EDM forming optimization system based on AI

Abstract

The present invention relates to the field of forming control technology, specifically to an AI-based electric spark forming optimization system, the system including a deviation assessment adjustment module, a surface quality optimization module, a wear and consumption identification module and a maintenance judgment adjustment module. The present invention dynamically adjusts the discharge current and voltage through real-time acquisition and comparison of conductivity and temperature data, improves processing accuracy and response speed, can more accurately adapt to changes in the medium, effectively prevent processing defects caused by parameter mismatch, improve product quality and reduce scrap rate, and utilizes convolutional neural networks to automatically identify and classify surface defects of workpieces, making the adjustment process more targeted. By adjusting the pulse frequency and duration, the processing quality control is refined to ensure that the surface quality of the workpiece reaches a higher standard. By real-time monitoring and analysis of electrode consumption and maintenance prediction based on the consumption rate, the efficient and stable operation of the equipment is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of forming control technology, and in particular to an AI-based electric spark forming optimization system. Background Art

[0002] The field of molding control technology involves the use of a variety of control technologies to monitor and optimize the mechanical and physical parameters of the molding process. The molding control field focuses on ensuring that molding processes such as EDM, injection molding, or metal extrusion are accurate and repeatable in producing high-quality parts. By monitoring equipment performance and workpiece quality in real time, molding control technology dynamically adjusts processing parameters to adapt to changes in raw materials or fluctuations in machine performance. Using sensing technology and data analysis, molding control can significantly improve production efficiency, reduce scrap, and ensure product consistency and compliance with specifications.

[0003] Among them, the EDM forming optimization system is a control system applied to EDM machine tool forming processing, mainly used for precision processing of hard materials such as hard alloys and high-speed steel. The system adjusts the discharge parameters through algorithms or control logic, optimizes the EDM process, and automatically adjusts the EDM parameters such as current, pulse interval and pulse duration to improve processing efficiency and workpiece surface quality. This optimization can not only reduce the wear and tear of the workpiece during processing, but also significantly increase the processing speed and reduce energy consumption, and optimize the workpiece forming processing effect.

[0004] Traditional forming systems rely on fixed parameters in EDM processing and ignore the impact of raw materials or environmental changes on forming quality, which will lead to processing errors caused by parameter inadaptability during the forming process, such as inaccurate dimensions, poor surface quality and other problems, increasing scrap rate and production costs. The lack of an effective electrode wear monitoring mechanism makes it difficult to optimize equipment maintenance and electrode replacement cycles, affecting overall production efficiency and equipment life. As a result, traditional systems are unable to ensure processing efficiency and cost control and are unable to meet modern needs for high-efficiency and high-quality production. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose an AI-based EDM forming optimization system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an AI-based EDM forming optimization system, the system comprising:

[0007] The deviation evaluation and adjustment module obtains the conductivity and temperature data of the forming processing liquid medium based on the preset parameters of the EDM forming process, compares them with the conductivity and temperature of the standard liquid medium, and adjusts the discharge current and discharge voltage of the EDM forming process according to the conductivity and temperature deviation to obtain the deviation adjustment result;

[0008] The surface quality optimization module obtains the workpiece surface image based on the deviation adjustment result, identifies the defects on the workpiece surface through the convolution neural network, evaluates the severity of the defects, and adjusts the pulse frequency and duration in the EDM process according to the severity of the defects to obtain optimization adjustment information;

[0009] The wear and consumption identification module obtains an image of the electrode working area of ​​the EDM equipment based on the optimization adjustment information, analyzes the image of the electrode working area, identifies the electrode consumption degree, and adjusts the discharge intensity during the EDM process according to the electrode consumption degree to obtain optimization correction information;

[0010] The maintenance judgment and adjustment module evaluates the electrode consumption rate based on the electrode consumption degree and combines the historical data of electrode wear and consumption, predicts the remaining service life of the electrode, determines whether the electrode needs to be replaced and maintained, notifies the management personnel to perform maintenance and replacement operations, and obtains electrode status update information.

[0011] The present invention is improved in that the step of obtaining the deviation adjustment result is:

[0012] Based on the preset parameters of the electrospark forming machining, the conductivity and temperature data of the electrospark forming machining liquid medium are collected to obtain the current conductivity and temperature data;

[0013] Based on the current conductivity and temperature data, compared with the corresponding data of the standard liquid medium, the formula is:

[0014]

[0015] and

[0016]

[0017] Calculating conductivity deviation and temperature deviation ;

[0018] in, Indicates the current conductivity, Indicates the current temperature. represents the standard conductivity, Indicates standard temperature, represents the conductivity deviation, Indicates temperature deviation;

[0019] Based on the conductivity deviation and temperature deviation , through the formula:

[0020]

[0021] and

[0022]

[0023] Calculate the adjusted discharge current and the adjusted discharge voltage , and obtain the deviation adjustment result;

[0024] in, represents the reference discharge current, represents the reference discharge voltage, , , and is the adjustment factor, represents the adjusted discharge current, represents the adjusted discharge voltage, represents the conductivity deviation, Indicates temperature deviation.

[0025] The present invention is improved in that the method for evaluating the severity of the defect is:

[0026] Use image sensors to obtain images of the workpiece surface, and use convolutional neural networks to extract defect features in the image. The defect features include defect type and defect size.

[0027] Based on the defect characteristics, the formula:

[0028]

[0029] Calculating the severity score of a defect , scored according to the severity of the defect Size, assess the severity of the defect:

[0030] in, is the severity score of the defect, is the defect type index, is the defect size, , and is the weight coefficient, is a constant.

[0031] The present invention is improved in that the step of obtaining the optimization adjustment information is:

[0032] Based on the EDM process, the baseline values ​​of pulse frequency and duration are obtained;

[0033] Based on the baseline values ​​of pulse frequency and duration and the severity score of the defect , through the formula:

[0034]

[0035] and

[0036]

[0037] Calculate the adjusted pulse frequency and the adjusted duration , get optimization adjustment information;

[0038] in, and are the weight coefficients for frequency and time adjustment, is the adjustment coefficient, and are the adjustment thresholds for frequency and time, respectively. is a constant, and are the baseline values ​​of pulse frequency and duration, and are the adjusted pulse frequency and duration, is the base of natural logarithms.

[0039] The present invention is improved in that the method for identifying the degree of electrode consumption is:

[0040] By using an image sensor, an image of the electrode working area is captured to obtain electrode image information;

[0041] Based on the electrode image information, the formula:

[0042]

[0043] Calculation of electrode consumption index , according to the electrode consumption index The size of the electrode is used to evaluate the degree of electrode consumption;

[0044] in, The first The color intensity of the region, is the color intensity baseline of the complete electrode, The image is The surface smoothness of the area, , and is the adjustment factor, is the base of natural logarithms, It is the electrode consumption index.

[0045] The present invention is improved in that the step of obtaining the optimized correction information is:

[0046] Based on the electrode consumption index , through the formula:

[0047]

[0048] Calculate consumption correction parameters ;

[0049] in, is the electrode consumption index, and is the weight coefficient, is the attenuation coefficient, is the threshold value, is the base of natural logarithms, Consumption correction parameter.

[0050] Based on the consumption correction parameter , the discharge intensity during the EDM process is adjusted to obtain optimized correction information.

[0051] The present invention is improved in that the method for evaluating the electrode consumption rate is:

[0052] Based on the electrode consumption degree, collecting historical electrode consumption data of the sinker EDM equipment;

[0053] Based on the historical electrode consumption data, the formula:

[0054]

[0055] Calculate electrode consumption rate ;

[0056] in, is the current electrode consumption index, is the initial electrode consumption index, For the current time point, is the initial time point, and is the adjustment coefficient, is the electrode consumption rate;

[0057] Based on the electrode consumption rate ,according to The value is used to evaluate the speed of electrode consumption.

[0058] The present invention is improved in that the method for determining whether the electrode needs to be replaced and maintained is:

[0059] Based on the electrode consumption rate , combined with the electrode consumption index, through the formula:

[0060]

[0061] Calculate the expected remaining service life of the electrode ;

[0062] in, is the maximum durability consumption index of the electrode, is the current electrode consumption index, is the electrode consumption rate, and is the adjustment factor, is the baseline constant, is the stability constant, is the expected remaining service life of the electrode.

[0063] Based on the expected remaining service life of the electrode , compared with the preset safety threshold to determine whether the electrode needs to be replaced and maintained.

[0064] Compared with the prior art, the advantages and positive effects of the present invention are:

[0065] In the present invention, the discharge current and voltage are dynamically adjusted through the real-time acquisition and comparison of conductivity and temperature data, thereby improving the processing accuracy and response speed, being able to adapt to changes in the medium more accurately, effectively preventing processing defects caused by parameter mismatch, improving product quality and reducing scrap rate, and utilizing convolutional neural networks to automatically identify and classify surface defects of workpieces, making the adjustment process more targeted, and refining processing quality control by adjusting pulse frequency and duration to ensure that the surface quality of the workpiece reaches a higher standard, and through real-time monitoring and analysis of electrode consumption and maintenance prediction based on the consumption rate, the service life of the electrode is extended and the maintenance cost is reduced, thereby ensuring efficient and stable operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is a system flow chart of the present invention;

[0067] Figure 2 A flow chart for obtaining deviation adjustment results for the present invention;

[0068] Figure 3 A flow chart for evaluating the severity of defects for the present invention;

[0069] Figure 4 A flow chart for obtaining optimization adjustment information for the present invention;

[0070] Figure 5 A flow chart for identifying the degree of electrode consumption according to the present invention;

[0071] Figure 6 A flow chart for optimizing correction information for the present invention;

[0072] Figure 7 Flow chart for evaluating electrode consumption rate for the present invention;

[0073] Figure 8 This is a flow chart for judging whether an electrode needs to be replaced and maintained according to the present invention. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0075] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example

[0076] See also Figure 1 The present invention provides a technical solution: an AI-based EDM forming optimization system, the system comprising:

[0077] The deviation evaluation and adjustment module obtains the conductivity and temperature data of the forming processing liquid medium based on the preset parameters of the EDM forming process, compares them with the conductivity and temperature of the standard liquid medium, and adjusts the discharge current and discharge voltage of the EDM forming process according to the conductivity and temperature deviation to obtain the deviation adjustment result;

[0078] The surface quality optimization module obtains the workpiece surface image based on the deviation adjustment result, identifies the defects on the workpiece surface through the convolutional neural network, evaluates the severity of the defects according to the defect type and defect size, and adjusts the pulse frequency and duration during the EDM process according to the severity of the defects to obtain optimization adjustment information;

[0079] The wear and consumption identification module obtains the image of the electrode working area of ​​the EDM equipment based on the optimization adjustment information, analyzes the image of the electrode working area, identifies the electrode consumption degree, adjusts the discharge intensity during the EDM process according to the electrode consumption degree, and obtains the optimization correction information;

[0080] The maintenance judgment and adjustment module evaluates the electrode consumption rate based on the electrode consumption degree and combines the historical data of electrode wear and consumption, predicts the remaining service life of the electrode, determines whether the electrode needs to be replaced and maintained, notifies the management personnel to perform maintenance and replacement operations, optimizes the stable operation of the EDM equipment, and obtains electrode status update information;

[0081] The deviation adjustment results include error trend assessment, expected adjustment feedback and real-time correction parameters. The optimization adjustment information includes surface integrity information, defect type identification and optimization parameter output. The optimization correction information includes wear degree information, electrode performance attenuation monitoring and operation adjustment instructions. The electrode status update information includes electrode replacement cycle and maintenance cycle prompts.

[0082] See also Figure 2 , the steps to obtain the deviation adjustment results are:

[0083] Based on the preset parameters of the electrospark forming machining, the conductivity and temperature data of the electrospark forming machining liquid medium are collected to obtain the current conductivity and temperature data;

[0084] Based on the current conductivity and temperature data, compared with the corresponding data of the standard liquid medium, the formula is:

[0085]

[0086] and

[0087]

[0088] Calculating conductivity deviation and temperature deviation ;

[0089] in, Indicates the current conductivity, Indicates the current temperature. represents the standard conductivity, Indicates standard temperature, represents the conductivity deviation, Indicates temperature deviation;

[0090] Based on conductivity deviation and temperature deviation , through the formula:

[0091]

[0092] and

[0093]

[0094] Calculate the adjusted discharge current and the adjusted discharge voltage , and obtain the deviation adjustment result;

[0095] in, represents the reference discharge current, represents the reference discharge voltage, , , and is the adjustment factor, represents the adjusted discharge current, represents the adjusted discharge voltage, represents the conductivity deviation, Indicates temperature deviation.

[0096] formula:

[0097]

[0098] and

[0099]

[0100] and

[0101]

[0102] and

[0103]

[0104] The meaning and acquisition method of parameters:

[0105] and : Actual and standard temperatures, respectively, are measured directly in the molding process liquid medium by sensors.

[0106] and : Actual and standard conductivity, also measured directly in the liquid medium by the sensor.

[0107] and : The reference discharge current and voltage are fixed values ​​set according to the standard configuration of the equipment or previous experience.

[0108] , , and : The coefficient is obtained by analyzing the previous test data and is used to adjust the weight of the impact of temperature and conductivity changes on discharge parameters.

[0109] Calculation example:

[0110] Assume the following numbers for calculation:

[0111] Standard temperature , actual temperature

[0112] Standard conductivity , actual conductivity

[0113] Reference discharge current , reference voltage

[0114] coefficient

[0115] Calculate the deviations in temperature and conductivity:

[0116]

[0117]

[0118] Enter the adjustment formula:

[0119]

[0120]

[0121]

[0122]

[0123]

[0124]

[0125] The calculation results show that the actual temperature and conductivity are higher than the standard values, so the adjusted discharge current and voltage are increased to 10.3 amps and 51 volts respectively to adapt to the changes in the medium in the actual working environment. This adjustment helps to maintain the stability of the processing effect and ensure the processing quality.

[0126] See also Figure 3 , the method to assess the severity of the defect is:

[0127] Use image sensors to obtain images of the workpiece surface, and use convolutional neural networks to extract defect features in the image. The defect features include defect type and defect size.

[0128] Based on the defect characteristics, through the formula:

[0129]

[0130] Calculating the severity score of a defect , scored according to the severity of the defect Size, assess the severity of the defect:

[0131] in, is the severity score of the defect, is the defect type index, is the defect size, , and is the weight coefficient, is a constant.

[0132] formula:

[0133]

[0134] The meaning and acquisition method of parameters:

[0135] : Defect type index, obtained from image processing software by identifying defects of different shapes and sizes. Different defect types may represent cracks, dents, etc. Each type has a preset index to reflect the impact of the defect type.

[0136] : Defect size, measured by image processing software, the area or maximum linear dimension of the defect, in pixels or millimeters.

[0137] , and :The weight coefficient is adjusted according to historical data and engineering requirements to ensure the accuracy and applicability of the model. The weight setting reflects the impact of different types and sizes of defects on the quality of the final product.

[0138] : A small constant used to ensure computational stability and prevent division by zero errors when the execution defect size is zero.

[0139] Calculation example:

[0140] Assume the following data:

[0141] Defect Type (Assuming it is a crack)

[0142] Defect size (in square millimeters)

[0143] Weight coefficient

[0144] Small constant

[0145] Substitute the data into the formula to calculate the severity of the defect:

[0146]

[0147]

[0148]

[0149] Substituting into the formula:

[0150]

[0151]

[0152]

[0153]

[0154] Calculation results , indicating the severity of the defect. The higher this score is, the greater the impact of the defect on product quality and the more stringent processing adjustments are required.

[0155] See also Figure 4 , the steps to obtain the optimization adjustment information are:

[0156] Based on the EDM process, the baseline values ​​of pulse frequency and duration are obtained;

[0157] Baseline values ​​of pulse frequency and duration and severity scores of defects , through the formula:

[0158]

[0159] and

[0160]

[0161] Calculate the adjusted pulse frequency and the adjusted duration , get optimization adjustment information;

[0162] in, and are the weight coefficients for frequency and time adjustment, is the adjustment coefficient, and are the adjustment thresholds for frequency and time, respectively. is a constant, and are the baseline values ​​of pulse frequency and duration, and are the adjusted pulse frequency and duration, is the base of natural logarithms.

[0163] formula:

[0164]

[0165] and

[0166]

[0167] The meaning and acquisition method of parameters:

[0168] and It is the baseline value for pulse frequency and duration. The value is usually set according to the recommended settings of the equipment or based on past operation data to ensure the process runs at standard without defect identification.

[0169] and are the weight coefficients for frequency and time adjustment. The coefficients are obtained through previous experimental data and empirical estimation to adjust the response under different working conditions.

[0170] is the adjustment factor of the exponential decay, which is used to adjust the sensitivity of the frequency response. The coefficient is optimized based on material properties and processing conditions.

[0171] and The thresholds for frequency and duration adjustments are determined by the thresholds where significant adjustments to pulse frequency and duration begin, and are usually set based on specific operating conditions and the severity of the defect.

[0172] It is a small constant used in calculations to ensure stability and prevent the denominator from being zero.

[0173] Calculation example:

[0174] Assume the following numbers for calculation:

[0175] Baseline pulse frequency Hz, baseline duration ms, defect severity assessment score , adjustment coefficient , , adjustment coefficient , threshold , , a small constant .

[0176] Calculate the pulse frequency adjustment:

[0177]

[0178]

[0179] calculate Get about ,therefore:

[0180]

[0181]

[0182]

[0183] Calculation duration adjustment:

[0184]

[0185]

[0186] calculate Get about ,therefore:

[0187]

[0188]

[0189]

[0190] Calculation results and Indicates the adjusted pulse frequency and duration based on the severity of the defect. This adjustment ensures that the machining process is more finely adapted to the actual conditions of the workpiece surface, improving machining quality and efficiency.

[0191] See also Figure 5 , the method to identify the degree of electrode consumption is:

[0192] By using an image sensor, an image of the electrode working area is captured to obtain electrode image information;

[0193] Based on the electrode image information, the formula:

[0194]

[0195] Calculation of electrode consumption index , according to the electrode consumption index The size of the electrode is used to evaluate the degree of electrode consumption;

[0196] in, The first The color intensity of the region, is the color intensity baseline of the complete electrode, The image is The surface smoothness of the area, , and is the adjustment factor, is the base of natural logarithms, It is the electrode consumption index.

[0197] formula:

[0198]

[0199] The meaning and acquisition method of parameters:

[0200] : represents the first The color intensity of each area is measured from the image of the electrode working area using image analysis software. The parameter reflects the degree of wear and tear in the area, and the change in color is usually related to the wear and tear of the material.

[0201] : is the color intensity baseline of the complete electrode, usually obtained by analyzing the standard image data of the new electrode. It is a reference value used to compare with the actual measured value. Compare to determine the extent of wear and tear.

[0202] :Indicates the first The surface smoothness of each area is obtained by analyzing the surface texture changes through image processing software. The change of surface smoothness can reflect the degree of physical wear and tear of the material.

[0203] , and : The coefficients are adjusted based on previous experimental data and experience, where and Adjust the contribution weight of color change and smoothness change to wear and tear evaluation, and is a decay coefficient that affects the decay rate of the exponential function to adapt to different materials and wear behaviors.

[0204] Calculation example:

[0205] Assume that there are three regions in the electrode image, and the specific values ​​of each region are as follows:

[0206] (Color intensity baseline for intact electrode)

[0207] (Color intensity of each area)

[0208] (Smoothness of each area)

[0209] The adjustment factor is set to

[0210] Calculate the wear contribution of each area:

[0211] For the first region:

[0212]

[0213]

[0214]

[0215]

[0216] For the second region:

[0217]

[0218]

[0219]

[0220]

[0221] For the third region:

[0222]

[0223]

[0224]

[0225]

[0226] Total wear and tear is the sum of the wear contributions of these three regions:

[0227]

[0228]

[0229]

[0230] Calculation results Indicates the overall wear and tear of the electrode. Values ​​lower than 0.05 indicate significant wear and tear on the electrode and may require more frequent maintenance or replacement.

[0231] See also Figure 6 , the steps to obtain the optimized correction information are:

[0232] Based on the electrode consumption index , through the formula:

[0233]

[0234] Calculate consumption correction parameters ;

[0235] in, is the electrode consumption index, and is the weight coefficient, is the attenuation coefficient, is the threshold value, is the base of natural logarithms, Consumption correction parameter.

[0236] Consumption-based correction parameters , the discharge intensity during the EDM process is adjusted to obtain optimized correction information.

[0237] formula:

[0238]

[0239] The meaning and acquisition method of parameters:

[0240] : Electrode consumption index, calculated by the previous step.

[0241] : Weight coefficient, used to adjust the wear and consumption index after logarithmic transformation The coefficients are adjusted based on historical data and experimental results to ensure that the response to wear is reasonable.

[0242] : Weight coefficient used to smooth the wear index The effect of is adjusted by the sigmoid function. The coefficients are also adjusted based on historical data and experimental results to make the model's response smoother.

[0243] : Attenuation coefficient, used to adjust the sigmoid function The coefficient determines the sensitivity and response speed of the function and is usually optimized based on the material properties and processing conditions.

[0244] : Threshold, used in sigmoid function, set The starting point at which the calculation results begin to be significantly affected. It is a parameter determined based on material properties and processing requirements, and is intended to ensure that the adjustment is only activated when the wear reaches a certain level.

[0245] Calculation example:

[0246] Assumptions:

[0247] (Electrode wear index), , , , .

[0248] Substitute into the formula to calculate :

[0249]

[0250]

[0251]

[0252]

[0253]

[0254]

[0255]

[0256]

[0257]

[0258]

[0259] Calculation results Indicates the consumption correction parameter adjusted according to the wear consumption index of the electrode. This parameter value is used to adjust the discharge intensity of the EDM equipment to ensure the optimization of processing quality and electrode efficiency.

[0260] See also Figure 7 , the method for evaluating the electrode consumption rate is:

[0261] Based on the degree of electrode consumption, collect historical electrode consumption data of EDM sinker equipment;

[0262] Based on historical electrode consumption data, the formula:

[0263]

[0264] Calculate electrode consumption rate ;

[0265] in, is the current electrode consumption index, is the initial electrode consumption index, For the current time point, is the initial time point, and is the adjustment coefficient, is the electrode consumption rate;

[0266] Based on electrode consumption rate ,according to The value is used to evaluate the speed of electrode consumption.

[0267] formula:

[0268]

[0269] The meaning and acquisition method of parameters:

[0270] Current electrode consumption index : Indicates the degree of electrode wear and consumption at the time of measurement, calculated using the previous method.

[0271] Initial electrode consumption index : Refers to the electrode wear and consumption status at the beginning of the project, usually measured when a new electrode is installed, as a benchmark for subsequent wear assessments.

[0272] Current time point : Indicates the point in time when the current wear index measurement is taken, usually calculated in months after the start of the project.

[0273] Initial time point : The time point at the beginning of the project, usually 0, indicating the time when the new electrode is installed.

[0274] Adjustment coefficient : Used to adjust the wear rate contribution of the linear part, obtained through regression analysis based on historical wear data to ensure that the calculated wear rate is consistent with the actual wear.

[0275] Adjustment coefficient : Used to adjust the contribution of the logarithmic part and strengthen the response to high values ​​of the wear index. It is determined based on experimental data to match the nonlinear characteristics of wear behavior.

[0276] Calculation example:

[0277] Assumptions (Current electrode wear index)

[0278] (Initial electrode wear index)

[0279] (Current time in months)

[0280] (initial time, in months)

[0281] (Adjustment coefficient)

[0282] (Adjustment coefficient)

[0283] Calculation process:

[0284] Calculate the linear portion of the consumption rate:

[0285]

[0286]

[0287]

[0288] Calculate the logarithmic part of the consumption rate:

[0289]

[0290]

[0291]

[0292]

[0293] Total consumption rate:

[0294]

[0295]

[0296] Calculated consumption rate Describes the rate of electrode wear, that is, the electrode wear index increases by about 1.2572 units per month. This result is crucial for judging the remaining service life of the electrode and its replacement time. A higher wear rate indicates that the electrode may need more frequent inspections and earlier replacement, helping to maintain the stable operation of the processing equipment and processing quality.

[0297] See also Figure 8 , the method to determine whether the electrode needs to be replaced and maintained is:

[0298] Based on electrode consumption rate , combined with the electrode consumption index, through the formula:

[0299]

[0300] Calculate the expected remaining service life of the electrode ;

[0301] in, is the maximum durability consumption index of the electrode, is the current electrode consumption index, is the electrode consumption rate, and is the adjustment factor, is the baseline constant, is the stability constant, is the expected remaining service life of the electrode.

[0302] Based on the expected remaining service life of the electrode , compared with the preset safety threshold to determine whether the electrode needs to be replaced and maintained.

[0303] formula:

[0304]

[0305] The meaning and acquisition method of parameters:

[0306] : The maximum durability consumption index of the electrode represents the maximum degree of consumption that the electrode can reach, the limit before the electrode performance begins to significantly decline. This value is usually determined based on the manufacturer's specifications and through statistical analysis of historical performance data of the electrode under similar working conditions.

[0307] : The current electrode consumption index can be obtained by calculating in the previous steps.

[0308] : Electrode consumption rate, calculated by the previous step.

[0309] : Adjustment coefficient, used to adjust the influence of wear difference in remaining life calculation. This parameter is adjusted according to the characteristics of electrode materials and processing conditions to ensure the accuracy of the model.

[0310] : Baseline constant, added to the numerator of the remaining life calculation to ensure the stability of the calculation and avoid abnormally high remaining life predictions due to low wear rates.

[0311] : Adjustment factor, used to adjust the wear rate The square root of the effect on the remaining lifetime increases the sensitivity to high rate changes.

[0312] : Stable constant, added to the denominator to avoid division by zero errors in calculations and to ensure the stability of the formula.

[0313] Calculation example:

[0314] Assume the following parameters:

[0315] : The maximum consumption index that the electrode can withstand.

[0316] : Current electrode consumption index.

[0317] : Monthly consumption rate.

[0318] : Adjustment coefficient.

[0319] : Baseline constant.

[0320] : Square root adjustment factor.

[0321] : Stability constant.

[0322] Calculation process:

[0323] Calculate remaining useful life :

[0324]

[0325]

[0326]

[0327]

[0328]

[0329] Calculation results The latest data from the Institute of Electrical and Mechanical Engineers (IEM) shows that based on the current wear rate and electrode wear state, the electrode is expected to last approximately 12 months. This information is critical to equipment maintenance planning and electrode replacement strategies, helping managers make data-based decisions to ensure production efficiency and quality are not affected.

[0330] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. AI-based EDM optimization system, It is characterized in that The system comprises: The deviation evaluation and adjustment module obtains the conductivity and temperature data of the forming processing liquid medium based on the preset parameters of the EDM forming process, compares them with the conductivity and temperature of the standard liquid medium, and adjusts the discharge current and discharge voltage of the EDM forming process according to the conductivity and temperature deviation to obtain the deviation adjustment result; The steps for obtaining the deviation adjustment result are: Based on the preset parameters of the electrospark forming machining, the conductivity and temperature data of the electrospark forming machining liquid medium are collected to obtain the current conductivity and temperature data; Based on the current conductivity and temperature data, compared with the corresponding data of the standard liquid medium, the formula is: ； and ； Calculating conductivity deviation and temperature deviation ; in, Indicates the current conductivity, Indicates the current temperature. represents the standard conductivity, Indicates standard temperature, represents the conductivity deviation, Indicates temperature deviation; Based on the conductivity deviation and temperature deviation , through the formula: ； and ； Calculate the adjusted discharge current and the adjusted discharge voltage , and obtain the deviation adjustment result; in, represents the reference discharge current, represents the reference discharge voltage, , , and is the adjustment factor, represents the adjusted discharge current, represents the adjusted discharge voltage, represents the conductivity deviation, Indicates temperature deviation; The surface quality optimization module obtains the workpiece surface image based on the deviation adjustment result, identifies the defects on the workpiece surface through the convolution neural network, evaluates the severity of the defects, and adjusts the pulse frequency and duration in the EDM process according to the severity of the defects to obtain optimization adjustment information; The method for assessing the severity of the defect is: Use image sensors to obtain images of the workpiece surface, and use convolutional neural networks to extract defect features in the image. The defect features include defect type and defect size. Based on the defect characteristics, the formula: ； Calculating the severity score of a defect , scored according to the severity of the defect Size, assess the severity of the defect: in, is the severity score of the defect, is the defect type index, is the defect size, , and is the weight coefficient, is a constant; The steps for obtaining the optimization adjustment information are as follows: Based on the EDM process, the baseline values ​​of pulse frequency and duration are obtained; Based on the baseline values ​​of pulse frequency and duration and the severity score of the defect , through the formula: ； and ； Calculate the adjusted pulse frequency and the adjusted duration , get optimization adjustment information; in, and are the weight coefficients for frequency and time adjustment, is the adjustment coefficient, and are the adjustment thresholds for frequency and time, respectively. is a constant, and are the baseline values ​​of pulse frequency and duration, and are the adjusted pulse frequency and duration, is the base of natural logarithms; The wear and consumption identification module obtains an image of the electrode working area of ​​the EDM equipment based on the optimization adjustment information, analyzes the image of the electrode working area, identifies the electrode consumption degree, and adjusts the discharge intensity during the EDM process according to the electrode consumption degree to obtain optimization correction information; The maintenance judgment and adjustment module evaluates the electrode consumption rate based on the electrode consumption degree and combines the historical data of electrode wear and consumption, predicts the remaining service life of the electrode, determines whether the electrode needs to be replaced and maintained, notifies the management personnel to perform maintenance and replacement operations, and obtains electrode status update information.

2. The AI-based EDM optimization system according to claim 1, It is characterized in that The method for identifying the degree of electrode consumption is: By using an image sensor, an image of the electrode working area is captured to obtain electrode image information; Based on the electrode image information, the formula: ； Calculation of electrode consumption index , according to the electrode consumption index The size of the electrode is used to evaluate the degree of electrode consumption; in, The first The color intensity of the region, is the color intensity baseline of the complete electrode, The image is The surface smoothness of the area, , and is the adjustment factor, is the base of natural logarithms, It is the electrode consumption index.

3. According to the AI-based EDM optimization system of claim 2, It is characterized in that The steps for obtaining the optimization correction information are as follows: Based on the electrode consumption index , through the formula: ； Calculate consumption correction parameters ; in, is the electrode consumption index, and is the weight coefficient, is the attenuation coefficient, is the threshold value, is the base of natural logarithms, Correction parameters for consumption; Based on the consumption correction parameter , the discharge intensity during the EDM process is adjusted to obtain optimized correction information.

4. The AI-based EDM optimization system according to claim 1, It is characterized in that The method for evaluating the electrode consumption rate is: Based on the electrode consumption degree, collecting historical electrode consumption data of the sinker EDM equipment; Based on the historical electrode consumption data, the formula: ； Calculate electrode consumption rate ; in, is the current electrode consumption index, is the initial electrode consumption index, For the current time point, is the initial time point, and is the adjustment coefficient, is the electrode consumption rate; Based on the electrode consumption rate ,according to The value is used to evaluate the speed of electrode consumption.

5. The AI-based EDM optimization system according to claim 4, It is characterized in that The method for determining whether the electrode needs to be replaced and maintained is: Based on the electrode consumption rate , combined with the electrode consumption index, through the formula: ； Calculate the expected remaining service life of the electrode ; in, is the maximum durability consumption index of the electrode, is the current electrode consumption index, is the electrode consumption rate, and is the adjustment factor, is the baseline constant, is the stability constant, is the expected remaining service life of the electrode; Based on the expected remaining service life of the electrode , compared with the preset safety threshold to determine whether the electrode needs to be replaced and maintained.

Images