Intelligent monitoring method and system for numerical control sawing machine

Abstract

The invention relates to the technical field of numerical control sawing machines, and discloses a numerical control sawing machine intelligent monitoring method and system.The method comprises the steps that initial control parameters used for driving a numerical control sawing machine to execute sawing operation are obtained; predicted operation parameters which correspond to the initial control parameters and cause damage to the sawing machine or the workpiece are obtained in advance; and obtaining predictive optimization control parameters for adjusting the sawing operation of the numerical control sawing machine based on the predictive operation parameters in advance. The system corresponds to the method. According to the method, the targeted predicted operation parameters are obtained before the actual operation parameters are generated, the time interval is shortened, the exposure time of the sawing machine in the risk state is remarkably shortened, and the damage probability of the sawing machine and the workpiece is reduced from the source.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of numerical control sawing machine, and particularly relates to a numerical control sawing machine intelligent monitoring method and system. BACKGROUND

[0002] In the technical field of numerical control sawing machine, the traditional monitoring method relies on actual operation parameter feedback adjustment. When the sawing machine performs sawing operation, the control system needs to judge the equipment state based on the real-time collected motor current, saw blade vibration and other operation parameters. However, there is inherent time delay from parameter collection, transmission to analysis and processing, which leads to feedback control lag. For example, when sawing high-hardness alloy materials, the sudden increase of saw blade load may cause fracture, but the traditional system needs to wait for the actual parameter to exceed the limit to trigger adjustment, at which time the damage has occurred.

[0003] To solve the lag problem, the existing technology tries to introduce a prediction model, but it is only used for quality analysis or fault warning. For example, the Chinese patent application file with the application publication number CN119917923A discloses a metal sawing band saw machine intelligent manufacturing process control chart pattern recognition method and system, which can predict the trend of processing quality, but does not use the predicted parameters for early optimization control. In addition, the traditional monitoring system uniformly collects and analyzes all operation parameters, and lacks targeted monitoring of high-risk parameters. For example, the same sampling frequency is used for key parameters such as saw blade tension and motor temperature rise as for conventional parameters, which leads to the inability to respond in time when the risk mutates.

[0004] The above problems lead to the extension of the exposure time of the sawing machine in the risk state, and the high equipment failure rate, so a new numerical control sawing machine intelligent monitoring technical scheme is urgently needed. SUMMARY

[0005] The purpose of the present application is to provide a numerical control sawing machine intelligent monitoring method and system to solve the technical problems proposed in the background.

[0006] To achieve the above purpose, the present application discloses the following technical scheme: In a first aspect, the present application discloses a numerical control sawing machine intelligent monitoring method, which comprises: obtaining initial control parameters, the initial control parameters being used to drive the numerical control sawing machine to perform sawing operation; obtaining predicted operation parameters corresponding to the initial control parameters before actual operation parameters corresponding to the initial control parameters are generated, the time corresponding to the obtaining of the predicted operation parameters being the first time, and the predicted operation parameters being operation parameters leading to damage of the sawing machine or workpiece; Based on the predicted operation parameter, a predicted optimization control parameter is obtained, and a time point at which the predicted optimization control parameter is obtained is a second time point, the predicted optimization control parameter being used to adjust sawing operation of the numerical control sawing machine; wherein a time interval from the first time point to the second time point is less than a time interval from a time point corresponding to the actual operation parameter to a time point corresponding to an actual optimization control parameter obtained based on the actual operation parameter.

[0007] As preferred, the obtaining of the predicted operation parameter corresponding to the initial control parameter comprises: A prediction model is obtained based on historical operation data of the numerical control sawing machine, the prediction model being used to output the predicted operation parameter, and the historical operation data comprising control parameters and working condition information; The initial control parameter and real-time working condition information are input into the prediction model, and the predicted operation parameter is output, the predicted operation parameter corresponding to a parameter type causing damage to the numerical control sawing machine or the workpiece; The predicted operation parameter is subjected to confidence verification, the confidence verification comprising comparing the predicted operation parameter with an operation parameter corresponding to a historical similar working condition, verifying the predicted operation parameter based on a comparison result, and determining that the predicted operation parameter is valid when the verification is passed.

[0008] As preferred, the obtaining of the predicted optimization control parameter based on the predicted operation parameter comprises: A preset safe operation boundary of the numerical control sawing machine and the workpiece is obtained, the numerical control sawing machine comprising a saw blade, and the safe operation boundary at least comprising a maximum bearing tension of the saw blade, a motor allowable load range, and a workpiece machining precision threshold value; The predicted operation parameter determined to be valid and the safe operation boundary are compared, and a control parameter exceeding the safe operation boundary and causing damage to the numerical control sawing machine or the workpiece is optimized; The predicted operation parameter is regressed to be within the safe operation boundary as a target, and the predicted optimization control parameter is obtained.

[0009] As preferred, the method further comprises: A time point corresponding to the predicted operation parameter to a time point corresponding to the actual optimization control parameter is defined as a risk intervention period; The actual operation parameter of the numerical control sawing machine in the risk intervention period is subjected to key monitoring, the key monitoring comprising screening the actual operation parameter in the risk intervention period to obtain a key operation parameter for preferential collection and analysis; The key operation parameter is continuously collected and analyzed to feed back optimization.

[0010] As preferred, the key monitoring comprises screening key operating parameters from actual operating parameters in the risk intervention period for priority collection and analysis, including: performing parameter importance evaluation on the actual operating parameters in the risk intervention period to determine key operating parameters, the parameter importance evaluation being based on impact weight setting of actual operating parameters on sawing quality and equipment wear, the key operating parameters at least including saw blade vibration amplitude and motor current; configuring a preset priority collection and analysis strategy for the key operating parameters, and a preset regular monitoring frequency for non-key parameters.

[0011] As preferred, the key monitoring further comprises damage assessment in the risk intervention period, the damage assessment including: obtaining evaluation data, the evaluation data being obtained by monitoring saw blade wear state, temperature change of equipment key components, and workpiece deformation amount; analyzing damage degree of the sawing machine and the workpiece in the risk intervention period based on the evaluation data to obtain damage assessment results; when the damage assessment results are greater than a damage threshold, triggering an early maintenance prompt.

[0012] As preferred, the damage threshold determination process comprises: obtaining performance degradation data of each key component of the numerical control sawing machine in different damage states during regular maintenance of the numerical control sawing machine, the key components at least including the saw blade and the motor bearing; establishing a correlation between damage degree and equipment remaining life based on the performance degradation data; setting the damage degree corresponding to a preset proportion of the equipment remaining life as the damage threshold, the preset proportion of the equipment remaining life being determined based on the regular maintenance results.

[0013] As preferred, the key monitoring further comprises over-limit pre-control of equipment state parameters, the over-limit pre-control including: obtaining a safety threshold and a warning threshold corresponding to the equipment state parameters, the warning threshold being less than the safety threshold; real-time monitoring the change rate of the equipment state parameters, and when the change rate is greater than a preset acceleration threshold, triggering a first pre-control instruction, the first pre-control instruction including adjusting the feed parameters.

[0014] As preferred, the over-limit pre-control is based on multi-dimensional correlation data, and the over-limit pre-control further includes: the multi-dimensional correlation data at least including motor current, saw blade vibration amplitude, and hydraulic system pressure; establish a parameter correlation model, the parameter correlation model includes a normal logical relationship and a proportional range between different parameters; when any parameter corresponding correlation data violates the normal logical relationship or does not belong to the proportional range, a second pre-control instruction is immediately triggered, and the second pre-control instruction includes suspending saw cutting and recalibrating parameters.

[0015] In a second aspect, the application discloses a numerical control sawing machine intelligent monitoring system, which applies the numerical control sawing machine intelligent monitoring method described above, and the system comprises: an initial control parameter module, configured to acquire initial control parameters, the initial control parameters being used to drive the numerical control sawing machine to perform sawing operations; a predicted running parameter module, configured to acquire predicted running parameters corresponding to the initial control parameters before actual running parameters corresponding to the initial control parameters are generated, the time when the predicted running parameters are acquired being a first time, and the predicted running parameters being running parameters that cause damage to the numerical control sawing machine or a workpiece; a predicted optimized control parameter module, configured to obtain predicted optimized control parameters based on the predicted running parameters, the time when the predicted optimized control parameters are obtained being a second time, and the predicted optimized control parameters being used to adjust sawing operations of the numerical control sawing machine; wherein a time interval from the first time to the second time is less than a time interval from a time corresponding to the actual running parameters to a time corresponding to actual optimized control parameters obtained based on the actual running parameters.

[0016] Beneficial effects: the numerical control sawing machine intelligent monitoring method and system of the application significantly reduce exposure time of the numerical control sawing machine in a risk state by acquiring targeted predicted running parameters before actual running parameters are generated, in combination with shortened time intervals, thereby reducing the probability of damage to the numerical control sawing machine and the workpiece from the source; the prediction model, in combination with historical data and real-time working conditions, ensures prediction reliability through confidence verification, thereby avoiding invalid adjustments; only damage parameters that exceed a safety boundary are optimized, unnecessary interventions are reduced while safety is ensured, and operation continuity is improved; by defining a risk intervention period and implementing key monitoring, key parameters are preferentially collected and analyzed, thereby improving monitoring efficiency and response speed; damage assessment and dynamic damage threshold setting realize equipment state prediction, thereby extending equipment life through early maintenance prompts; out-of-limit pre-control of multi-dimensional correlation data further constructs a safety protection closed loop, thereby comprehensively improving operation safety, stability and sawing precision of the numerical control sawing machine. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only show some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0018] Figure 1 A flowchart of the intelligent monitoring method for a CNC sawing machine provided in an embodiment of the present application; Figure 2 This is a structural block diagram of the intelligent monitoring system for CNC sawing machines provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The following is a clear and complete description of the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] In this document, the term "comprising" is intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0021] In traditional CNC sawing machine monitoring systems, feedback control based on actual operating parameters has inherent time delays, resulting in prolonged exposure of the equipment to risky conditions. To address this issue, the present invention proposes an intelligent monitoring method and system for CNC sawing machines. By obtaining predicted operating parameters before actual operating parameters are generated and shortening the time interval between prediction and optimization, this method enables early intervention in sawing operations, significantly reducing the risk of damage to the sawing machine and workpiece.

[0022] Example 1 like Figure 1 As shown, this embodiment discloses a method for intelligent monitoring of a CNC sawing machine, the method comprising: Initial control parameters are obtained, and the initial control parameters are used to drive the CNC sawing machine to perform sawing operations. In this embodiment, the initial control parameters are set based on the actual sawing operation, and can also be a patterned control parameter combination for a type of workpiece based on existing technology.

[0023] Before the actual operating parameters corresponding to the initial control parameters are generated, the predicted operating parameters corresponding to the initial control parameters are obtained. The moment corresponding to the predicted operating parameters are obtained is the first moment. The predicted operating parameters are the operating parameters that cause damage to the saw machine or the workpiece. In this embodiment, the predicted operating parameters can be but are not limited to operating parameters such as motor current and feed speed that directly cause damage to the saw machine or the workpiece.

[0024] Based on the predicted operating parameter, a predicted optimization control parameter is obtained, and a time point at which the predicted optimization control parameter is obtained is a second time point, and the predicted optimization control parameter is used to adjust sawing operation of the numerical control sawing machine; wherein a time interval from the first time point to the second time point is less than a time interval from a time point corresponding to the actual operating parameter to a time point corresponding to the actual optimization control parameter obtained based on the actual operating parameter.

[0025] In actual application, there is a certain time length from the initial control parameter acquisition time T0→the actual operating parameter generation time T2→the actual optimization control parameter generation time T4, which causes the numerical control sawing machine to be exposed to risk for a long time; in the embodiment, the early intervention is realized through the initial control parameter acquisition time T0→the predicted operating parameter acquisition time T1→the predicted optimization control parameter acquisition time T3; it should be noted that the predicted operating parameter is an operating parameter causing damage to the sawing machine or the workpiece, and the data amount is less than the actual operating parameter, so the time T1 is earlier than the time T2; it can be understood that the predicted optimization control parameter corresponding to the predicted operating parameter also meets the above analysis, so the time T3 is earlier than the time T4; based on the above time advance, the time length corresponding to T1-T3 is less than the time length corresponding to T2-T4, thereby shortening the running time of the numerical control sawing machine in the unoptimized state and reducing the risk of damage.

[0026] The existing prediction model for the numerical control sawing machine generally generalizes all operating parameters related to the numerical control sawing machine, and lacks targeted prediction of high-risk parameters. The embodiment further limits the acquisition process of the predicted operating parameter, realizes one aspect of improving the targeting of the prediction data, and another aspect of shortening the response time length by reducing the amount of prediction data. The prediction model is trained through historical data, only the parameter type that may cause damage is predicted, and the reliability of the prediction result is ensured through confidence verification, thereby improving the safety orientation and response timeliness of the monitoring system.

[0027] Specifically, the predicted operating parameter corresponding to the initial control parameter is obtained, including: The prediction model is obtained based on historical operating data of the numerical control sawing machine, the prediction model is used to output the predicted operating parameter, and the historical operating data includes control parameters and working condition information; in the embodiment, the existing machine learning technology is used to realize the construction of the prediction model, for example, the deep learning technology.

[0028] The initial control parameter and the real-time working condition information are input into the prediction model, and the predicted operating parameter is output, the predicted operating parameter corresponds to the parameter type causing damage to the numerical control sawing machine or the workpiece; based on this, the embodiment realizes the prediction of only the parameter type causing damage to the numerical control sawing machine or the workpiece, realizes one aspect of improving the targeting of the prediction data, and another aspect of shortening the response time length by reducing the amount of prediction data.

[0029] The confidence verification of the predicted operation parameter includes comparing the predicted operation parameter with the operation parameter corresponding to the historical same working condition, verifying the predicted operation parameter based on the comparison result, and determining that the predicted operation parameter is valid when the verification is passed. In the embodiment, the existing confidence analysis technology can be used to compare the predicted operation parameter with the operation parameter corresponding to the historical same working condition. For example, the relationship between the deviation value of the two and the preset deviation value threshold is analyzed to realize the confidence verification.

[0030] The traditional control system often intervenes in all control parameters when the parameters are abnormal, which easily leads to unnecessary shutdown. The embodiment further optimizes the control logic, sets a safe operation boundary, and only optimizes the parameters that exceed the boundary and may cause damage, thereby ensuring the safety of the equipment, reducing invalid adjustment, reducing the amount of data processed for adjustment, improving the continuity of the sawing process and the timeliness of the adjustment response.

[0031] Specifically, the predicted optimization control parameter is obtained based on the predicted operation parameter, including: The preset safe operation boundary of the numerical control sawing machine and the workpiece is obtained, the numerical control sawing machine includes a saw blade, and the safe operation boundary at least includes the maximum bearing tension of the saw blade, the motor allowable load range and the workpiece machining precision threshold. In the embodiment, the safe operation boundary is the experience value corresponding to the maximum bearing tension of the saw blade, the motor allowable load range and the workpiece machining precision threshold known to those skilled in the art.

[0032] The predicted operation parameter and the safe operation boundary are compared to determine the effective predicted operation parameter, and the control parameter that exceeds the safe operation boundary and causes damage to the numerical control sawing machine or the workpiece is optimized. Based on this, the embodiment only optimizes the control parameter that causes damage to the numerical control sawing machine or the workpiece, thereby improving the pertinence of the control parameter optimization on one hand, and shortening the response time by reducing the data amount of the control parameter optimization on the other hand.

[0033] The predicted optimization control parameter is obtained by taking the predicted operation parameter returning to the safe operation boundary as the goal. In the embodiment, the existing review analysis method is used to realize the predicted operation parameter returning to the safe operation boundary.

[0034] The existing numerical control sawing machine monitoring lacks a targeted monitoring strategy for the risk period, resulting in insufficient monitoring of key parameters. The present application defines a risk intervention period and implements focused monitoring of actual operating parameters within this period, prioritizing the collection and analysis of key parameters, enabling accurate identification and rapid response to risks, and effectively shortening the risk processing cycle. It should be noted that the numerical control sawing machine is configured with corresponding regular maintenance in actual application, therefore, the technician has a judgment on the equipment state of the numerical control sawing machine, so from the initial control parameter acquisition time T0 to the predicted operating parameter acquisition time T1 is based on the white box state that can ensure the safe operation of the numerical control sawing machine, but from the predicted operating parameter acquisition time T1 to the time corresponding to the actual optimized control parameter T4, due to the unknown nature of the sawing operation between the numerical control sawing machine and the workpiece, the numerical control sawing machine is essentially in a controlled black box state, based on this phenomenon, in order to ensure the safe operation of the numerical control sawing machine throughout the cycle, it is necessary to implement focused monitoring during the T1 to T4 period.

[0035] Specifically, the method further comprises: The time corresponding to the predicted operating parameter to the time corresponding to the actual optimized control parameter is defined as the risk intervention period.

[0036] Focused monitoring of the actual operating parameters of the numerical control sawing machine during the risk intervention period includes selecting key operating parameters from the actual operating parameters during the risk intervention period for priority collection and analysis.

[0037] Continuously collecting and analyzing key operating parameters to provide feedback for optimization; in this embodiment, feedback optimization can be directed at changes in optimized initial control parameters in this sawing operation, or it can be directed at the optimization of initial control parameter acquisition, that is, the focused monitoring of the risk intervention period provides technical support for improving the monitoring quality of the numerical control sawing machine.

[0038] In actual operating parameter monitoring, traditional methods use uniform collection frequency for all parameters, resulting in key parameter monitoring lag. This embodiment further refines the focused monitoring strategy by selecting key operating parameters such as saw blade vibration amplitude, motor current, and workpiece processing quality through parameter importance evaluation, and configuring a priority collection strategy, significantly improving the timeliness of risk early warning.

[0039] Specifically, focused monitoring includes selecting key operating parameters from actual operating parameters during the risk intervention period for priority collection and analysis, including: The actual operation parameters in the risk intervention period are evaluated for parameter importance to determine the key operation parameters, and the parameter importance evaluation is based on the influence weight setting of the actual operation parameters on the sawing quality and equipment loss, and the key operation parameters at least include the saw blade vibration amplitude and the motor current; in this embodiment, the parameter importance evaluation can be realized based on the experience of parameter importance judgment known to those skilled in the art and existing data processing technology.

[0040] The preset priority collection and analysis strategy is configured for the key operation parameters, and the non-key parameters adopt the preset regular monitoring frequency; in this embodiment, the priority collection and analysis strategy and the regular monitoring frequency can be set based on actual needs, but the priority collection and analysis strategy is more intensive in terms of monitoring frequency than the regular monitoring frequency.

[0041] In the actual operation and maintenance of the numerical control sawing machine, the evaluation of equipment damage mainly depends on the post-detection, and it is difficult to prevent in advance. And when the numerical control sawing machine runs based on the optimized control parameters, the damage caused thereby can be understood as normal loss. Based on the foregoing analysis, we can determine that in the risk intervention period from the acquisition time T1 of the predicted operation parameters to the time T4 corresponding to the actual optimized control parameters, the unknown hesitancy causes more serious damage to the numerical control sawing machine. Therefore, in this embodiment, a dynamic damage evaluation mechanism is introduced in the risk intervention period, the degree of damage is evaluated in real time by monitoring the data such as saw blade wear, component temperature and workpiece deformation, and compared with the dynamic damage threshold, the advance maintenance prompt is realized, and the service life of the equipment is prolonged.

[0042] Specifically, the key monitoring further includes damage evaluation in the risk intervention period, and the damage evaluation includes: The evaluation data are obtained by monitoring the saw blade wear state, the temperature change of the key components of the equipment and the workpiece deformation; The damage degree of the sawing machine and the workpiece in the risk intervention period is analyzed based on the evaluation data, and the damage evaluation result is obtained; when the damage evaluation result is greater than the damage threshold, the advance maintenance prompt is triggered.

[0043] The traditional damage threshold is usually a fixed value, which cannot adapt to the dynamic changes of the numerical control sawing machine. This embodiment further optimizes the determination method of the damage threshold, establishes the correlation between the damage degree and the remaining life of the equipment through the regular maintenance data, dynamically sets the damage threshold, so that the early warning is more suitable for the actual state of the equipment, and the excessive maintenance or insufficient maintenance is avoided.

[0044] Specifically, the determination process of the damage threshold includes: When the numerical control sawing machine is regularly maintained, the performance degradation data of each key component of the numerical control sawing machine in different damage states are obtained, and the key components at least include the saw blade and the motor bearing.

[0045] establishing the correlation between the damage degree and the remaining life of the equipment based on the performance degradation data; in this embodiment, the correlation between the damage degree and the remaining life of the equipment based on the performance degradation data is established by using existing data analysis technology.

[0046] The damage degree corresponding to the preset proportion of the remaining life of the equipment is set as a damage threshold, and the preset proportion of the remaining life of the equipment is determined based on the result of the regular maintenance; based on this, the reasonable assessment of the possible damage of the numerical control sawing machine is realized in combination with the result of the regular maintenance.

[0047] The existing overrun pre-control for the numerical control sawing machine only focuses on the absolute value of the parameter and ignores the change trend. In this embodiment, by monitoring the change rate of the equipment state parameter, the pre-control instruction is triggered in advance before the parameter approaches the safety threshold or the early warning threshold, thereby effectively preventing the equipment damage caused by the overrun of the parameter.

[0048] Specifically, the focus monitoring further includes overrun pre-control of the equipment state parameter, and the overrun pre-control includes: obtaining a safety threshold and a warning threshold corresponding to the preset equipment state parameter, the warning threshold being smaller than the safety threshold; real-time monitoring the change rate of the equipment state parameter, and triggering a first pre-control instruction when the change rate is greater than a preset acceleration threshold, the first pre-control instruction including adjusting the feed parameter.

[0049] The traditional numerical control sawing machine monitoring responds independently to single parameter abnormality, and lacks logical correlation analysis between parameters. This embodiment further proposes a multi-dimensional correlation pre-control mechanism, and by establishing a logical relationship model between parameters such as motor current, saw blade vibration and hydraulic pressure, the pre-control instruction is triggered through correlation verification at the initial stage of parameter abnormality, thereby achieving more comprehensive risk protection.

[0050] Specifically, the overrun pre-control is based on multi-dimensional correlation data, and the overrun pre-control further includes: The multi-dimensional correlation data at least includes motor current, saw blade vibration amplitude and hydraulic system pressure; establishing a parameter correlation model, the parameter correlation model including normal logical relationships and proportional ranges between different parameters; when the correlation data corresponding to any parameter violates the normal logical relationship or is not within the proportional range, a second pre-control instruction is immediately triggered, and the second pre-control instruction includes suspending sawing and recalibrating the parameter.

[0051] The present application also provides a numerical control sawing machine intelligent monitoring system, which combines prediction and optimization control with actual running parameter feedback through modular design, shortens the control time interval, realizes precise intervention in the sawing process, and provides a systematic solution for the safe and efficient operation of the numerical control sawing machine.

[0052] Embodiment two As Figure 2 The embodiment discloses a numerical control sawing machine intelligent monitoring system, which applies the numerical control sawing machine intelligent monitoring method. An initial control parameter module is configured to obtain initial control parameters, which are used to drive the numerical control sawing machine to perform sawing operations. A predicted running parameter module is configured to obtain predicted running parameters corresponding to the initial control parameters before actual running parameters corresponding to the initial control parameters are generated, and the time point for obtaining the predicted running parameters is the first time point. The predicted running parameters are running parameters that cause damage to the sawing machine or the workpiece. A predicted optimization control parameter module is configured to obtain predicted optimization control parameters based on the predicted running parameters, and the time point for obtaining the predicted optimization control parameters is the second time point. The predicted optimization control parameters are used to adjust the sawing operations of the numerical control sawing machine. The time interval from the first time point to the second time point is less than the time interval from the time point corresponding to the actual running parameters to the time point corresponding to the actual optimization control parameters based on the actual running parameters.

[0053] It should be noted that the numerical control sawing machine intelligent monitoring system of the embodiment corresponds to the numerical control sawing machine intelligent monitoring method described above. Therefore, the contents not specifically described in the numerical control sawing machine intelligent monitoring system of the embodiment can be, but are not limited to, function definitions, working principles, and technical effects, and can all refer to the descriptions in the numerical control sawing machine intelligent monitoring method described above. This text will not be repeated here.

[0054] In summary, the numerical control sawing machine intelligent monitoring method and system of the embodiment significantly reduce the exposure time of the sawing machine in the risk state by obtaining the corresponding predicted running parameters before the actual running parameters are generated, in combination with the design of the shortened time interval, thereby reducing the probability of damage to the sawing machine and the workpiece from the source. The prediction model combines historical data and real-time working conditions, and the confidence verification ensures the prediction reliability, thereby avoiding invalid adjustments. Only the damage parameters that exceed the safety boundary are optimized, which reduces unnecessary intervention while ensuring safety and improves the running continuity. By defining the risk intervention period and implementing key monitoring, key parameters are preferentially collected and analyzed, thereby improving the monitoring efficiency and response speed. Damage assessment and dynamic damage threshold setting realize equipment state prediction, thereby extending the service life of the equipment. The out-of-limit pre-control of multi-dimensional associated data further constructs a safety protection closed loop, thereby comprehensively improving the running safety, stability, and sawing precision of the numerical control sawing machine.

[0055] In the embodiments provided by the present application, it should be understood that the embodiments described herein can be realized by hardware, software, firmware, middleware, codes or any proper combination thereof. For hardware implementation, the processor can be realized in one or more of the following components: an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For software implementation, the procedures described herein can be implemented with a computer program that is written in any suitable programming language. The program can be stored in a computer readable storage medium or transmitted as one or more instructions or codes on the computer readable storage medium. The computer readable storage medium includes any storage medium that can be accessed by a computer. The computer readable storage medium can include but is not limited to the following media: a RAM, a ROM, an EEPROM, a CD-ROM or other optical disc storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer.

[0056] Finally, it should be noted that the above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, modifications or equivalent replacements of some technical features described in the foregoing embodiments can be made by those skilled in the art, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for intelligent monitoring of a CNC sawing machine, characterized in that: The method includes: Acquiring initial control parameters, wherein the initial control parameters are used to drive the CNC sawing machine to perform a sawing operation; Before the actual operating parameters corresponding to the initial control parameters are generated, the predicted operating parameters corresponding to the initial control parameters are obtained, the time corresponding to the predicted operating parameters being obtained being the first time, and the predicted operating parameters being the operating parameters that cause damage to the sawing machine or the workpiece; Based on the predicted operating parameters, predicted optimization control parameters are obtained, and the moment when the predicted optimization control parameters are obtained is the second moment. The predicted optimization control parameters are used to adjust the sawing operation of the CNC sawing machine; wherein, the time interval from the first moment to the second moment is less than the time interval from the moment corresponding to the actual operating parameters to the moment corresponding to the actual optimization control parameters obtained based on the actual operating parameters.

2. The intelligent monitoring method for a CNC sawing machine according to claim 1, characterized in that: The obtaining of the predicted operating parameters corresponding to the initial control parameters includes: Obtaining a prediction model based on historical operating data of the CNC sawing machine, wherein the prediction model is used to output the predicted operating parameters, wherein the historical operating data includes control parameters and operating condition information; Inputting the initial control parameters and real-time operating condition information into the prediction model, and outputting the predicted operating parameters, wherein the predicted operating parameters correspond to the parameter types that cause damage to the CNC sawing machine or the workpiece; The predicted operating parameters are subjected to confidence verification, the confidence verification comprising comparing the predicted operating parameters with operating parameters corresponding to similar historical operating conditions, verifying the predicted operating parameters based on the comparison results, and determining that the predicted operating parameters are valid when the verification passes.

3. The intelligent monitoring method for CNC sawing machine according to claim 2, characterized in that: The step of obtaining the predicted optimization control parameters based on the predicted operating parameters includes: Obtaining preset safe operating boundaries of a CNC sawing machine and a workpiece, wherein the CNC sawing machine includes a saw blade, and the safe operating boundaries include at least a maximum tension of the saw blade, an allowable load range of the motor, and a workpiece processing accuracy threshold; Comparing the predicted operating parameters determined to be valid with the safe operating boundaries, and optimizing the control parameters that exceed the safe operating boundaries and cause damage to the CNC sawing machine or the workpiece; The predicted optimization control parameters are obtained with the goal of returning the predicted operating parameters to within the safe operating boundary.

4. The intelligent monitoring method for a CNC sawing machine according to claim 2, characterized in that: The method further includes: The time from the predicted operating parameter to the actual optimized control parameter is defined as a risk intervention period; Implementing focused monitoring on the actual operating parameters of the CNC sawing machine during the risk intervention period, wherein the focused monitoring includes screening the actual operating parameters during the risk intervention period to obtain key operating parameters for priority collection and analysis; Continuously collect and analyze the key operating parameters for feedback optimization.

5. The intelligent monitoring method for a CNC sawing machine according to claim 4, characterized in that: The key monitoring includes screening the actual operating parameters during the risk intervention period to obtain key operating parameters for priority collection and analysis, including: Performing a parameter importance evaluation on actual operating parameters during the risk intervention period to determine key operating parameters, wherein the parameter importance evaluation is based on a weighting of the influence of the actual operating parameters on sawing quality and equipment loss, and the key operating parameters include at least saw blade vibration amplitude and motor current; A preset priority collection and analysis strategy is configured for the key operating parameters, and a preset regular monitoring frequency is used for non-key parameters.

6. The intelligent monitoring method for a CNC sawing machine according to claim 4, characterized in that: The key monitoring also includes conducting damage assessment during the risk intervention period, and the damage assessment includes: Acquiring evaluation data, the evaluation data being obtained by monitoring saw blade wear, temperature changes of key equipment components, and workpiece deformation; The damage degree of the sawing machine and the workpiece during the risk intervention period is analyzed based on the assessment data to obtain a damage assessment result; when the damage assessment result is greater than a damage threshold, an early maintenance prompt is triggered.

7. The intelligent monitoring method for a CNC sawing machine according to claim 6, characterized in that: The process of determining the damage threshold includes: During regular maintenance of the CNC sawing machine, performance degradation data of key components of the CNC sawing machine under different damage states are obtained, wherein the key components include at least the saw blade and the motor bearing; Establishing a correlation between the degree of damage and the remaining life of the equipment based on the performance degradation data; The damage threshold is set as the damage level corresponding to a preset proportion of the remaining life of the equipment, where the preset proportion of the remaining life of the equipment is determined based on the result of the scheduled maintenance.

8. The intelligent monitoring method for a CNC sawing machine according to claim 4, characterized in that: The key monitoring also includes pre-control of equipment status parameters before they exceed the limit, and the pre-control includes: Obtaining a safety threshold and a warning threshold corresponding to a preset device status parameter, wherein the warning threshold is less than the safety threshold; The rate of change of the device status parameter is monitored in real time. When the rate of change is greater than a preset growth rate threshold, a first pre-control instruction is triggered in advance. The first pre-control instruction includes adjusting a feed parameter.

9. The intelligent monitoring method for a CNC sawing machine according to claim 8, characterized in that: The overrun pre-control is performed based on multi-dimensional correlation data, and the overrun pre-control further includes: The multi-dimensional correlation data includes at least motor current, saw blade vibration amplitude and hydraulic system pressure; A parameter association model is established, which includes the normal logical relationship and proportional range between different parameters; when the associated data corresponding to any parameter violates the normal logical relationship or does not fall within the proportional range, a second pre-control instruction is immediately triggered, and the second pre-control instruction includes pausing sawing and recalibrating the parameters.

10. An intelligent monitoring system for a CNC sawing machine, applying the intelligent monitoring method for a CNC sawing machine according to any one of claims 1 to 9, characterized in that: The system includes: An initial control parameter module, used to obtain initial control parameters, wherein the initial control parameters are used to drive the CNC sawing machine to perform sawing operations; a predicted operating parameter module, configured to obtain predicted operating parameters corresponding to the initial control parameters before actual operating parameters corresponding to the initial control parameters are generated, wherein the moment corresponding to the predicted operating parameters being obtained is a first moment, and the predicted operating parameters are operating parameters that cause damage to the sawing machine or the workpiece; A prediction optimization control parameter module is used to obtain the prediction optimization control parameter based on the predicted operating parameter, the moment when the prediction optimization control parameter is obtained is the second moment, and the prediction optimization control parameter is used to adjust the sawing operation of the CNC sawing machine; wherein, the time interval from the first moment to the second moment is less than the time interval from the moment corresponding to the actual operating parameter to the moment corresponding to the actual optimization control parameter obtained based on the actual operating parameter.

Images