A kind of penetration detection method, penetration detection device, storage medium and electronic equipment

Abstract

The application provides a kind of penetration detection method, penetration detection device, storage medium and electronic equipment.The method comprises: collecting the voltage signal between electrode and workpiece, current signal and the position signal of electrode in real time during electric spark hole forming processing;According to the current signal between the electrode and the workpiece, the gap discharge state between the electrode and the workpiece is obtained;According to the voltage signal and current signal between the electrode and the workpiece, it is judged whether penetration starts;According to the gap discharge state and the position signal of the electrode, it is judged whether penetration ends.The method can accurately detect the start and end of penetration in electric spark hole forming processing.

Description

Technical Field

[0001] This invention relates to a detection method, and more particularly to a penetration detection method, a penetration detection device, a storage medium, and an electronic device. Background Technology

[0002] Among all components of an aero-engine, the high-pressure turbine blade is the part closest to the combustion chamber outlet and bears the greatest heat load. To reduce its heat load, multiple rows of fine-diameter film cooling holes are typically machined on the blade surface using a hole-making process to assist in heat dissipation. The diameter of the film cooling holes is usually 0.3–0.6 mm, and the depth-to-diameter ratio can reach more than 10, making machining quite difficult. Among various machining methods, electrical discharge machining (EDM) has the advantages of no cutting force, high machining accuracy, good hole surface quality, high machining efficiency, and large hole depth-to-diameter ratio, making it one of the most widely used and mature methods for machining film cooling holes on turbine blades.

[0003] In current electrical discharge machining (EDM) processes, a specified depth is often used. However, due to the complex internal structure and thermal stress during the casting process of turbine blades, there is a certain contour error between the cast blades and the design model. Therefore, in mass production, the depth of the film cooling holes at the same location on each blade of the same model in a batch is not the same. If machining is performed at the specified depth, some holes will be penetrated, while others will be partially penetrated or not penetrated at all, resulting in a large amount of rework. In addition, the size of the back cavity at the outlet of the hole at the same location on the same batch of blades will also vary due to the fluctuations in the casting process of these blades. Since film cooling hole machining cannot allow further damage to the internal structure after penetration, how to reliably detect the penetration of the EDM electrode in real time and stop machining in time to avoid the electrode damaging the inner wall on the other side of the hole outlet and causing internal damage is crucial to the blade machining quality and yield rate, and has become one of the technical problems that technicians in related fields urgently need to solve. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a penetration detection method, penetration detection device, storage medium and electronic device in electrical discharge machining, so as to solve the problem that it is difficult to detect electrode penetration in real time and reliably in the prior art.

[0005] To achieve the above and other related objectives, a first aspect of the present invention provides a penetration detection method in electrical discharge machining (EDM), the method comprising: real-time acquisition of voltage signals, current signals, and electrode position signals between an electrode and a workpiece during EDM; obtaining the gap discharge state between the electrode and the workpiece based on the current signal between the electrode and the workpiece; determining whether penetration has started based on the voltage and current signals between the electrode and the workpiece; and determining whether penetration has ended based on the gap discharge state and the electrode position signal.

[0006] In one embodiment of the first aspect, determining whether penetration has started based on the voltage signal and current signal between the electrode and the workpiece includes: processing the voltage signal between the electrode and the workpiece to obtain voltage spectrum data; processing the current signal between the electrode and the workpiece to obtain current spectrum data; and determining whether penetration has started based on the voltage spectrum data and the current spectrum data.

[0007] In one embodiment of the first aspect, determining whether penetration has ended based on the gap discharge state and the position signal of the electrode includes: determining that penetration has ended when the gap discharge state satisfies a first penetration end feature and the position signal of the electrode satisfies a second penetration end feature; otherwise, determining that penetration has not ended.

[0008] In one embodiment of the first aspect, the method further includes: processing the position signal of the electrode using a trained artificial intelligence classification model to determine whether the position signal of the electrode satisfies the second penetration termination feature.

[0009] In one embodiment of the first aspect, processing the position signal of the electrode using a trained artificial intelligence classification model to determine whether the position signal of the electrode satisfies the second penetration termination feature includes: performing moving window processing on the position signal of the electrode to obtain multiple data frames; and processing the multiple data frames using the artificial intelligence classification model to determine whether the position signal of the electrode satisfies the second penetration termination feature.

[0010] In one embodiment of the first aspect, the training method of the artificial intelligence classification model includes: acquiring hole-making data, the hole-making data including electrode position data of the penetration stage corresponding to one or more holes; marking the hole-making data as pre-penetration data or post-penetration data; and training the artificial intelligence classification model using the marked hole-making data.

[0011] In one embodiment of the first aspect, the gap discharge state includes the discharge rate and / or short-circuit rate between the electrode and the workpiece.

[0012] A second aspect of the present invention provides a penetration detection device for electrical discharge machining (EDM), the device comprising: a data acquisition module for real-time acquisition of voltage signals, current signals, and electrode position signals between the electrode and the workpiece during EDM; a gap discharge state acquisition module for acquiring the gap discharge state between the electrode and the workpiece based on the current signal between the electrode and the workpiece; and a penetration state detection module for determining whether penetration has started based on the voltage and current signals between the electrode and the workpiece, and determining whether penetration has ended based on the gap discharge state and the electrode position signal.

[0013] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the penetration detection method in electrical discharge machining as described in any of the first aspects of the present invention.

[0014] A fourth aspect of the present invention provides an electronic device comprising: a memory storing a computer program; and a processor communicatively connected to the memory, wherein, when the computer program is invoked, the processor executes the penetration detection method in electrical discharge machining as described in any of the first aspects of the present invention.

[0015] As described above, the penetration detection method, penetration detection device, storage medium, and electronic device described in one or more embodiments of the present invention have the following beneficial effects:

[0016] The penetration detection method can comprehensively determine the start and end of penetration based on the voltage signal, current signal and position signal between the collected electrode and the workpiece, and has high accuracy. It can meet the process requirements of air film pore with blades featuring small back gap and complex internal cavity structure.

[0017] Furthermore, in the penetration detection method, current can be used to assist in determining the gap discharge state, thereby enabling a more accurate determination of the penetration end point.

[0018] Furthermore, in the penetration detection method, a recurrent neural network can be used to process the time series of the feed axis position. By introducing the position state of previous moments into the prediction model, the robustness of the model can be effectively improved. Attached Figure Description

[0019] Figure 1 The flowchart shown is a specific embodiment of the penetration detection method described in this invention.

[0020] Figure 2A The diagram shows a detailed flowchart of step S13 in a specific embodiment of the penetration detection method of the present invention.

[0021] Figure 2B The flowchart shown is a process for obtaining the penetration start condition in a specific embodiment of the penetration detection method described in this invention.

[0022] Figure 3A The flowchart shown is a process for training an artificial intelligence classification model in a specific embodiment of the penetration detection method described in this invention.

[0023] Figure 3B The flowchart shown is a process for determining whether the position signal of the electrode satisfies the second penetration termination feature in a specific embodiment of the penetration detection method of the present invention.

[0024] Figure 4 The diagram shown is a structural schematic of the penetration detection device described in this invention in a specific embodiment.

[0025] Figure 5 The diagram shown is a structural schematic of the electronic device described in a specific embodiment of the present invention.

[0026] Component designation explanation

[0027] 400 Penetration Detection Device

[0028] 410 Data Acquisition Module

[0029] 420 Gap Discharge Status Acquisition Module

[0030] 430 Penetration Status Detection Module

[0031] 500 electronic devices

[0032] 510 Memory

[0033] 520 processor

[0034] 530 monitor

[0035] Steps S11 to S14

[0036] Steps S131~S133

[0037] Steps S1331~S1333

[0038] S31a~S33a Steps

[0039] S31b~S32b Steps Detailed Implementation

[0040] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0041] It should be noted that the illustrations provided in the following embodiments are merely schematic representations of the basic concept of the present invention. The illustrations only show components relevant to the present invention and are not drawn according to the actual number, shape, and size of the components in implementation. In actual implementation, the form, quantity, and proportion of each component can be arbitrarily changed, and the component layout may also be more complex. Furthermore, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0042] Furthermore, in this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0043] Due to the complex internal structure and thermal stress during the casting process of turbine blades, there is a certain contour error between the cast blade and the design model. Therefore, the depth of the film cooling hole at the same location is not the same on each blade, and it cannot be machined to a general depth. In addition, the size of the back cavity at the outlet of the hole at the same location on the same batch of blades will also vary depending on the casting state of these blades. This can easily lead to some holes hitting the inner wall of the back cavity while others are not completely drilled through, thus increasing the difficulty of drilling. Therefore, in large-scale batch production, when there are fluctuations in the size and contour of the blade blank itself, how to reliably detect electrode penetration in real time and stop processing in time to avoid electrode damage to the inner wall on the opposite side and causing back damage has become one of the technical problems that need to be solved by technicians in related fields. In particular, for turbine blades, the following technical difficulties exist in the electrode penetration detection process. First, the internal space of the turbine blade is small, leaving very little room for the electrode to penetrate. Second, the angle between the axis of some film cooling holes and the blade surface is particularly small, resulting in a large slope of the hole, making it difficult to accurately determine the position where the film cooling hole is completely drilled through. Third, the discharge state of electric sparks is highly random, and the changes in various signals during penetration are complex and unstable, making it difficult to find robust feature quantities that can accurately, stably and reliably detect the end of penetration.

[0044] To address at least the aforementioned problems, this invention provides a penetration detection method. This method can comprehensively determine the start and end of penetration based on the voltage and current signals between the collected electrode and the workpiece, as well as the electrode's position signal. It exhibits high accuracy and can meet the process requirements of film pore technology for blades with complex internal structures and small back gaps. Furthermore, in this embodiment, current can be used to assist in determining the gap discharge state, thereby enabling more accurate determination of the penetration end point.

[0045] The penetration detection method provided by the present invention will now be described in detail with reference to specific embodiments and accompanying drawings.

[0046] Please see Figure 1 In one embodiment of the present invention, the penetration detection method in the electrical discharge machining process includes the following steps S11 to S14.

[0047] S11, during the electrical discharge machining (EDM) process, the voltage signal, current signal, and electrode position signal between the electrode and the workpiece are acquired in real time. The voltage signal between the electrode and the workpiece can be acquired, for example, using a high-speed voltage acquisition circuit. The current signal between the electrode and the workpiece can be acquired, for example, by converting it into a voltage signal using a Hall sensor. The electrode position signal indicates the electrode position, i.e., the position of the feed axis. In this embodiment, the electrode position signal can be obtained, for example, through the machine tool system.

[0048] S12, the gap discharge state between the electrode and the workpiece is obtained based on the current signal between the electrode and the workpiece. The gap discharge state can be categorized into open-circuit state, normal spark discharge state, stable arc discharge state, and short-circuit state based on the waveform characteristics of the gap pulse voltage and current. Preferably, the gap discharge state obtained in step S12 includes the discharge rate and / or short-circuit rate between the electrode and the workpiece.

[0049] S13 determines whether penetration has started based on the voltage and current signals between the electrode and the workpiece.

[0050] S14, determine whether the penetration has ended based on the discharge state of the gap between the electrode and the workpiece and the position signal of the electrode.

[0051] It should be noted that the labels S11 to S14 above are only used to distinguish different steps, not to restrict the execution order of these steps. In specific applications, the execution order of the above steps can be adjusted according to actual needs. Taking steps S12 and S13 as examples, step S12 can be executed first and then step S13, or step S13 can be executed first and then step S12, or steps S12 and S13 can be executed simultaneously.

[0052] As described above, the penetration detection method provided in this embodiment can comprehensively determine the start and end of penetration based on the voltage signal, current signal, and electrode position signal between the collected electrode and the workpiece. It has high accuracy and can meet the process requirements of film pores in blades with complex internal structures and small back gaps. Furthermore, this penetration detection method can use current to assist in determining the gap discharge state, thereby more accurately determining the penetration end point.

[0053] Please see Figure 2A In one embodiment of the present invention, determining whether penetration has started based on the voltage signal and current signal between the electrode and the workpiece includes the following steps S131 to S133.

[0054] S131, the voltage signal between the electrode and the workpiece is processed to obtain voltage spectrum data. Specifically, in step S131, a frequency domain transformation method can be used to convert the voltage signal between the electrode and the workpiece into voltage spectrum data in a certain frequency domain. In some embodiments, the above conversion can be implemented using existing data processing software, such as LabVIEW.

[0055] S132, the current signal between the electrode and the workpiece is processed to obtain current spectrum data. Specifically, in step S132, a frequency domain transformation method can be used to convert the current signal between the electrode and the workpiece into current spectrum data in a certain frequency domain. In some embodiments, the above conversion can be implemented using existing data processing software, such as LabVIEW.

[0056] S133: Determine whether penetration has started based on voltage spectrum data and current spectrum data. Specifically, penetration start conditions can be pre-configured according to actual needs. When the voltage spectrum data and current spectrum data meet the penetration start conditions, it can be determined that penetration has started.

[0057] Optionally, please refer to Figure 2B In this embodiment, the penetration start condition can be obtained through the following steps S1331 to S1333.

[0058] S1331, acquire multiple penetration start voltage signals and penetration start current signals. The penetration start voltage signal refers to the voltage signal at the penetration start point during the EDM (Electronic Discharge Machining) process, and the penetration start current signal refers to the current signal at the penetration start point during the EDM process. To acquire these penetration start voltage and start voltage signals, in this embodiment, a certain number of EDM experiments can be performed beforehand under certain processing conditions. For any hole 'a' processed in the EDM experiment, the voltage and current signals at the penetration start point can be acquired using sensors during the processing of hole 'a', serving as a penetration start voltage signal and a penetration start current signal, respectively. This method allows for the acquisition of multiple required penetration start voltage and penetration start current signals.

[0059] S1332, acquire the voltage spectrum data corresponding to each penetration start voltage signal and the current spectrum data corresponding to each penetration start current signal. Specifically, in step S1332, a frequency conversion method can be used to convert each penetration start voltage signal into a corresponding voltage spectrum signal and each penetration start current signal into a corresponding current spectrum signal.

[0060] S1333: The penetration start condition is obtained based on the voltage spectrum data corresponding to each penetration start voltage signal and the current spectrum data corresponding to each penetration start current signal. For example, by statistically analyzing the voltage spectrum data corresponding to each penetration start voltage signal, the distribution of the voltage spectrum data can be obtained, and thus a confidence interval for the voltage spectrum data can be obtained. Similarly, by statistically analyzing the current spectrum data corresponding to each penetration start current signal, the distribution of the current spectrum data can be obtained, and thus a confidence interval for the current spectrum data can be obtained. Based on this, in step S133, if the voltage spectrum data obtained in step S131 is within the confidence interval of the aforementioned voltage spectrum data, and the current spectrum data obtained in step S132 is within the confidence interval of the aforementioned current spectrum data, then penetration can be determined to have started.

[0061] It should be noted that the above method for obtaining the penetration start condition is only one feasible way of the present invention, but the present invention is not limited thereto.

[0062] In one embodiment of the present invention, determining whether penetration has ended based on the gap discharge state and the electrode position signal includes: determining that penetration has ended when the gap discharge state meets a first penetration end characteristic and the electrode position signal meets a second penetration end characteristic; otherwise, determining that penetration has not ended. The first penetration end characteristic can be set according to actual needs or experience, or it can be obtained through statistical analysis of the gap discharge state at the penetration end point in multiple EDM drilling experiments under certain processing conditions. The second penetration end characteristic can be set according to actual needs or experience, or it can be obtained through statistical analysis of the electrode position signal at the penetration end point in multiple EDM drilling experiments under certain processing conditions.

[0063] Optionally, the penetration detection method in this embodiment may further include: processing the position signal of the electrode using a trained artificial intelligence classification model to determine whether the position signal of the electrode satisfies the second penetration termination feature.

[0064] Preferably, the artificial intelligence classification model can be a recurrent neural network (RNN) model. A recurrent neural network is a type of recurrent neural network that takes sequential data as input, recursively processes data in the direction of sequence evolution, and connects all nodes (recurrent units) in a chain-like manner. In this embodiment, processing the electrode position signal using a recurrent neural network allows the incorporation of the position state from previous time steps into the model, thereby effectively improving the model's robustness.

[0065] Please see Figure 3A The training method for the artificial intelligence classification model in this embodiment may include the following steps S31a to S33a.

[0066] S31a, acquire hole-making data, which includes electrode position data for the penetration stage corresponding to one or more holes. Specifically, for any hole b, the electrode position data for the penetration stage refers to the electrode position data throughout the entire penetration stage when hole b is machined using electrical discharge machining (EDM). To obtain the above hole-making data, a certain number of EDM experiments can be performed beforehand under specific machining conditions, before training the artificial intelligence classification model. The hole-making data can be obtained by collecting the electrode position data during the EDM experiments.

[0067] S32a, the hole-making data is marked as pre-penetration data or post-penetration data. For example, in step S32, the hole-making data can be marked as pre-penetration data or post-penetration data by manual marking or other methods, but the present invention is not limited thereto.

[0068] S33a, the labeled hole data is used to train the artificial intelligence classification model. The training of this artificial intelligence classification model can be achieved using existing technologies, such as gradient descent and conjugate gradient methods, which will not be elaborated upon here.

[0069] Optionally, in step S32a, marking the perforation data as pre-penetration data or post-penetration data includes: using a moving window function to divide the perforation data into frames of a certain length, and marking these frames as pre-penetration data or post-penetration data. Based on this, in step S33a, the marked frames can be used to train the artificial intelligence classification model.

[0070] Optionally, please refer to Figure 3B In this embodiment, the position signal of the electrode is processed by a trained artificial intelligence classification model to determine whether the position signal of the electrode satisfies the second penetration termination feature, including the following steps S31b and S32b.

[0071] S31b performs moving window processing on the position signal of the electrode to obtain multiple data frames.

[0072] S32b uses an artificial intelligence classification model to process the above multiple data frames to determine whether the position signal of the electrode satisfies the second penetration termination feature.

[0073] In one embodiment of the present invention, before obtaining the gap discharge state between the electrode and the workpiece based on the current signal between the electrode and the workpiece, the penetration detection method may further include: performing signal conditioning on the data acquired in real time in step S11. The data acquired in real time includes the voltage signal, current signal, and electrode position signal acquired in real time between the electrode and the workpiece. Signal conditioning refers to the process of processing the data acquired in real time in step S11 to convert it into a standard signal. This process may include, for example, debouncing, filtering, conversion, voltage reduction, isolation, and other processing.

[0074] In one embodiment of the present invention, after determining that the penetration stage has ended, the penetration detection method may further include: sending a stop processing signal to the electrical discharge machining (EDM) machine tool via an industrial control computer, so that the EDM machine tool stops processing the workpiece. This method can effectively prevent electrode damage to the inner wall of the workpiece on the opposite side.

[0075] The scope of protection of the penetration detection method described in this invention is not limited to the execution order of the steps listed in the above embodiments. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this invention is included within the scope of protection of this invention.

[0076] Based on the above description of the penetration detection method, the present invention also provides a penetration detection device for electrical discharge machining. Figure 4 The diagram shown is a structural schematic of a penetration detection device 400 according to an embodiment of the present invention. Figure 4 As shown, the penetration detection device 400 in this embodiment includes a data acquisition module 410, a gap discharge state acquisition module 420, and a penetration state detection module 430. The data acquisition module 410 is used to acquire, in real time, the voltage signal, current signal, and electrode position signal between the electrode and the workpiece during the electrical discharge machining process. The gap discharge state acquisition module 420 is connected to the data acquisition module 410 and is used to acquire the gap discharge state between the electrode and the workpiece based on the current signal between them. The penetration state detection module 430 is connected to both the data acquisition module 410 and the gap discharge state acquisition module 420 and is used to determine whether penetration has started based on the voltage and current signals between the electrode and the workpiece, and to determine whether penetration has ended based on the gap discharge state and the electrode position signal.

[0077] It should be noted that the modules included in the penetration detection device 400 in this embodiment are respectively related to... Figure 1 Steps S11 to S14 in the penetration detection method shown correspond to each other, and will not be elaborated on here to save space in the manual.

[0078] It should be understood that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the penetration state detection module 430 can be a separate processing element, or it can be integrated into a chip in the above system. Alternatively, it can be stored as program code in the memory of the above system, and its functions can be called and executed by a processing element of the system. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0079] The penetration state detection device provided by the present invention can implement the penetration state detection method described in the present invention. However, the implementation device of the penetration state detection method described in the present invention includes, but is not limited to, the structure of the penetration state detection device listed in this embodiment. All structural modifications and substitutions of the prior art made in accordance with the principles of the present invention are included within the protection scope of the present invention.

[0080] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements... Figure 1 The invention illustrates a penetration detection method in electrical discharge machining (EDM). In this invention, a computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM, ROM, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0081] The present invention also provides an electronic device. Please refer to [link / reference]. Figure 5 The diagram shows a structural schematic of an electronic device 500 according to an embodiment of the present invention. Figure 5As shown, the electronic device 500 in this invention includes a memory 510 and a processor 520. The memory 510 stores a computer program. The processor 520 is communicatively connected to the memory 510, and when the computer program is invoked, it executes the penetration detection method in the electrical discharge machining described in the above embodiments.

[0082] Optionally, the electronic device 500 may also include a display 530, which is communicatively connected to the memory 510 and the processor 520, for displaying the relevant GUI (Graphical User Interface) interactive interface of the penetration detection method.

[0083] Preferably, the processor 520 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0084] In summary, one or more embodiments of the present invention provide a penetration detection method. This penetration detection method can comprehensively determine the start and end of penetration based on the voltage signal, current signal, and electrode position signal acquired in real time between the electrode and the workpiece, exhibiting high accuracy. In some embodiments, the electrode penetration margin measured after using this penetration detection method is less than 0.8 mm, which can meet the process requirements of air film venting with blades featuring small back gaps and complex internal cavity structures. Furthermore, in this penetration detection method, current can be used to assist in determining the gap discharge state, thereby more accurately determining the penetration end point. Further, in some embodiments, a recurrent neural network can be used to process the time series of the feed axis position; by incorporating the position state at previous moments into the prediction model, the robustness of the model can be effectively improved. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has high industrial applicability.

[0085] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A penetration detection method in electrical discharge machining, characterized in that, The method includes: During the electrical discharge machining process, the voltage signal, current signal and electrode position signal between the electrode and the workpiece are collected in real time. The discharge state of the gap between the electrode and the workpiece is obtained based on the current signal between the electrode and the workpiece; Determine whether penetration has begun based on the voltage and current signals between the electrode and the workpiece; Determine whether the penetration has ended based on the gap discharge state and the position signal of the electrode; Determining whether penetration has started based on the voltage and current signals between the electrode and the workpiece includes: processing the voltage signal between the electrode and the workpiece to obtain voltage spectrum data; processing the current signal between the electrode and the workpiece to obtain current spectrum data; if the voltage spectrum data is within the confidence interval of the voltage spectrum data and the current spectrum data is within the confidence interval of the current spectrum data, then it is determined that penetration has started; otherwise, it is determined that penetration has not started. The method for obtaining the confidence intervals of the voltage spectrum data and the current spectrum data includes: acquiring multiple penetration start voltage signals and penetration start current signals; acquiring voltage spectrum data corresponding to each penetration start voltage signal and current spectrum data corresponding to each penetration start current signal; and acquiring the confidence intervals of the voltage spectrum data and the current spectrum data based on the voltage spectrum data corresponding to each penetration start voltage signal and the current spectrum data corresponding to each penetration start current signal. Determining whether penetration has ended based on the gap discharge state and the electrode position signal includes: performing moving window processing on the electrode position signal to obtain multiple data frames; using a trained artificial intelligence classification model to process the multiple data frames to determine whether the electrode position signal meets the second penetration end feature; when the gap discharge state meets the first penetration end feature and the electrode position signal meets the second penetration end feature, penetration is determined to have ended; otherwise, penetration is determined not to have ended.

2. The method according to claim 1, characterized in that, The training method for the artificial intelligence classification model includes: Acquire hole-making data, which includes electrode position data for the penetration stage corresponding to one or more holes; The hole-making data is marked as either pre-penetration data or post-penetration data; The labeled hole-making data is used to train the artificial intelligence classification model.

3. The method according to claim 1, characterized in that, The gap discharge state includes the discharge rate and / or short circuit rate between the electrode and the workpiece.

4. A penetration detection device for electrical discharge machining, characterized in that, The device includes: The data acquisition module is used to acquire voltage signals, current signals, and electrode position signals between the electrode and the workpiece in real time during the electrical discharge machining process. A gap discharge state acquisition module is used to acquire the gap discharge state between the electrode and the workpiece based on the current signal between the electrode and the workpiece. The penetration state detection module is used to determine whether penetration has started based on the voltage and current signals between the electrode and the workpiece, and to determine whether penetration has ended based on the gap discharge state and the position signal of the electrode. The penetration state detection module determines whether penetration has started based on the voltage and current signals between the electrode and the workpiece by: processing the voltage signal between the electrode and the workpiece to obtain voltage spectrum data; processing the current signal between the electrode and the workpiece to obtain current spectrum data; if the voltage spectrum data is within the confidence interval of the voltage spectrum data and the current spectrum data is within the confidence interval of the current spectrum data, then penetration is determined to have started; otherwise, penetration is determined not to have started. The method for obtaining the confidence intervals of the voltage spectrum data and the current spectrum data includes: acquiring multiple penetration start voltage signals and penetration start current signals; acquiring voltage spectrum data corresponding to each penetration start voltage signal and current spectrum data corresponding to each penetration start current signal; and acquiring the confidence intervals of the voltage spectrum data and the current spectrum data based on the voltage spectrum data corresponding to each penetration start voltage signal and the current spectrum data corresponding to each penetration start current signal. Determining whether penetration has ended based on the gap discharge state and the electrode position signal includes: performing moving window processing on the electrode position signal to obtain multiple data frames; using a trained artificial intelligence classification model to process the multiple data frames to determine whether the electrode position signal meets the second penetration end feature; when the gap discharge state meets the first penetration end feature and the electrode position signal meets the second penetration end feature, penetration is determined to have ended; otherwise, penetration is determined not to have ended.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When executed by a processor, the computer program implements the penetration detection method in electrical discharge machining as described in any one of claims 1 to 3.

6. An electronic device, characterized in that, The electronic device includes: A memory that stores a computer program; The processor, which is communicatively connected to the memory, executes the penetration detection method in electrical discharge machining as described in any one of claims 1 to 3 when calling the computer program.

Images