weight combination.

[0043] Each weight value in the dynamic weight combination is compared with a preset weight threshold range. The weight threshold range is set to 0.10-0.35 to ensure a relatively balanced weight distribution among environmental variables and to avoid bias caused by excessively high weights for a single variable. If the weight value of an environmental variable exceeds the upper limit of 0.35 or falls below the lower limit of 0.10, the weight combination is determined to need adjustment and optimization.

[0044] A weighted average method is used to process the dynamic weight combination, summing the adjustment instructions from similar cases according to their similarity and environmental variable weights. Specifically, the adjustment instruction value for each case is multiplied by its similarity weight and the dynamic weight of the corresponding environmental variable, and then the weighted values ​​of all cases are summed to obtain the merged adjustment instruction value. The similarity weight is obtained by normalizing the similarity values ​​of each case, that is, dividing the similarity value of each case by the sum of the similarity values ​​of all similar cases, so that the sum of the similarity weights of all cases equals 1. Similar weighted fusion calculations are performed on adjustment instructions such as temperature regulation, energy consumption limits, and task allocation to form a preliminary adjustment plan.

[0045] The initial adjustment plan is validated through a rules engine to ensure it conforms to current production constraints and equipment capacity limitations. This consistency comparison includes three levels of verification: First, checking whether each instruction in the adjustment plan is within the physical execution capacity of the equipment; for example, the load adjustment range does not exceed the rated load change rate of the equipment, and the temperature adjustment range is within the adjustment capacity of the workshop temperature control system. Second, checking whether the adjustment plan conflicts with the overall production line scheduling plan; for example, whether the production cycle after load reduction can meet delivery schedule requirements, and whether task redistribution affects the coordinated operation of other equipment. Third, checking the logical consistency between each instruction in the adjustment plan; for example, whether reducing the load requires a corresponding reduction in energy consumption limits, and whether temperature adjustment matches the equipment's heat dissipation capacity.

[0046] Non-compliance identified during consistency comparison is corrected and adjusted. If an instruction exceeds the equipment's capabilities, it is corrected to the equipment's maximum or minimum allowable value. If it conflicts with the scheduling plan, the instruction is fine-tuned while satisfying scheduling constraints. If there are logical contradictions between instructions, secondary instructions are adjusted according to priority rules to ensure the execution of primary instructions. The corrected adjustment scheme undergoes another consistency verification. Once confirmed to be conflict-free, it is determined as the final optimized control instruction.

[0047] In step S15, key variables are extracted from the optimized control instructions. If there are conflicts among the key variables, a genetic algorithm is iteratively applied to resolve the conflicts and determine conflict-free control instructions, including: Key variables are obtained from the optimized control instructions, the conflict between the key variables is analyzed, and conflicting variable pairs are identified. The conflicting variable pairs are iteratively optimized using a genetic algorithm to obtain the adjusted variable combinations and determine the temporary instruction set. An executability check is performed on the temporary instruction set. If the check fails, the failed instructions are adjusted to obtain conflict-free control instructions. If the check passes, the temporary instruction set is directly determined as conflict-free control instructions.

[0048] Specifically, key variables are extracted from the optimized control instructions obtained in step S14. These key variables include core parameters such as equipment load rate, temperature setpoint, energy consumption limit, production cycle time, runtime, and task priority. These key variables are then categorized into two types based on their role in the control instructions: constraint variables (such as upper limit of load rate and temperature range) and regulation variables (such as production cycle time and runtime).

[0049] Analyze the conflicts between key variables. For any two variables, check whether their current values ​​meet the preset constraints. These constraints are determined by the physical characteristics and process requirements of the equipment. For example, the constraint relationship between load rate and runtime is: when the load rate exceeds 75%, the continuous runtime must not exceed 8 hours; the constraint relationship between temperature and energy consumption is: when the workshop temperature is higher than 26℃, the cooling energy consumption needs to be increased by an additional 0.1kW. Check the current values ​​of key variables pair by pair. If the value combination of a certain variable pair violates the constraints, then the variable pair is identified as a conflicting variable pair, and all identified conflicting variable pairs are recorded as a conflict set.

[0050] A genetic algorithm is applied iteratively to optimize the pairs of variables in the conflict set. The optimization objective of the genetic algorithm is to minimize the adjustment range of the variables while maintaining closeness to the original optimization control command, all while satisfying all constraints. The values ​​of the conflicting variable pairs are used as optimization variables, and chromosome encoding is constructed, with each chromosome containing all possible combinations of conflicting variable values.

[0051] The specific process is as follows: Initialize the population, setting the population size to 40-60 individuals. Use the variable values ​​from the original optimal control command as one of the initial individuals, and generate the remaining individuals through random perturbation within the constraints. Define a fitness function to evaluate the quality of each individual. The fitness is obtained by weighted summation of three indicators: constraint satisfaction index, obtained by dividing the number of constraints satisfied by the individual's variable combination by the total number of constraints; variable deviation index, which is obtained by first calculating the relative deviation of each variable from the original optimal control command value, summing the relative deviations of all variables, taking the average, and then subtracting the average from 1; and objective function value index, which is obtained by performing min-max normalization on three indicators: production efficiency (pieces / hour), energy consumption level (kW), and equipment utilization rate (%), and then weighting and summing them with weights of 0.4, 0.3, and 0.3 respectively. Finally, the fitness of the current variable is obtained by weighted summation of these three indicators.

[0052] Subsequently, a selection process is performed on the population using a roulette wheel selection method. The probability of selection is determined by an individual's fitness score, with individuals possessing higher fitness scores having a greater probability of being selected. Individuals with higher fitness are selected as parents, and crossover is performed to generate offspring. The crossover operation uses a single-point crossover method, randomly selecting a crossover point on the chromosome and exchanging gene segments at that point between the two parent individuals, generating two new offspring individuals. The offspring individuals then undergo a mutation operation, with a 5-10% probability of mutation applied to a randomly selected gene locus. The mutation method involves randomly selecting a new value within the allowable range of that variable.

[0053] Through repeated selection, crossover, and mutation operations, the individuals in the population gradually converge after 30-50 generations of iteration. The algorithm is considered convergent when the fitness score of the best individual changes by less than 0.01 over five consecutive generations. A maximum iteration count of 100 is set to prevent indefinite iteration. The individual with the highest fitness score in the final population is selected, and its variable value combination becomes the adjusted variable combination. This adjusted variable combination is then updated into the optimization control instructions, forming a temporary instruction set.

[0054] The executability of the temporary instruction set is verified to ensure its feasibility in a real production environment. This executability verification includes three levels of validation. First, physical feasibility verification checks whether the values ​​of each variable are within the physical execution capabilities of the equipment. For example, does the load adjustment rate exceed the equipment's rated change rate, and does the temperature adjustment fall within the temperature control system's adjustment capabilities? Second, logical consistency verification checks for logical contradictions between variables in the instructions. For example, does reducing the load correspondingly reduce energy consumption, and does increasing the production cycle time ensure sufficient equipment runtime? Third, scheduling compatibility verification checks whether the temporary instruction set is compatible with the overall production line scheduling plan. For example, does the adjusted production cycle time meet delivery schedule requirements, and does the equipment maintenance schedule conflict with the production plan?

[0055] The verification results at the three levels are comprehensively evaluated. If all verification items pass, the executability test is deemed passed, and the temporary instruction set is directly identified as conflict-free control instructions. If any verification item fails, the failed item and its reason are recorded, and the relevant instructions are adjusted. The adjustment method is determined based on the type of failure. If the physical feasibility verification fails, variable values ​​exceeding the equipment's capabilities are corrected to the equipment's allowed boundary values; if the logical consistency verification fails, related variables are adjusted according to the logical relationships between variables to ensure logical consistency; if the scheduling compatibility verification fails, variables are fine-tuned while satisfying scheduling constraints. The adjusted instructions are then re-verified for executability until all verification items pass, at which point they are identified as conflict-free control instructions.

[0056] For example, for optimized control commands such as a load rate of 70%, a temperature of 25°C, energy consumption of 0.92kW, a production cycle of 91 units / hour, and a runtime of 10 hours, no direct conflicts were found after extracting key variables and performing conflict analysis. However, the analysis revealed that if the ambient temperature rises to 28°C during actual execution, the cooling energy consumption would need to increase to 0.95kW, conflicting with the energy consumption limit of 0.92kW. Therefore, temperature and energy consumption were identified as a potential conflicting variable pair.

[0057] Optimization was performed using a genetic algorithm, with a population size of 50 individuals and 40 generations. After optimization, the optimal combination of variables for the individuals was: temperature adjusted to 24℃, energy consumption limit adjusted to 0.88kW. A temporary instruction set was generated: load rate 70%, temperature 24℃, energy consumption 0.88kW, production cycle 91 units / hour, and runtime 10 hours.

[0058] The executability of the temporary instruction set was verified. Physical feasibility verification, logical consistency verification, and scheduling compatibility verification all passed. The temporary instruction set was determined to be a conflict-free control instruction set: equipment load rate 70%, workshop temperature adjusted to 24℃, energy consumption limit 0.88kW, production cycle 91 pieces / hour, and continuous operation duration 10 hours.

[0059] In step S16, the feedback signal of the current production line is acquired, and the feedback signal is used to calibrate the deviation of the conflict-free control command to obtain the final control command, including: Obtain real-time feedback data from the current production line, perform integrity verification and supplementation, and obtain a complete feedback signal; The deviation between the feedback signal and the conflict-free control command is calculated, and the conflict-free control command is corrected based on the deviation to obtain the final control command.

[0060] Specifically, feedback data is collected in real time from various equipment and sensor nodes on the production line. This feedback data includes status parameters such as the current load rate of the equipment, actual operating temperature, real-time energy consumption level, current production cycle time, elapsed running time, and task completion progress. The feedback data is transmitted to the monitoring system through the production line communication network, with each data packet carrying a timestamp, equipment identifier, and parameter value information.

[0061] The collected real-time feedback data undergoes integrity verification to check the integrity and validity of the data packets. This integrity verification includes three aspects: First, data packet integrity check, verifying that the start identifier, data fields, and checksum of the data packets are complete and without missing information; second, timestamp continuity check, verifying that the timestamp interval between adjacent data packets is within the normal range (usually set to 1-3 times the sampling period); if it exceeds the range, data loss is determined; third, numerical reasonableness check, verifying that the parameter values ​​are within the physical possible range of the equipment, for example, the load rate should be within the range of 0-100%, and the temperature should be within the operating temperature range of the equipment.

[0062] Issues discovered during integrity verification are supplemented. If data packets are missing or corrupted, linear interpolation is used to fill in the missing data. This linear interpolation calculates an estimated value for the missing point using the values ​​of two valid data points before and after the missing point, along with the timestamp, according to a time ratio. If multiple consecutive data packets are missing (more than 5 sampling periods), the average value from the same historical period is used for supplementation. If the value exceeds a reasonable range, it is determined to be a sensor malfunction or communication interference, and the most recent valid value is used to replace or mark it as invalid data. After supplementation, a complete feedback signal dataset is formed.

[0063] Calculate the deviation between the complete feedback signal and the conflict-free control command obtained in step S15. The deviation calculation is performed separately for each corresponding parameter. The deviation value is the actual value of the feedback signal minus the set value of the conflict-free control command. The deviation values ​​are calculated for all key parameters and concatenated into a vector to form a deviation vector.

[0064] Statistical analysis is performed on the deviation vector, and the deviation of each parameter is determined to be within an acceptable range based on preset deviation tolerance thresholds. These tolerance thresholds are set according to the control accuracy requirements of the parameters; for example, the load rate deviation tolerance threshold is set to ±5%, the temperature deviation tolerance threshold to ±2℃, and the energy consumption deviation tolerance threshold to ±0.1kW. If the absolute value of the deviation of a parameter exceeds the tolerance threshold, it is determined that the parameter needs to be corrected.

[0065] The conflict-free control command is corrected based on the deviation. For example, a PID control algorithm is used, correcting the deviation through three stages: proportional (P), integral (I), and derivative (D). Different PID parameter combinations are set for different types of parameters: for parameters with fast response requirements, such as load rate, Kp=0.8, Ki=0.3, Kd=0.1; for parameters with slow response, such as temperature, Kp=0.5, Ki=0.2, Kd=0.05; for parameters with high stability requirements, such as energy consumption, Kp=0.6, Ki=0.15, Kd=0.08. The current deviation used in the calculation is the difference between the feedback signal and the control command. The cumulative deviation is calculated by summing the deviation values ​​of the most recent 10 sampling periods. The deviation change rate is the difference between the current deviation and the deviation of the previous sampling period divided by the sampling time interval. After the correction value is calculated by the PID algorithm, the original control command value is added to the correction value to obtain the corrected control command. It should be noted that, in actual implementation, the PID parameters are tuned using the Ziegler-Nichols method or based on the dynamic response characteristics of the device; the example values ​​are for reference only.

[0066] The corrected parameter values ​​are updated in the control command to form the final control command. The final control command includes a complete set of parameters such as the corrected equipment load rate, temperature setpoint, energy consumption limit, production cycle time, and runtime, as well as the correction range and reason for each parameter, which facilitates subsequent execution tracking and effect evaluation.

[0067] In step S17, execution signals are distributed to production line equipment based on the final control command, and the updated operating parameters after the signal execution are collected and compared with preset operating parameter thresholds to determine the parameter deviation range.

[0068] Specifically, based on the final control instructions, various control parameters are converted into a signal format executable by the equipment. Pre-transmission verification of signal data packets is performed using Cyclic Redundancy Check (CRC) to ensure error-free signals. Execution signals are distributed to target equipment via the production line communication network, following the equipment's priority order. The signal reception timestamps and response confirmation information for each device are recorded.

[0069] After the signal is executed, the updated operating parameters of the equipment are collected in real time at a frequency of 1-5 seconds per acquisition, continuously for a complete execution cycle (usually 5-10 minutes), forming time-series data of the updated operating parameters. The updated operating parameters are then compared with preset operating parameter thresholds. These thresholds are set based on the target value and allowable deviation range of the final control command. The allowable deviation range is determined through statistical analysis of historical stable operating data, typically using ±1.5 times the standard deviation of the target value as the upper and lower bounds of the threshold. For example, if the target load rate is 70.9% and the historical data standard deviation is 3%, then the operating parameter threshold range is 70.9% ± 4.5%, or 66.4%-75.4%. The operating parameters at each collected moment are compared point-by-point to determine if they are within the threshold range. The number of data points exceeding the threshold range and their duration are counted, and the parameter deviation interval is determined based on the direction and magnitude of the deviation.

[0070] It should be noted that the priority order of signal distribution should be determined based on the criticality of the equipment in the production line and the dependencies between equipment. Upstream equipment takes precedence over downstream equipment, and core process equipment takes precedence over auxiliary equipment. The setting of operating parameter thresholds should comprehensively consider the control accuracy requirements and the dynamic response characteristics of the equipment. For parameters with slower responses (such as temperature), the threshold range can be appropriately relaxed, while for parameters with faster responses (such as load rate), stricter thresholds should be set. The criterion for determining the duration of deviation should avoid misjudging instantaneous fluctuations as systematic deviations. Generally, a continuous deviation exceeding the threshold for more than 3-5 sampling periods is considered a valid deviation.

[0071] For example, for the final control command (load rate 70.9%, temperature 25℃, energy consumption 0.91kW), the parameters are converted into execution signals and distributed to the target device. The device responds with confirmation within 2.1 seconds. After the execution signal, updated operating parameters are continuously collected for 10 minutes, with an average load rate of 72.5%, an average temperature of 25.3℃, and an average energy consumption of 0.92kW. Comparing the operating parameter thresholds, all parameters are found to be within the threshold range. According to the deviation severity judgment rules, a deviation exceeding 1.5 times the allowable range (4.5%) is judged as high severity, 0.5-1.5 times as medium severity, and less than 0.5 times as low severity. The actual average load rate of 72.5% is 1.6% higher than the target value of 70.9%, which is judged as a low severity deviation. The parameter deviation range is determined as follows: a 1.6% increase in load rate lasting for 10 minutes indicates low severity.

[0072] In step S18, the updated operating parameters are corrected according to the parameter deviation range to obtain the final operating parameter control scheme.

[0073] Specifically, the correction strategy is determined based on the severity of the deviation within the parameter deviation range: for high-severity deviations, an active correction strategy is adopted; for medium-severity deviations, a gradual correction strategy is adopted; and for low-severity deviations, an observational correction strategy is adopted. For high-severity deviations, the control parameters are immediately adjusted significantly (80%-100% of the deviation value), and a manual review process is triggered to ensure equipment safety. For medium-severity deviations, the control parameters are gradually corrected over 3-5 adjustment cycles (20%-30% of the deviation value each time), and the correction effect is continuously monitored. For low-severity deviations, only the deviation information is recorded, and a small-scale fine-tuning is performed in the next control cycle (10%-20% of the deviation value) to avoid frequent adjustments affecting system stability. The corrected control parameters are then validated against constraints to ensure that the corrected parameter combination meets the physical and process constraints of the equipment. The corrected control parameters are then integrated into the final operating parameter control scheme.

[0074] A closed-loop feedback mechanism is established to feed back the final operating parameter control scheme to the parameter acquisition stage in step S11, forming a continuously optimized control loop. In the next control cycle, the revised control scheme is used as the new control benchmark, and the complete process from steps S11 to S18 is repeated to achieve dynamic optimization and continuous improvement of the equipment's operating status.

[0075] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

[0076] Reference Figure 2 The second embodiment of the present invention provides an automated control system for circuit board processing, comprising: The data acquisition module is used to collect the initial operating parameters of the equipment, perform time series analysis on the initial operating parameters, and obtain a set of operating parameters. The coordination requirement determination module is used to simulate and iteratively calculate the mutual influence relationship between the parameters based on the set of operating parameters using a genetic algorithm, determine the weight distribution result of the parameter influence, and generate the coordination requirement vector of the equipment based on the weight distribution result. The constraint group generation module is used to perform hierarchical processing on the data portion of the coordination demand vector that exceeds the preset coordination threshold to obtain a hierarchical dataset, perform feature separation on the hierarchical dataset, perform region segmentation on the separated features and determine the boundary constraint range after segmentation, and determine the production restriction constraint group based on the boundary constraint range. The instruction optimization module is used to obtain similar cases from a preset historical control instruction database for the production constraint group, generate a preliminary adjustment scheme by weighted fusion based on the similar cases, and perform consistency comparison and verification on the preliminary adjustment scheme to obtain optimized control instructions. The conflict resolution module is used to extract key variables from the optimized control instructions. If there is a conflict between the key variables, a genetic algorithm is iteratively applied to resolve the conflict and determine the conflict-free control instructions. The instruction calibration module is used to acquire the feedback signal of the current production line, and use the feedback signal to calibrate the deviation of the conflict-free control instruction to obtain the final control instruction. The execution monitoring module is used to distribute execution signals to production line equipment based on the final control command, collect updated operating parameters after signal execution and compare them with preset operating parameter thresholds to determine the parameter deviation range; The final correction module is used to correct the updated operating parameters according to the parameter deviation range to obtain the final operating parameter control scheme.

[0077] It should be noted that the circuit board processing automation control system provided in this embodiment of the invention is used to execute all the process steps of the circuit board processing automation control method in the above embodiment. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0078] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a circuit board manufacturing automation control program. When the processor executes the computer program, it implements the steps described in the various circuit board manufacturing automation control method embodiments above, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above system embodiments, such as the data acquisition module.

[0079] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0080] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0081] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0082] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0083] If the modules / units integrated into the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0084] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0085] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. An automated control method for circuit board processing, characterized in that, include: The initial operating parameters of the acquisition device are collected, and time series analysis is performed on the initial operating parameters to obtain a set of operating parameters. Based on the set of operating parameters, a genetic algorithm is used to simulate and iteratively calculate the mutual influence relationship between the parameters, determine the weight distribution result of the parameter influence, and generate the equipment coordination demand vector according to the weight distribution result. The data portion of the coordination demand vector that exceeds the preset coordination threshold is processed in layers to obtain a layered dataset. Feature separation is performed on the layered dataset, and the separated features are segmented into regions to determine the boundary constraint range after segmentation. Production restriction constraint groups are determined based on the boundary constraint range. For the production constraint group, similar cases are obtained from a preset historical control instruction database. Based on the similar cases, a weighted fusion is used to generate a preliminary adjustment scheme. The preliminary adjustment scheme is then compared and verified for consistency to obtain an optimized control instruction. Key variables are extracted from the optimized control instructions. If there is a conflict between the key variables, a genetic algorithm is iteratively applied to resolve the conflict and determine the conflict-free control instructions. Obtain the feedback signal from the current production line, and use the feedback signal to calibrate the deviation of the conflict-free control command to obtain the final control command; Based on the final control command, execution signals are distributed to the production line equipment, and the updated operating parameters after the signal execution are collected and compared with the preset operating parameter thresholds to determine the parameter deviation range. The updated operating parameters are corrected based on the parameter deviation range to obtain the final operating parameter control scheme.

2. The automated control method for circuit board processing according to claim 1, characterized in that, The initial operating parameters of the acquisition device are subjected to time series analysis to obtain a set of operating parameters, including: The initial operating parameters of the equipment are collected through a sensor network; The initial operating parameters are denoised and segmented to obtain a preliminarily organized parameter dataset; The parameter dataset is decomposed into time series components to extract trend and periodic components. Feature values ​​are calculated for the trend and periodic components to determine key parameters of the equipment's operating status. The key parameters are then integrated to obtain a set of operating parameters.

3. The automated control method for circuit board processing according to claim 1, characterized in that, Based on the set of operating parameters, a genetic algorithm is used to simulate and iteratively calculate the mutual influence relationships between the parameters to determine the weight distribution of the parameter influences. Based on the weight distribution results, a coordination demand vector for the equipment is generated, including: The set of operating parameters is standardized to obtain a set of standard parameters; For the set of standard parameters, calculate the correlation strength between each parameter, construct a mutual influence matrix between parameters based on the correlation strength, and calculate and determine the preliminary weight set of the parameter influence based on the mutual influence matrix; If the weight value of at least one parameter in the preliminary weight set exceeds the preset weight optimization threshold, a genetic algorithm is used to iteratively simulate and optimize the preliminary weight set to obtain the optimized weight distribution result. Based on the weight distribution results, the current deviation of each parameter is multiplied by the corresponding optimization weight to generate the coordination requirement vector of the equipment.

4. The automated control method for circuit board processing according to claim 1, characterized in that, The step of performing feature separation on the hierarchical dataset, segmenting the separated features into regions and determining the boundary constraint range after segmentation, and determining the production restriction constraint group based on the boundary constraint range includes: For the hierarchical dataset, feature separation is performed on dynamic environmental variables to determine the set of separated variable features; If at least one feature value in the variable feature set exceeds the preset feature threshold range, then the variable feature set is segmented into regions to obtain the segmented boundary constraint range. Based on the boundary constraint range, constraint integration is used to combine and map the production constraints to obtain a production constraint set.

5. The automated control method for circuit board processing according to claim 1, characterized in that, For the production constraint group, similar cases are obtained from a preset historical control instruction database. Based on these similar cases, a weighted fusion is used to generate a preliminary adjustment scheme. The preliminary adjustment scheme is then subjected to consistency comparison and verification to obtain optimized control instructions, including: From a preset historical control instruction database, obtain case data related to the production constraint group, calculate the similarity between the case data and the production constraint group, and filter similar cases based on the similarity. For the aforementioned similar cases, dynamic weights are calculated for the environmental variables of the case data to obtain dynamic weight combinations; If at least one value in the dynamic weight combination exceeds the preset weight threshold range, then the similar cases are weighted and fused based on the dynamic weight combination to obtain a preliminary adjustment scheme. The initial adjustment scheme is compared and verified for consistency to obtain optimized control instructions.

6. The automated control method for circuit board processing according to claim 1, characterized in that, The process of extracting key variables from the optimized control instructions, and if conflicts exist among the key variables, iteratively applying a genetic algorithm to resolve the conflicts and determine conflict-free control instructions, includes: Key variables are obtained from the optimized control instructions, the conflict between the key variables is analyzed, and conflicting variable pairs are identified. The conflicting variable pairs are iteratively optimized using a genetic algorithm to obtain the adjusted variable combinations and determine the temporary instruction set. An executability check is performed on the temporary instruction set. If the check fails, the failed instructions are adjusted to obtain conflict-free control instructions. If the check passes, the temporary instruction set is directly determined as conflict-free control instructions.

7. The automated control method for circuit board processing according to claim 1, characterized in that, The process of acquiring the feedback signal from the current production line and using the feedback signal to calibrate the deviation of the conflict-free control command to obtain the final control command includes: Obtain real-time feedback data from the current production line, perform integrity verification and supplementation, and obtain a complete feedback signal; The deviation between the feedback signal and the conflict-free control command is calculated, and the conflict-free control command is corrected based on the deviation to obtain the final control command.

8. An automatic control system for circuit board processing, characterized in that, include: The data acquisition module is used to collect the initial operating parameters of the equipment, perform time series analysis on the initial operating parameters, and obtain a set of operating parameters. The coordination requirement determination module is used to simulate and iteratively calculate the mutual influence relationship between the parameters based on the set of operating parameters using a genetic algorithm, determine the weight distribution result of the parameter influence, and generate the coordination requirement vector of the equipment based on the weight distribution result. The constraint group generation module is used to perform hierarchical processing on the data portion of the coordination demand vector that exceeds the preset coordination threshold to obtain a hierarchical dataset, perform feature separation on the hierarchical dataset, perform region segmentation on the separated features and determine the boundary constraint range after segmentation, and determine the production restriction constraint group based on the boundary constraint range. The instruction optimization module is used to obtain similar cases from a preset historical control instruction database for the production constraint group, generate a preliminary adjustment scheme by weighted fusion based on the similar cases, and perform consistency comparison and verification on the preliminary adjustment scheme to obtain optimized control instructions. The conflict resolution module is used to extract key variables from the optimized control instructions. If there is a conflict between the key variables, a genetic algorithm is iteratively applied to resolve the conflict and determine the conflict-free control instructions. The instruction calibration module is used to acquire the feedback signal of the current production line, and use the feedback signal to calibrate the deviation of the conflict-free control instruction to obtain the final control instruction. The execution monitoring module is used to distribute execution signals to production line equipment based on the final control command, collect updated operating parameters after signal execution and compare them with preset operating parameter thresholds to determine the parameter deviation range; The final correction module is used to correct the updated operating parameters according to the parameter deviation range to obtain the final operating parameter control scheme.

Images