System and method for monitoring an electrical discharge machining process

Abstract

A system for monitoring an electrical discharge machining (EDM) process comprises at least one acoustic unit (9) adapted to be placed at a workpiece (5) to be machined and capturing acoustic emissions during the electrical discharge machining process of the workpiece (5); and at least one computing unit (10) connected to said at least one acoustic unit (9) and adapted to: - process the signals corresponding to the acoustic emissions during the electrical discharge machining process; - compare the processed signals with expected acoustic signals, wherein the expected acoustic signals correspond to a specific machining phase and / or EDM process condition; and - indicate when the difference between the processed signals and the expected acoustic signals for the specific machining phase and / or EDM process condition exceeds a range of tolerance.

Description

System and method for monitoring an electrical discharge machining processDescriptionTECHNICAL FIELD

[0001] The present disclosure concerns a system and a method for monitoring an electrical discharge machining process.BACKGROUND ART

[0002] Electrical discharge machining (EDM) is a metal fabrication process whereby a desired shape is obtained by using electrical discharges.

[0003] The physical principle of electrical discharge machining (EDM) removal is to bring about a series of acoustic emissions, controlled, non- stationary electrical discharges, between an electrode and the workpiece, separated by a dielectric liquid and subject to an electric voltage, causing local micro erosion of the metal.

[0004] EDM has several advantages. It allows machining of complex shapes that would otherwise be difficult to produce with conventional cutting tools. By means of EDM it is possible to machine extremely hard material to very close tolerances and very small work pieces can be machined where conventional cutting tools may damage the part from excess cutting tool pressure.

[0005] As there is no direct contact between tool and workpiece, delicate sections and weak materials can be machined without perceivable distortion. EDM allows obtaining a good surface finish, and very fine holes and tapered holes may be produced. Also, EDM allows to add curves, 3D surfaces, complex geometry, especially in areas inaccessible to traditional machining.

[0006] Different types of EDM are known.

[0007] Sinking EDM consists of an electrode and workpiece submerged in a dielectric liquid. The electrode and workpiece are connected to a suitable power supply. The power supply generates an electrical potential between the two parts. As the electrode approaches the workpiece, dielectric breakdown occurs in the fluid, forming a plasmachannel and a small spark jumps.

[0008] Another type of EDM is known as wire-cut EDM and wire cutting. In this process, a thin single-strand metal wire, usually brass, is fed through the workpiece, submerged in a tank of dielectric fluid, typically deionized water. Wire-cut EDM is typically used to cut plates as thick as 300mm and to make punches, tools, and dies from hard metals that are difficult to machine with other methods. The wire, which is constantly fed from a spool, is held between upper and lower diamond guides which is centered in a water nozzle head. The guides, usually CNC-controlled, move in the x-y plane.

[0009] Since the activities of the EDM technological process take place within a work area where both the electrode and the piece are completely submerged by a dielectric fluid (often contaminated by debris and pollution coming from the eroded material that give a dark color), it is quite difficult to evaluate the correct performance of the process thought a visual assessment.

[0010] Potential process anomalies, such as defects, may lead to an increase of cycle times or cause serious uncontrolled or unintended geometrical issues on the piece, which can be detected only at the end of the process.

[0011] EDM processes are usually monitored by means of sensors which detect process parameters. However, this monitoring is not satisfactory and reliable. The normal value of the process parameters may not correspond to a correct process condition, which may lead to the production of defective process. By means of the known monitoring method, the machining process continues even though the machined product has defects.

[0012] Accordingly, an improved system and method for monitoring an EDM process would be welcomed in the technology. More in general, it would be desirable to provide a more reliable and timely monitoring of the process.

[0013] Another purpose is to allow an intervention during the process as soon as a problem is detected, either to change the parameters or by interrupting the process if necessary.

[0014] Another purpose of the invention is also to maintain stable conditions during the EDM process, increasing quality and reducing costs.SUMMARY

[0015] In one aspect, the subject matter disclosed herein is directed to a system for monitoring an EDM process having the features defined in claim 1.

[0016] The system for monitoring an EDM process comprises at least one acoustic unit adapted to be placed at a workpiece to be machined and capturing acoustic emissions during the electrical discharge machining process of the workpiece and at least one computing unit connected to said at least one acoustic unit. The computing unit is adapted to process the signals corresponding to the acoustic emissions during the electrical discharge machining process, compare the processed signals with expected acoustic signals, wherein the expected acoustic signals correspond to a specific machining phase and / or EDM process condition. Ultimately, the computing unit is adapted to indicate whether the difference between the processed signals and the expected acoustic signals for the specific machining phase and / or EDM process condition exceeds a range of tolerance.

[0017] In another aspect, the subject matter disclosed herein concerns a method for monitoring an EDM process having the features defined in claim 13.

[0018] The method comprises the step of a capturing acoustic emissions during the electrical discharge machining process. The method also provides processing the signals corresponding to the acoustic emissions during the electrical discharge machining process, and comparing the processed signals with expected acoustic signals corresponding to a specific machining phase and / or EDM process condition. Ultimately, the method provides a step of indicating whether the difference between the processed signals and the expected acoustic signals for the specific machining step and / or EDM process condition exceeds a range of tolerance.

[0019] Thanks to the acoustic monitoring it is possible to identify in advance and then to intercept potential anomalies on the production process. Furthermore, the claimed solution offers the possibility of developing adaptive systems capable of optimizing the process parameters in real time with consequent benefits by reducing productionand quality costs.BRIEF DESCRIPTION OF THE DRAWINGS

[0020] A more complete appreciation of the disclosed embodiments of the invention and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein:Fig. 1 illustrates a schematic of a monitoring system in a preferred embodiment of the present invention applied to an EDM apparatus;Fig. 2 illustrates a monitoring system, according to a first embodiment;Fig. 3 illustrates a flowchart of a monitoring method, according to a second embodiment;Fig. 4 illustrates an example of process monitoring in case of errors;Fig. 5 illustrates an example of adaptive machining based on the method of the present invention;Fig. 6 illustrates a monitoring system, according to an embodiment of the present application;Fig. 7 illustrates computing unit, according to an embodiment of the present application;Fig. 8 illustrates computing unit, according to a further embodiment of the present application.DETAILED DESCRIPTION OF EMBODIMENTS

[0021] According to one aspect, the present subject matter is directed to a system for monitoring an Electrical Discharge Machining (EDM).

[0022] Referring now to the drawings, Fig.1 shows schematically a system 1 for monitoring an Electrical Discharge Machining (EDM) process applied to an EDM apparatus 2 in a preferred embodiment of the present invention.

[0023] The EDM apparatus 2 comprises a tank 3 containing a dielectric liquid 4, like a hydrocarbon fluid. A workpiece 5 to be machined is placed in the tank 3. Near the workpiece 5 an electrode 6 is positioned. The electrode 6 is connected to a generator 7. The EDM apparatus 2 comprises a control unit 8 adapted to control the machiningoperations. The control unit 8 is also adapted to control machining parameters, to receive input and provide output concerning the process.

[0024] The system 1 according to the invention comprises at least one acoustic unit 9 adapted to be placed at the workpiece 5 to be machined and capturing acoustic emissions during the electrical discharge machining process of the workpiece 5. The system 1 comprises at least one computing unit 10 connected to said at least one acoustic unit 9 and adapted to process the signals corresponding to the acoustic emissions during the electrical discharge machining process; compare the processed signals with expected acoustic signals, wherein the expected acoustic signals correspond to a specific machining phase and / or EDM process condition; and indicate when the difference between the processed signals and the expected acoustic signals for the specific machining phase and / or process condition exceeds a range of tolerance.

[0025] The acoustic unit 9 preferably comprises at least one acoustic emission sensor. In particular, the acoustic unit 9 comprises at least one microphone 91 and / or at least one hydrophone 92.

[0026] In the embodiment shown in Figure 1, the acoustic unit comprises a microphone 91 and a hydrophone 92.

[0027] The microphone 91 is placed above the dielectric liquid level. Preferably, the microphone 91 is placed at a distance between about 15 cm and about 40cm from the dielectric liquid level. The microphone 91 is placed in the direction of the working area and in a position free from collision.

[0028] The hydrophone 92 is placed in the dielectric liquid. Preferably, the hydrophone 92 is placed at a distance between about 15 cm and about 150 cm from the electrode 6. Advantageously, the hydrophone 92 is placed at a distance between about 5 cm and about 30 cm below the dielectric liquid level. The hydrophone 92 is placed in the direction of the working area and in a position free from collision.

[0029] The acoustic sensors are selected and installed to minimize external noises effects.

[0030] The computing unit 10 is preferably connectable to the apparatus control unit8. The computing unit 10 may be a PC or a tablet. The computing unit 10 is preferably a portable device. For example, the computing unit 10 may comprise a NUC PC programmed to filter digital signals and compress files. The computing unit 10 may comprise or may be connected to an analog to digital converter 11. In some embodiments the analog to digital converter 11 is integrated into the computing unit 10. In some embodiments the analog to digital converter 11 is interposed between with the acoustic unit 9 and the computing unit 10.

[0031] Advantageously, the computing unit 10 is connectable to a user input / output interface 12, for example a tablet or a touch screen.

[0032] In an alternative embodiment, the computing unit may be a program or application which can be integrated or loaded in the apparatus control unit 8. Also data can be uploaded to a central data repository.

[0033] The computing unit 10 allows preferably an on-site edge computing.

[0034] This allows near real time analytics, up to less than 1 minute from a signal input to an operator feedback and / or from a signal input to a processed acoustic signal up to less than 1 minute. For example, when an acoustic emission is over a threshold value, the corresponding process issue detected is shown on a visual device to prompt an action.

[0035] Figure 2 shows schematically the monitoring system 2 according to a preferred embodiment of the invention.

[0036] The acoustic unit 9 detects the acoustic emissions during the EDM process. The acoustic emissions are recorded and then converted into at least one digital file or a digital signal. An analogue to digital converter 11 may for example be used. The digital file is sent to the computing unit 10. The digital file can be elaborated as a computed value, a derived value, and / or processed signals. In some embodiments the analog to digital converter 11 is integrated into the acoustic unit 9.

[0037] The computing unit 10 preferably comprises a Digital Transformation Management Module (DTMM) 20. The DTMM 20 transforms the digital file of the acoustic emission in a digitally transformed signal, such as a computed value, a derivedvalue, and / or a processed signal. The digitally transformed signal is derived into one or more derived digital values, that is assessed against thresholds of the acoustic emissions corresponding to a specific machining phase and / or EDM process condition.

[0038] In a specific embodiment, the DTMM 20 preferably comprises an initial DTMM 13 that transform the digital file of the acoustic emission in the digitally transformed signal, such as a computed value, a derived value, and / or a processed signal. The DTMM 20 can also comprise a Multiple DTMM 14’, 14”, that compares computed value, derived value and / or processed signal and derives one or more derived digital values assessed, e.g. compared, against thresholds of the acoustic emissions corresponding to a specific machining phase and / or EDM process condition. In a specific embodiment, as shown in Figure 7, the Multiple DTMM 14’, 14” can comprise Multiple in-parallel Digital Transformations 14’, specifically iterative Multiple in-Par-allel Digital Transformations. This Multiple DTMM 14’, 14” may run a plurality of iterations to derive a derived digital value, wherein the inputs at each iteration are signals converted by the analog to digital converter 11 and / or previously derived digital values that were compared against a threshold by a comparison module 16, as described below. In a further specific embodiment, as shown in Figure 8, the Multiple DTMM 14’, 14” can be a Multiple in-series Digital Transformations 14”, specifically an iterative Multiple in-series Digital Transformations.

[0039] Other embodiments, not shown in the figures, provide Multiple in-Parallel Digital Transformations 14’ in combination with Multiple in-series Digital Transformations 14”. In this way, digital transformations and other mathematical operations on amplitude and frequency of the digital signals may be split. These operations may be split regardless of the input of the computing unit 10.

[0040] The computing unit 10 preferably processes acoustic emission digital signal corresponding to specific EDM process phases carried out in standard conditions of mechanical machining, e.g., using similar parameters of machining devices for roughing, finishing, and / or polishing. The reference digitally transformed signal, such as a computed value, a derived value, and / or a processed signal advantageously include predefined digitally transformed signals corresponding to at least one specific EDM condition, such as the dielectric purity, the metallization, the mineralization, etc. Thereference digitally transformed signal are preferably stored in a database and / or in the computing unit. The computing unit may retrieve the reference digitally transformed signal from a database.

[0041] The computing unit 10 preferably comprises a signal processing module 14. The signal processing module 14 scans the filtered digitally transformed signals. Advantageously, the signal processing module 14 performs an amplification, in particular a digital amplification, of any signal anomalies.

[0042] Advantageously, the computing unit 10 comprises a machine learning module 15.

[0043] The computing unit 10 comprises a comparison module 16. The comparison module 16 compares the actual signal, in particular the actual frequencies derived from the acoustic emissions of the EDM process, with the expected signal, in particular the expected frequencies. The expected signal may be a stored reference digitally transformed signal corresponding to a specific machining phase and / or EDM process condition. The expected digitally transformed signal may be a digitally transformed signal corresponding to a specific machining phase and / or EDM process condition previously captured during the EDM process. Advantageously, the expected signal or frequency is a predicted digitally transformed signal obtained by processing at least the actual signal or frequency and / or the reference signal or frequency. In a preferred embodiment, the expected digitally transformed signal is a predicted digitally transformed signal obtained by processing at least the actual signal and / or the signal previously captured during the EDM process.

[0044] The computing unit 10 preferably comprises a data communication module 17. The data communication module 17 outputs the result of the comparison. The data communication module 17 preferably comprises a user interface, like a tablet. The result may be graphically visualized. Preferably the data communication module 17 stores the results of the comparison.

[0045] In the preferred embodiment shown in figure 2, the system comprises an input module 18. In the input module 18 the operator enters additional data, for exampleconcerning the process or the workpiece. The input module 18 preferably stores reference data and / or the results of the comparison.

[0046] The machine learning module 15 is preferably interposed between the signal processing module 14 and the comparison module 16. The machine learning module 15 preferably takes into account the data stored or entered in the input module 18. The machine learning module 15 preferably comprises Artificial Intelligence (Al) algorithms. The data stored or entered in the input module 18 are fed back to the machine learning module 15 to confirm whether the prediction was actually true or not, in order to teach the Al algorithms.

[0047] In some embodiments the machine learning module 15 comprises multiple inparallel digital transformations 14’ and / or multiple in-series digital transformations 14”. In a preferred embodiment the machine learning module 15 receives and learns from previously derived digital values that were compared against a threshold by a comparison module 16, derived digital values from a database comprising historical data derived from the acoustic emission of the EDM process, and / or expected digitally transformed signals. The machine learning module 15 may generalize these derived digital values to unseen data to confirm the prediction.

[0048] In particular, the Al algorithms use the operator inputs, the actual signals and the stored digitally transformed signal to obtain the predicted signals. The operator input thus contributes training insights for machine learning.

[0049] Merely for the sake of clarity, machine learning ML can be considered as a sub-set of Artificial Intelligence Al and key components of a ML model are usually:- Data: a large, representative, and clean labelled dataset is crucial. This data is often split into training, validation, and testing sets to prevent bias.- Algorithm: the learning algorithm is the core that detects patterns and makes predictions.- Parameters: these are the internal settings (like weights and biases) of the model that are adjusted during training to improve accuracy.- Loss Function: a function that quantifies the error between the model's predictions and the actual labels in the training data.- Optimization Algorithm: used to adjust the model's parameters to minimizethe loss function and thus improve its performance.

[0050] In particular, training machine learning models involve feeding a machine learning algorithm with a large, labelled dataset to help models learn patterns, make predictions, and adjust its internal parameters to accurately predict and minimize errors. Patterns of interest can exist and be identified within various process and environmental permutations and are therefore adaptive and not measured against a pre-defined / definitive reference.

[0051] Advantageously, new labelled data can be added to the algorithm to further optimize the output predictions for accuracy, quality, new features and minimizing errors within existing or new processes and environmental permutations.

[0052] Labelling data for training of the machine learning model is typically undertaken by “Professionally skilled personnel” (Pre & Post Deployment). The invention allows “machine operators and semi-skilled personnel” to perform data labelling activities in real-time, near-real time or within typical production cycle, in a production environment. This enables the rapid iteration of ML models used in production to be drawn upon insights into a broader knowledge base to further optimize the output predictions for accuracy, quality, new features and minimizing errors within existing or new processes and environmental permutations.

[0053] In other words, the method according to the invention enables machine operators and semi-skilled staff to label data within the production cycle, real-time or near-real-time, directly in the operational environment. This facilitates faster model iteration and improves prediction accuracy, quality, and adaptability to process variations. In such a way, machine learning models are continuously evolving and adaptive to process and environmental variability.

[0054] According to another aspect, the present subject matter is directed to a method for monitoring an Electrical Discharge Machining (EDM).

[0055] The method for monitoring an Electrical Discharge Machining (EDM) comprises:-a capturing step (SI) which comprise capturing acoustic emissions during the electrical discharge machining process;-a processing step (S2) which comprise processing the signals corresponding to the acoustic emissions during the electrical discharge machining process;-a comparison step (S3) which comprise comparing the processed signals with expected acoustic signals corresponding to a specific machining phase and / or EDM process condition;-an output step (S4) which comprise indicating when the difference between the processed signals and the expected acoustic signals for the specific machining step and / or EDM process condition exceeds a range of tolerance.

[0056] In a preferred embodiment, the method comprises the step of determining at least one reference signal corresponding to a specific machining phase and / or EDM process condition.

[0057] The reference signals are predefined signals corresponding to a specific machining phase and / or EDM process condition. The reference signals are preferably stored in a database and / or in a computing unit. In particular, the reference signals are included in at least one program run in the computing unit.

[0058] The method advantageously comprises the step of filtering the signals of the acoustic signals captured during the electrical discharge machining process, so as to derive the signals corresponding to a specific machining phase and / or EDM process condition.

[0059] Preferably, the method comprises a deriving step wherein predicted reference signals are derived by processing at least reference signals which correspond to a specific machining phase and / or EDM process condition; and / or actual acoustic signals captured during the electrical discharge machining process.

[0060] In a preferred embodiment, the expected acoustic signal is an acoustic signal corresponding to the acoustic emissions previously captured during the electrical discharge machining process.

[0061] The deriving step advantageously comprises processing operator input data to derive the predicted acoustic signals.

[0062] According to an advantageous embodiment, the comparison step and / or the deriving step comprises artificial intelligence (Al) algorithms.

[0063] According to a preferred embodiment of the invention, the system and method is applied to a sinking electrical discharge machining process.

[0064] An advantageous application of the method according to the present invention is the machining of products having repetitive features, in particular the machining of an impeller, for example a centrifugal compressor impeller. In fact the cavities of the impeller have a repetitive pattern and the monitoring system can easily detect anomalies in the pattern.

[0065] The monitoring method is carried out in particular for machining phases like roughing or polishing (finishing).

[0066] Figure 4 shows an example of the method applied when two errors occur. In the example a “dielectric purity” error and a “metallization” error are considered.

[0067] The dielectric purity error relates to the build-up of small metal particles in the dielectric liquid due to the machining of the workpiece.

[0068] The metallization error relates to the build-up of material on the electrode.

[0069] The computing unit may derive quantum of predicted values over time against a threshold.

[0070] Figure 5 shows a further step of the method according to a preferred embodiment of the invention.

[0071] The method comprises the step of changing at least one process parameter according to the result of the output step.

[0072] The acoustic emission is compared to a standard range of frequency for a specific condition.

[0073] For example, metallization relates to the condition of the tool. The digitally transformed signals corresponding to a normal metallization should be comprised in a tolerance range.

[0074] If the digitally transformed signal values derived during the process exceed the tolerance range, measures are taken on the tool to overcome the problem, for example improving flushing, filtering, or prompting the operator for action to remove the material build up on the electrode.

[0075] Dielectric purity relates to the condition of the liquid. The digitally transformed signals corresponding to the operation in a standard purity condition of the dielectric liquid should be comprised in a tolerance range.

[0076] If the digitally transformed signal values derived during the process exceed the tolerance range, measures are taken to overcome the problem, for example a filtering system is activated.

[0077] The tolerance range may be defined starting from predefined digitally transformed signals, e.g., stored in a database and / or in a computing unit, or it may be defined starting from digitally transformed signals of acoustic emissions previously captured during the electrical discharge machining process.

[0078] This allows a real time monitoring of the process.

[0079] Another condition which can be monitored relate to the electrode mineralization. Mineralization destroys graphite tool. In the production of impellers, mineralization creates “pitting” inside the cavities of the impeller. The pitting generated in parts of the product causes an acoustic emission which is different from the one of a nondefective product.

[0080] The monitoring system and method according to the invention offers the possibility of developing adaptive systems capable of optimizing the process parameters in real time with consequent benefits by reducing production and quality costs.

[0081] The monitoring system and method according to the invention can be adaptive to process variability by continuously changing electrical signal due to 3-dimentionalmachining process involving a tool shape and tool path where electrical discharge varies against changing work surface area and geometry.

[0082] Again, the monitoring system and method according to the invention can be adaptive to environmental variability. Influences of environmental variability may comprise dialectic condition, tool wear, debris from machining, foreign objects within machining area and directed dialectic flow (flushing).

[0083] Acoustic monitoring thus allows intervention during the process also to parameters which do not directly relate to the machining, but which influence the quality of the final product.

[0084] In other words, with the usual monitoring of the machining process it is possible to change the machining parameters according to the machining operations, but it is not possible to consider other parameters like liquid purity or tool wear, so that the process could in principle be carried out under standard machining conditions, but the final product would be defective. In order to consider additional conditions, it would be possible to use specific sensors, which however imply a more complex and less reliable structure.

[0085] On the contrary, by means of the acoustic monitoring, it is sufficient to use an acoustic sensor unit to derive all necessary parameters related to the process conditions. The correct operation of the acoustic sensor can be easily checked at the beginning, so that the reliability of monitoring results is enhanced.

[0086] While aspects of the invention have been described in terms of various specific embodiments, it will be apparent to those of ordinary skill in the art that many modifications, changes, and omissions are possible without departing form the spirt and scope of the claims. In addition, unless specified otherwise herein, the order or sequence of any process or method steps may be varied or re-sequenced according to alternative embodiments.

[0087] Reference has been made in detail to embodiments of the disclosure, one or more examples of which are illustrated in the drawings. Each example is provided by way of explanation of the disclosure, not limitation of the disclosure. In fact, it will be apparent to those skilled in the art that various modifications and variations can bemade in the present disclosure without departing from the scope or spirit of the disclosure. Reference throughout the specification to "one embodiment" or "an embodiment" or “some embodiments” means that the particular feature, structure or characteristic described in connection with an embodiment is included in at least one embodiment of the subject matter disclosed. Thus, the appearance of the phrase "in one embodiment" or "in an embodiment" or "in some embodiments" in various places throughout the specification is not necessarily referring to the same embodiment(s). Further, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments.

[0088] When elements of various embodiments are introduced, the articles “a”, “an”, “the”, and “said” are intended to mean that there are one or more of the elements. The terms “comprising”, “including”, and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements.

[0089] The subject matter described herein can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structural means disclosed in this specification and structural equivalents thereof, or in combinations of them. The subject matter described herein can be implemented as one or more computer program products, such as one or more computer programs tangibly embodied in an information carrier (e.g., in a machine-readable storage device), or embodied in a propagated signal, for execution by, or to control the operation of, data processing apparatus (e.g., a programmable processor, a computer, or multiple computers). A computer program (also known as a program, software, software application, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file. A program can be stored in a portion of a file that holds other programs or data, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.

[0090] The processes and logic nows described in this specification, including the method steps of the subject matter described herein, can be performed by one or more programmable processors executing one or more computer programs to perform functions of the subject matter described herein by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus of the subject matter described herein can be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0091] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory, or a random access memory, or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. Information carriers suitable for embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, (e.g., EPROM, EEPROM, and flash memory devices); magnetic disks, (e.g., internal hard disks or removable disks); magneto-optical disks; and optical disks (e.g., CD and DVD disks). The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0092] To provide for interaction with a user, the subject matter described herein can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to the user and a keyboard and a pointing device, (e.g., a mouse or a trackball), by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well. For example, feedback provided to the user can be any form of sensory feedback, (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0093] The techniques described herein can be implemented using one or more modules. As used herein, the term “module” refers to computing software, firmware, hardware, and / or various combinations thereof. At a minimum, however, modules are not to be interpreted as software that is not implemented on hardware, firmware, or recorded on a non-transitory processor readable recordable storage medium (i.e., modules are not software per se). Indeed “module” is to be interpreted to always include at least some physical, non-transitory hardware such as a part of a processor or computer. Two different modules can share the same physical hardware (e.g., two different modules can use the same processor and network interface). The modules described herein can be combined, integrated, separated, and / or duplicated to support various applications. Also, a function described herein as being performed at a particular module can be performed at one or more other modules and / or by one or more other devices instead of or in addition to the function performed at the particular module. Further, the modules can be implemented across multiple devices and / or other components local or remote to one another. Additionally, the modules can be moved from one device and added to another device, and / or can be included in both devices.

[0094] The subj ect matter described herein can be implemented in a computing system that includes a back-end component (e.g., a data server), a middleware component (e.g., an application server), or a front-end component (e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the subject matter described herein), or any combination of such back-end, middleware, and front-end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), e.g., the Internet.

Claims

System and method for monitoring an electrical discharge machining process CLAIMS1. A system for monitoring an electrical discharge machining (EDM) process comprising:at least one acoustic unit (9) adapted to be placed at a workpiece (5) to be machined and capturing acoustic emissions during the electrical discharge machining process of the workpiece (5); andat least one computing unit (10) connected to said at least one acoustic unit (9), wherein the computing unit (10) comprises a machine learning module (15) and is adapted to:- process the signals corresponding to the captured acoustic emissions to obtain actual acoustic signals;- derive, by means of the machine learning module (15), predicted acoustic signals corresponding to a specific machining phase and / or electrical discharge machining (EDM) process condition;- compare the actual acoustic signals with the predicted acoustic signals; and - indicate when the difference between the actual acoustic signals and the predicted acoustic signals exceeds a range of tolerance.

2. The system according to claim 1, wherein the acoustic unit (9) comprises at least one microphone (91) and / or at least one hydrophone (92).

3. The system according to claim 1 or 2, comprising an input / output interface (12) connected to the computing unit (10).

4. The system according to any one of the preceding claims, further comprising at least one analog to digital converter (11) in connection with the acoustic unit (9) and / or the computing unit (10).

5. The system according the preceding claim, wherein the at least one analog to digital converter (11) is interposed between the acoustic unit (9) and the computing unit (10).

6. The system according to any one of the preceding claims, wherein the computing unit (10) is adapted to be connected to an electric discharge machining apparatus (1).

7. The system according to any one of the preceding claims, wherein the computing unit (10) is adapted to store at least one reference acoustic signal corresponding to a specific machining phase and / or electrical discharge machining (EDM) process condition.

8. The system according to any one of the preceding claims, wherein the computing unit (10) comprises a digital transformation signal management module (20) adapted to filter digitally transformed signals of the captured acoustic emissions.

9. The system according to the preceding claim, wherein the computing unit (10) comprises a signal processing module (14) adapted to scan the filtered digitally transformed signals.

10. The system according to any one of the preceding claims, wherein the computing unit (10) comprises a machine learning module (15) adapted to:- receive input from an operator;- process reference acoustic signals, wherein the at least one reference acoustic signal is a predefined signal corresponding to a specific machining phase and / or electrical discharge machining (EDM) process condition and / or process actual acoustic signals corresponding to acoustic emissions captured during the electrical discharge machining process of the workpiece;- derive predicted acoustic signals, wherein the predicted acoustic signals correspond to the specific machining phase and / or electrical discharge machining (EDM) process condition.

11. The system according to any one of the preceding claims, wherein the expected acoustic signal is a reference predefined acoustic signal corresponding to a specific machining phase and / or electrical discharge machining (EDM) process con-dition or a predicted acoustic signal derived by processing the actual signals corresponding to the acoustic emissions during the electrical discharge machining process.

12. The system according to any one of the preceding claims 1- 10, wherein the expected acoustic signal is an acoustic signal corresponding to the acoustic emissions previously captured during the electrical discharge machining process.

13. A method for monitoring an electrical discharge machining (EDM) process comprising:- a capturing step (SI) which comprise capturing acoustic emissions during the electrical discharge machining process;-a processing step (S2) which comprise processing the signals corresponding to the acoustic emissions during the electrical discharge machining process;-a comparison step (S3) which comprise comparing the processed signals with expected acoustic signals corresponding to a specific machining phase and / or EDM process condition;-an output step (S4) which comprise indicating when the difference between the processed signals and the expected acoustic signals for the specific machining step and / or electrical discharge machining (EDM) process condition exceeds a range of tolerance.

14. The method according to the preceding claim, comprising a step of determining at least one reference acoustic signal corresponding to a specific machining phase and / or electrical discharge machining (EDM) process condition.

15. The method according to any one of the preceding claims 13 -14, comprising a step of filtering digitally transformed signals of the acoustic signals captured during the electrical discharge machining process.

16. The method according to any one of the preceding claims 13 -15, comprising a deriving step wherein predicted acoustic signals are derived by processing at least:-reference acoustic signals which are predefined acoustic signals corresponding to a specific machining phase and / or electrical discharge machining (EDM) process condition; and / or-actual acoustic signals captured during the electrical discharge machining process.

17. The method according to the preceding claim, wherein the deriving step comprises processing operator input data to derive the predicted acoustic signals.

18. The method according to any one of the preceding claims 16-17, wherein the comparison step and / or the deriving step comprises artificial intelligence (Al) algorithms.

19. The method according to any one of the preceding claims 13-18, comprising the step of changing at least one process parameter according to the result of the output step.

20. The method according to any one of the preceding claims 13-19, wherein the electrical discharge machining process is a sinking electrical discharge machining process.

21. The method according to any one of the preceding claims 13-19, wherein the electrical discharge machining process is a wire-cut electrical discharge machining process.

22. The method according to any one of the preceding claims 13-21, wherein the workpiece is an impeller.

23. The method according to any one of the preceding claims 13-22, wherein the machining phases comprise at least roughing and / or polishing.

24. The method according to any one of the preceding claims 13-23, wherein the process conditions comprise at least the dielectric purity and / or metallization-21-and / or electrode mineralization.-22-

Images