Machine tool equipment data transmission security method and system

Abstract

The application relates to a machine tool equipment data transmission security method and system. The machine tool equipment data transmission security method comprises the following steps: a virtual model preconfigured in a machine tool equipment receives a machining instruction, and performs virtual pre-execution on the machining instruction to simulate the physical behavior of the machine tool equipment; the consistency between the virtual pre-execution result and a preset physical behavior benchmark is evaluated; whether the machining instruction has abnormal behavior is determined according to the evaluation result; if it is determined that the machining instruction does not have abnormal behavior, the machine tool equipment actually executes according to the machining instruction; if it is determined that the machining instruction has abnormal behavior, the actual execution of the machining instruction is blocked, an alarm is sent out, and relevant information is recorded. The safety of the instruction is evaluated from the network level to the physical behavior level by introducing the virtual pre-execution mechanism, and the integrity and authenticity of the machine tool equipment data transmission are improved.

Description

Technical Field

[0001] This application relates to the field of equipment data transmission, and in particular to a secure method and system for data transmission in machine tool equipment. Background Technology

[0002] In modern industry, precision machine tools, as core equipment for manufacturing high-value components, generate and transmit critical data such as machining instructions, real-time sensor readings, and operational status reports during operation. The confidentiality and integrity of this data transmission directly affect production safety, product quality, and efficiency. Leakage or tampering can lead to serious production losses, product defects, and safety accidents, necessitating reliable security protection.

[0003] To meet this security requirement, many advanced machine tools integrate dedicated hardware security module (HSM) chips. These chips are primarily used to perform encryption operations, generate and securely manage session keys, and enable data encryption and decryption between the machine tool and the central control system. This ensures that intercepted data packets cannot be easily deciphered, and unauthorized modifications can be detected through integrity checks. However, this security architecture still has potential vulnerabilities and cannot provide comprehensive protection, leaving opportunities for attacks.

[0004] A stealthy data tampering attack exploits this vulnerability in the HSM chip, enabling minute-level forgery of processing instructions. This attack primarily leverages two key factors: first, the statistical weakness of the HSM chip firmware's session keys under high-frequency encryption loads; and second, the extended key update cycle caused by communication parameter optimization. Specifically, when faced with continuous high-frequency encryption requests, the firmware entropy pool refresh mechanism intermittently skips these requests, causing the HSM to rely on deterministic pseudo-random numbers to generate some session keys in the short term, exhibiting statistical predictability. Engineers extend the key update cycle to increase transmission throughput, significantly expanding the attack window.

[0005] The combination of these two factors allows a skilled attacker to passively eavesdrop on machine tool network traffic over a long period. Using traffic analysis and statistical methods, they can identify pseudo-random number key patterns and predict future session keys during periods of high load. This allows them to intercept and decrypt critical machining commands sent by the central control system, make minor alterations, re-encrypt them, and inject them into the network, thus compromising data transmission integrity. The deviation from this alteration is so small that it fails to trigger real-time machine tool safety alarms and is difficult to detect in a timely manner using traditional quality control methods.

[0006] More significantly, the existing security log and monitoring systems for machine tools have obvious shortcomings. They only focus on network-level anomaly detection and recording, lacking in-depth analysis capabilities of encryption primitives, failing to monitor session key statistical characteristics, and unable to detect subtle pattern deviations in entropy sources and key generation processes. This allows attackers to continuously exploit this complex vulnerability, as security logs cannot capture relevant abnormal signals, and quality issues caused by forged instructions remain hidden for a long time, making it extremely difficult to trace the root cause. Summary of the Invention

[0007] This application provides a secure data transmission method and system for machine tool equipment, which at least solves the problem of covert data tampering attacks on data transmission in machine tool equipment in related technologies. These attacks exploit the statistical weaknesses of session keys in the firmware of hardware security module chips under specific high-frequency encryption loads, and combine this with the extension of key update cycles caused by communication parameter optimization, to achieve minute forgery of machining instructions. Moreover, existing security monitoring mechanisms have difficulty detecting such anomalies.

[0008] In a first aspect, this application provides a method for secure data transmission in machine tool equipment, comprising the following steps: The virtual model pre-configured within the machine tool receives machining instructions and performs virtual pre-execution of the machining instructions to simulate the physical behavior of the machine tool. Based on the virtual pre-execution results, evaluate their consistency with the preset physical behavior benchmark; Based on the evaluation results, determine whether the processing instruction exhibits any abnormal behavior: If it is determined that the machining instruction does not exhibit any abnormal behavior, the machine tool will actually execute the machining instruction accordingly. If the processing instruction is determined to have abnormal behavior, the actual execution of the processing instruction will be blocked, an alarm will be issued, and relevant information will be recorded.

[0009] Optionally, evaluating the consistency between the virtual pre-execution results and the preset physical behavior benchmark includes: The virtual model receives and stores the complete multi-stage processing instruction sequence of the workpiece to be processed; The current instruction in the processing instruction sequence is virtually pre-executed to simulate the physical behavior of the machine tool on the virtual workpiece; Based on the pre-execution results, the current simulation state of the virtual workpiece is updated, and the current simulation state is used as the initial state for the virtual pre-execution of subsequent instructions; During the virtual pre-execution process, the effects of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece are continuously calculated and accumulated. After each key stage of the processing instruction sequence is completed, the consistency between the cumulative state of the virtual workpiece and the preset final physical behavior benchmark is evaluated.

[0010] Optionally, during the virtual pre-execution process, continuously calculating and accumulating the influence of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece includes: During virtual pre-execution, the instantaneous temperature distribution and stress state of the current processing area of ​​the virtual workpiece are acquired in real time; Based on the instantaneous temperature distribution and the stress state, the material parameters of the virtual workpiece are dynamically adjusted, wherein the material parameters include constitutive parameters and thermophysical parameters; Based on the adjusted material parameters, calculate the incremental impact of the current command on the virtual workpiece's geometry, surface morphology, and internal stress distribution; The incremental effects are accumulated into the overall state of the virtual workpiece, thereby continuously calculating and accumulating the influence of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece.

[0011] Optionally, after each key stage of the processing instruction sequence is completed, evaluating the consistency between the cumulative state of the virtual workpiece and a preset final physical behavior benchmark includes: During virtual pre-execution, sensor data from the machine tool equipment is received in real time; Based on the sensor data, the operating parameters and environmental parameters in the virtual model are dynamically updated; Based on the updated operating parameters and environmental parameters, the cumulative effect of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece is calculated. The cumulative effect is compared with a preset final physical behavior benchmark, wherein the final physical behavior benchmark is dynamically adjusted based on the sensor data; Based on the comparison results, it is determined whether there is any abnormal behavior in the processing instruction sequence.

[0012] Optionally, comparing the cumulative effect with a preset final physical behavior benchmark, wherein the final physical behavior benchmark is dynamically adjusted based on the sensor data, includes: The sensor data is subjected to consistency verification, which includes: checking the numerical range of the sensor data to ensure that the sensor data is within a preset physical reasonable range; checking the rate of change of the sensor data to ensure that the trend of the sensor data changes in accordance with physical laws; and cross-validating the sensor data from different types of sensors or the same type of sensors at different locations to ensure logical consistency between the sensor data. Once the sensor data passes the consistency check, the key parameters in the final physical behavior benchmark are dynamically adjusted based on the checked sensor data. The cumulative effects are compared with the adjusted final physical behavior benchmark to obtain the comparison results; Based on the comparison results, it is determined whether there is any abnormal behavior in the processing instruction sequence.

[0013] Optionally, the cross-validation of data from different types of sensors or sensors of the same type but at different locations to ensure logical consistency between the sensor data includes: Receive data from different types of sensors or sensors of the same type but in different locations; Based on the physical characteristics of the sensor data and the current processing stage, a correlation analysis method is dynamically selected. Specifically, for nonlinear correlations between the sensor data, a nonlinear mapping function or numerical simulation based on a physical model is used to establish the mapping relationship between the sensor data. For time-varying correlations between the sensor data, the weights or parameters of the mapping relationship are adjusted in real time according to the progress of the current processing instruction sequence, the machine tool operating mode, or the virtual workpiece material state. For multimodal correlations between the sensor data, feature extraction and fusion are performed on the sensor data from different physical domains to construct a multidimensional feature vector. The deviation between the sensor data is calculated based on the distance or similarity between the multidimensional feature vectors; The deviation is compared with a preset dynamic adjustment threshold, and based on the comparison result, it is determined whether there is a logical inconsistency in the sensor data.

[0014] Optionally, comparing the deviation with a preset dynamic adjustment threshold and determining whether there is a logical inconsistency in the sensor data based on the comparison result includes: Real-time monitoring of machine tool equipment operation data, including: running time, number of processed workpieces, cumulative cutting amount of the tool, and ambient temperature change trend; Based on the operational data, calculate the adjustment factor for the dynamic adjustment threshold; The adjustment factor is applied to the dynamic adjustment threshold to obtain the current adaptive threshold; Based on the comparison result between the deviation and the adaptability threshold, it is determined whether there is a logical inconsistency in the sensor data.

[0015] Optionally, calculating the adjustment factor for the dynamic adjustment threshold based on the operational data includes: Identify the current machining data of the machine tool equipment, including the equipment model, the material type of the workpiece to be processed, and the type of cutting tool currently being used; Based on the identified processing data, the corresponding nonlinear mapping function set and weight parameter set are retrieved from the preset parameter influence library; For the running data, feature transformation is performed by applying the corresponding functions in the set of nonlinear mapping functions respectively; The transformed running data is then weighted and fused with the set of weight parameters. The weighted fusion result is used as an adjustment factor for the preset dynamic adjustment threshold.

[0016] Optionally, using the weighted fusion result as an adjustment factor for the preset dynamic adjustment threshold includes: Real-time monitoring of machine tool equipment operating status parameters, including spindle load rate, cutting force fluctuation amplitude, and temperature gradient of the machining area; When any of the operating status parameters exceeds the preset extreme operating condition threshold, the safety margin correction mechanism is activated. The safety margin correction mechanism calculates a dynamic safety margin factor based on the degree of deviation of the operating state parameters from the preset extreme operating condition threshold. The weighted fusion result is multiplied by the dynamic safety margin factor to obtain the corrected adjustment factor; The modified adjustment factor is used as the adjustment factor for the preset dynamic adjustment threshold.

[0017] Secondly, this application provides a data transmission security system for machine tool equipment, the system comprising: The virtual pre-execution module is used to receive machining instructions from a pre-configured virtual model within the machine tool and to perform virtual pre-execution of the machining instructions to simulate the physical behavior of the machine tool. The consistency evaluation module is used to evaluate the consistency between the virtual pre-execution results and the preset physical behavior benchmark. The anomaly detection and blocking module is used to determine whether the processing instruction exhibits abnormal behavior based on the evaluation results. If it is determined that the machining instruction does not exhibit any abnormal behavior, the machine tool will actually execute the machining instruction accordingly. If the processing instruction is determined to have abnormal behavior, the actual execution of the processing instruction will be blocked, an alarm will be issued, and relevant information will be recorded.

[0018] Compared with related technologies, the machine tool equipment data transmission security method and system provided in this application have at least the following technical advantages: By pre-configuring a virtual model within the machine tool, processing instructions are received and virtually pre-executed to simulate the physical behavior of the machine tool. Based on the virtual pre-execution results, the consistency between the pre-execution and the preset physical behavior benchmark is evaluated, and the presence of abnormal behavior in the processing instructions is determined according to the evaluation results. If no abnormal behavior is found, the machine tool executes the instructions accordingly; if abnormal behavior is found, the actual execution of the instructions is blocked, an alarm is issued, and relevant information is recorded. This application elevates the security assessment of instructions from the network layer to the physical behavior layer by introducing a virtual pre-execution mechanism. Even minor forged instructions that are insufficient to trigger traditional collision detection or stress overload alarms can be detected in a timely manner through deviations in physical behavior simulated by the virtual model. This avoids long-term production quality problems and traceability issues caused by minor forged instructions, and improves the integrity and authenticity of data transmission in the machine tool.

[0019] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating a secure data transmission method for machine tool equipment according to an exemplary embodiment.

[0021] Figure 2 This is a flowchart illustrating step S2 according to an exemplary embodiment.

[0022] Figure 3 This is a flowchart illustrating step S24 according to an exemplary embodiment.

[0023] Figure 4 This is a flowchart illustrating step S25 according to an exemplary embodiment.

[0024] Figure 5 This is a flowchart illustrating step S254 according to an exemplary embodiment.

[0025] Figure 6 This is a block diagram illustrating a secure data transmission system for machine tool equipment according to an exemplary embodiment. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0027] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any creative effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0028] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0029] In related technologies, skilled attackers can passively eavesdrop on machine tool network traffic over a long period. Using traffic analysis and statistical methods, they can identify pseudo-random number key patterns and predict future session keys during periods of high load. They can then intercept and decrypt critical machining commands sent by the central control system, subtly modify them, re-encrypt them, and inject them into the network, thus compromising data transmission integrity. This tampering is so minute that it fails to trigger real-time machine tool safety alarms and is difficult to detect in a timely manner using traditional quality control methods.

[0030] More significantly, the existing security log and monitoring systems for machine tools have obvious shortcomings. They only focus on network-level anomaly detection and recording, lacking in-depth analysis capabilities of encryption primitives, failing to monitor session key statistical characteristics, and unable to detect subtle pattern deviations in entropy sources and key generation processes. This allows attackers to continuously exploit this complex vulnerability, as security logs cannot capture relevant abnormal signals, and quality issues caused by forged instructions remain hidden for a long time, making it extremely difficult to trace the root cause.

[0031] Based on the above, embodiments of the present invention provide a method and system for secure data transmission in machine tool equipment, which will be described in detail below with reference to specific embodiments and accompanying drawings.

[0032] Example 1 This invention provides a method for ensuring secure data transmission in machine tool equipment. Figure 1 This is a flowchart illustrating a secure data transmission method for machine tool equipment according to an exemplary embodiment. Figure 1 As shown, the method includes: S1. The virtual model pre-configured within the machine tool receives machining instructions and performs virtual pre-execution of the machining instructions to simulate the physical behavior of the machine tool. In this embodiment, the virtual model is a simplified geometric model that can simulate tool paths, material removal processes, and initial changes in workpiece shape in a virtual environment based on received machining instructions. For example, the virtual model may only simulate macroscopic geometric changes in the workpiece without considering the microstructure or thermodynamic response of the material.

[0033] S2. Based on the virtual pre-execution results, evaluate their consistency with the preset physical behavior benchmark; In this embodiment, the virtual pre-execution result, such as the final shape or size of the virtual workpiece, is subsequently used to evaluate its consistency with a preset physical behavior benchmark. As one implementation, the preset physical behavior benchmark can be a fixed range of final workpiece geometric dimensions determined by design specifications. The evaluation process can simply compare the final workpiece dimensions obtained from the virtual pre-execution with the preset size range. If the final dimensions of the virtual workpiece fall within the preset range, it is considered consistent; otherwise, it is considered inconsistent.

[0034] S3. Based on the evaluation results, determine whether the processing instruction exhibits abnormal behavior: If it is determined that the machining instruction does not exhibit any abnormal behavior, the machine tool will actually execute the machining instruction accordingly. If the processing instruction is determined to have abnormal behavior, the actual execution of the processing instruction will be blocked, an alarm will be issued, and relevant information will be recorded.

[0035] In this embodiment, if the virtual pre-execution result is inconsistent with the preset physical behavior benchmark, the machining instruction is determined to have abnormal behavior. If the machining instruction is determined not to have abnormal behavior, the machine tool equipment executes the machining instruction accordingly. Conversely, if the machining instruction is determined to have abnormal behavior, the actual execution of the machining instruction is blocked, an alarm is issued, and relevant information is recorded for subsequent analysis and tracing.

[0036] The technical solution described in the above embodiments effectively solves the problem of the difficulty in detecting covert data tampering attacks in the prior art by introducing a virtual pre-execution and physical behavior benchmark evaluation mechanism. Specifically, by pre-executing the machining instructions using a virtual model before the actual execution of the instructions and comparing the results with preset physical behavior benchmarks, even extremely minor abnormal behaviors that may lead to product quality problems can be identified in advance. This proactive detection mechanism significantly improves the security of data transmission in machine tool equipment and the reliability of the machining process, avoids production losses and quality risks caused by covert attacks, and complements and enhances traditional security mechanisms.

[0037] In one possible design, Figure 2 This is a flowchart illustrating step S2 according to an exemplary embodiment. (Refer to the attached document.) Figure 2 Step S2 includes: S21. The virtual model receives and stores a complete multi-stage processing instruction sequence for the workpiece to be processed; In this embodiment, the virtual model is a digital twin of the machine tool and its workpiece, configured to receive and store a complete multi-stage machining instruction sequence for the workpiece. This sequence includes all machining steps and parameters from the raw material to the final product, ensuring a comprehensive view of the entire machining process. Upon receiving the machining instruction sequence, the virtual model stores it for virtual pre-execution of each instruction.

[0038] S22. Perform virtual pre-execution on the current instruction in the processing instruction sequence to simulate the physical behavior of the machine tool on the virtual workpiece; In this embodiment, the virtual model performs virtual pre-execution on each current instruction in the machining instruction sequence. This simulates the physical behavior that the machine tool may exhibit when executing the instruction, such as tool path, cutting force, material removal amount, and resulting workpiece deformation. In this way, the potential impact of the instruction can be predicted without actually operating the machine tool.

[0039] S23. Based on the pre-execution result, update the current simulation state of the virtual workpiece, and use the current simulation state as the initial state for the virtual pre-execution of subsequent instructions; In this embodiment, the current simulation state of the virtual workpiece is updated in real time based on the results of virtual pre-execution. The current simulation state includes key physical properties of the virtual workpiece, such as its geometry, surface roughness, and internal stress distribution. The updated simulation state is then used as the initial state for subsequent virtual pre-execution of instructions, ensuring that the simulation process of the entire machining instruction sequence is continuous and cumulative, accurately reflecting changes in the workpiece at different machining stages.

[0040] S24. During the virtual pre-execution process, the influence of the machining instruction sequence on the geometric dimensions, surface morphology, or internal stress distribution of the virtual workpiece is continuously calculated and accumulated. In this embodiment, throughout the entire virtual pre-execution process, the system continuously calculates and accumulates the impact of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece. That is, every minute change in the physical properties of the workpiece caused by each instruction is precisely quantified and superimposed on the overall state of the virtual workpiece, thereby forming a dynamically changing cumulative impact model.

[0041] S25. After each key stage of the processing instruction sequence is completed, evaluate the consistency between the cumulative state of the virtual workpiece and the preset final physical behavior benchmark. In this embodiment, after each key stage of the processing instruction sequence is completed, the cumulative state of the virtual workpiece is extracted and evaluated for consistency with a preset final physical behavior benchmark. The key stages can be predefined nodes such as roughing completion, semi-finishing completion, or completion of specific feature processing. By evaluating these nodes, potential deviations or anomalies during processing can be detected promptly without waiting for the entire processing to finish.

[0042] The technical solution of the above embodiments achieves a more refined and comprehensive safety assessment of machine tool processing instructions. By virtually pre-executing the complete processing instruction sequence and calculating the cumulative impact in multiple stages, potential abnormal behaviors can be identified earlier and more accurately, such as unreasonable toolpaths, excessive cutting forces, or instructions that may cause workpiece deformation. This phased assessment mechanism significantly improves the sensitivity and timeliness of abnormal behavior detection. Specifically, firstly, the complete processing instruction sequence is received and stored to ensure a comprehensive understanding and simulation of the entire processing process; then, each instruction in the sequence is virtually pre-executed, and the simulation state of the virtual workpiece is dynamically updated based on the pre-executing results, achieving continuous and accurate simulation of the processing process; during this process, the incremental impact of processing instructions on the virtual workpiece's geometry, surface morphology, or internal stress distribution is continuously calculated and accumulated, enabling the virtual model to reflect the physical changes of the workpiece in real time; finally, after each key stage of the processing instruction sequence is completed, the cumulative state of the virtual workpiece is evaluated against the preset final physical behavior benchmark, thereby enabling the timely detection of potential abnormal behaviors and avoiding the lag that may result from a one-time inspection after processing.

[0043] In one possible design, Figure 3 This is a flowchart illustrating step S24 according to an exemplary embodiment. (Refer to the attached document.) Figure 3 Step S24 includes: S241. During virtual pre-execution, the instantaneous temperature distribution and stress state of the current processing area of ​​the virtual workpiece are obtained in real time. In this embodiment, at each time step or key processing stage of virtual pre-execution, the local temperature field and stress field of the virtual workpiece under the current processing command are calculated and obtained through a simulation model (e.g., a finite element analysis model), thereby capturing the transient physical changes caused by factors such as cutting heat, friction and material deformation during the processing.

[0044] S242. Based on the instantaneous temperature distribution and the stress state, dynamically adjust the material parameters of the virtual workpiece, wherein the material parameters include constitutive parameters and thermophysical parameters; In this embodiment, based on a pre-established material database or constitutive model, the material properties of the virtual workpiece are corrected in real time according to the instantaneous temperature distribution and stress state obtained in real time. Among them, constitutive parameters are parameters describing the mechanical behavior of materials, such as elastic modulus, yield strength, hardening parameters, etc., which change with temperature and stress state; thermophysical parameters are parameters describing the thermal behavior of materials, such as thermal conductivity, specific heat capacity, coefficient of thermal expansion, etc., which are also affected by temperature.

[0045] S243. Based on the adjusted material parameters, calculate the incremental impact of the current command on the virtual workpiece's geometry, surface morphology, and internal stress distribution; In this embodiment, by utilizing updated material parameters and employing high-precision simulation algorithms (such as physics-based cutting force models, material removal models, and deformation models), the minute changes in geometry, surface roughness, and internal residual stress of the virtual workpiece caused by the current machining command are accurately calculated. This quantifies the specific impact of a single command on the workpiece state and lays the foundation for calculating the cumulative effect.

[0046] S244. Accumulate the incremental influence into the overall state of the virtual workpiece, thereby continuously calculating and accumulating the influence of the processing instruction sequence on the geometric dimensions, surface morphology, or internal stress distribution of the virtual workpiece. In this embodiment, the incremental impact of each instruction is superimposed on the current simulation state of the virtual workpiece, forming a continuously updated workpiece state model. This allows for continuous tracking of the cumulative effects of the machining instruction sequence on the virtual workpiece's geometry, surface morphology, or internal stress distribution.

[0047] In the technical solution of the above embodiments, by considering the instantaneous temperature and stress state of the processing area in real time during the virtual pre-execution process, and dynamically adjusting the material parameters of the virtual workpiece accordingly, the virtual model can more realistically reflect the physical response of the material under actual processing conditions, ultimately improving the accuracy of virtual pre-execution, especially in scenarios involving complex material behavior and high-precision machining. By dynamically adjusting the material parameters, the virtual model can more accurately predict the deformation, residual stress, and surface quality changes of the workpiece during processing, thereby making the consistency assessment based on the virtual pre-execution results more reliable, effectively avoiding misjudgments or omissions caused by inaccurate material parameters, and further enhancing the security of data transmission and the stability of the machining process.

[0048] In one possible design, Figure 4 This is a flowchart illustrating step S25 according to an exemplary embodiment. (Refer to the attached document.) Figure 4 Step S25 includes: S251. During virtual pre-execution, receive sensor data from the machine tool equipment in real time; In this embodiment, during the virtual pre-execution process, the machine tool receives real-time sensor data from its internal or external sources. This sensor data includes, but is not limited to, spindle speed, feed rate, cutting force, vibration, temperature, and ambient humidity, reflecting the current actual operating status of the machine tool and the environmental conditions it is in.

[0049] S252. Dynamically update the operating parameters and environmental parameters in the virtual model based on the sensor data; In this embodiment, the operating parameters and environmental parameters in the virtual model are dynamically updated based on the received sensor data. Operating parameters refer to parameters related to the operation of the machine tool, such as tool wear, spindle load, and motor current; environmental parameters refer to the temperature, humidity, and air pressure of the machining area. By updating these parameters in real time, the virtual model can more accurately simulate the physical behavior of the machine tool under current actual working conditions.

[0050] S253. Based on the updated operating parameters and environmental parameters, calculate the cumulative effect of the processing instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece. In this embodiment, based on updated operating and environmental parameters, the system calculates the cumulative impact of the machining command sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece. By considering actual operating and environmental factors, the deformation, surface roughness changes, and internal stress accumulation of the virtual workpiece can be simulated and calculated more accurately.

[0051] S254. Compare the cumulative effect with a preset final physical behavior benchmark, wherein the final physical behavior benchmark is dynamically adjusted according to the sensor data; In this embodiment, the final physical behavior benchmark is not fixed, but dynamically adjusted based on real-time received sensor data. For example, if the sensor data shows an increase in ambient temperature, the parameters in the benchmark regarding the thermal expansion of the material may be adjusted accordingly to more realistically reflect the expected behavior of the workpiece at high temperatures.

[0052] S255. Based on the comparison result, determine whether there is any abnormal behavior in the processing instruction sequence; In this embodiment, the presence of abnormal behavior in the processing instruction sequence can be determined by comparing the cumulative impact with the dynamically adjusted final physical behavior benchmark. For example, if there is a significant deviation between the cumulative impact and the adjusted benchmark, it may indicate a potential safety risk or abnormal operation in the processing instructions.

[0053] In the technical solution of the above embodiments, by introducing real-time sensor data and dynamically updating the operating parameters and environmental parameters of the virtual model based on this data, as well as dynamically adjusting the final physical behavior benchmark, the accuracy and adaptability of the machine tool equipment data transmission security method are improved. Specifically, real-time sensor data provides realistic feedback on the current working condition of the machine tool equipment, enabling the virtual model to simulate physical behavior more closely to reality; dynamically updating the operating parameters and environmental parameters in the virtual model significantly improves the accuracy of virtual pre-execution, ensuring more accurate calculation of the cumulative impact of machining command sequences; the dynamic adjustment mechanism of the final physical behavior benchmark allows the benchmark to adapt to various changes that may occur during actual machining, such as material batch differences, tool wear, and environmental temperature fluctuations, thereby avoiding misjudgments caused by benchmark mismatch, enabling more accurate and robust assessment of the safety of machining commands, effectively identifying potential abnormal behaviors, and reducing the risk of production interruption.

[0054] In one example, suppose a CNC milling machine is machining an aluminum alloy workpiece. During the machining process, the machine tool's spindle load sensor, vibration sensor, and machining area temperature sensor collect data in real time. For example, when the spindle load sensor shows a sudden increase in load, or the vibration sensor shows abnormal vibration, or the temperature sensor shows that the machining area temperature exceeds the normal range, this sensor data will be transmitted to the virtual model in real time.

[0055] After receiving this data, the virtual model dynamically updates its internal operating parameters and environmental parameters, such as tool wear parameters and material thermal expansion coefficients, based on this real-time data. For example, if the temperature rises, the virtual model will adjust the thermal expansion coefficient of the aluminum alloy material to more accurately simulate the dimensional changes of the workpiece at the current temperature.

[0056] Based on these updated parameters, the virtual model recalculates the cumulative impact of the current machining command sequence on the virtual workpiece's geometry, surface morphology, and internal stress distribution. Simultaneously, the preset final physical behavior benchmark is dynamically adjusted based on this sensor data. For example, if sensor data indicates increased tool wear, the expected value for surface roughness in the benchmark may be appropriately relaxed to accommodate the slight increase in roughness that might result from tool wear.

[0057] Finally, the recalculated cumulative impact is compared with the dynamically adjusted final physical behavior benchmark. If a deviation exceeding the allowable range is found between the cumulative impact and the adjusted benchmark (e.g., the simulated value of a key dimension of the virtual workpiece does not match the expected range of the adjusted benchmark), the system will determine that there is abnormal behavior in the machining instruction sequence, immediately block the execution of subsequent instructions, and issue an alarm. In this way, even when actual working conditions change, the solution of this application can accurately identify the real anomaly, avoiding misjudgments caused by environmental changes.

[0058] In one possible design, Figure 5 This is a flowchart illustrating step S254 according to an exemplary embodiment. (Refer to the attached document.) Figure 5 Step S254 includes: S2541. Perform a consistency check on the sensor data, wherein the consistency check includes: checking the numerical range of the sensor data to ensure that the sensor data is within a preset physical reasonable range; checking the rate of change of the sensor data to ensure that the trend of the sensor data changes in accordance with physical laws; and performing cross-validation on sensor data from different types of sensors or sensors of the same type but at different locations to ensure logical consistency between the sensor data. In this embodiment, sensor data consistency verification is used to ensure that the sensor data used to dynamically adjust the final physical behavior benchmark is reliable and effective. Specifically, the numerical range of the sensor data is checked by comparing the received sensor data with preset physical upper and lower limits. For example, temperature sensor data should be between the melting point and solidification point of the material, and pressure sensor data should be within the maximum pressure range of the equipment. This eliminates abnormal readings that clearly exceed physical common sense or the equipment's capacity.

[0059] The rate of change of sensor data is checked, monitoring the magnitude of changes in sensor data at continuous time points and comparing it with a preset reasonable rate of change threshold. For example, the machine tool spindle speed should not experience drastic and unreasonable jumps within a short period of time. This helps identify sudden data abrupt changes or jitters, which may indicate sensor malfunctions or data transmission errors.

[0060] Cross-validation is performed on data from different types of sensors or sensors of the same type but in different locations. Logical consistency is determined by analyzing the physical correlations between different sensor data. For example, when the cutting force sensor shows a significant increase in cutting force, the data from the spindle power sensor and vibration sensor should also show a corresponding trend. This helps identify potential biases or malfunctions in individual sensors, and by cross-validating data from multiple sources, the overall reliability of the data is improved.

[0061] S2542. After the sensor data passes the consistency check, the key parameters in the final physical behavior benchmark are dynamically adjusted based on the checked sensor data. In this embodiment, sensor data is considered reliable once it passes the aforementioned consistency verification. At this point, key parameters in the final physical behavior benchmark are dynamically adjusted based on the verified sensor data. These key parameters include, but are not limited to, the material's yield strength, hardness, coefficient of thermal expansion, etc., or geometric tolerances and surface roughness thresholds related to the processing process. For example, if the verified temperature sensor data shows a continuous increase in the temperature of the processing area, the thermophysical parameters of the material are adjusted accordingly to more accurately reflect the actual physical behavior of the current workpiece.

[0062] S2543. Compare the cumulative effects with the adjusted final physical behavior benchmark to obtain the comparison results; S2544. Based on the comparison result, determine whether there is any abnormal behavior in the processing instruction sequence; In the technical solution of the above embodiments, by introducing a consistency verification mechanism for sensor data, erroneous adjustments to the final physical behavior benchmark caused by abnormal or tampered sensor data are effectively avoided, thereby ensuring the accuracy of abnormal behavior judgment. Specifically, by performing multi-dimensional checks on the numerical range, rate of change, and logical consistency between different sensors of the sensor data, abnormal data caused by sensor failure, environmental interference, or malicious attacks can be filtered out. For example, if a temperature sensor reading suddenly spikes to an unreasonably high value, the numerical range check will immediately mark it as abnormal; if the spindle speed jumps from zero to its maximum value within milliseconds, the rate of change check will identify this abrupt change that does not conform to physical laws; if the cutting force sensor shows a high load while the spindle power sensor shows a low power, the cross-validation mechanism will find this logical inconsistency. Only when the sensor data passes these rigorous checks and is confirmed to be true, valid, and logically consistent will it be used to dynamically adjust the final physical behavior benchmark. This ensures that the final physical behavior benchmark adjustment is based on accurate and reliable real-time information, making the comparison between the subsequent cumulative impact and the benchmark more precise, determining whether there is abnormal behavior in the processing instruction sequence, and reducing the risk of misjudgment due to data errors.

[0063] In one example, suppose a CNC milling machine is performing a complex machining task. During the machining process, the system receives feedback data in real time from multiple sensors, including a spindle speed sensor, a cutting force sensor, a vibration sensor, and a temperature sensor for the machining area.

[0064] First, the system performs consistency checks on these sensor data. For example, the spindle speed sensor data is checked to ensure its value is within a preset range of 0 to 24,000 RPM and its rate of change is within a reasonable range of ±500 RPM per second. Simultaneously, the cutting force sensor data is cross-validated with the spindle power sensor data; that is, when the cutting force suddenly increases, the spindle power should also increase accordingly. If a temperature sensor reading suddenly shows -50℃ (outside the physically reasonable range), or the cutting force jumps from 100N to 10,000N in a very short time (exceeding the rate of change threshold), or there is a significant mismatch between the cutting force and spindle power data (cross-validation failure), then this sensor data will be marked as unreliable.

[0065] Only after all sensor data has passed the aforementioned consistency check and been confirmed as reliable will the system dynamically adjust the key parameters in the final physical behavior benchmark based on this verified sensor data. For example, if the verified temperature data shows that the temperature in the processing area remains consistently at a high level, the system will adjust the thermal expansion coefficient parameter of the material accordingly to more accurately predict the geometric changes of the workpiece at the current temperature.

[0066] Subsequently, the cumulative impact calculated by the virtual pre-execution is compared with this dynamically adjusted final physical behavior benchmark based on reliable sensor data. If the comparison shows a significant deviation between the two, such as the simulated dimensions of the virtual workpiece not matching the adjusted benchmark dimensions, an abnormal behavior is determined in the processing instruction sequence, and blocking measures are immediately taken. In this way, even in environments where sensor data may be interfered with, the solution of this application can ensure the accuracy of the final physical behavior benchmark, ultimately improving the reliability of abnormal behavior determination.

[0067] In one possible design, step S2541, which involves cross-validating data from different types of sensors or sensors of the same type but at different locations to ensure logical consistency between the sensor data, includes: S25411, Receive data from sensors of different types or sensors of the same type but at different locations; In this embodiment, the system continuously acquires real-time data streams from various sensors deployed on the machine tool. For example, it can simultaneously receive data from spindle speed sensors, cutting force sensors, tool wear sensors, and machining area temperature sensors. These data may be transmitted at different sampling frequencies and data formats. The sensor data includes, but is not limited to, temperature sensor data, vibration sensor data, force sensor data, and displacement sensor data, which may originate from different parts of the machine tool, such as the spindle, cutting tool, workpiece fixture, or machining area.

[0068] S25412. Based on the physical characteristics of the sensor data and the current processing stage, dynamically select the correlation analysis method. Specifically, for nonlinear correlations between the sensor data, a nonlinear mapping function or numerical simulation based on a physical model is used to establish the mapping relationship between the sensor data. For time-varying correlations between the sensor data, the weights or parameters of the mapping relationship are adjusted in real time according to the progress of the current processing instruction sequence, the machine tool operating mode, or the virtual workpiece material state. For multimodal correlations between the sensor data, feature extraction and fusion are performed on the sensor data from different physical domains to construct a multidimensional feature vector. In this embodiment, for the nonlinear correlations between the sensor data, such as the complex relationship between cutting force and spindle current, nonlinear mapping functions such as multinomial regression, support vector machines, and neural networks can be used for modeling, or their mutual influence can be predicted through numerical simulation methods based on physical models, such as finite element analysis and computational fluid dynamics. The aim is to accurately capture the complex nonlinear dependencies between the data. For time-varying correlations between the sensor data, such as during roughing and finishing stages, changes in cutting parameters and workpiece material states can lead to changes in the sensor data correlation pattern. In this case, the weights or parameters of the mapping relationship can be adjusted in real time based on the progress of the current machining command sequence, the machine tool operating mode (e.g., high-speed cutting, low-speed feed), or the virtual workpiece material state (e.g., hardness, toughness) to adapt to dynamically changing working conditions. The purpose is to ensure the real-time performance and accuracy of the correlation analysis. For multimodal correlation among the sensor data, features are extracted from the frequency domain characteristics of vibration signals, the statistical characteristics of temperature signals, and the time domain characteristics of force signals. These features are then fused using methods such as principal component analysis, independent component analysis, or deep learning to construct a multidimensional feature vector that comprehensively reflects the operating status of the machine tool equipment. The aim is to achieve comprehensive analysis of multi-source heterogeneous sensor data.

[0069] S25413. Calculate the deviation between the sensor data based on the distance or similarity between the multidimensional feature vectors; In this embodiment, measurement methods such as Euclidean distance, Mahalanobis distance, cosine similarity, or Pearson correlation coefficient can be used to calculate the degree of difference between the multidimensional feature vector constructed at the current moment and the reference feature vector under the preset normal operating state, thereby quantifying the logical inconsistency between sensor data.

[0070] S25414. Compare the deviation with a preset dynamic adjustment threshold, and based on the comparison result, determine whether there is a logical inconsistency in the sensor data; In this embodiment, the dynamic adjustment threshold can be set and adjusted based on the historical operating data of the machine tool, expert experience, or real-time operating conditions to adapt to different processing environments and requirements.

[0071] In the technical solutions of the above embodiments, by performing refined cross-validation on sensor data from different types or locations, potential logical inconsistencies in the sensor data can be effectively identified, improving the accuracy and robustness of sensor data consistency verification in the machine tool equipment data transmission security method. Specifically, by dynamically selecting correlation analysis methods, this solution can flexibly address complex correlation characteristics such as nonlinearity, time-varying nature, and multimodal nature among sensor data. For example, for nonlinear correlation, using nonlinear mapping functions or physical model simulation can more accurately capture the inherent relationships between data, avoiding misjudgments that may be caused by traditional linear models. For time-varying correlation, the mapping relationship is adjusted in real time according to the processing stage, ensuring the accuracy of verification under different working conditions. For multimodal correlation, multidimensional feature vectors are constructed through feature extraction and fusion, achieving comprehensive perception and integrated evaluation of the machine tool equipment's operating status. Thus, by calculating the deviation between multidimensional feature vectors and comparing it with dynamically adjusted thresholds, anomalies in sensor data that do not conform to physical laws or logical relationships can be detected in a timely manner.

[0072] In one possible design, step S25414 includes: S254141. Real-time monitoring of machine tool equipment operation data, including: running time, number of processed workpieces, cumulative cutting amount of the tool, and ambient temperature change trend; In this embodiment, various key parameters of the machine tool are continuously acquired and recorded during operation. Among them, the operating data are indicators reflecting the current working status and historical cumulative status of the machine tool. For example, the running time can indicate the overall service life and potential wear of the equipment; the number of workpieces processed can reflect the production load of the equipment and the wear of the cutting tools; the cumulative cutting amount of the cutting tools is directly related to the wear status and cutting performance of the cutting tools; and the trend of ambient temperature change may affect the accuracy of sensor data and the physical behavior of materials such as thermal expansion.

[0073] S254142. Calculate the adjustment factor of the dynamic adjustment threshold based on the operating data; In this embodiment, the monitored operational data is used to generate a coefficient for correcting the original dynamic adjustment threshold through a preset algorithm or model. This adjustment factor aims to quantify the impact of current operating conditions on the logical consistency judgment standard of sensor data. For example, when the tool is severely worn, the sensor data may fluctuate more, and the adjustment factor can appropriately relax the threshold; conversely, when the equipment is in optimal condition, the adjustment factor can tighten the threshold.

[0074] S254143. Apply the adjustment factor to the dynamic adjustment threshold to obtain the current adaptive threshold; In this embodiment, the calculated adjustment factor is mathematically calculated (e.g., multiplication, addition, or more complex function mapping) and the original dynamic adjustment threshold to generate a judgment threshold that better adapts to the current operating conditions of the machine tool. This adaptive threshold can be dynamically adjusted according to the actual working conditions of the machine tool, ensuring that the accuracy of the judgment is maintained under different operating conditions.

[0075] S254144. Based on the comparison result between the deviation and the adaptability threshold, determine whether there is a logical inconsistency in the sensor data; In this embodiment, the sensor data deviation obtained through methods such as cross-validation is compared with an adaptive threshold adjusted by operational data. If the deviation exceeds the adaptive threshold, the sensor data is considered to have logical inconsistencies, indicating possible abnormal behavior; otherwise, the data is considered normal. This process ensures the flexibility and accuracy of anomaly detection.

[0076] In the technical solution of the above embodiments, by introducing real-time monitoring of machine tool operating data and calculating adjustment factors based on this data to correct the dynamic adjustment threshold, the accuracy and robustness of the machine tool data transmission security method are improved. Specifically, because the dynamic adjustment threshold can adaptively adjust according to the actual operating state, wear condition, and environmental changes of the machine tool, it can maintain high accuracy in determining the logical consistency of sensor data even under complex working conditions such as equipment aging, tool wear, or environmental fluctuations. This not only effectively reduces false alarms caused by improper threshold settings, avoiding unnecessary downtime and inspections, but also improves the detection sensitivity of real abnormal behavior, ensuring the data transmission security of the machine tool under various working conditions, thereby guaranteeing the stability of the machining process and the quality of the workpiece.

[0077] In one example, suppose a CNC milling machine is machining a precision part. In the early stages of machining, the machine tool runs for a short time, the cumulative cutting amount is small, and the ambient temperature is stable. At this time, the calculated adjustment factor may be close to 1, keeping the dynamic adjustment threshold at a relatively strict level to ensure that even minor anomalies in the high-precision machining process can be detected in a timely manner.

[0078] However, as the machining task continues, the machine tool's operating time gradually increases, the cumulative cutting volume of the tool reaches a certain level, and the ambient temperature may also rise slightly due to prolonged operation. At this point, the system monitors this operating data in real time and calculates an adjustment factor slightly greater than 1 based on a preset model (e.g., a machine learning model trained on historical data or an empirical formula). This adjustment factor is applied to the original dynamic adjustment threshold, slightly relaxing it to obtain an adaptive threshold. For example, if the original dynamic adjustment threshold is 0.05 and the adjustment factor is 1.1, the new adaptive threshold becomes 0.055. When the deviation between sensor data is compared with this new adaptive threshold, even if the deviation increases slightly (this could be due to normal fluctuations caused by slight tool wear or minor thermal deformation of the equipment), as long as it does not exceed 0.055, it will not be misjudged as abnormal. Conversely, if the deviation suddenly increases significantly, for example, reaching 0.08, it will still exceed the adaptive threshold, thus being accurately judged as a logical inconsistency and triggering an alarm. In this way, the solution proposed in this application can intelligently adjust the criteria for anomaly judgment based on the actual "health" status and working environment of the machine tool equipment, making the detection results more consistent with the actual situation and improving the intelligence level and reliability of the system.

[0079] In one possible design, step S254142 includes: S2541421. Identify the current machining data of the machine tool equipment, wherein the machining data includes the equipment model, the material type of the workpiece to be processed, and the type of cutting tool currently being used; In this embodiment, the system automatically acquires relevant information about the machining task currently being performed by the machine tool, such as the specific model of the machine tool, the type of material used in the workpiece (e.g., stainless steel, aluminum alloy, composite materials), and the type of cutting tool currently in use (e.g., milling cutter, drill bit, turning tool). This machining data is a key factor affecting the physical behavior of the machine tool and the characteristics of sensor data.

[0080] S2541422. Based on the identified processing data, retrieve the corresponding nonlinear mapping function set and weight parameter set from the preset parameter influence library; In this embodiment, the system maintains a database containing a large number of predefined functions and weight parameters, i.e., a parameter influence library. When a specific combination of equipment model, material type, and tool type is identified, the system can match and extract the most suitable set of nonlinear mapping functions and weight parameters for the current working condition from this parameter influence library. These functions and parameters are pre-established based on a large amount of historical data, experimental results, or expert knowledge, and are used to describe the complex nonlinear relationship between operating data and adjustment factors under different processing conditions.

[0081] S2541423. For the running data, apply the corresponding functions in the set of nonlinear mapping functions to perform feature transformation; In this embodiment, the corresponding functions in the set of nonlinear mapping functions are applied to the running data for feature transformation. For example, if the running data includes running time, number of processed workpieces, cumulative cutting amount of the tool and ambient temperature change trend, one or more preset nonlinear functions (such as polynomial function, exponential function, logarithmic function, sigmoid function, etc.) will be applied to transform each type of running data in order to better capture its nonlinear influence on the adjustment factor and map it to a unified feature space.

[0082] S2541424. The running data after feature transformation is combined with the weight parameter set for weighted fusion. In this embodiment, the various operational data features, after nonlinear transformation, are assigned different weights based on their importance under the current machining conditions, and then combined linearly or nonlinearly. For example, in the finishing stage, the weight of the cumulative cutting amount may be higher, while in the roughing stage, the weight of the spindle load may be higher. Through weighted fusion, the influence of various operational data on the adjustment factor is comprehensively considered, ultimately forming a more comprehensive and accurate overall evaluation.

[0083] S2541425. The weighted fusion result is used as an adjustment factor for the preset dynamic adjustment threshold; In this embodiment, a correction coefficient that can accurately reflect the current operating status and processing conditions of the machine tool is provided. This coefficient is used to dynamically adjust the threshold for determining the logical consistency of sensor data, so that the threshold can adapt to different processing scenarios and improve the accuracy and robustness of the determination.

[0084] In the technical solution of the above embodiments, by introducing the identification of processing data and combining it with the nonlinear mapping function set and weight parameter set in the preset parameter influence library, the obtained adjustment factor can more accurately correct the dynamic adjustment threshold, thereby improving the reliability of the sensor data logic consistency judgment. Specifically, identifying processing data enables the system to customize the calculation logic of the adjustment factor according to the current specific processing task (equipment model, material, tool), avoiding the simple "one-size-fits-all" calculation method; by retrieving the nonlinear mapping function set and weight parameter set that match the current processing data from the parameter influence library, it is ensured that the subsequent feature transformation and weighted fusion process can accurately reflect the real impact of various operating data on the adjustment factor under the current working condition; the use of the nonlinear mapping function set enables the effective capture of complex nonlinear relationships in the operating data, improving the accuracy of feature expression; finally, these feature-transformed operating data are weighted and fused, and by assigning different weights to different operating data, the calculation of the adjustment factor is further refined, enabling it to more comprehensively and accurately reflect the actual operating status of the machine tool equipment.

[0085] In one possible design, step S2541425 includes: S25414251. Real-time monitoring of the operating status parameters of machine tool equipment, including spindle load rate, cutting force fluctuation amplitude and temperature gradient of machining area; In this embodiment, key performance indicators of the machine tool are continuously acquired and analyzed during the machining process. These key performance indicators directly reflect the current workload and potential risks of the equipment. Specifically, the spindle load rate is the ratio of the actual output power of the spindle motor to its rated power, reflecting the magnitude of the cutting load; the cutting force fluctuation amplitude refers to the range of changes in the force acting on the tool during the cutting process over a short period of time; drastic fluctuations may indicate tool wear, uneven workpiece material, or machining instability; and the machining area temperature gradient refers to the temperature difference between different locations within the machining area; excessively large temperature gradients may lead to workpiece thermal deformation or tool overheating. Real-time monitoring of these parameters aims to provide a data foundation for identifying extreme operating conditions.

[0086] S25414252. When any parameter in the operating status parameters exceeds the preset extreme operating condition threshold, the safety margin correction mechanism is activated. In this embodiment, the preset extreme operating condition threshold is determined comprehensively based on the machine tool model, processing technology, material characteristics, and historical operating data, and is used to define the boundary between the normal operating range and the abnormal or high-risk operating range. Once a certain operating state parameter (such as spindle load rate) exceeds its corresponding extreme operating condition threshold, it indicates that the machine tool may be in an atypical or high-risk operating state, and at this time, the dynamic adjustment threshold needs to be more carefully corrected.

[0087] S25414253, The safety margin correction mechanism calculates a dynamic safety margin factor based on the degree of deviation of the operating state parameters that exceed the preset extreme operating condition threshold. In this embodiment, the deviation is the difference or ratio between the current operating state parameter value and the extreme operating condition threshold. The greater the deviation, the more extreme the operating condition. The dynamic safety margin factor is a multiplicative factor, typically greater than 1, and increases with the deviation. Its purpose is to increase the dynamic adjustment threshold under extreme operating conditions by increasing the adjustment factor, thereby making the consistency verification of sensor data more rigorous and reducing the risk of misjudgment. For example, when the spindle load rate exceeds the threshold by 10%, the dynamic safety margin factor may be calculated as 1.1; when it exceeds 20%, it may be calculated as 1.2, and so on.

[0088] S25414254. Multiply the weighted fusion result by the dynamic safety margin factor to obtain the corrected adjustment factor; In this embodiment, the multiplication operation enables the original adjustment factor to be amplified according to the actual risk level under extreme operating conditions, thereby generating a more adaptive and safer adjustment factor.

[0089] S25414255, The modified adjustment factor is used as the adjustment factor for the preset dynamic adjustment threshold; In this embodiment, when performing sensor data consistency verification, the dynamically adjusted threshold used will no longer be based solely on the weighted fusion result of conventional operating data, but will further consider the actual risks of machine tool equipment under extreme operating conditions, thereby making the consistency verification more accurate and reliable.

[0090] In the technical solution of the above embodiments, by introducing real-time monitoring of machine tool equipment operating status parameters and a safety margin correction mechanism, the consistency verification of sensor data can maintain higher sensitivity and accuracy when facing abnormal or high-risk operating environments, avoiding false alarms caused by excessively low thresholds or inappropriate thresholds, and improving the robustness and reliability of the machine tool equipment data transmission security method under complex and extreme working conditions.

[0091] In summary, the machine tool equipment data transmission security method provided by this invention pre-configures a virtual model within the machine tool equipment, receives machining instructions, and performs virtual pre-execution to simulate the physical behavior of the machine tool equipment. Based on the virtual pre-execution results, it evaluates the consistency between the pre-execution results and a preset physical behavior benchmark, and determines whether the machining instructions exhibit abnormal behavior based on the evaluation results. If no abnormal behavior is determined, the machine tool equipment executes the instructions accordingly; if abnormal behavior exists, the actual execution of the instructions is blocked, an alarm is issued, and relevant information is recorded. This avoids long-term production quality problems and traceability issues caused by subtle forged instructions, and improves the integrity and authenticity of machine tool equipment data transmission.

[0092] Example 2 Embodiment 2 of the present invention provides a data transmission security system for machine tool equipment. Figure 6 This is a block diagram illustrating a data transmission security system for machine tool equipment according to an exemplary embodiment. For example... Figure 6 As shown, the data transmission security system of this machine tool equipment includes: The virtual pre-execution module 01 is used to receive machining instructions from a pre-configured virtual model within the machine tool and to perform virtual pre-execution of the machining instructions to simulate the physical behavior of the machine tool. The consistency evaluation module 02 is used to evaluate the consistency between the virtual pre-execution results and the preset physical behavior benchmark. The anomaly detection and blocking module 03 is used to determine whether the processing instruction exhibits abnormal behavior based on the evaluation results. If it is determined that the machining instruction does not exhibit any abnormal behavior, the machine tool will actually execute the machining instruction accordingly. If the processing instruction is determined to have abnormal behavior, the actual execution of the processing instruction will be blocked, an alarm will be issued, and relevant information will be recorded.

[0093] The machine tool equipment data transmission security system provided in Embodiment 2 of this invention pre-configures a virtual model within the machine tool equipment, receives machining instructions, and performs virtual pre-execution to simulate the physical behavior of the machine tool equipment. Based on the virtual pre-execution results, it evaluates the consistency between the pre-execution results and a preset physical behavior benchmark, and determines whether the machining instructions exhibit abnormal behavior based on the evaluation results. If no abnormal behavior is determined, the machine tool equipment executes the instructions accordingly; if abnormal behavior exists, the actual execution of the instructions is blocked, an alarm is issued, and relevant information is recorded. This application, by introducing a virtual pre-execution mechanism, elevates the security assessment of instructions from the network level to the physical behavior level. Even minor forged instructions that are insufficient to trigger traditional collision detection or stress overload alarms can be promptly detected through deviations in physical behavior simulated by the virtual model. This avoids long-term production quality problems and traceability issues caused by minor forged instructions, and improves the integrity and authenticity of machine tool equipment data transmission.

[0094] In a possible implementation, the present invention can also be implemented as a program product comprising program code, which, when the program product is run on a terminal device, is used to cause the terminal device to perform the steps of implementing the machine tool equipment data transmission security method in Embodiment 1.

[0095] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0096] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for secure data transmission in machine tool equipment, characterized in that, Includes the following steps: The virtual model pre-configured within the machine tool receives machining instructions and performs virtual pre-execution of the machining instructions to simulate the physical behavior of the machine tool. Based on the virtual pre-execution results, evaluate their consistency with the preset physical behavior benchmark; Based on the evaluation results, determine whether the processing instruction exhibits any abnormal behavior: If it is determined that the machining instruction does not exhibit any abnormal behavior, the machine tool will actually execute the machining instruction accordingly. If the processing instruction is determined to have abnormal behavior, the actual execution of the processing instruction will be blocked, an alarm will be issued, and relevant information will be recorded.

2. The method for secure data transmission in machine tool equipment according to claim 1, characterized in that, The evaluation of the consistency between the virtual pre-execution results and the preset physical behavior benchmark includes: The virtual model receives and stores the complete multi-stage processing instruction sequence of the workpiece to be processed; The current instruction in the processing instruction sequence is virtually pre-executed to simulate the physical behavior of the machine tool on the virtual workpiece; Based on the pre-execution results, the current simulation state of the virtual workpiece is updated, and the current simulation state is used as the initial state for the virtual pre-execution of subsequent instructions; During the virtual pre-execution process, the effects of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece are continuously calculated and accumulated. After each key stage of the processing instruction sequence is completed, the consistency between the cumulative state of the virtual workpiece and the preset final physical behavior benchmark is evaluated.

3. The method for secure data transmission in machine tool equipment according to claim 2, characterized in that, During the virtual pre-execution process, the continuous calculation and accumulation of the influence of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece includes: During virtual pre-execution, the instantaneous temperature distribution and stress state of the current processing area of ​​the virtual workpiece are acquired in real time; Based on the instantaneous temperature distribution and the stress state, the material parameters of the virtual workpiece are dynamically adjusted, wherein the material parameters include constitutive parameters and thermophysical parameters; Based on the adjusted material parameters, calculate the incremental impact of the current command on the virtual workpiece's geometry, surface morphology, and internal stress distribution; The incremental effects are accumulated into the overall state of the virtual workpiece, thereby continuously calculating and accumulating the influence of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece.

4. The method for secure data transmission in machine tool equipment according to claim 2, characterized in that, The step of evaluating the consistency between the cumulative state of the virtual workpiece and the preset final physical behavior benchmark after each key stage of the processing instruction sequence is completed includes: During virtual pre-execution, sensor data from the machine tool equipment is received in real time; Based on the sensor data, the operating parameters and environmental parameters in the virtual model are dynamically updated; Based on the updated operating parameters and environmental parameters, the cumulative effect of the machining instruction sequence on the geometry, surface morphology, or internal stress distribution of the virtual workpiece is calculated. The cumulative effect is compared with a preset final physical behavior benchmark, wherein the final physical behavior benchmark is dynamically adjusted based on the sensor data; Based on the comparison results, it is determined whether there is any abnormal behavior in the processing instruction sequence.

5. The method for secure data transmission in machine tool equipment according to claim 4, characterized in that, The step of comparing the cumulative impact with a preset final physical behavior benchmark, wherein the final physical behavior benchmark is dynamically adjusted based on the sensor data, includes: The sensor data is subjected to consistency verification, which includes: checking the numerical range of the sensor data to ensure that the sensor data is within a preset physical reasonable range; checking the rate of change of the sensor data to ensure that the trend of the sensor data changes in accordance with physical laws; and cross-validating the sensor data from different types of sensors or the same type of sensors at different locations to ensure logical consistency between the sensor data. Once the sensor data passes the consistency check, the key parameters in the final physical behavior benchmark are dynamically adjusted based on the checked sensor data. The cumulative effects are compared with the adjusted final physical behavior benchmark to obtain the comparison results; Based on the comparison results, it is determined whether there is any abnormal behavior in the processing instruction sequence.

6. The method for secure data transmission in machine tool equipment according to claim 5, characterized in that, The cross-validation of data from different types of sensors or sensors of the same type but at different locations to ensure logical consistency between the sensor data includes: Receive data from different types of sensors or sensors of the same type but in different locations; Based on the physical characteristics of the sensor data and the current processing stage, a correlation analysis method is dynamically selected. Specifically, for nonlinear correlations between the sensor data, a nonlinear mapping function or numerical simulation based on a physical model is used to establish the mapping relationship between the sensor data. For time-varying correlations between the sensor data, the weights or parameters of the mapping relationship are adjusted in real time according to the progress of the current processing instruction sequence, the machine tool operating mode, or the virtual workpiece material state. For multimodal correlations between the sensor data, feature extraction and fusion are performed on the sensor data from different physical domains to construct a multidimensional feature vector. The deviation between the sensor data is calculated based on the distance or similarity between the multidimensional feature vectors; The deviation is compared with a preset dynamic adjustment threshold, and based on the comparison result, it is determined whether there is a logical inconsistency in the sensor data.

7. The method for secure data transmission in machine tool equipment according to claim 6, characterized in that, The step of comparing the deviation with a preset dynamic adjustment threshold and determining whether there is a logical inconsistency in the sensor data based on the comparison result includes: Real-time monitoring of machine tool equipment operation data, including: running time, number of processed workpieces, cumulative cutting amount of the tool, and ambient temperature change trend; Based on the operational data, calculate the adjustment factor for the dynamic adjustment threshold; The adjustment factor is applied to the dynamic adjustment threshold to obtain the current adaptive threshold; Based on the comparison result between the deviation and the adaptability threshold, it is determined whether there is a logical inconsistency in the sensor data.

8. The method for secure data transmission in machine tool equipment according to claim 7, characterized in that, The step of calculating the adjustment factor for the dynamic adjustment threshold based on the operational data includes: Identify the current machining data of the machine tool equipment, including the equipment model, the material type of the workpiece to be processed, and the type of cutting tool currently being used; Based on the identified processing data, the corresponding nonlinear mapping function set and weight parameter set are retrieved from the preset parameter influence library; For the running data, feature transformation is performed by applying the corresponding functions in the set of nonlinear mapping functions respectively; The transformed running data is then weighted and fused with the set of weight parameters. The weighted fusion result is used as an adjustment factor for the preset dynamic adjustment threshold.

9. The method for secure data transmission in machine tool equipment according to claim 8, characterized in that, The step of using the weighted fusion result as an adjustment factor for the preset dynamic adjustment threshold includes: Real-time monitoring of machine tool equipment operating status parameters, including spindle load rate, cutting force fluctuation amplitude, and temperature gradient of the machining area; When any of the operating status parameters exceeds the preset extreme operating condition threshold, the safety margin correction mechanism is activated. The safety margin correction mechanism calculates a dynamic safety margin factor based on the degree of deviation of the operating state parameters from the preset extreme operating condition threshold. The weighted fusion result is multiplied by the dynamic safety margin factor to obtain the corrected adjustment factor; The modified adjustment factor is used as the adjustment factor for the preset dynamic adjustment threshold.

10. A data transmission security system for machine tool equipment, characterized in that, The system includes: The virtual pre-execution module is used to receive machining instructions from a pre-configured virtual model within the machine tool and to perform virtual pre-execution of the machining instructions to simulate the physical behavior of the machine tool. The consistency evaluation module is used to evaluate the consistency between the virtual pre-execution results and the preset physical behavior benchmark. The anomaly detection and blocking module is used to determine whether the processing instruction exhibits abnormal behavior based on the evaluation results. If it is determined that the machining instruction does not exhibit any abnormal behavior, the machine tool will actually execute the machining instruction accordingly. If the processing instruction is determined to have abnormal behavior, the actual execution of the processing instruction will be blocked, an alarm will be issued, and relevant information will be recorded.

Images