High-precision plasma cutting method and equipment

Abstract

The high-precision plasma cutting method comprises the following steps that S1, real-time voltage information is collected, a feedback circuit of a cutting torch is connected into an FPGA, and a real-time voltage value ai of the cutting torch is obtained; s2, acquiring an expected voltage value a0 in the MCU; s3, comparing the real-time voltage value with the expected voltage value; s4, comparing the real-time voltage value with an expected voltage value, and calculating an error value; s5, according to the error value, the control quantity is calculated through calculation of three links of proportion, integration and differentiation; s6, taking the calculated control quantity as a basis for adjusting power supply output, and putting the control quantity into an expected voltage value to obtain a required input voltage value; according to the method, the voltage of the cutting torch is adjusted through the PID algorithm and the approaching method, so that the influence of environmental factors can be avoided, the expected voltage value and the real-time voltage value are adjusted to be within the absolute value range of 2, and the threshold value does not influence the actual cutting precision and speed of the cutting torch.

Description

Technical Field

[0001] The present invention relates to the field of plasma cutting, and in particular to a high-precision plasma cutting method and equipment. Background Art

[0002] Temperature fluctuations in the plasma cutting environment can affect the power supply and torch. High temperatures can alter the performance of electronic components within the power supply, such as semiconductor devices. This can cause changes in the conduction characteristics, potentially reducing the power supply's output voltage. Furthermore, the torch's performance can degrade due to poor heat dissipation in high-temperature environments, impacting voltage stability.

[0003] In low-temperature environments, the performance of semiconductor devices in power supplies (such as transistors and diodes) will be significantly affected. Taking transistors as an example, their base-emitter voltage will increase as the temperature drops, reducing the output current of the power supply. Under the condition of unchanged load, the output voltage will increase, thus affecting the normal operating voltage of the cutting torch. The impact of voltage on the cutting torch is crucial. When the output voltage does not meet the expected voltage, the cutting speed, accuracy and other aspects of the cutting torch will be affected. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, the present invention provides a high-precision plasma cutting method and equipment.

[0005] The technical solution of the present invention is achieved as follows:

[0006] A high-precision plasma cutting method comprises the following steps:

[0007] S1, collects real-time voltage information, connects the feedback circuit of the cutting torch to FPGA, and obtains the real-time voltage value of the cutting torch a i ;

[0008] S2, obtain the expected voltage value a0 in the MCU;

[0009] S3, comparing the real-time voltage value with the expected voltage value;

[0010] S4, compare the real-time voltage value with the expected voltage value and calculate the error value;

[0011] S5, based on the error value, calculates the control quantity through the three operations of proportion, integration and differentiation; S6, uses the calculated control quantity as the basis for adjusting the power supply output, and puts the control quantity into the expected voltage value to obtain the required input voltage value.

[0012] Preferably, in step S5, the proportional calculation formula is e=V 期望 -V 实时 ,u p =Kp ×e; where e is the error value, u p is the control quantity, K p is the proportional coefficient. In the initial debugging stage, first set K p Set it to 0.1 and observe the system response. If the real-time voltage converges too slowly to the expected voltage, gradually increase K. p Adjust the absolute value of until the system can respond quickly to errors but without significant oscillation.

[0013] Preferably, in step S5, the integral formula is Among them, K i is the integral coefficient, and t is the time. The integral term will continuously accumulate errors. As time goes by, even if the error is small, the integral control amount will gradually increase, thereby pushing the real-time voltage closer to the desired voltage.

[0014] Preferably, in step S5, the differential formula is u d =K d ×d e / d t ; In the initial debugging stage, first set K d Set Kd to 0.1 and observe the system response. If the real-time voltage converges to the expected voltage too slowly, gradually increase the absolute value of Kd until the system can respond to the error quickly without obvious oscillation.

[0015] Preferably, in step S6, the control amount is the sum of the proportional, integral and differential control amounts u=u p +u i +u d , the total control quantity u is obtained, and the real-time measured voltage value V is known, then the ratio k between the control quantity and the real-time voltage value V can be known, k = V / u, and finally the adjusted input voltage value V1 can be obtained, V1 = V+k×u.

[0016] A high-precision plasma cutting device comprises a plasma cutting torch for implementing the above-mentioned high-precision plasma cutting method.

[0017] The present invention adjusts the voltage of the cutting torch through the PID algorithm and the proximity method, so that it can be exempted from the influence of environmental factors, and adjusts the expected voltage value and the real-time voltage value to an absolute value range of 2. This threshold does not affect the actual cutting accuracy and speed of the cutting torch. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of a high-precision plasma cutting method of the present invention. DETAILED DESCRIPTION

[0019] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present application. Rather, they are merely examples of methods and systems consistent with certain aspects of the present application, as detailed in the appended claims.

[0020] The terms used in this application are for the purpose of describing particular embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0021] The following describes in detail the specific implementation methods, features and effects of the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0022] Example 1

[0023] The present invention provides a high-precision plasma cutting method, comprising the following steps:

[0024] S1, collects real-time voltage information, connects the feedback circuit of the cutting torch to FPGA, and obtains the real-time voltage value of the cutting torch a i ;

[0025] S2, obtain the expected voltage value a0 in the MCU;

[0026] S3, comparing the real-time voltage value with the expected voltage value; in actual applications, due to the seasonal and regional influences on temperature and humidity, the difference between the real-time voltage value and the expected voltage value is large, requiring real-time adjustment. To address the seasonal and regional influences on temperature and humidity, step S3 further includes the following sub-steps:

[0027] S31, creating a table to record historical data, including real-time voltage values ​​and expected voltage values;

[0028] S32, from the table, the linear relationship value K0 between the real-time voltage value and the expected voltage value is obtained;

[0029] S33, adjusting the voltage for the first time, through K0, obtaining the output voltage value a1 = expected voltage value a0 × linear relationship value K0;

[0030] S34, compare a1 and a0. If the comparison result is within the absolute value of 20, skip steps S4 and S5. If the comparison result exceeds the absolute value of 20, perform the error value and control amount calculation in steps S4 and S5. However, K0 will change with the season and region. Therefore, the linear relationship value is only used within the first 10 days of the table, as well as the 20 days before and after the same month and day in previous years. The average value of the comparison is the linear relationship value K0 at this time.

[0031] S4, compare the real-time voltage value with the expected voltage value and calculate the error value;

[0032] S5, based on the error value, calculates the control quantity through the proportional, integral and differential (PID) operations;

[0033] S6, using the calculated control quantity as the basis for adjusting the power supply output, and putting the control quantity into the expected voltage value to obtain the required input voltage value;

[0034] The step S6 further comprises the following sub-steps:

[0035] S61, obtain the real-time voltage value a again t , a t Compare with the expected voltage value;

[0036] S62, by comparing the results, t Make a coarse adjustment to get closer to the method, each time a t Move closer to a0 by 5 units until a t The comparison result with a0 is within 20 in absolute value;

[0037] S63, for a t Make fine adjustments, each time making ±2 unit value adjustments, approaching a0, until the comparison result value is within the absolute value of 2.

[0038] Preferably, in step S5, the proportional calculation formula is e=V 期望 -V 实时 ,u p =K p ×e; where e is the error value, u p is the control quantity, K p is the proportional coefficient. In the initial debugging stage, first set K p Set it to 0.1 and observe the system response. If the real-time voltage converges too slowly to the expected voltage, gradually increase K. p Adjust the absolute value of until the system can respond quickly to errors but without significant oscillation.

[0039] Preferably, in step S5, the integral formula is Among them, Ki is the integral coefficient, and t is the time. The integral term will continuously accumulate errors. As time goes by, even if the error is small, the integral control amount will gradually increase, thereby pushing the real-time voltage closer to the desired voltage.

[0040] Preferably, in step S5, the differential formula is u d =K d ×d e / d t ; In the initial debugging stage, first set K d Set it to 0.1 and observe the system response. If the real-time voltage converges too slowly to the expected voltage, gradually increase K. d Adjust the absolute value of until the system can respond quickly to errors but without significant oscillation.

[0041] Preferably, in step S6, the control amount is the sum of the proportional, integral and differential control amounts u=u p +u i +u d , the total control quantity u is obtained, and the real-time measured voltage value V is known, then the ratio k between the control quantity and the real-time voltage value V can be known, k = V / u, and finally the adjusted input voltage value V1 can be obtained, V1 = V+k×u.

[0042] Preferably, the feedback circuit according to step S1 is an important component for transmitting the nozzle voltage signal to the FPGA for collection and processing, which includes:

[0043] A sensor for detecting and measuring changes in nozzle voltage;

[0044] Amplifier: In the feedback circuit, the amplifier is usually used to amplify the voltage signal obtained from the sensor and match the output of the sensor; the filter is used to remove noise and interference in the sensor output and pass the accurate voltage signal to the FPGA; the analog-to-digital converter ADC is a key component in the feedback circuit, used to convert the analog voltage signal into a digital AD value. The ADC discretizes the continuous analog voltage signal.

[0045] A high-precision plasma cutting device comprises a plasma cutting torch for implementing the above-mentioned high-precision plasma cutting method.

[0046] Example 2

[0047] S1, data acquisition, connects the cutting torch's feedback circuit to the FPGA to obtain the torch's real-time voltage value. At the same time, install temperature and humidity sensors, air pressure sensors, etc. to collect environmental data. In addition, it is also necessary to collect parameters such as the cutting torch's current value and plasma gas flow rate to provide more input features for the neural network. Continuous data over a period of time is collected to form time series data, so that the neural network can better learn dynamic changes.

[0048] S2, data labeling and organization, labels the collected data, and the labeling content includes the corresponding expected voltage value and the evaluation level of the cutting effect.

[0049] The data is sorted and normalized so that data of different dimensions are in a similar numerical range, which is convenient for training neural networks.

[0050] S3, the neural network model construction stage, can choose a deep neural network with good nonlinear fitting ability, such as a combination of multi-layer perceptron (MLP), convolutional neural network (CNN) and long short-term memory network (LSTM), etc. The input layer receives real-time voltage value, temperature and humidity, air pressure, current value, plasma gas flow and other parameters, and the output layer is the expected voltage value.

[0051] S4, model training, divides the organized data into training, validation, and test sets. The neural network is trained using the training set, and the network weights and biases are continuously adjusted through the backpropagation algorithm to minimize the error between the predicted and actual values.

[0052] During training, use the validation set to monitor model performance and prevent overfitting. When the model's performance on the validation set stops improving, training can be stopped. For example, use a deep learning framework like TensorFlow or PyTorch to build and train a neural network model.

[0053] S5, the model application stage, during the actual cutting process, the various parameters collected in real time are input into the trained neural network model, and the model will output the dynamic expected voltage value.

[0054] Because the neural network can learn the complex relationship between different environmental parameters and operating conditions and the expected voltage, it can more accurately adapt to seasonal and regional influences.

[0055] Uncertainty estimation: In addition to outputting the expected voltage value, the neural network can also estimate the uncertainty of the output. For example, methods such as Monte Carlo dropout can be used to run the neural network multiple times and observe the range of variation in the output to understand the degree of uncertainty in the prediction.

[0056] If the uncertainty is large, a more conservative adjustment strategy can be adopted, or additional monitoring and adjustments can be carried out.

[0057] S6, voltage comparison and adjustment stage, intelligent comparison and feedback, compares the real-time voltage value with the expected voltage value predicted by the neural network and calculates the error.

[0058] The error information is fed back to the neural network so that the network can take this error into account in subsequent predictions, further improving the accuracy of the predictions.

[0059] Adaptive adjustment strategy:

[0060] Based on the magnitude of the error and the uncertainty estimate of the neural network, an adaptive adjustment strategy is developed. If the error is small and the uncertainty is low, a smaller adjustment step size can be used; if the error is large or the uncertainty is high, more aggressive adjustment measures can be taken, such as increasing the frequency or amplitude of adjustments.

[0061] S7, the power output adjustment and feedback stage, in which the intelligent power control uses the expected voltage value predicted by the neural network as the basis for adjusting the power output, communicates with the intelligent power controller through a digital interface, and accurately adjusts the power output; the power controller can dynamically adjust the output based on parameters such as real-time feedback of voltage and current values ​​to ensure that the actual output voltage is close to the expected voltage.

[0062] Closed-loop feedback and model update: Establish a strict closed-loop feedback system to continuously monitor various parameters and cutting effects during the actual cutting process.

[0063] If it is found that the actual cutting effect deviates significantly from the expected one, these new data can be added to the training set and the neural network can be updated online or offline to continuously optimize the performance of the model.

[0064] Preferably, the closed-loop feedback system can continuously monitor various key parameters during the actual cutting process, such as the real-time voltage value of the cutting torch, temperature and humidity, air pressure, current value, plasma gas flow rate, and actual cutting effect. This real-time monitoring enables the system to promptly detect deviations from the desired state and quickly take corrective measures.

[0065] For example, when there is a large deviation between the real-time voltage value and the expected voltage value predicted by the neural network, the system can immediately trigger the power output adjustment mechanism and quickly change the output voltage through the intelligent power controller to make the actual voltage closer to the expected voltage.

[0066] The closed-loop feedback system effectively reduces the impact of external interference and internal system uncertainties on the cutting process by continuously comparing and adjusting the actual output with the desired target. This helps improve the stability and reliability of the system, ensuring excellent cutting performance under various working environments and conditions.

[0067] For example, even when there are large seasonal and regional changes in temperature and humidity, the closed-loop feedback system can adjust system parameters in a timely manner based on real-time monitoring data to ensure the stability of the cutting process.

[0068] During the plasma cutting process, various factors may change dynamically over time, such as thermal deformation of the material, consumption of plasma gas, and wear of the equipment. A closed-loop feedback system can sense these changes in real time and adjust system parameters accordingly, keeping the system in optimal working condition at all times.

[0069] For example, as cutting time increases, the temperature of the cutting torch may rise, which may affect the performance and voltage output of the torch. A closed-loop feedback system can monitor changes in the cutting torch temperature. Online updating refers to adding new data to the training set in real time during the actual cutting process and updating the neural network. This method allows the model to quickly adapt to changes in actual work, improving its real-time performance and accuracy.

[0070] For example, if the system detects a significant deviation between the actual cutting effect and the expected value, it can immediately add the current parameters (including real-time voltage, temperature and humidity, air pressure, current, etc.) and the actual cutting effect as new data points to the training set. Then, using optimization algorithms such as mini-batch stochastic gradient descent, the neural network is updated online, allowing the model to adapt to new situations more quickly.

[0071] The frequency of online updates can be adjusted based on actual conditions. If changes in the cutting process are frequent, a higher update frequency can be set; if changes are relatively slow, the update frequency can be appropriately reduced to avoid excessive updates that may cause model instability.

[0072] S8: Collect large amounts of new data at regular intervals and then retrain the neural network. This approach can more comprehensively consider the long-term trends of the system and improve the model's generalization capabilities. For example, new data can be collected daily or weekly, and the neural network can be updated offline during non-working hours. During this update process, additional training techniques, such as data augmentation and regularization, can be used to improve model performance and stability.

[0073] Offline updates can be combined with online updates to form a hybrid update strategy. For example, online updates can be performed during daily cutting to quickly adapt to short-term changes, while offline updates can be performed during regular maintenance to fully optimize the model's performance.

[0074] S9: Select and filter the newly added data to ensure its quality and validity. Data can be filtered based on certain criteria, such as removing outliers and selecting representative data points. For example, you can set data quality indicators, such as data completeness, accuracy, and consistency. Only data that meets these indicators will be added to the training set for model updates. Additionally, data can be weighted based on its importance, giving important data a greater impact on the model update. S9: Evaluate and validate the updated model to ensure improved performance. You can use a validation set or a test set to evaluate the model and compare performance metrics before and after the update, such as accuracy and mean squared error.

[0075] For example, if the performance of the updated model on the validation set is significantly better than that of the model before the update, it means that the model update is effective; if the performance does not improve significantly or even deteriorates, it may be necessary to adjust the update strategy or reconsider the model architecture and parameters.

[0076] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A high-precision plasma cutting method, characterized in that: The steps include: S1, collect real-time voltage information, connect the feedback circuit of the cutting torch to FPGA, and obtain the real-time voltage value of the cutting torch a i ; S2, obtain the expected voltage value a0 in the MCU; S3, comparing the real-time voltage value with the expected voltage value; S4, comparing the real-time voltage value with the expected voltage value and calculating the error value; S5, according to the error value, the control amount is calculated through the operation of three links: proportional, integral and differential (PID); S6, using the calculated control amount as the basis for adjusting the power supply output, and putting the control amount into the expected voltage value to obtain the required input voltage value.

2. A high-precision plasma cutting method according to claim 1, characterized in that: The step S3 also includes the following sub-steps: S31, establish a table to record historical data, including real-time voltage value and expected voltage value; S32, obtain the linear relationship value K0 between the real-time voltage value and the expected voltage value from the table; S33, adjusting the voltage for the first time, through K0, obtaining an output voltage value a1 = expected voltage value a0 × linear relationship value K0; S34, compare a1 and a0. When the comparison result is within the absolute value of 20, skip steps S4 and S5. When the comparison result exceeds the absolute value of 20, perform the error value and control amount calculation of steps S4 and S5.

3. A high-precision plasma cutting method according to claim 1, characterized in that: The step S6 also includes the following sub-steps: S61, obtain the real-time voltage value a again t , a t Compare with the expected voltage value; S62, by comparing the results, t Make a rough adjustment to get closer to the method, each time a t Move 5 units closer to a0 until a t The comparison result with a0 is within 20 in absolute value; S63, for a t Make fine adjustments, each time by ±2 units, approaching a0 until the comparison result is within the absolute value of 2.

4. A high-precision plasma cutting method according to claim 1, characterized in that: In step S5, the proportional calculation formula is e=V 期望 -V 实时 , u p =K p ×e; where e is the error value, u p is the control quantity, K p is the proportional coefficient. In the initial debugging stage, first set K p Set K to 0.1 and observe the response of the system. If the real-time voltage converges to the expected voltage too slowly, gradually increase K p The absolute value of is adjusted until the system can respond quickly to errors but without showing noticeable oscillations.

5. A high-precision plasma cutting method according to claim 1, characterized in that: In step S5, the integral formula is: Among them, K i is the integral coefficient, and t is the time; the integral term will continuously accumulate errors. As time goes by, even if the error is small, the integral control amount will gradually increase, thereby pushing the real-time voltage closer to the desired voltage.

6. A high-precision plasma cutting method according to claim 1, characterized in that: In step S5, the differential formula is u d =K d ×d e / d t ; In the initial debugging stage, first set K d Set Kd to 0.1 and observe the response of the system. If the real-time voltage converges to the expected voltage too slowly, gradually increase the absolute value of Kd until the system can respond to the error quickly without obvious oscillation.

7. A high-precision plasma cutting method according to claim 1, characterized in that: In step S6, the control amount is the sum of the proportional, integral and differential control amounts u=u p +u i +u d , the total control amount u is obtained, and the real-time measured voltage value V is known, then the ratio k between the control amount and the real-time voltage value V can be known, k = V / u, and finally the adjusted input voltage value V1 can be obtained, V1 = V+k×u.

8. A high-precision plasma cutting method according to claim 1, characterized in that: The feedback circuit according to step S1 is an important component for transmitting the nozzle voltage signal to the FPGA for collection and processing, which includes: A sensor for detecting and measuring changes in the nozzle voltage; Amplifier: In feedback circuits, amplifiers are usually used to amplify the voltage signal obtained from the sensor to match the output of the sensor; Filter: The filter is used to remove noise and interference in the sensor output and pass the accurate voltage signal to the FPGA; The analog-to-digital converter (ADC) is a key component in the feedback circuit and is used to convert analog voltage signals into digital AD values. The ADC discretizes the continuous analog voltage signal.

9. A high-precision plasma cutting device, characterized in that: The invention comprises a plasma cutting torch realizing any one of claims 1 to 8.

Images