A CNC machine tool casting quality analysis and tracking system

Abstract

This invention discloses a CNC machine tool casting quality analysis and tracking system, belonging to the field of intelligent manufacturing and quality control technology. It includes a multi-physics field fusion monitoring module for real-time acquisition of multi-dimensional physical signals from the machine tool and the construction of a real-time state feature vector based on these signals; a real-time defect evolution inversion module for combining the real-time state feature vector with a preset initial defect factor in the casting and calculating a real-time defect activation index through a machining-induced defect activation index model; and a cutting parameter dynamic optimization module for determining the optimal cutting parameter set based on the machining-induced defect activation index model and preset process constraints by solving a normalized machining utility function. This invention significantly improves the first-pass yield of high-value precision castings, especially in the manufacturing of core components in the aerospace field, and substantially reduces rework and scrap costs.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing and quality control technology, specifically to a CNC machine tool casting quality analysis and tracking system. Background Technology

[0002] In high-end manufacturing fields such as aerospace, precision castings of core components such as turbine blades often contain latent metallurgical defects such as microscopic porosity and inclusions in the blank stage. During high-speed CNC precision machining, the intense cutting heat and the thermal field formed by the cutting force will have a complex coupling effect with these latent defects. The technical problem faced in this field is that this coupling effect will activate and induce the expansion of originally stable defects, resulting in secondary damage. Therefore, simply pursuing high-efficiency machining strategies often leads to a decrease in yield, while conservative machining seriously affects the production cycle and cost. Existing technologies, whether using conservative machining parameters or relying on non-destructive testing after machining, cannot intervene in the process in real time, thus placing machining efficiency and defect control in a dilemma of mutual opposition and incompatibility. There is an urgent need in this field for an intelligent control method that can perceive and avoid machining-induced damage in real time to achieve a balance between efficiency and quality.

[0003] The information disclosed in the background section above is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a CNC machine tool casting quality analysis and tracking system to solve the problems mentioned in the background art.

[0005] The technical solution of the present invention includes: a multi-physics field fusion monitoring module, used to acquire multi-physics signals of the machine tool in real time, and to construct a real-time state feature vector based on the multi-physics signals;

[0006] The real-time defect evolution inversion module is used to combine the real-time state feature vector with the preset initial defect factor of the casting, and calculate the real-time defect activation index through the processing-induced defect activation index model.

[0007] The dynamic optimization module for cutting parameters is used to determine the optimal set of cutting parameters by solving the normalized machining utility function based on the machining-induced defect activation index model and preset process constraints.

[0008] The damage suppression mode switching module is used to compare the real-time defect activation index with preset safety thresholds and critical thresholds, and based on the comparison results, combined with the optimal cutting parameter set, to determine the final machining instructions to be sent to the CNC system.

[0009] Preferably, the multi-element physical signals include: high-frequency acoustic emission sensor signals, three-part force measuring instrument signals, high-precision accelerometer signals, and non-contact infrared thermometer signals.

[0010] Preferably, the steps for constructing the real-time state feature vector are as follows:

[0011] S11. Extract the root mean square value of the acoustic emission signal from the high-frequency acoustic emission sensor signal;

[0012] S12. Extract the resultant cutting force from the signal of the three-part force measuring instrument;

[0013] S13. Extract the kurtosis of the vibration signal from the high-precision accelerometer signal;

[0014] S14. Extract the cutting temperature from the signal of the non-contact infrared thermometer;

[0015] S15. Combine the root mean square value of the acoustic emission signal, the resultant cutting force, the kurtosis of the vibration signal, and the cutting temperature to construct a real-time state feature vector.

[0016] Preferably, the calculation steps for the processing-induced defect activation index are as follows:

[0017] S21. Determine the thermodynamic effect terms based on the cutting temperature;

[0018] S22. Determine the quasi-static mechanical effect term based on the root mean square value of the acoustic emission signal;

[0019] S23. Based on the kurtosis of the vibration signal and the resultant cutting force, determine the dynamic impact effect term;

[0020] S24. Weighted summation of thermodynamic effect term and quasi-static mechanical effect term to obtain combined effect term;

[0021] S25. Based on the combined effect term, dynamic impact effect term, and initial defect factor of casting, a real-time defect activation index is generated.

[0022] Preferably, the steps for determining the optimal set of cutting parameters are as follows:

[0023] S31. Calculate the material removal rate based on the cutting parameters to be optimized;

[0024] S32. Predict the state feature vector corresponding to the cutting parameters to be optimized by using a preset cutting process proxy model;

[0025] S33. Substitute the predicted state feature vector into the processing-induced defect activation index model to obtain the predicted defect activation index.

[0026] S34. Combining the material removal rate and the predicted defect activation index, solve for the maximum value of the normalized machining utility function to determine the optimal set of cutting parameters.

[0027] Preferably, the cutting process proxy model is obtained by establishing the mapping relationship from cutting parameters to state feature vectors through offline calibration experiments.

[0028] Preferably, the steps for determining the processing instructions are as follows:

[0029] If the real-time defect activation index is less than or equal to the safety threshold, the system enters the high-efficiency mode and uses the optimal set of cutting parameters calculated by the cutting parameter dynamic optimization module with the main goal of maximizing processing efficiency as the processing command.

[0030] If the real-time defect activation index is greater than the safety threshold but less than the critical threshold, the system enters the adaptive mode and uses the optimal set of cutting parameters calculated by the cutting parameter dynamic optimization module, which aims to balance machining efficiency and risk suppression, as the machining command.

[0031] If the real-time defect activation index is greater than or equal to the critical threshold, the preset emergency plan will be used as the processing instruction.

[0032] Preferably, the source of the safety threshold is: the value of the real-time defect activation index, calibrated through trial cutting experiments, which ensures that the microcrack density is lower than the allowable standard of the material under a preset confidence level.

[0033] Preferably, the source of the critical threshold is: the statistical lower limit of the instantaneous peak value of the real-time defect activation index of all failed samples just before failure, calibrated through destructive test cutting experiments.

[0034] This invention provides an improved CNC machine tool casting quality analysis and tracking system, which has the following improvements and advantages compared with the prior art:

[0035] Firstly, this invention achieves synergistic optimization of processing efficiency and workpiece quality, transforming their traditional antagonistic relationship into a synergistic improvement goal. A multi-physics field fusion monitoring module acquires real-time state feature vectors characterizing the processing process, which are then transformed into a quantitative assessment of internal damage risk by a real-time defect evolution inversion module. This establishes a reliable quantitative index associated with external measurable physical signals for the evolution of microscopic defects within the material, which cannot be directly observed. The system can proactively determine an optimal set of cutting parameters, which is essentially the highest efficiency solution achievable without triggering damage risk. This mechanism enables the system to dynamically and adaptively operate on the optimal boundary formed by efficiency and quality throughout the entire processing process.

[0036] Secondly, this invention transforms the quality control model from a passive response to post-process inspection to an active avoidance of defects during the process. Existing technologies for controlling machining-induced defects mainly rely on post-processing inspection; once a defect is discovered, the workpiece may already be scrapped, resulting in significant economic losses. This invention changes this situation through its damage suppression mode switching module design. It provides clear and physically meaningful boundary conditions for the system's autonomous decision-making. When the index is below the safety threshold, the system can boldly pursue efficiency. When the index falls between the safety and critical thresholds, the optimal cutting parameter set executed by the system is a prudent choice after balancing risks. When the index approaches or exceeds the critical threshold, the system will adopt the highest priority emergency plan to actively suppress the occurrence of damage. This layered, closed-loop real-time intervention capability avoids the generation of machining-induced defects, and its direct effect is to improve the first-pass yield of high-value precision castings, especially in the manufacturing of core components in the aerospace field, significantly reducing rework and scrap costs.

[0037] Thirdly, the overall technical solution proposed in this invention has high feasibility and engineering robustness. Each key custom parameter and model in this invention has a clear physical meaning and a definite calibration method. The weight coefficients of each item in the processing-induced defect activation index model, as well as the safety threshold and critical threshold on which the damage suppression mode switching module depends, are all given in the specification with specific determination steps based on physical experiments and data statistics. Similarly, the cutting process proxy model used by the cutting parameter dynamic optimization module also clarifies its technical path of establishing a mapping relationship through offline calibration experiments. This comprehensive explanation of the implementation details ensures that those skilled in the art can reproduce and deploy the system without creative labor, guaranteeing the feasibility of the technical solution. The four modules are tightly coupled through the two core data flows of real-time state feature vector and real-time defect activation index, forming a logically rigorous and clearly defined closed-loop system, ensuring the stability and effectiveness of the overall operation. Attached Figure Description

[0038] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0039] Figure 1 This is a flowchart of a CNC machine tool casting quality analysis and tracking system according to the present invention;

[0040] Figure 2 This is a diagram illustrating the construction steps of the real-time state feature vector of this invention;

[0041] Figure 3 This is a diagram illustrating the calculation steps for the processing-induced defect activation index of this invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0043] Example 1:

[0044] Please see Figure 1 The present invention provides a technical solution for a CNC machine tool casting quality analysis and tracking system, comprising: a multi-physics field fusion monitoring module, used to acquire multi-dimensional physical signals of the machine tool in real time, and to construct a real-time state feature vector based on the multi-dimensional physical signals;

[0045] The real-time defect evolution inversion module is used to combine the real-time state feature vector with the preset initial defect factor of the casting, and calculate the real-time defect activation index through the processing-induced defect activation index model.

[0046] The dynamic optimization module for cutting parameters is used to determine the optimal set of cutting parameters by solving the normalized machining utility function based on the machining-induced defect activation index model and preset process constraints.

[0047] The damage suppression mode switching module is used to compare the real-time defect activation index with preset safety thresholds and critical thresholds, and based on the comparison results, combined with the optimal cutting parameter set, to determine the final machining instructions to be sent to the CNC system.

[0048] This embodiment provides a CNC machine tool casting quality analysis and tracking system. This system solves the technical dilemma of mutually restricting processing efficiency and finished product quality during the finishing process of high-end castings, caused by the inability to predict and avoid the deterioration of internal defects in real time. The system's architecture, through the coordinated operation of its four main modules, forms a complete closed-loop control logic of perception-cognition-decision-execution. The multi-physics field fusion monitoring module acts as the system's perception unit, capturing the processing status in real time; the real-time defect evolution inversion module acts as the cognitive core, interpreting the status and assessing risks; the dynamic optimization module for cutting parameters acts as the decision-making brain, planning the optimal strategy; and finally, the damage suppression mode switching module acts as the execution supervisor, ensuring the safe issuance of instructions. This design allows the system to no longer passively adapt but proactively control, thereby transforming the traditionally opposing relationship between processing efficiency and quality control into a unified goal that can be synergistically optimized.

[0049] Example 2

[0050] The multi-element physical signals include: high-frequency acoustic emission sensor signals, three-part force measuring instrument signals, high-precision accelerometer signals, and non-contact infrared thermometer signals;

[0051] refer to Figure 2 As shown, the specific steps for constructing the real-time state feature vector are as follows:

[0052] S11. Extract the root mean square value of the acoustic emission signal from the high-frequency acoustic emission sensor signal;

[0053] S12. Extract the resultant cutting force from the signal of the three-part force measuring instrument;

[0054] S13. Extract the kurtosis of the vibration signal from the high-precision accelerometer signal;

[0055] S14. Extract the cutting temperature from the signal of the non-contact infrared thermometer;

[0056] S15. Combine the root mean square value of the acoustic emission signal, the resultant cutting force, the kurtosis of the vibration signal, and the cutting temperature to construct a real-time state feature vector.

[0057] In this implementation, the functionality of its multiphysics fusion monitoring module is refined. This module captures a carefully selected set of multi-physics signals through a sensor array deployed at key locations on the machine tool. These signals cover multiple dimensions, including heat, force, vibration, and microscopic activity within the material, ensuring comprehensive information input. After acquiring the raw signals, the module constructs a real-time state feature vector through a series of defined steps. It extracts the root mean square value characterizing the energy release of microcracks from the high-frequency acoustic emission sensor signal. The resultant cutting force, reflecting the total level of the cutting load, is calculated from the signal of the three-part force measuring instrument. Extracting vibration signal kurtosis, which is extremely sensitive to impact events, from high-precision accelerometer signals. The cutting temperature of the tool tip-workpiece contact area is obtained from the signal of the non-contact infrared thermometer. These refined key features are combined into a time-varying... Standardized real-time state feature vector of change ;

[0058] The standardization of the real-time state feature vector can be achieved using the min-max standardization method, which transforms each original feature value... Linearly mapped to the interval [0, 1]; the calculation formula is: ,in and These are the minimum and maximum values ​​of the feature observed in offline calibration or historical data, respectively; this standardization process can eliminate the differences in units and numerical ranges of different physical signals, which is beneficial to the computational stability of subsequent models.

[0059] The construction of this vector provides a quantitative, multi-dimensional data foundation for the subsequent analysis of the entire system, which can comprehensively depict the physical profile of the cutting process at the current moment. Its direct benefit is to ensure the accuracy and reliability of the subsequent defect evolution inversion.

[0060] Example 3

[0061] refer to Figure 3 As shown, the specific steps for calculating the processing-induced defect activation index are as follows:

[0062] S21. Determine the thermodynamic effect terms based on the cutting temperature;

[0063] S22. Determine the quasi-static mechanical effect term based on the root mean square value of the acoustic emission signal;

[0064] S23. Based on the kurtosis of the vibration signal and the resultant cutting force, determine the dynamic impact effect term;

[0065] S24. Weighted summation of thermodynamic effect term and quasi-static mechanical effect term to obtain combined effect term;

[0066] S25. Based on the combined effect term, dynamic impact effect term, and initial defect factor of casting, a real-time defect activation index is generated.

[0067] In the core of this system, namely the real-time defect evolution inversion module, the above steps are processed to induce a defect activation index. What the model carries;

[0068] Origin and Technological Motivation: The initial concept of this model draws upon the damage superposition principle in materials damage mechanics and the energy release rate theory in fracture mechanics. The core technological motivation lies in deconstructing the complex, multi-physics-field-coupled internal defect activation process during cutting into a linear and nonlinear combination of three key physical dimensions: thermodynamic effects, quasi-static mechanical effects, and dynamic impact effects. Furthermore, it aims to establish a calculable, quantifiable single indicator to characterize this risk. The essence of this approach is to establish a mathematical probe that correlates the evolution of internal damage, which cannot be directly observed, with externally measurable physical signals.

[0069] The core calculations of this module follow the following formula:

[0070] ;

[0071] in, The dimensionless processing-induced defect activation index at time t The instantaneous value; Thermodynamic effect term, calculation formula is: , It is the real-time cutting temperature. It is the creep initiation temperature of the material. It is the temperature at which a material undergoes a critical phase transition or its strength decreases significantly. The latter two are obtained from material handbooks or determined experimentally by differential scanning calorimetry. For the quasi-static mechanical effect term, the calculation formula is: , It is the root mean square value of the acoustic emission signal. It is the critical root mean square value that the acoustic emission signal can reach before the material undergoes macroscopic fracture. It is derived from the experimental calibration by stretching a standard specimen until it fractures. The dynamic impact effect term is calculated as follows: , It is the kurtosis of the vibration signal. The reference kurtosis under stable cutting conditions has a theoretical value of 3. It is the resultant cutting force. The latter two are the reference cutting forces for smooth cutting, and are derived from the statistical average of a large amount of normal machining data; The physical weighting coefficients for thermodynamic effects, quasi-static mechanical effects, and dynamic impact effects are derived from metallographic analysis of a series of test pieces, with the goal of maximizing the goodness of fit, and satisfy the following conditions: ; The initial defect factor of the casting, which characterizes the inherent quality of the workpiece, is derived from the non-destructive testing results of the blank upon its arrival at the factory.

[0072] This inverse calculation process can be constructed as an optimization problem; through metallographic analysis and other methods, an actual damage measure is quantified for each test piece i. For example, the microcrack density per unit area; by substituting the feature vectors from the machining process of the test piece into the model, the corresponding machining-induced defect activation index can be calculated. The goal of optimization is to find a set of weights. The objective function J is to minimize the sum of squared errors between the predicted values ​​and the actual damage measures for all samples; this objective function can be expressed as: ,in The total number of trial cut pieces, For a general Physical damage measurement The associated calibration function can be a linear proportional relationship in the simplest case; this optimization problem can be solved using nonlinear least squares methods, such as the Levenberg-Marquardt algorithm.

[0073] The initial defect factor of the casting, which characterizes the inherent quality of the workpiece, is derived from the non-destructive testing results of the blank upon its arrival at the factory.

[0074] In application, this module receives real-time status feature vectors from the monitoring module. Substitute its components into the above formula, and combine with the preset... Real-time calculation and output of a defect activation index curve The direct technical effect of this calculation process is to achieve a precise mapping from external physical characteristics to internal damage risk. It transforms the originally vague and qualitative problem of good or bad processing status into a specific and continuously changing risk value, providing a quantitative basis for subsequent optimization decisions and safety control.

[0075] Example 4

[0076] The specific steps for determining the optimal set of cutting parameters are as follows:

[0077] S31. Calculate the material removal rate based on the cutting parameters to be optimized;

[0078] S32. Predict the state feature vector corresponding to the cutting parameters to be optimized by using a preset cutting process proxy model;

[0079] S33. Substitute the predicted state feature vector into the processing-induced defect activation index model to obtain the predicted defect activation index.

[0080] S34. Combining the material removal rate and the predicted defect activation index, solve for the maximum value of the normalized machining utility function to determine the optimal set of cutting parameters;

[0081] The cutting process proxy model is obtained by establishing the mapping relationship from cutting parameters to state feature vectors through offline calibration experiments.

[0082] The dynamic optimization module for cutting parameters in this system, as an intelligent decision-making unit, does not passively respond but actively plan; in order to predict different sets of cutting parameters... To address the impact of defect activation risk, this system first constructed a surrogate model of the cutting process through offline calibration experiments; this surrogate model Essentially, it uses machine learning techniques such as support vector machines or neural networks to establish a feature vector from cutting parameters to predicted state. The mapping relationship ensures the physical basis of the prediction; among which, the cutting parameter set Including spindle speed Feed rate and depth of cut The proxy model This refers to using a cutting process proxy model to analyze the input set of cutting parameters. Mapping yields the predicted state feature vector The predicted state feature vector specifically includes the predicted root mean square value of the acoustic emission signal. Predicted cutting resultant force Predicted vibration signal kurtosis and the predicted cutting temperature ;

[0083] After acquiring predictive capabilities, this module solves for a normalized processing utility function. The problem is to maximize the efficiency of the material removal rate (MRR); the construction of this function originates from the multi-objective optimization theory in operations research; the technical motivation is to combine the processing efficiency characterized by the material removal rate (MRR) with the efficiency characterized by the predicted defect activation index. The two essentially conflicting objectives—the penalty term representing the processing quality—are cleverly integrated into a unified, dimensionless utility function, thereby giving the optimization problem a unique and solvable optimal solution.

[0084] The utility function takes the following form:

[0085] ;

[0086] in, This is a dimensionless comprehensive processing utility value; To be compatible with cutting parameters Directly related material removal rate; The reference material removal rate is derived from process manuals or trial cutting databases and is used as a benchmark for efficiency normalization. It is the predicted defect activation index obtained through the surrogate model and the defect activation index model; Efficiency-quality balance factor ( Its source is the work order requirements issued by the upper-level manufacturing execution system, which is used to adjust the priority weight of efficiency and quality; and These are the preset safety threshold and critical threshold, respectively; it is worth noting that the squared form of the penalty term ensures that when the predicted defect activation index... Once the safety threshold is exceeded, its negative impact on total utility will be amplified dramatically on a quadratic level.

[0087] This module uses intelligent optimization algorithms, such as genetic algorithms or particle swarm optimization, to solve for the maximum value of the function within process constraints, thereby determining the optimal set of cutting parameters. ;

[0088] Taking the particle swarm optimization algorithm as an example, as a non-limiting implementation, its parameters can be set as follows: particle population size of 50, maximum number of iterations of 100, and inertia weight. The cognitive factor decreased linearly from 0.9 to 0.4. social factors All parameters are set to 2.0. The search space is based on the cutting parameters and spindle speed preset in the process knowledge base. feed rate Cutting depth Defined by the upper and lower limits;

[0089] The technical effect of this process is that it achieves forward-looking adaptive optimization; the system can predict the optimal combination of parameters that maximizes the material removal rate and strictly controls the risk of defect activation within a safe range before or during processing; this allows the dynamic operation of the processing process to operate at the highest allowable efficiency boundary, achieving a synergy between efficiency and quality.

[0090] Example 5

[0091] The specific steps for determining the machining instructions are as follows:

[0092] If the real-time defect activation index is less than or equal to the safety threshold, the system enters the high-efficiency mode and uses the optimal set of cutting parameters calculated by the cutting parameter dynamic optimization module with the main goal of maximizing processing efficiency as the processing command.

[0093] If the real-time defect activation index is greater than the safety threshold but less than the critical threshold, the system enters the adaptive mode and uses the optimal set of cutting parameters calculated by the cutting parameter dynamic optimization module, which aims to balance machining efficiency and risk suppression, as the machining command.

[0094] If the real-time defect activation index is greater than or equal to the critical threshold, the preset emergency plan will be used as the processing instruction.

[0095] The safety threshold is derived from the real-time defect activation index value, calibrated through trial cutting experiments, which ensures that the microcrack density is lower than the allowable standard of the material under a preset confidence level.

[0096] The critical threshold is derived from the statistical lower limit of the instantaneous peak value of the real-time defect activation index of all failed samples just before failure, determined through destructive test cutting experiments.

[0097] As the final execution supervision layer of the system, the damage suppression mode switching module ensures the stability and security of the entire system; the effectiveness of this module highly depends on two key thresholds. and These two thresholds are not arbitrary assumptions, but rather obtained through rigorous experimental calibration, ensuring that the model calculations are anchored to physical reality.

[0098] Safety threshold The determination process involves: performing a series of trial cutting experiments covering a wide range of parameters, followed by metallographic analysis of the specimens to establish the processing parameters. The correlation between peak value and subsurface microcrack density will ultimately be able to ensure with 99% confidence that the microcrack density is below the allowable standard for materials. Value, defined as ;

[0099] Critical threshold The determination process is even more stringent: a set of destructive test cuts designed to induce failure are performed, and the results of all samples are recorded just moments before failure events such as macroscopic cracks or chipping occur. For instantaneous peak values, the statistical lower bound of these peak data, such as the 10th percentile, is defined as follows: This value represents the precipice where the damage is about to spiral out of control.

[0100] After obtaining these two anchor points, the module determines the final machining instructions to be issued to the CNC system based on a clear three-stage rule logic; when real-time monitoring... Less than or equal to At that time, the system is in high-efficiency mode, fully adopting the optimization modules. In pursuit of maximum production efficiency; when Between and During this period, the system enters adaptive mode, at which point it adopts... This is already the result of optimizing the module by balancing risk and efficiency, achieving a dynamic balance; and once... breakthrough If this happens, the highest priority damage suppression mode will be triggered. The module will immediately reject any optimization suggestions and enforce an extremely conservative emergency plan, such as suspending the feed and activating high-pressure cooling.

[0101] At the CNC system level, this emergency plan can be broken down into the following series of commands: Immediately send a feed hold signal to the CNC system; while pausing the feed, instruct the tool to rapidly lift along the Z-axis or other safe coordinate axes, for example, G00Z+10.0, to detach it from the workpiece; send an M code to activate or maximize the flow of high-pressure coolant for forced cooling of the cutting area; the system records all status data of the triggered event in the background and issues an audible and visual alarm to prompt the operator to intervene and inspect; this series of actions aims to instantly stop the further expansion of damage and provide safety assurance for subsequent manual handling or replanning.

[0102] This entire set of switching logic based on physical calibration thresholds provides the system with clear safety boundaries and multi-layered response strategies. It enables the system to boldly improve efficiency in safe zones, prudently adapt and adjust in risk zones, and decisively intervene before danger occurs, thus putting proactive prevention into practice.

[0103] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A quality analysis and tracking system for CNC machine tool castings, characterized in that, include: The multi-physics field fusion monitoring module is used to acquire multi-dimensional physical signals of the machine tool in real time and construct a real-time state feature vector based on the multi-dimensional physical signals. The real-time defect evolution inversion module is used to combine the real-time state feature vector with the preset initial defect factor of the casting, and calculate the real-time defect activation index through the processing-induced defect activation index model. The dynamic optimization module for cutting parameters is used to determine the optimal set of cutting parameters by solving the normalized machining utility function based on the machining-induced defect activation index model and preset process constraints. The damage suppression mode switching module is used to compare the real-time defect activation index with the preset safety threshold and critical threshold, and based on the comparison results, combined with the optimal cutting parameter set, to determine the final machining command to be sent to the CNC system. The specific steps for calculating the processing-induced defect activation index are as follows: S21. Determine the thermodynamic effect terms based on the cutting temperature; S22. Determine the quasi-static mechanical effect term based on the root mean square value of the acoustic emission signal; S23. Based on the kurtosis of the vibration signal and the resultant cutting force, determine the dynamic impact effect term; S24. Weighted summation of thermodynamic effect term and quasi-static mechanical effect term to obtain combined effect term; S25. Based on the combined effect term, the dynamic impact effect term, and the initial defect factor of the casting, a real-time defect activation index is generated. The specific steps for determining the machining instructions are as follows: If the real-time defect activation index is less than or equal to the safety threshold, the system enters the high-efficiency mode and uses the optimal set of cutting parameters calculated by the cutting parameter dynamic optimization module with the main goal of maximizing processing efficiency as the processing command. If the real-time defect activation index is greater than the safety threshold but less than the critical threshold, the system enters the adaptive mode and uses the optimal set of cutting parameters calculated by the cutting parameter dynamic optimization module, which aims to balance machining efficiency and risk suppression, as the machining command. If the real-time defect activation index is greater than or equal to the critical threshold, the preset emergency plan will be used as the processing instruction.

2. The CNC machine tool casting quality analysis and tracking system according to claim 1, characterized in that, The multi-element physical signals include: high-frequency acoustic emission sensor signals, three-part force measuring instrument signals, high-precision accelerometer signals, and non-contact infrared thermometer signals.

3. The CNC machine tool casting quality analysis and tracking system according to claim 1, characterized in that, The specific steps for constructing the real-time state feature vector are as follows: S11. Extract the root mean square value of the acoustic emission signal from the high-frequency acoustic emission sensor signal; S12. Extract the resultant cutting force from the signal of the three-part force measuring instrument; S13. Extract the kurtosis of the vibration signal from the high-precision accelerometer signal; S14. Extract the cutting temperature from the signal of the non-contact infrared thermometer; S15. Combine the root mean square value of the acoustic emission signal, the resultant cutting force, the kurtosis of the vibration signal, and the cutting temperature to construct a real-time state feature vector.

4. The CNC machine tool casting quality analysis and tracking system according to claim 1, characterized in that, The specific steps for determining the optimal set of cutting parameters are as follows: S31. Calculate the material removal rate based on the cutting parameters to be optimized; S32. Predict the state feature vector corresponding to the cutting parameters to be optimized by using a preset cutting process proxy model; S33. Substitute the predicted state feature vector into the processing-induced defect activation index model to obtain the predicted defect activation index. S34. Combining the material removal rate and the predicted defect activation index, solve for the maximum value of the normalized machining utility function to determine the optimal set of cutting parameters.

5. The CNC machine tool casting quality analysis and tracking system according to claim 4, characterized in that, The cutting process proxy model is obtained by establishing the mapping relationship from cutting parameters to state feature vectors through offline calibration experiments.

6. The CNC machine tool casting quality analysis and tracking system according to claim 1, characterized in that, The safety threshold is derived from the real-time defect activation index value, calibrated through trial cutting experiments, which ensures that the microcrack density is below the allowable standard of the material under a preset confidence level.

7. The CNC machine tool casting quality analysis and tracking system according to claim 1, characterized in that, The critical threshold is derived from the statistical lower limit of the instantaneous peak value of the real-time defect activation index of all failed samples just before failure, determined through destructive test cutting experiments.

Images