Control method of green depainting self-circulation treatment equipment

Abstract

The invention relates to a control method of green paint removal self-circulation treatment equipment, and relates to the technical field of paint cleaning, and the method comprises the following steps: S1, collecting liquid level signals of a clear water tank, a stock solution tank, a soaking tank and a turnover tank, and values of pH value, liquid temperature, conductivity, pump body vibration frequency, motor current and motor voltage; and S2, a clean water pump is controlled to inject clean water of a set volume into the soaking tank, a stock solution pump is controlled to inject stock solution, cleaning liquid for paint removal is prepared, and the concentration of the cleaning liquid is calculated through a machine learning model established based on the workpiece material type, the paint layer thickness and historical paint removal records. Through the machine learning model based on the workpiece material type, the paint layer thickness and the historical paint removal record, the concentration of the cleaning liquid is accurately calculated, automatic matching of the cleaning liquid is achieved, the stability of the paint removal effect is improved, the matching can be dynamically adjusted according to the characteristics of different workpieces, the risk of excessive corrosion or incomplete cleaning is reduced, and the working efficiency is improved. Therefore, the production efficiency and the workpiece quality are improved.

Description

Technical Field

[0001] This application relates to the technical field of paint cleaning, and specifically relates to a control method for a green paint stripping self-circulation treatment device. Background Art

[0002] The green paint stripping self-circulation treatment device is an automated system that realizes paint layer stripping through chemical cleaning liquid and recycles the treatment liquid, and is widely used in the field of surface remanufacturing and reprocessing of metal workpieces. Such devices usually integrate liquid storage tanks, heating units, spraying mechanisms, and liquid discharge and recovery devices, and their operation depends on a precise control method to coordinate multiple links such as liquid ratio, soaking process, liquid recovery, and equipment status monitoring. However, existing control strategies mostly adopt fixed parameters or empirical settings. Especially during the preparation process of the cleaning liquid, there is a lack of targeted identification and adjustment of factors such as workpiece material and paint layer thickness, resulting in the difficulty of dynamically adapting the cleaning liquid concentration to specific paint stripping requirements, thus affecting the paint stripping efficiency and cleaning quality. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides a control method for a green paint stripping self-circulation treatment device, which solves the problems mentioned in the above background art.

[0004] To achieve the above objectives, the present invention is realized through the following technical solutions: A control method for a green paint stripping self-circulation treatment device includes the following steps: S1. Collect the liquid level signals of the fresh water tank, stock solution tank, soaking tank, and turnover tank, as well as the values of pH, liquid temperature, conductivity, pump body vibration frequency, motor current, and motor voltage; S2. Control the fresh water pump to inject a set volume of fresh water into the soaking tank, and control the stock solution pump to inject the stock solution to prepare the cleaning liquid for paint stripping, where the concentration of the cleaning liquid is calculated by a machine learning model established based on the workpiece material type, paint layer thickness, and historical paint stripping records; S3. Start the soaking operation, read the pH, conductivity, and liquid temperature in real time, adjust the opening and closing state of the heating valve according to the target control range, and keep each parameter stable. The soaking duration is predicted and determined by a model trained with paint stripping data; S4. Open the drain valve of the soaking tank and the slag discharge and water filtering conveyor belt to guide the soaked liquid and paint slag to the recovery water tank and the waste slag bucket respectively; S5. Judge whether the liquid level of the turnover tank is lower than the recovery start threshold. If the condition is met, start the recovery pump to transport the recovered liquid to the turnover tank; S6. Start the cleaning pump, spray fresh water on the surface of the workpiece, and synchronously operate the conveyor belt to remove the residual liquid and paint slag; S7. Continuously collect the operating parameters of the pump body, and combine with the historical operating condition data to identify potential fault trends through a trained deep learning model and generate maintenance suggestions.

[0005] Preferably, the step of collecting data includes: real-time reading of the liquid level signals of the clean water tank, stock solution tank, soaking tank, and turnover tank, and simultaneously recording the pH value, temperature, conductivity, pump body operating status, and conveyor belt start / stop time.

[0006] Preferably, the step of preparing the cleaning solution includes: According to the read clean water injection time and the target pH value range, select the stock solution injection time with approximate conditions from the historical operation data, and use the interpolation calculation method to determine the current injection duration; The interpolation calculation includes: Select two samples with the closest pH values to the target pH value from the known historical data, and assume that their corresponding pH values are respectively 、 , and the corresponding stock solution injection times are 、 , then the current injection time is determined by the following formula: Wherein, is the target pH value set for this paint stripping process.

[0007] Preferably, during the ratio calculation process, by identifying the cleaning solution parameters corresponding to the workpiece material and paint layer thickness, and combining the previous paint stripping results, automatically optimize the ratio of the stock solution to the clean water to update the subsequent injection control instructions.

[0008] Preferably, the soaking control process includes: reading the pH value, temperature, and conductivity every set time interval. If a certain parameter exceeds the preset range, automatically adjust the opening and closing state of the heating valve or the state of the liquid supplement valve to restore it to the target range.

[0009] Preferably, the method for determining the soaking duration includes: extracting the average processing time of this type of workpiece from the data of the completed paint stripping operation as the basic duration, and dynamically adjusting the termination moment of this soaking in combination with the real-time performance of the current liquid parameters; Among them, if any two of the three items of pH value, temperature, and conductivity deviate from the target range for three consecutive cycles, automatically extend the soaking time; if the parameters return to stability and meet the termination conditions, end the treatment in advance and enter the next process.

[0010] Preferably, the steps for constructing the machine learning model used to calculate the cleaning solution concentration include: Collect the stock solution injection time, clean water injection time, target pH value, and actual paint stripping residue corresponding to different workpiece materials and paint layer thicknesses; Input the above data as training samples into the regression algorithm model to generate the functional relationship for predicting the ratio of the original liquid to clear water. During subsequent operation, input the current workpiece parameters as the model input to obtain the time parameter output for this injection.

[0011] Preferably, the steps for establishing the deep learning model for identifying fault trends include: Record the pump body vibration frequency, motor current changes, voltage fluctuations, and historical maintenance records to establish an equipment status sample set. Use a convolutional neural network to extract the characteristic patterns of the above time series data and train a discriminant model for identifying abnormal operation trends of the pump body. Continuously input the current status data during equipment operation, compare the model determination output. If the abnormal score exceeds the set threshold, generate a maintenance prompt.

[0012] Preferably, the cleaning step includes: after opening the slag discharge conveyor belt and the drainage valve of the soaking tank, start the cleaning pump to spray clear water on the surface of the workpiece, and the cleaning duration is automatically matched from the database according to the workpiece category.

[0013] Preferably, during the whole process of cleaning liquid preparation, soaking treatment, liquid recovery, and spray cleaning, continuously monitor the pump body vibration, motor current, and working time, and combine historical abnormal working condition data to identify the operation trend to prompt possible fault points in advance.

[0014] In summary, the present application includes at least one of the following beneficial technical effects: 1. The present invention accurately calculates the concentration of the cleaning liquid through a machine learning model based on the workpiece material type, paint layer thickness, and historical paint stripping records, realizes the automatic proportioning of the cleaning liquid, not only improves the stability of the paint stripping effect, but also can dynamically adjust the proportion according to the characteristics of different workpieces, reduces the risk of over-corrosion or incomplete cleaning, thereby improving production efficiency and workpiece quality; 2. The present invention adopts a soaking process control method based on real-time monitoring. By automatically adjusting the opening and closing states of the heating valve and the liquid supply valve, the pH value, temperature, and conductivity of the liquid are always maintained within the target range. In addition, dynamically adjusting the soaking duration, combining historical data prediction and real-time changes of current liquid parameters, can ensure the best paint stripping effect, thereby improving the efficiency of the entire paint stripping process; 3. The present invention uses a deep learning model to analyze the operation data of the equipment, continuously monitors multi-dimensional parameters such as pump body vibration, motor current, and voltage, can predict potential equipment fault trends in advance, and generate maintenance suggestions, thereby being able to reduce the downtime of the equipment, reduce unnecessary maintenance costs, and improve the reliability and availability of the system. Description of the Drawings

[0015] Figure 1 This is the flowchart of the present invention. Detailed implementation manners

[0016] The following will further elaborate on this application in conjunction with the attached Figure 1 drawings.

[0017] Embodiment: The embodiment of the present invention provides a control method for a green paint stripping self - circulation treatment device, including the following steps: S1. Collect the liquid level signals of the clean water tank, stock solution tank, soaking tank, and turnover tank, as well as the values of pH, liquid temperature, conductivity, pump body vibration frequency, motor current, and motor voltage; S2. Control the clean water pump to inject a set volume of clean water into the soaking tank, and control the stock solution pump to inject the stock solution to prepare the cleaning solution for paint stripping, where the concentration of the cleaning solution is calculated by a machine learning model established based on the workpiece material type, paint layer thickness, and historical paint stripping records; S3. Start the soaking operation, read the pH, conductivity, and liquid temperature in real - time, adjust the opening and closing state of the heating valve according to the target control range, and keep each parameter stable. The soaking duration is predicted and determined by a model trained with paint stripping data; S4. Open the drainage valve of the soaking tank and the slag - discharging and water - filtering conveyor belt to guide the soaked liquid and paint slag to the recovery water tank and the waste slag bucket respectively; S5. Judge whether the liquid level of the turnover tank is lower than the recovery start threshold. If the condition is met, start the recovery pump to transport the recovered liquid to the turnover tank; S6. Turn on the cleaning pump, spray clean water on the surface of the workpiece, and synchronously operate the conveyor belt to remove the residual liquid and paint slag; S7. Continuously collect the operation parameters of the pump body, and combine with the historical operation condition data to identify the potential fault trend through a trained deep - learning model and generate maintenance suggestions.

[0018] Specifically, by collecting the liquid level signals of the clean water tank, stock solution tank, soaking tank, and turnover tank in real - time, and combining parameters such as pH, temperature, conductivity, motor current, and pump body vibration, the closed - loop control of the entire paint stripping process is completed. The control logic is based on inputs such as workpiece material and paint layer thickness, automatically adjusting the liquid - mixing ratio, heating time, and soaking rhythm to ensure the stable and efficient paint stripping process. During the processing, the device can dynamically adjust the control strategy according to the real - time changes in the liquid state to achieve adaptive operation, avoiding the deviation caused by manual parameter setting. At the same time, during operation, by continuously analyzing the operation state of the device, potential fault risks are identified in advance, and maintenance suggestions are generated. It has strong environmental adaptability and processing consistency, significantly improving the paint stripping efficiency and cleaning quality, reducing energy consumption and manual dependence, and realizing an integrated green, energy - saving, and intelligent paint stripping process.

[0019] The steps of collecting data include: real-time reading of the liquid level signals of the fresh water tank, stock solution tank, soaking tank, and turnover tank, and synchronously recording the pH value, temperature, conductivity, pump operation status, and conveyor belt start / stop time.

[0020] Specifically, this control method realizes real-time perception of the whole process working conditions by continuously monitoring the liquid levels of key liquid units, including the fresh water tank, stock solution tank, soaking tank, and turnover tank, and synchronously collecting operation data such as the pH value, temperature, conductivity of the liquid, pump operation status, and motor current. This comprehensive data acquisition method ensures the integrity and timeliness of the parameters required for each stage of the paint stripping process, provides a sufficient data basis for subsequent control decisions, and can accurately identify key issues such as whether the liquid preparation is accurate, whether the heating meets the standard, and whether the cleaning is uniform by fusing multi-point parameters to judge the liquid state, thereby triggering timely adjustment to ensure the stable operation of the process. Compared with the traditional mode that relies on manual inspection and experience judgment, this method greatly improves the intelligence and processing efficiency of control and reduces the paint stripping failure rate caused by parameter deviation.

[0021] The steps of preparing the cleaning solution include: According to the read fresh water injection time and the target pH value range, select the stock solution injection time under approximate conditions from the historical operation data, and use the interpolation calculation method to determine the current injection duration; The interpolation calculation includes: Select two samples with the closest pH values to the target pH value from the known historical data, and set their corresponding pH values as 、 , and the corresponding stock solution injection times are 、 , then the current injection time is determined by the following formula: Among them, is the target pH value set for this paint stripping process.

[0022] Specifically, in the cleaning solution preparation stage, according to the actually read pure water injection time and the target pH value, the historical stock solution injection duration sample closest to the current conditions is extracted from the database, and the interpolation algorithm is used to accurately calculate the current stock solution injection time, so as to form a cleaning solution concentration that better meets the paint stripping requirements. This combination strategy of "sample comparison + interpolation prediction" instead of fixed-ratio injection significantly improves the accuracy of solution preparation, and can flexibly adjust the injection volume according to the fluctuation of pure water flow or temperature change, avoiding the influence of cleaning solution concentration deviation on the paint stripping effect. Since the control method has the ability to respond to on-site real-time data, while maintaining the stability of paint stripping quality, it also reduces the waste of stock solution, improves the utilization rate of raw materials, and at the same time, compared with the empirical ratio, this method is more intelligent and adaptable, and is suitable for stable operation under complex working conditions.

[0023] During the above-mentioned ratio calculation process, by identifying the cleaning solution parameters corresponding to the workpiece material and paint layer thickness, the ratio of stock solution to pure water is automatically optimized in combination with the previous paint stripping result, so as to update the subsequent injection control instruction.

[0024] Specifically, during the cleaning solution preparation process, according to the identified workpiece material and paint layer thickness information, the paint stripping data under the corresponding conditions in history is retrieved, and the relationship between the actual concentration of the cleaning solution and the paint stripping effect is automatically analyzed, so as to optimize the injection ratio of the stock solution to pure water. The control method not only issues adjustment instructions for the current solution preparation process, but also feeds back the optimization result to the formula library for updating the control strategy under subsequent similar conditions. Through this method, the ratio of the cleaning solution can be intelligently adapted according to the workpiece differences and no longer depends on the preset empirical values, ensuring that the concentration meets the paint stripping requirements without causing resource waste.

[0025] The above-mentioned soaking control process includes: reading the pH value, temperature and conductivity every set time interval. If a certain parameter exceeds the preset range, the opening and closing state of the heating valve or the state of the liquid supplement valve is automatically adjusted to restore it to the target range.

[0026] Specifically, during the workpiece soaking process, key liquid parameters including pH value, temperature and conductivity are collected at set time intervals and compared with the set target range in real time. When any parameter deviates from the control range, the device automatically judges the deviation direction and amplitude, and intelligently controls the opening and closing of the heating valve or the stock solution liquid supplement valve to quickly correct and stabilize the liquid state. Compared with the traditional timed heating or fixed-concentration injection method, a feedback closed-loop regulation mechanism is introduced, so that the liquid state is always within the physicochemical range beneficial to the paint stripping reaction, improving the paint stripping efficiency and the uniformity of surface treatment, and also significantly reducing problems such as incomplete cleaning or workpiece corrosion caused by abnormal liquid.

[0027] The method for determining the soaking duration includes: extracting the average processing time of this type of workpiece from the data that has completed the paint stripping operation as the basic duration, and dynamically adjusting the termination moment of this soaking in combination with the real-time performance of the current liquid parameters; Among them, if any two of the pH value, temperature, and conductivity deviate from the target range for three consecutive cycles, the soaking time is automatically extended; if the parameters return to stability and meet the termination conditions, the processing is ended in advance and the next process is entered.

[0028] Specifically, during the soaking process, the average processing duration of historical similar workpieces is used as the initial reference value, and the liquid state parameters monitored in real time are introduced for dynamic judgment. If any two of the pH value, conductivity, or temperature deviate from the target control range for three consecutive sampling cycles, the current soaking time is automatically extended; if the parameters are stable within the set range for two consecutive cycles, the soaking is terminated in advance. This control logic based on "parameter stability" effectively avoids the phenomena of insufficient cleaning or excessive corrosion caused by external disturbances or liquid deterioration, makes the paint stripping treatment more accurate and controllable, and improves the intelligent level of the entire process and the coordination of the processing rhythm.

[0029] The steps for constructing the machine learning model used to calculate the concentration of the cleaning liquid include: Collect the original liquid injection time, clean water injection time, target pH value, and actual paint stripping residue corresponding to different workpiece materials and paint layer thicknesses; Input the above data as training samples into the regression algorithm model to generate a functional relationship for predicting the ratio of the original liquid to clean water; In subsequent operations, input the current workpiece parameters as the model input to obtain the time parameter output for this injection.

[0030] Specifically, in the liquid preparation control stage, the method of the present invention constructs multi-dimensional training samples by collecting different workpiece materials, paint layer thicknesses, injection times, target pH values, and paint stripping effect indicators in historical operation data, and uses the regression algorithm to establish a concentration prediction model. In actual application, the system inputs the current workpiece information into the model and outputs the optimal injection time and ratio, thereby realizing personalized adjustment of the cleaning liquid preparation, effectively improving the scientificity and adaptability of the liquid preparation control, changing the concentration adjustment from empirical setting to data-driven prediction, avoiding resource waste while improving the paint stripping efficiency, and being particularly suitable for flexible manufacturing scenarios with multiple categories and small batches.

[0031] The steps for establishing the deep learning model for identifying fault trends include: Record the pump body vibration frequency, motor current change, voltage fluctuation, and historical maintenance records to establish an equipment status sample set; Use a convolutional neural network to extract the characteristic patterns of the above time series data and train a discriminant model for identifying abnormal operation trends of the pump body; During the operation of the device, continuously input the current state data, compare the model judgment output, and if the abnormal score exceeds the set threshold, generate a maintenance prompt.

[0032] Specifically, by continuously collecting key state data during the operation of the device, including pump body vibration frequency, motor current, voltage fluctuation, start-stop frequency, etc., and matching with the historical fault sample set, using a convolutional neural network to extract sequence change features, establishing a trend prediction model, during the operation of the device, input new data in real time and calculate the abnormal score, when the threshold is exceeded, the system prompt for pre-maintenance is triggered, improving the recognition accuracy of potential abnormalities of the device, realizing the transformation from passive maintenance to active early warning, significantly reducing the sudden failure rate and maintenance downtime, and enhancing the guarantee ability of the control method for the operation safety of the device.

[0033] The cleaning step includes: after opening the slag discharge conveyor belt and the soaking tank drain valve, start the cleaning pump to spray clean water on the surface of the workpiece, and the cleaning duration is automatically matched from the database according to the workpiece category.

[0034] Specifically, in the cleaning stage, this control method calls the corresponding cleaning time parameters based on the workpiece type, controls the start and stop of the slag discharge conveyor belt and the opening and closing of the soaking tank drain valve, and at the same time starts the spray pump to perform the cleaning operation. The method sets a timed spray cycle and automatically matches the spray duration in combination with the workpiece classification model to ensure the rationality of the cleaning intensity and time for different workpieces, can effectively remove the residual paint stripping liquid and paint slag particles, shorten the unnecessary flushing time at the same time, improve the overall processing efficiency, and prevent problems such as secondary pollution or difficulties in subsequent processing caused by insufficient cleaning, which is an indispensable optimization link in the paint stripping process.

[0035] During the whole process of cleaning liquid preparation, soaking treatment, liquid recovery and spray cleaning, continuously monitor the pump body vibration, motor current and working time, and identify the operation trend in combination with the historical abnormal working condition data to prompt possible fault points in advance.

[0036] Specifically, the control method of the present invention continuously collects and analyzes state parameters such as motor current, pump body vibration frequency, running time, etc. during the whole process of cleaning liquid preparation, soaking treatment, and cleaning switching, and constructs a trend recognition model in combination with historical abnormal behavior data to dynamically judge the stability of the operation state. When the system determines that the parameter change is close to the precursor of historical faults, immediately issue a maintenance warning, realizing the state perception and trend recognition of the whole life cycle of the processing equipment operation, making the maintenance activity no longer rely on manual inspection or fixed cycle, but actively respond based on the risk level, which helps to significantly improve the equipment utilization rate and ensure production continuity and operation safety.

[0037] The embodiments of this specific implementation manner are all preferred embodiments of this application, and do not limit the protection scope of this application accordingly. The same components are denoted by the same reference numerals. Therefore, all equivalent changes made according to the structure, shape, and principle of this application shall be covered within the protection scope of this application.

Claims

1. A control method for a green paint stripping self-circulation treatment device, characterized in that, It includes the following steps: S1. Collect the liquid level signals of the clean water tank, stock solution tank, soaking tank, and turnover tank, as well as the values of pH, liquid temperature, conductivity, pump body vibration frequency, motor current, and motor voltage; S2. Control the clean water pump to inject a set volume of clean water into the soaking tank, control the stock solution pump to inject the stock solution, and prepare the cleaning solution for paint stripping. The concentration of the cleaning solution is calculated by a machine learning model established based on the workpiece material type, paint layer thickness, and historical paint stripping records; S3. Start the soaking operation, read the pH, conductivity, and liquid temperature in real time, adjust the opening and closing state of the heating valve according to the target control range, and keep each parameter stable. The soaking duration is predicted and determined by a model trained with paint stripping data; S4. Open the drainage valve of the soaking tank and the slag discharge and water filtering conveyor belt, and guide the soaked liquid and paint slag to the recovery water tank and the waste slag bucket respectively; S5. Judge whether the liquid level of the turnover tank is lower than the recovery start threshold. If the condition is met, start the recovery pump to transport the recovered liquid to the turnover tank; S6. Turn on the cleaning pump, spray clean water on the surface of the workpiece, and synchronously operate the conveyor belt to remove the residual liquid and paint slag; S7. Continuously collect the pump body operation parameters, and combine the historical operation condition data to identify potential fault trends through a trained deep learning model and generate maintenance suggestions.

2. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that, The step of collecting data includes: reading the liquid level signals of the clean water tank, stock solution tank, soaking tank, and turnover tank in real time, and synchronously recording the pH, temperature, conductivity, pump body operation state, and conveyor belt start and stop time.

3. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that The step of preparing the cleaning solution includes: According to the read clean water injection time and the target pH value range, select the stock solution injection time with approximate conditions from the historical operation data, and use the interpolation calculation method to determine the current injection duration; The interpolation calculation includes: Select two sets of samples with the pH values closest to the target pH value from the known historical data, and let the corresponding pH values be , , respectively. The corresponding liquid injection times of the stock solutions are , . Then the current liquid injection time is determined by the following formula: Among them, is the target pH value set for this paint stripping process.

4. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that, In the ratio calculation process, by identifying the cleaning solution parameters corresponding to the workpiece material and paint layer thickness, and combining the previous paint stripping result, automatically optimize the ratio of the stock solution to the clean water to update the subsequent injection control instruction.

5. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that, The soaking control process includes: reading the pH, temperature, and conductivity at each set time interval. If a certain parameter exceeds the preset range, automatically adjust the opening and closing state of the heating valve or the state of the liquid supplement valve to restore it to the target range.

6. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that The method for determining the soaking duration includes: extracting the average processing time of this type of workpiece from the data of the completed paint stripping operation as the basic duration, and dynamically adjusting the termination moment of this soaking in combination with the real-time performance of the current liquid parameters; Among them, if any two of the three items of pH, temperature, and conductivity deviate from the target range for three consecutive cycles, the soaking time is automatically extended; if the parameters return to stability and meet the termination conditions, the treatment is ended in advance and the next process is entered.

7. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that, The steps for constructing the machine learning model used to calculate the cleaning solution concentration include: Collect the stock solution injection time, clean water injection time, target pH value, and actual paint stripping residue corresponding to different workpiece materials and paint layer thicknesses; Input the above data as training samples into the regression algorithm model to generate a functional relationship for predicting the ratio of the stock solution to the clean water; In subsequent operations, input the current workpiece parameters as the model input to obtain the time parameter output for this injection.

8. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that, The steps for establishing the deep learning model for identifying fault trends include: Record the vibration frequency of the pump body, the change in motor current, voltage fluctuations, and historical maintenance records, and establish a sample set of equipment states; Use a convolutional neural network to extract the characteristic patterns of the above time series data and train a discriminant model for identifying abnormal operation trends of the pump body; Continuously input the current state data during equipment operation, compare the model's judgment output. If the abnormal score exceeds the set threshold, generate a maintenance prompt.

9. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that, The cleaning steps include: After opening the slag discharge conveyor belt and the drainage valve of the soaking tank, start the cleaning pump to spray clean water on the surface of the workpiece, and the cleaning duration is automatically matched from the database according to the workpiece category.

10. The control method of a green paint stripping self-circulation treatment device according to claim 1, characterized in that, During the whole process of cleaning liquid preparation, soaking treatment, liquid recovery, and spray cleaning, continuously monitor the pump body vibration, motor current, and working time, and combine historical abnormal working condition data to identify the operation trend to prompt possible fault points in advance.

Images