A dynamic parameter optimization method in electric discharge machining

Abstract

The application discloses a dynamic parameter optimization method in electric spark machining, and relates to the technical field of electric spark machining, and comprises the following steps: installing a high-frequency acoustic emission sensor on an electric spark machine tool, collecting acoustic emission signals, processing the acoustic emission signals, extracting key features, comparing the key features with preset key feature thresholds, adopting different adjustment strategies according to comparison results, synchronously collecting spindle motor currents, dynamically adjusting the preset key feature thresholds, testing the adjustment strategies according to preset steps, adjusting the preset key feature thresholds and optimizing the adjustment strategies according to test results, and the application establishes the correlation between current changes and acoustic emission signal strengths by synchronously collecting spindle motor currents, and improves the machining efficiency and product quality by testing and optimizing the adjustment strategies under different discharge states, so that the demand of the modern high-end manufacturing field for high-precision and high-efficiency machining is better met.

Description

Technical Field

[0001] The present invention relates to the technical field of electric spark machining, and in particular to a dynamic parameter optimization method in electric spark machining. Background Art

[0002] In recent years, EDM technology, as a special processing method that uses the heat energy generated by pulse discharge to process workpieces, has been widely used in high-end manufacturing fields such as mold manufacturing, aerospace, and precision instruments due to its unique advantages in processing high-hardness, high-toughness and complex-shaped parts. As modern industry's requirements for part processing accuracy, surface quality and production efficiency continue to increase, how to achieve real-time monitoring of the processing process and dynamic parameter optimization has become the key to improving the quality and efficiency of EDM.

[0003] In the existing technology, the adjustment of EDM parameters mostly depends on pre-set fixed parameters, which makes it difficult to respond to different discharge states during the machining process in real time. Although some methods have introduced signal detection means, there are problems with weak anti-interference ability and inaccurate feature extraction in signal processing, resulting in delayed judgment of abnormal discharge and energy shortage. At the same time, the preset threshold is fixed and cannot be dynamically adjusted according to real-time feedback during the machining process, which makes the adjustment strategy less adaptable and prone to untimely or excessive adjustment, thereby affecting machining stability and efficiency, and making it difficult to meet the high-precision and high-efficiency modern machining needs. Summary of the Invention

[0004] The technical problem solved by the present invention is that the adjustment of EDM parameters mostly depends on pre-set fixed parameters, and it is difficult to respond to different discharge states during the machining process in real time. Although some methods have introduced signal detection means, there are problems of weak anti-interference ability and inaccurate feature extraction in signal processing, which leads to delayed judgment of abnormal discharge and energy shortage. At the same time, the preset threshold is fixed and cannot be dynamically adjusted according to real-time feedback during the machining process, which makes the adaptability of the adjustment strategy poor, and it is easy to make untimely or excessive adjustments, which in turn affects the machining stability and efficiency, and it is difficult to meet the high-precision and high-efficiency modern machining needs.

[0005] To solve the above technical problems, the present invention provides the following technical solution: a method for optimizing dynamic parameters in electrospark machining, comprising the following steps:

[0006] Step S1, installing a high-frequency acoustic emission sensor on an electric spark machine tool, and collecting an acoustic emission signal from the high-frequency acoustic emission sensor;

[0007] Step S2, processing the acoustic emission signal and extracting key features of the processed acoustic emission signal;

[0008] Step S3, using a hardware comparator to compare the key feature with a preset key feature threshold, obtaining a comparison result, and adopting different adjustment strategies according to the comparison result;

[0009] Step S4, synchronously collecting the spindle motor current, and dynamically adjusting the preset key feature threshold according to the spindle motor current;

[0010] The dynamically adjusting the preset key feature threshold includes: when the current is detected to increase, the acoustic emission signal is also enhanced, and the preset key feature threshold is increased in real time; when the current is detected to decrease, the acoustic emission signal is also weakened, and the preset key feature threshold is lowered in real time; and the adjusted preset key feature threshold is input into the hardware comparator;

[0011] Step S5: testing the adjustment strategy according to the preset steps, and adjusting the preset key feature threshold and optimizing the adjustment strategy according to the test results.

[0012] As a preferred solution of the dynamic parameter optimization method in electrospark machining according to the present invention, step S1 specifically includes:

[0013] A high-frequency acoustic emission sensor is installed on the electric spark machine tool to capture the position of the sound waves in the cutting process, including the position near the cutting area and the electrode installation point, and collect the acoustic emission signal of the high-frequency acoustic emission sensor. The acoustic emission signal is transmitted to the signal processing module, and the signal processing module is used to process the acoustic emission signal according to the anti-interference ability and input channel.

[0014] As a preferred solution of the dynamic parameter optimization method in electrospark machining according to the present invention, step S2 specifically includes:

[0015] The acoustic emission signal is processed by a signal processing module, and key features of the processed acoustic emission signal are extracted, wherein the key features include signal energy, signal peak intensity, signal duration, and signal rise time.

[0016] As a preferred solution of the dynamic parameter optimization method in electrospark machining according to the present invention, the processing of the acoustic emission signal by the signal processing module specifically includes:

[0017] The acoustic emission signal is filtered through a hardware filter to remove environmental noise and low-frequency interference generated by the operation of the electric spark machine tool itself to obtain a first acoustic emission signal, and a high-frequency signal within a preset frequency range of the first acoustic emission signal is retained to obtain a second acoustic emission signal;

[0018] The second acoustic emission signal is amplified by a hardware amplifier circuit to obtain a third acoustic emission signal.

[0019] As a preferred solution of the dynamic parameter optimization method in electrospark machining according to the present invention, step S3 specifically includes:

[0020] The hardware comparator inside the signal processing module is used to compare the key features with the preset key feature thresholds, which include the energy threshold of the preset signal, the peak intensity threshold of the preset signal, the preset signal duration threshold and the preset signal rise time threshold. The comparison results are obtained, and it is judged based on the comparison results whether the current processing state is abnormal. The abnormal conditions include abnormal discharge, insufficient discharge energy and decreased processing stability. When an abnormal condition occurs, different adjustment strategies are adopted according to different abnormal conditions.

[0021] As a preferred solution of the dynamic parameter optimization method in EDM of the present invention, the step of judging whether an abnormality occurs in the current machining state according to the comparison result specifically includes:

[0022] When the energy of the signal is greater than the energy threshold of the preset signal, abnormal discharge occurs during processing and is judged as an abnormal situation;

[0023] When the peak intensity of the signal is less than the preset signal peak intensity threshold, the spark discharge energy during processing is insufficient and it is judged as an abnormal situation;

[0024] When the signal duration is greater than or less than the preset signal duration threshold, the processing stability decreases and it is judged as an abnormal situation;

[0025] When the signal rise time is greater than or less than the preset signal rise time threshold, the processing stability decreases and it is judged as an abnormal situation.

[0026] As a preferred solution of the dynamic parameter optimization method in electrospark machining according to the present invention, the method of adopting different adjustment strategies according to different abnormal situations specifically includes:

[0027] When abnormal discharge occurs, immediately suspend the spark discharge, reduce the current amplitude and pulse width, increase the servo voltage, and increase the pulse interval;

[0028] When the discharge energy is insufficient, the signal energy is increased, the current amplitude and pulse width are increased, the servo voltage is reduced, and the pulse interval is shortened;

[0029] When the processing stability decreases, the difference between the signal duration and the signal rise time within the preset time is calculated to obtain the signal fluctuation amplitude, and the servo voltage is dynamically adjusted according to the signal fluctuation amplitude. The servo voltage is increased when the signal fluctuation amplitude is large, and the servo voltage is reduced when the signal fluctuation amplitude is small.

[0030] As a preferred solution of the dynamic parameter optimization method in electrospark machining according to the present invention, step S4 specifically includes:

[0031] The spindle motor current is synchronously collected as an indirect feedback signal, and a correlation between the current change and the acoustic emission signal intensity is established through a software algorithm. The preset key feature threshold is dynamically adjusted based on the correlation.

[0032] As a preferred solution of the dynamic parameter optimization method in electrospark machining according to the present invention, step S5 specifically includes:

[0033] The adjustment strategy is tested according to preset steps for different spark discharge states, including open circuit state, normal discharge state, short circuit state and arc discharge state. The preset key feature thresholds and optimized adjustment strategy are adjusted according to the test results.

[0034] As a preferred solution of the dynamic parameter optimization method in EDM of the present invention, the testing of the adjustment strategy according to the preset steps specifically includes:

[0035] Simulate different spark discharge states, collect and record the change trends of the spindle motor current under the different spark states, dynamically adjust the preset key feature threshold according to the recorded current change trend, input the adjusted preset key feature threshold into the hardware comparator, and compare it with the key features collected in real time through the hardware comparator to determine whether different adjustment strategies can be triggered in time according to the adjusted preset key feature threshold in abnormal situations, thereby verifying the effectiveness of dynamically adjusting the preset key feature threshold;

[0036] The verification of the effectiveness of dynamically adjusting the preset key feature threshold includes:

[0037] After adjusting the preset key feature threshold according to the current change trend, if different adjustment strategies can be triggered in time under abnormal conditions, it is determined that the dynamic adjustment of the preset key feature threshold is effective;

[0038] After adjusting the preset key feature threshold according to the current change trend, if different adjustment strategies cannot be triggered in time under abnormal circumstances, it is determined that the dynamic adjustment of the preset key feature threshold is invalid.

[0039] The beneficial effects of the present invention are as follows: the present invention synchronously collects the spindle motor current, establishes the correlation between the current change and the acoustic emission signal intensity, realizes the dynamic adjustment of the preset key feature threshold, breaks the limitation of the traditional fixed threshold, and enables the preset key feature threshold to be adjusted in real time with the processing status, greatly enhancing the adaptability of the adjustment strategy to complex processing environments. By testing and optimizing the adjustment strategy under different discharge states, the reliability and stability of the method are further improved, effectively reducing the impact of abnormal discharge on workpiece precision and electrode loss, improving processing efficiency and product quality, and better meeting the needs of modern high-end manufacturing for high-precision and high-efficiency processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic flow chart of the steps of a method for dynamic parameter optimization in electrospark machining provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0042] Example 1, with reference to Figure 1 , as an embodiment of the present invention, provides a method for dynamic parameter optimization in electrospark machining, comprising the following steps:

[0043] Step S1: Install a high-frequency acoustic emission sensor on an electric spark machine tool and collect acoustic emission signals from the high-frequency acoustic emission sensor.

[0044] Step S2: Process the acoustic emission signal and extract key features of the processed acoustic emission signal.

[0045] In step S3, the key feature is compared with a preset key feature threshold by using a hardware comparator to obtain a comparison result, and different adjustment strategies are adopted according to the comparison result.

[0046] Step S4: synchronously collect the spindle motor current, and dynamically adjust the preset key feature threshold according to the spindle motor current.

[0047] Among them, the dynamic adjustment of the preset key feature threshold includes that when the current is detected to increase, the acoustic emission signal will also be enhanced, and the preset key feature threshold will be increased in real time; when the current is detected to decrease, the acoustic emission signal will also be weakened, and the preset key feature threshold will be lowered in real time, and the adjusted preset key feature threshold will be input into the hardware comparator.

[0048] Step S5: testing the adjustment strategy according to the preset steps, and adjusting the preset key feature threshold and optimizing the adjustment strategy according to the test results.

[0049] Step S1 specifically comprises:

[0050] The high-frequency acoustic emission sensor is installed on the EDM machine tool to capture the positions of the acoustic waves during the cutting process, including positions close to the cutting area and the electrode installation position, and the acoustic emission signals of the high-frequency acoustic emission sensor are collected and transmitted to the signal processing module, which is used to process the acoustic emission signals according to the anti-interference ability and input channels.

[0051] The high-frequency acoustic emission sensor is installed on the EDM machine tool to capture the positions of the acoustic waves during the cutting process, which can maximize the reception of acoustic emission waves generated by the EDM discharge itself and the micro-physical changes it causes, thereby obtaining acoustic emission signals, which are transmitted to the signal processing module for optimization according to different channel characteristics, ensuring that key feature information that truly reflects the processing state is extracted, providing a reliable and pure data basis for subsequent parameter optimization decisions.

[0052] Step S2 specifically comprises:

[0053] The signal processing module is used to process the acoustic emission signals and extract the key features of the processed acoustic emission signals, including the energy of the signal, the peak intensity of the signal, the signal duration, and the signal rise time.

[0054] The energy of the signal reflects the overall intensity of the discharge, the peak intensity of the signal represents the instantaneous maximum amplitude of a single discharge pulse, the signal duration represents the length of a single pulse, and the signal rise time represents the time required for the signal to reach its peak value from the start. These key features can quantify the changes in acoustic emission signals from different dimensions, providing specific and quantifiable basis for subsequent judgment of processing state and identification of abnormal discharge.

[0055] The signal processing module is used to process the acoustic emission signals specifically comprising:

[0056] The acoustic emission signals are filtered through a hardware filter to remove environmental noise and low-frequency interference generated by the EDM machine tool itself, obtaining a first acoustic emission signal, and retaining high-frequency signals within a predetermined frequency range of the first acoustic emission signal to obtain a second acoustic emission signal.

[0057] The second acoustic emission signal is signal-amplified through a hardware amplification circuit to obtain a third acoustic emission signal.

[0058] Through filtering and amplification processing, environmental noise and machine tool low-frequency interference are effectively removed, and high-frequency effective signals representing the discharge process are retained and enhanced, improving signal quality and providing a clearer and more reliable signal basis for subsequent feature extraction and state judgment.

[0059] Step S3 specifically includes:

[0060] The hardware comparator inside the signal processing module is used to compare the key features with the preset key feature thresholds. The preset key feature thresholds include the energy threshold of the preset signal, the peak intensity threshold of the preset signal, the preset signal duration threshold and the preset signal rise time threshold. The comparison results are obtained, and it is judged based on the comparison results whether the current processing state is abnormal. Abnormal conditions include abnormal discharge, insufficient discharge energy and decreased processing stability. When abnormal conditions occur, different adjustment strategies are adopted according to different abnormal conditions.

[0061] By using the hardware comparator inside the signal processing module to compare the key features with the preset key feature threshold, the system can quickly and objectively evaluate the stability of the current discharge process. This comparison result is directly used to determine specific issues such as whether there is abnormal discharge, whether the energy is sufficient, or whether the processing is stable.

[0062] Different adjustment strategies are adopted according to different abnormal situations. Once an abnormal situation is identified, the system can quickly start the preset differentiated adjustment strategy based on the type of abnormality, thereby dynamically adjusting the processing parameters to suppress undesirable conditions and restore stable processing, which greatly improves the adaptability and control accuracy of the processing process.

[0063] Judging whether the current processing state is abnormal based on the comparison results specifically includes:

[0064] When the energy of the signal is greater than the energy threshold of the preset signal, abnormal discharge occurs during processing and is judged as an abnormal situation.

[0065] This judgment is based on the signal characteristics of excessive energy, which usually indicates that the energy of the discharge channel is too high or the discharge is too concentrated, resulting in unnecessary burns and arcing on the electrode or workpiece, and other adverse consequences. Therefore, the system will judge this as an abnormal situation.

[0066] When the peak intensity of the signal is less than the preset signal peak intensity threshold, the electric spark discharge energy during processing is insufficient and it is judged as an abnormal situation.

[0067] This judgment is based on the signal characteristics reflected by the low peak intensity, which usually means that the energy of a single discharge pulse is not strong enough and may not be able to effectively remove material or maintain a stable discharge channel, which in turn leads to low processing efficiency or poor processing surface quality. Therefore, the system will judge this as an abnormal situation.

[0068] When the signal duration is greater than or less than the preset signal duration threshold, the processing stability decreases and it is judged as an abnormal situation.

[0069] A signal duration that is too long may mean that the discharge channel fails to extinguish in time, which can cause overheating or burning of the electrode or workpiece. A signal duration that is too short may indicate that the discharge is too weak or brief, failing to effectively remove the material, which can also disrupt a stable machining process. Both situations indicate that the machining process fails to maintain a stable discharge state, and the system will therefore determine this as an abnormality.

[0070] When the signal rise time is greater than or less than the preset signal rise time threshold, the processing stability decreases and it is judged as an abnormal situation.

[0071] A signal rise time that is too long means that the formation process of the discharge channel is relatively slow or the discharge energy release is not concentrated enough, which will lead to reduced etching efficiency and even unstable discharge. A signal rise time that is too short means that the discharge is triggered too suddenly or the discharge energy is too concentrated in an instant, which will cause impact damage to the electrode and workpiece surface and also disrupt the stable processing process. Therefore, the system will judge this as an abnormal situation.

[0072] According to different abnormal situations, different adjustment strategies are adopted, including:

[0073] When abnormal discharge occurs, immediately stop the spark discharge, reduce the current amplitude and pulse width, increase the servo voltage, and increase the pulse interval.

[0074] The discharge energy is reduced by immediately pausing the discharge, lowering the current amplitude and pulse width, while the servo voltage is increased to make the electrode retract quickly, and the pulse interval is increased to promote deionization, thereby effectively suppressing the persistence and expansion of the abnormality and helping the system to quickly restore a stable processing state.

[0075] When the discharge energy is insufficient, the signal energy is increased, the current amplitude and pulse width are increased, the servo voltage is reduced, and the pulse interval is shortened.

[0076] Increase the current amplitude and pulse width to improve the energy output of each discharge. At the same time, reduce the servo voltage so that the electrode can be closer to the workpiece, increase the stability of the discharge, shorten the pulse interval to increase the discharge frequency, thereby generating more discharge energy per unit time and ensuring the smooth progress of the machining process.

[0077] When the processing stability decreases, the difference between the signal duration and the signal rise time within the preset time is calculated to obtain the signal fluctuation amplitude. The servo voltage is dynamically adjusted according to the signal fluctuation amplitude. The servo voltage is increased when the signal fluctuation amplitude is large, and the servo voltage is reduced when the signal fluctuation amplitude is small.

[0078] Calculate the change difference of the signal duration and the signal rise time within the preset time, determine the initial and final durations and rise times within the preset time, calculate the duration change difference and the rise time change difference, and add these two change differences to obtain the total change difference. The initial duration is the acoustic emission signal measured at the start of the time, the final duration is the acoustic emission signal measured at the end of the time, the initial rise time is the rise time of the acoustic emission signal measured at the start of the time, and the final rise time is the rise time of the acoustic emission signal measured at the end of the time.

[0079] The servo voltage is dynamically adjusted according to the signal fluctuation amplitude. This on-demand adjustment makes the servo response more accurate and timely, effectively balances stability and efficiency, and improves processing quality.

[0080] This method of classification processing and dynamic parameter adjustment enables the system to deal with various processing problems more accurately and effectively, thereby significantly improving the stability, efficiency and final workpiece quality of EDM.

[0081] Step S4 specifically includes:

[0082] The spindle motor current is synchronously collected as an indirect feedback signal, and a correlation between the current change and the acoustic emission signal intensity is established through a software algorithm. The preset key feature threshold is dynamically adjusted based on the correlation.

[0083] A software algorithm establishes a correlation between current changes and acoustic emission signal intensity, providing a quantitative basis for dynamically adjusting the threshold. This enables the system to infer the acoustic emission change trend based on current feedback, thereby intelligently adjusting the threshold and improving the accuracy and reliability of anomaly detection.

[0084] Step S5 specifically includes:

[0085] The adjustment strategy is tested according to preset steps for different spark discharge states, including open circuit state, normal discharge state, short circuit state and arc discharge state. The preset key feature thresholds and optimized adjustment strategy are adjusted according to the test results.

[0086] Adjusting the preset key feature thresholds and optimizing the adjustment strategy based on the test results shows that the preset key feature thresholds and adjustment strategies are not static, but their effectiveness needs to be verified through actual testing. Fine-tuning the thresholds can make them more in line with the characteristics of the actual processing signals and reduce misjudgments. At the same time, optimizing the adjustment strategy can make its response to various discharge states more accurate and efficient. This process ensures that the control system can continue to evolve with test feedback and ultimately achieve better processing state identification and control effects.

[0087] Testing the adjustment strategy according to the preset steps includes:

[0088] Simulate different spark discharge states, collect and record the changing trends of the spindle motor current under different spark states, dynamically adjust the preset key feature threshold according to the recorded current changing trend, input the adjusted preset key feature threshold into the hardware comparator, and compare it with the key features collected in real time through the hardware comparator to determine whether different adjustment strategies can be triggered in time according to the adjusted preset key feature threshold under abnormal circumstances, and verify the effectiveness of dynamically adjusting the preset key feature threshold.

[0089] Verifying the effectiveness of dynamically adjusting preset key feature thresholds includes:

[0090] After adjusting the preset key feature threshold according to the current change trend, if different adjustment strategies can be triggered in time under abnormal circumstances, it is determined that the dynamic adjustment of the preset key feature threshold is effective.

[0091] After adjusting the preset key feature threshold according to the current change trend, if different adjustment strategies cannot be triggered in time under abnormal circumstances, it is determined that the dynamic adjustment of the preset key feature threshold is invalid.

[0092] By simulating different states during the EDM process and collecting motor current data, we dynamically optimize the key feature thresholds. These optimized thresholds are then verified on the hardware comparator to confirm whether these new thresholds enable the comparator to more accurately and quickly trigger the preset adjustment strategy when abnormal discharge is detected. This series of operations is intended to evaluate and confirm the effectiveness of this method of dynamically adjusting thresholds and its practical value in improving the control accuracy of the machining process.

[0093] The present invention synchronously collects the spindle motor current, establishes the correlation between the current change and the acoustic emission signal intensity, realizes the dynamic adjustment of the preset key feature threshold, breaks the limitation of the traditional fixed threshold, and enables the preset key feature threshold to be adjusted in real time with the processing status, greatly enhancing the adaptability of the adjustment strategy to complex processing environments. By testing and optimizing the adjustment strategy under different discharge states, the reliability and stability of the method are further improved, effectively reducing the impact of abnormal discharge on workpiece precision and electrode loss, improving processing efficiency and product quality, and better meeting the needs of modern high-end manufacturing for high-precision and high-efficiency processing.

[0094] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPM), or a combination thereof. , referred to as EEPROM), Erasable Programmable Read Only Memory (Erasable Programmable Read Only Memory, referred to as EPROM), Programmable Read Only Memory ( , referred to as PROM), read-only memory ( , referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A dynamic parameter optimization method in electrospark machining, characterized in that: The following steps are involved: Step S1, installing a high-frequency acoustic emission sensor on an electric spark machine tool, and collecting an acoustic emission signal from the high-frequency acoustic emission sensor; Step S2, processing the acoustic emission signal and extracting key features of the processed acoustic emission signal; Step S3, using a hardware comparator to compare the key feature with a preset key feature threshold, obtaining a comparison result, and adopting different adjustment strategies according to the comparison result; Step S4, synchronously collecting the spindle motor current, and dynamically adjusting the preset key feature threshold according to the spindle motor current; The dynamically adjusting the preset key feature threshold includes: when the current is detected to increase, the acoustic emission signal is also enhanced, and the preset key feature threshold is increased in real time; when the current is detected to decrease, the acoustic emission signal is also weakened, and the preset key feature threshold is lowered in real time; and the adjusted preset key feature threshold is input into the hardware comparator; Step S5: testing the adjustment strategy according to the preset steps, and adjusting the preset key feature threshold and optimizing the adjustment strategy according to the test results.

2. The method for dynamic parameter optimization in electrospark machining according to claim 1, wherein: The step S1 specifically includes: A high-frequency acoustic emission sensor is installed on the electric spark machine tool to capture the position of the sound waves in the cutting process, including the position near the cutting area and the electrode installation point, and collect the acoustic emission signal of the high-frequency acoustic emission sensor. The acoustic emission signal is transmitted to the signal processing module, and the signal processing module is used to process the acoustic emission signal according to the anti-interference ability and input channel.

3. The method for dynamic parameter optimization in electrospark machining according to claim 1, wherein: The step S2 specifically includes: The acoustic emission signal is processed by a signal processing module, and key features of the processed acoustic emission signal are extracted, wherein the key features include signal energy, signal peak intensity, signal duration, and signal rise time.

4. The method for dynamic parameter optimization in electrospark machining according to claim 3, wherein: The processing of the acoustic emission signal by the signal processing module specifically includes: The acoustic emission signal is filtered through a hardware filter to remove environmental noise and low-frequency interference generated by the operation of the electric spark machine tool itself to obtain a first acoustic emission signal, and a high-frequency signal within a preset frequency range of the first acoustic emission signal is retained to obtain a second acoustic emission signal; The second acoustic emission signal is amplified by a hardware amplifier circuit to obtain a third acoustic emission signal.

5. The method for dynamic parameter optimization in electrospark machining according to claim 1, wherein: The step S3 specifically includes: The hardware comparator inside the signal processing module is used to compare the key features with the preset key feature thresholds, which include the energy threshold of the preset signal, the peak intensity threshold of the preset signal, the preset signal duration threshold and the preset signal rise time threshold. The comparison results are obtained, and it is judged based on the comparison results whether the current processing state is abnormal. The abnormal conditions include abnormal discharge, insufficient discharge energy and decreased processing stability. When an abnormal condition occurs, different adjustment strategies are adopted according to different abnormal conditions.

6. The method for dynamic parameter optimization in electrospark machining according to claim 5, wherein: The determining whether the current processing state is abnormal according to the comparison result specifically includes: When the energy of the signal is greater than the energy threshold of the preset signal, abnormal discharge occurs during processing and is judged as an abnormal situation; When the peak intensity of the signal is less than the preset signal peak intensity threshold, the spark discharge energy during processing is insufficient and it is judged as an abnormal situation; When the signal duration is greater than or less than the preset signal duration threshold, the processing stability decreases and it is judged as an abnormal situation; When the signal rise time is greater than or less than the preset signal rise time threshold, the processing stability decreases and it is judged as an abnormal situation.

7. The method for dynamic parameter optimization in electrospark machining according to claim 5, wherein: According to different abnormal situations, different adjustment strategies are adopted, including: When abnormal discharge occurs, immediately suspend the spark discharge, reduce the current amplitude and pulse width, increase the servo voltage, and increase the pulse interval; When the discharge energy is insufficient, the signal energy is increased, the current amplitude and pulse width are increased, the servo voltage is reduced, and the pulse interval is shortened; When the processing stability decreases, the difference between the signal duration and the signal rise time within the preset time is calculated to obtain the signal fluctuation amplitude, and the servo voltage is dynamically adjusted according to the signal fluctuation amplitude. The servo voltage is increased when the signal fluctuation amplitude is large, and the servo voltage is reduced when the signal fluctuation amplitude is small.

8. The method for dynamic parameter optimization in electrospark machining according to claim 1, wherein: The step S4 specifically includes: The spindle motor current is synchronously collected as an indirect feedback signal, and a correlation between the current change and the acoustic emission signal intensity is established through a software algorithm. The preset key feature threshold is dynamically adjusted based on the correlation.

9. The method for dynamic parameter optimization in electrospark machining according to claim 1, wherein: The step S5 specifically includes: The adjustment strategy is tested according to preset steps for different spark discharge states, including open circuit state, normal discharge state, short circuit state and arc discharge state. The preset key feature thresholds and optimized adjustment strategy are adjusted according to the test results.

10. The method for dynamic parameter optimization in electrospark machining according to claim 9, wherein: The testing of the adjustment strategy according to the preset steps specifically includes: Simulate different spark discharge states, collect and record the change trends of the spindle motor current under the different spark discharge states, dynamically adjust the preset key feature threshold according to the recorded current change trend, input the adjusted preset key feature threshold into the hardware comparator, and compare it with the key features collected in real time through the hardware comparator to determine whether different adjustment strategies can be triggered in time according to the adjusted preset key feature threshold under abnormal circumstances, thereby verifying the effectiveness of dynamically adjusting the preset key feature threshold; The verification of the effectiveness of dynamically adjusting the preset key feature threshold includes: After adjusting the preset key feature threshold according to the current change trend, if different adjustment strategies can be triggered in time under abnormal conditions, it is determined that the dynamic adjustment of the preset key feature threshold is effective; After adjusting the preset key feature threshold according to the current change trend, if different adjustment strategies cannot be triggered in time under abnormal circumstances, it is determined that the dynamic adjustment of the preset key feature threshold is invalid.

Images