Prediction method and device for electric spark discharge machining time, equipment and medium

Abstract

The invention discloses a prediction method, device, equipment and medium for electric spark discharge machining time, and relates to the field of electric spark discharge intelligent machining.The method comprises the steps that a simulation model of a to-be-machined workpiece is obtained, simulation machining treatment is conducted on the simulation model of the to-be-machined workpiece, and a residual body of the to-be-machined workpiece is obtained; performing solid treatment on the residual body of the to-be-processed workpiece to obtain a convergence body of the to-be-processed workpiece; at least one discharge electrode is arranged on the convergence body of the to-be-machined workpiece, and the discharge removal volume of the discharge treatment of all the discharge electrodes on the to-be-machined workpiece is calculated; and according to the discharge removal volume, the electric spark discharge machining time is determined. According to the method, the discharge removal volume of the discharge treatment of the to-be-machined workpiece can be calculated through software analogue simulation machining, and the discharge machining time of the workpiece can be evaluated more accurately.

Description

Technical Field

[0001] The present invention relates to the field of intelligent EDM machining, and particularly to a method, device, equipment and medium for predicting the machining time of EDM. Background Art

[0002] Currently, when the prior art estimates the machining time of EDM for a workpiece to be machined, it usually estimates the machining time of EDM by using the discharge area and depth. This method cannot accurately estimate the actual machining time of EDM, and has strong randomness and low effectiveness. Summary of the Invention

[0003] Embodiments of the present invention provide a method, device, equipment and medium for predicting the machining time of EDM to solve the problem of low prediction accuracy of the existing machining time of EDM.

[0004] In one embodiment, a method for predicting the machining time of EDM is provided, including: Obtaining a simulation model of a workpiece to be machined, performing simulated machining on the simulation model of the workpiece to be machined, and obtaining a residue of the workpiece to be machined; Performing a solidification process on the residue of the workpiece to be machined to obtain a convergence body of the workpiece to be machined; Setting at least one discharge electrode on the convergence body of the workpiece to be machined, and calculating the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined; Determining the machining time of EDM according to the discharge removal volume.

[0005] In one embodiment, performing a solidification process on the residue of the workpiece to be machined to obtain a convergence body of the workpiece to be machined includes: Invoking a UG function module to process the residue of the workpiece to be machined into a convergence body of the workpiece to be machined.

[0006] In one embodiment, the calculating the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined includes: Determining a first volume of the convergence body when the workpiece to be machined is not subjected to discharge treatment, and a second volume of the convergence body after the workpiece to be machined is subjected to discharge treatment by using the discharge electrode, calculating a difference between the first volume and the second volume, and obtaining the discharge removal volume.

[0007] In one embodiment, determining the machining time of EDM according to the discharge removal volume includes: Obtaining a workpiece discharge feature and an electrode discharge feature that are relevant to the machining time of EDM of the workpiece to be machined, where the electrode discharge feature includes the discharge removal volume; Determine the EDM processing time based on the workpiece discharge characteristics, electrode discharge characteristics, and in combination with the EDM processing time prediction model used to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics.

[0008] In one embodiment, the steps for determining the EDM processing time prediction model used to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics include: Set the workpiece discharge coefficient of the workpiece discharge characteristics and the electrode discharge coefficient of the electrode discharge characteristics, and construct an EDM processing time prediction model based on the workpiece discharge characteristics, the workpiece discharge coefficient, the electrode discharge characteristics, the electrode discharge coefficient, and the estimated discharge time; Obtain the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM processing time of the machined workpieces, and train the EDM processing time prediction model based on the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM processing time to obtain the initial model of the processing time prediction with optimized workpiece discharge coefficient and electrode discharge coefficient.

[0009] In one embodiment, the steps for determining the EDM processing time prediction model used to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics include: Set the workpiece discharge coefficient of the workpiece discharge characteristics and the electrode discharge coefficient of the electrode discharge characteristics, and construct an EDM processing time prediction model based on the workpiece discharge characteristics, the workpiece discharge coefficient, the electrode discharge characteristics, the electrode discharge coefficient, and the estimated discharge time; Obtain the historical workpiece discharge characteristics and historical electrode discharge characteristics of the machined workpieces, input the historical workpiece discharge characteristics and historical electrode discharge characteristics into the trained neural network model of the EDM processing time, output the historical EDM processing time, and train the EDM processing time prediction model based on the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM processing time to obtain the optimized model of the processing time prediction with optimized workpiece discharge coefficient and electrode discharge coefficient.

[0010] In one embodiment, training the EDM processing time prediction model based on the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM processing time includes: Set the initial value of the workpiece discharge coefficient and the initial value of the electrode discharge coefficient, input the historical workpiece discharge characteristics and the historical electrode discharge characteristics into the electric discharge machining time prediction model to obtain the predicted value of the electric discharge machining time, calculate the machining time deviation value between the predicted value of the electric discharge machining time and the historical electric discharge machining time, and iteratively update the workpiece discharge coefficient and the electrode discharge coefficient according to the machining time deviation value to obtain the optimized time prediction and backtracking model of the workpiece discharge coefficient and the electrode discharge coefficient.

[0011] In one embodiment, a prediction device for the electric discharge machining time is provided, including: A simulation machining module, configured to obtain a simulation model of a workpiece to be machined, perform simulation machining on the simulation model of the workpiece to be machined, and obtain the remaining body of the workpiece to be machined; A solid processing module, configured to perform solid processing on the remaining body of the workpiece to be machined to obtain the converged body of the workpiece to be machined; An electrode setting and volume calculation module, configured to set at least one discharge electrode on the converged body of the workpiece to be machined, and calculate the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined; A machining time calculation module, configured to determine the electric discharge machining time according to the discharge removal volume.

[0012] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned prediction method for the electric discharge machining time is implemented.

[0013] In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned prediction method for the electric discharge machining time is implemented.

[0014] The above-mentioned prediction method, device, equipment and medium for the electric discharge machining time obtain the remaining body of the workpiece to be machined by performing simulation machining on the simulation model of the workpiece to be machined; perform solid processing on the remaining body of the workpiece to be machined to obtain the converged body of the workpiece to be machined; set at least one discharge electrode on the converged body of the workpiece to be machined, and calculate the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined; determine the electric discharge machining time according to the discharge removal volume. The present invention can calculate the discharge removal volume of discharging the workpiece to be machined through software simulation, and can more accurately evaluate the electric discharge machining time of the workpiece. Description of the Drawings

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a schematic diagram of an application environment of a prediction method for the working hours of electrical discharge machining in an embodiment of the present invention; Figure 2 It is a flowchart of a prediction method for the working hours of electrical discharge machining in an embodiment of the present invention; Figure 3 It is a schematic diagram of arranging a discharge electrode on a convergence body in an embodiment of the present invention; Figure 4 It is a schematic diagram of determining the discharge removal volume of a workpiece to be processed for discharge treatment in an embodiment of the present invention; Figure 5 It is a schematic diagram of a prediction device for the working hours of electrical discharge machining in an embodiment of the present invention; Figure 6 It is a schematic diagram of a computer device in an embodiment of the present invention. Detailed implementation manners

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0018] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results of theory, methods, technologies, and application systems.

[0019] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0020] The prediction method for the working hours of electric discharge machining provided by the embodiments of the present invention can be applied in the application environment as Figure 1 shown. Specifically, this prediction method is applied in a prediction system for the working hours of electric discharge machining. The prediction system includes a client and a server as Figure 1 shown. The client communicates with the server through a network to achieve accurate prediction of the working hours of electric discharge machining. Among them, the client, also known as the user side, refers to a program that provides local services for clients corresponding to the server. The client can be installed on, but not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. For example, it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0021] In one embodiment, as Figure 2 shown, a prediction method for the working hours of electric discharge machining is provided. Taking the server in Figure 1 as an example, the method includes the following steps: S201. Obtain the simulation model of the workpiece to be machined, and perform simulation machining on the simulation model of the workpiece to be machined to obtain the residue of the workpiece to be machined; Among them, the tool path simulation of the simulation model of the workpiece to be machined can be carried out by using a 3D drawing file containing the workpiece to be machined and the electrode, combined with the programming program of the programming software, to simulate the machining process and obtain the residue of the workpiece to be machined. In this step, the residue refers to the part of the workpiece that is not machined in place or cannot be machined by CNC machining (computer numerical control precision machining). This remaining part needs to be discharged by the electrode to machine it out.

[0022] S202. Solidify the residue of the workpiece to be machined to obtain the convergent body of the workpiece to be machined; Among them, since the residue of the workpiece to be machined exists in the form of a small flat body with a hollow in the middle during the simulation process, which is a thin-sheet form of the model body with a hollow in the middle, the volume of the residue cannot be directly calculated. In order to facilitate the calculation of the discharge removal volume in the subsequent steps, the residue needs to be processed into a solid convergent body.

[0023] S203. Set at least one discharge electrode on the convergent body of the workpiece to be machined, and calculate the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined; Among them, the set positions and the set numbers of the electrodes of the workpiece to be processed can be different. Therefore, for the converged body of a certain workpiece to be processed obtained in the foregoing steps, one or more discharge electrodes need to be set on the converged body. As Figure 3 shown, according to the converged body marked as the discharge electrode, determine the discharge removal volume for the discharge treatment of the workpiece to be processed. As Figure 4 shown.

[0024] S204. Determine the EDM processing time according to the discharge removal volume.

[0025] Among them, after determining the discharge removal volume for the discharge treatment of the workpiece to be processed, the EDM processing time can be determined by combining other workpiece discharge characteristics and electrode discharge characteristics. For example, the workpiece discharge characteristics can include the surface area of the workpiece to be processed and the discharge removal volume of the workpiece to be processed, and the electrode discharge characteristics can include the electrode discharge removal volume and the discharge area of the discharge electrode.

[0026] Among them, the discharge removal volume of the workpiece to be processed refers to the volume V that the entire workpiece to be processed needs to be subjected to discharge treatment, while the electrode discharge removal volume is only the volume V1 that the current electrode performs discharge machining on the current workpiece to be processed, and V > V1.

[0027] In this step, the EDM processing time can be determined by inputting the workpiece discharge characteristics and electrode discharge characteristics containing the discharge removal volume into the trained neural network model of the EDM processing time.

[0028] The prediction method of the EDM processing time in this embodiment obtains the residual body of the workpiece to be processed by performing simulation machining on the simulation model of the workpiece to be processed; performs solid processing on the residual body of the workpiece to be processed to obtain the converged body of the workpiece to be processed; sets at least one discharge electrode on the converged body of the workpiece to be processed, and calculates the discharge removal volume of all the discharge electrodes for the discharge treatment of the workpiece to be processed; determines the EDM processing time according to the discharge removal volume. The present invention can calculate the discharge removal volume for the discharge treatment of the workpiece to be processed through software simulation, and can more accurately evaluate the EDM processing time of the workpiece.

[0029] In one embodiment, performing solid processing on the residual body of the workpiece to be processed to obtain the converged body of the workpiece to be processed includes: Invoking the UG function module to process the residual body of the workpiece to be processed into the converged body of the workpiece to be processed.

[0030] Among them, by invoking the Manufacturing (Machining) function module of the UG software, the residual body of the workpiece to be processed can be processed to obtain a solid converged body.

[0031] In one embodiment, calculating the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined includes: Determining a first volume of the converging body when the workpiece to be machined has not been subjected to discharge treatment, and a second volume of the converging body after the discharge treatment of the workpiece to be machined is completed using the discharge electrode, and calculating the difference between the first volume and the second volume to obtain the discharge removal volume.

[0032] Among them, the first volume is the volume of the converging body calculated after the converging body is formed on the workpiece to be machined in step S202 above, and the second volume is the volume of the converging body after all the discharge treatments on the workpiece to be machined in Figure 4 are completed. Boolean operation is used to find the intersection of the two to obtain the discharge removal volume.

[0033] In one embodiment, determining the EDM processing time according to the discharge removal volume includes: S301, obtaining workpiece discharge characteristics and electrode discharge characteristics that are relevant to the EDM processing time of the workpiece to be machined, where the workpiece discharge characteristics include the discharge removal volume; S302, determining the EDM processing time according to the workpiece discharge characteristics and electrode discharge characteristics, in combination with an EDM processing time prediction model used to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics.

[0034] Among them, the workpiece discharge characteristics refer to the characteristics of the workpiece to be machined, such as area, volume, material, etc., that can directly affect the discharge efficiency, energy distribution, and discharge stability during EDM; the electrode discharge characteristics refer to the characteristics of the position of the electrode relative to the workpiece, the shape and size of the electrode discharge marks, etc., that can directly affect the distribution of heat and current, current transmission efficiency, and discharge stability during EDM.

[0035] In this embodiment, the EDM processing time prediction model can be a non-linear regression model established to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics.

[0036] The prediction method for the working hours of electric discharge machining in this embodiment takes into account that the workpiece discharge characteristics of different workpiece materials and the electrode discharge characteristics of different electrode materials may have different effects on the workpiece discharge time. Therefore, by fully considering the relationship between the estimated discharge time, workpiece discharge characteristics, and electrode discharge characteristics, a workpiece discharge time prediction model based on different discharge characteristic parameters is used to estimate the discharge time of workpieces to be machined with different materials, so that the prediction result of the final discharge time is more accurate, can be closer to the actual discharge time, and reduce the prediction error; it solves the problem that the existing workpiece discharge time prediction model is difficult to be applicable to all types of workpieces and electrode materials, and the unsuitable prediction model will cause a deviation between the estimated discharge time and the actual situation, resulting in unstable workpiece processing quality.

[0037] In one embodiment, the determining steps of the electric discharge machining working hours prediction model for characterizing the relationship between the estimated discharge time, workpiece discharge characteristics, and electrode discharge characteristics include: S401, set the workpiece discharge coefficient of the workpiece discharge characteristics and the electrode discharge coefficient of the electrode discharge characteristics, and construct an electric discharge machining working hours prediction model according to the workpiece discharge characteristics, the workpiece discharge coefficient, the electrode discharge characteristics, the electrode discharge coefficient, and the estimated discharge time; S402, obtain the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical electric discharge machining working hours of the machined workpieces, and train the electric discharge machining working hours prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical electric discharge machining working hours to obtain the optimized workpiece discharge coefficient and electrode discharge coefficient.

[0038] Among them, the electric discharge machining working hours prediction model is: the product of the workpiece discharge characteristics and the workpiece discharge coefficient, plus the product of the electrode discharge characteristics and the electrode discharge coefficient, to obtain the electric discharge machining working hours. The workpiece discharge coefficient and the electrode discharge coefficient are unknowns to be solved. By substituting the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical electric discharge machining working hours into the electric discharge machining working hours prediction model, the workpiece discharge coefficient and the electrode discharge coefficient can be calculated.

[0039] In one embodiment, the determining steps of the electric discharge machining working hours prediction model for characterizing the relationship between the estimated discharge time, workpiece discharge characteristics, and electrode discharge characteristics include: S501, set the workpiece discharge coefficient of the workpiece discharge characteristics and the electrode discharge coefficient of the electrode discharge characteristics, and construct an electric discharge machining working hours prediction model according to the workpiece discharge characteristics, the workpiece discharge coefficient, the electrode discharge characteristics, the electrode discharge coefficient, and the estimated discharge time; S502. Obtain the historical workpiece discharge characteristics and historical electrode discharge characteristics of the machined workpiece, input the historical workpiece discharge characteristics and the historical electrode discharge characteristics into the trained neural network model for EDM processing time based on artificial intelligence to output the historical EDM processing time, and train the discharge processing time prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM processing time to obtain the workpiece discharge coefficient and electrode discharge coefficient with optimized parameters.

[0040] Among them, the discharge processing time prediction model is: the product of the workpiece discharge characteristics and the workpiece discharge coefficient, plus the product of the electrode discharge characteristics and the electrode discharge coefficient, to obtain the EDM processing time. The workpiece discharge coefficient and the electrode discharge coefficient are unknowns to be solved. By substituting the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM processing time output by the neural network model into the discharge processing time prediction model, the workpiece discharge coefficient and the electrode discharge coefficient can be calculated.

[0041] Illustrate with an example. The expression of the discharge processing time prediction model is as follows: Among them, T is the predicted EDM processing time, is the overall weight coefficient for reflecting the overall influencing factors of the workpiece discharge characteristics and the electrode discharge characteristics, is the surface area of the machined workpiece, is the discharge area of the discharge electrode, is the discharge depth of the discharge electrode, is the gap between the discharge electrode and the machined workpiece, is the volume of the machined workpiece, is the volume of the workpiece to be machined removed by each discharge of the discharge electrode (discharge removal volume), is the weight coefficient corresponding to the surface area of the machined workpiece, is the weight coefficient corresponding to the discharge area of the discharge electrode, is the weight coefficient corresponding to the volume of the machined workpiece, is the weight coefficient corresponding to the volume of the workpiece to be machined removed by each discharge of the discharge electrode, is the weight coefficient corresponding to the discharge depth of the discharge electrode, is the weight coefficient corresponding to the gap between the discharge electrode and the machined workpiece. Among them, 、 belong to the workpiece discharge characteristics, 、 、 belong to the electrode discharge characteristics.

[0042] In one embodiment, training the EDM machining time prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM machining time includes: Set the initial value of the workpiece discharge coefficient and the initial value of the electrode discharge coefficient. Input the historical workpiece discharge characteristics and the historical electrode discharge characteristics into the EDM machining time prediction model to obtain the predicted value of the EDM machining time. Calculate the machining time deviation value between the predicted value of the EDM machining time and the historical EDM machining time. Iteratively update the workpiece discharge coefficient and the electrode discharge coefficient according to the machining time deviation value to obtain the workpiece discharge coefficient and the electrode discharge coefficient with optimized parameters.

[0043] Wherein, after iteratively updating the workpiece discharge coefficient and the electrode discharge coefficient according to the machining time deviation value to obtain the workpiece discharge coefficient and the electrode discharge coefficient with optimized parameters, use the workpiece discharge coefficient and the electrode discharge coefficient with optimized parameters as known values, and input them into the EDM machining time prediction model again in combination with the historical workpiece discharge characteristics and the historical electrode discharge characteristics to obtain the updated predicted value of the EDM machining time. Calculate the updated machining time deviation value again, and determine whether the updated machining time deviation value is within the preset deviation range. If it is within the preset deviation range, output the workpiece discharge coefficient and the electrode discharge coefficient updated this time; if it is not within the preset deviation range, update the workpiece discharge coefficient and the electrode discharge coefficient again, and repeat the above process until the updated machining time deviation value calculated again is within the preset deviation range.

[0044] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0045] In one embodiment, a prediction device for EDM machining time is provided. The prediction device for EDM machining time corresponds one-to-one to the prediction method for EDM machining time in the above embodiment. As Figure 5 shown, the prediction device includes a simulation machining module 31, a solid processing module 32, an electrode setting and volume calculation module 33, and a machining time calculation module 34. The detailed description of each functional module is as follows: The simulation machining module 31 is used to obtain the simulation model of the workpiece to be machined, and perform simulation machining on the simulation model of the workpiece to be machined to obtain the residual body of the workpiece to be machined; The solid processing module 32 is used to perform solid processing on the residual body of the workpiece to be machined to obtain the convergent body of the workpiece to be machined; A volume calculation module 33, configured to set at least one discharge electrode on the convergent body of the workpiece to be machined, and calculate the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined; A man-hour calculation module 34, configured to determine the EDM man-hours according to the discharge removal volume.

[0046] In one embodiment, the solid processing module 32 includes: A calling sub-module, configured to call the UG function module to process the residual body of the workpiece to be machined into the convergent body of the workpiece to be machined.

[0047] In one embodiment, the volume calculation module 33 includes: A volume calculation sub-module, configured to determine a first volume of the convergent body when the workpiece to be machined is not subjected to discharge processing, and a second volume of the convergent body after the workpiece to be machined is subjected to discharge processing by using all the discharge electrodes, calculate a difference between the first volume and the second volume, and obtain the discharge removal volume.

[0048] A volume verification sub-module, configured to verify whether the sum of the discharge removal volumes before and after the workpiece to be machined undergoes the discharge process is equal to the sum of the discharge removal volumes of all the electrodes for separately discharging the workpiece to be machined.

[0049] In one embodiment, the man-hour calculation module 34 includes: A feature extraction sub-module, configured to obtain workpiece discharge features and electrode discharge features that are relevant to the EDM man-hours of the workpiece to be machined, where the electrode discharge features include the discharge removal volume; A prediction sub-module, configured to determine the EDM man-hours according to the workpiece discharge features and the electrode discharge features, in combination with an EDM man-hour prediction model that characterizes the relationship between the estimated discharge time and the workpiece discharge features and the electrode discharge features.

[0050] In one embodiment, the steps for determining the EDM man-hour prediction model that characterizes the relationship between the estimated discharge time and the workpiece discharge features and the electrode discharge features include: Set a workpiece discharge coefficient for the workpiece discharge features and an electrode discharge coefficient for the electrode discharge features, and construct an EDM man-hour prediction model according to the workpiece discharge features, the workpiece discharge coefficient, the electrode discharge features, the electrode discharge coefficient, and the estimated discharge time; Obtain the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM processing time of the processed workpiece, and train the EDM processing time prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM processing time to obtain an initial working hour prediction model with optimized workpiece discharge coefficient and electrode discharge coefficient.

[0051] In one embodiment, the determining step of the EDM processing time prediction model for characterizing the relationship between the estimated discharge time, workpiece discharge characteristics, and electrode discharge characteristics includes: Set the workpiece discharge coefficient of the workpiece discharge characteristics and the electrode discharge coefficient of the electrode discharge characteristics, and construct an EDM processing time prediction model according to the workpiece discharge characteristics, the workpiece discharge coefficient, the electrode discharge characteristics, the electrode discharge coefficient, and the estimated discharge time; Obtain the historical workpiece discharge characteristics and historical electrode discharge characteristics of the processed workpiece, input the historical workpiece discharge characteristics and the historical electrode discharge characteristics into the trained neural network model of EDM processing time, output the historical EDM processing time, and train the EDM processing time prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM processing time to obtain an optimized working hour prediction model with optimized workpiece discharge coefficient and electrode discharge coefficient.

[0052] In one embodiment, training the EDM processing time prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM processing time includes Set the initial values of the workpiece discharge coefficient and the electrode discharge coefficient, input the historical workpiece discharge characteristics and the historical electrode discharge characteristics into the EDM processing time prediction model to obtain the predicted value of EDM processing time, calculate the processing time deviation value between the predicted value of EDM processing time and the historical EDM processing time, and iteratively update the workpiece discharge coefficient and the electrode discharge coefficient according to the processing time deviation value to obtain a retrospective model of working hour prediction with optimized workpiece discharge coefficient and electrode discharge coefficient.

[0053] For the specific limitation of the prediction device for EDM processing time, reference can be made to the limitation of the prediction method for EDM processing time in the above text, which will not be elaborated here. Each module in the above prediction device for EDM processing time can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0054] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structural diagram may be as shown in Figure 6 . The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM working hours. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for predicting EDM working hours.

[0055] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the method for predicting EDM working hours in the above embodiment, such as Figure 2 the steps S201 - S204 shown. To avoid repetition, it will not be elaborated here. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the embodiment of the device for predicting EDM working hours, such as Figure 5 the working hour prediction function shown. To avoid repetition, it will not be elaborated here.

[0056] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, it implements the method for predicting EDM working hours in the above embodiment, such as Figure 2 the steps S201 - S204 shown. To avoid repetition, it will not be elaborated here. Alternatively, when the computer program is executed by the processor, it implements the functions of each module / unit in the above embodiment of the device for predicting EDM working hours, such as Figure 3 the working hour prediction function shown. To avoid repetition, it will not be elaborated here.

[0057] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a non-volatile computer-readable storage medium. When this computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0058] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0059] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A prediction method for the working hours of electric discharge machining, characterized in that, The prediction method for the EDM processing time includes: Obtain the simulation model of the workpiece to be processed, perform simulated machining on the simulation model of the workpiece to be processed, and obtain the residue of the workpiece to be processed; Perform solidification processing on the residue of the workpiece to be processed to obtain the converged body of the workpiece to be processed; Set at least one discharge electrode on the converged body of the workpiece to be processed, and calculate the discharge removal volume of all the discharge electrodes for discharging the workpiece to be processed; Determine the EDM processing time according to the discharge removal volume.

2. The prediction method of the EDM working hours according to claim 1, characterized in that Performing solidification processing on the residue of the workpiece to be processed to obtain the converged body of the workpiece to be processed includes: Call the UG function module to process the residue of the workpiece to be processed into the converged body of the workpiece to be processed.

3. The prediction method for the working hours of electric discharge machining according to claim 1, characterized in that The calculation of the discharge removal volume of all the discharge electrodes for discharging the workpiece to be processed includes: Determine the first volume of the converged body when the workpiece to be processed has not been discharged, and the second volume of the converged body after the workpiece to be processed has been discharged using the discharge electrode, calculate the difference between the first volume and the second volume to obtain the discharge removal volume.

4. The prediction method of the electric discharge machining time according to claim 1, wherein Determining the EDM processing time according to the discharge removal volume includes: Obtain the workpiece discharge characteristics and electrode discharge characteristics that are relevant to the EDM processing time of the workpiece to be processed, and the electrode discharge characteristics include the discharge removal volume; Determine the EDM processing time according to the workpiece discharge characteristics and electrode discharge characteristics, in combination with the EDM processing time prediction model used to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics.

5. The prediction method of the electric discharge machining time according to claim 4, characterized in that, The determination steps of the EDM processing time prediction model used to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics include: Set the workpiece discharge coefficient of the workpiece discharge characteristics and the electrode discharge coefficient of the electrode discharge characteristics, and construct an EDM processing time prediction model according to the workpiece discharge characteristics, the workpiece discharge coefficient, the electrode discharge characteristics, the electrode discharge coefficient, and the estimated discharge time; Obtain the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM processing time of the processed workpiece, and train the EDM processing time prediction model according to the historical workpiece discharge characteristics, historical electrode discharge characteristics, and historical EDM processing time to obtain the initial model of the processing time prediction with optimized workpiece discharge coefficient and electrode discharge coefficient.

6. The prediction method for the working hours of electrical discharge machining according to claim 4, characterized in that, The determination steps of the EDM processing time prediction model used to characterize the relationship between the estimated discharge time and the workpiece discharge characteristics and electrode discharge characteristics include: Set the workpiece discharge coefficient of the workpiece discharge characteristics and the electrode discharge coefficient of the electrode discharge characteristics, and construct an EDM processing time prediction model according to the workpiece discharge characteristics, the workpiece discharge coefficient, the electrode discharge characteristics, the electrode discharge coefficient, and the estimated discharge time; Obtain the historical workpiece discharge characteristics and historical electrode discharge characteristics of the machined workpiece, input the historical workpiece discharge characteristics and the historical electrode discharge characteristics into the trained neural network model for EDM machining time, output the historical EDM machining time, and train the machining time prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM machining time to obtain the optimized machining time prediction model with optimized workpiece discharge coefficient and electrode discharge coefficient.

7. The prediction method for EDM processing time according to claim 5 or 6, characterized in that Training the machining time prediction model according to the historical workpiece discharge characteristics, the historical electrode discharge characteristics, and the historical EDM machining time includes: Set the initial value of the workpiece discharge coefficient and the initial value of the electrode discharge coefficient, input the historical workpiece discharge characteristics and the historical electrode discharge characteristics into the machining time prediction model for EDM to obtain the predicted value of the EDM machining time, calculate the machining time deviation value between the predicted value of the EDM machining time and the historical EDM machining time, and iteratively update the workpiece discharge coefficient and the electrode discharge coefficient according to the machining time deviation value to obtain the optimized machining time prediction and backtracking model with optimized workpiece discharge coefficient and electrode discharge coefficient.

8. A prediction device for the working hours of electric discharge machining, characterized in that, Including: A simulation machining module for obtaining a simulation model of the workpiece to be machined and performing simulation machining on the simulation model of the workpiece to be machined for roughing to obtain the remaining body of the workpiece to be machined; A solid processing module for performing solid processing on the remaining body of the workpiece to be machined to obtain the converged body of the workpiece to be machined; A volume calculation module for setting at least one discharge electrode on the converged body of the workpiece to be machined and calculating the discharge removal volume of all the discharge electrodes for discharging the workpiece to be machined; A machining time calculation module for determining the EDM machining time according to the discharge removal volume.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the prediction method for EDM machining time according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the prediction method for EDM machining time according to any one of claims 1 to 7.

Images