Intelligent identification and self-adaptive suppression control method and system for reverse corona of electric dust collector

Abstract

The embodiment of the disclosure provides an electric dust collector reverse corona intelligent identification and adaptive suppression control method and system, belonging to the technical field of electric dust collector operation control. The method comprises: collecting each electric field secondary voltage and secondary current in real time; preliminarily determining the reverse corona state based on the slope and second derivative of the voltage-current characteristic curve; performing fast Fourier transform on the secondary current waveform, extracting the harmonic amplitude and phase, and calculating the reverse corona index in combination with the curve slope; adopting a multi-level determination strategy based on the index threshold, duration and consistency of adjacent electric fields to confirm the reverse corona event; automatically selecting adaptive suppression strategies such as voltage reduction, pulse power supply or intermittent pulse power supply according to the severity; calculating the suppression efficiency, and adjusting the weight coefficient and recalculating the index when the suppression efficiency is lower than the threshold. The disclosure realizes early and accurate identification and adaptive suppression of reverse corona, improves detection accuracy and control effectiveness, and guarantees stable and efficient operation of the electric dust collector.

Description

Technical Field

[0001] The embodiments disclosed herein belong to the field of electrostatic precipitator operation control technology, specifically relating to an intelligent identification and adaptive suppression control method and system for back corona discharge in electrostatic precipitators. Background Technology

[0002] Electrostatic precipitators (ESPs) are key equipment for flue gas dust control in coal-fired power plants, and their dust removal efficiency directly affects the power plant's emission standards and environmental performance. During ESP operation, back corona discharge is a common fault condition, characterized by a reverse electric field appearing inside the ESP, weakening the dust removal electric field strength. In severe cases, this can lead to a sharp drop in dust removal efficiency or even equipment damage.

[0003] The mechanism of back corona discharge is complex and mainly related to the following factors: when burning high-ash and high-sulfur coal, the resistivity of dust in the flue gas increases; the increase in flue gas temperature leads to changes in the conductivity of the dust surface; and improper setting of electric field operating parameters causes the electric field strength to exceed the critical value. After back corona discharge occurs, the electric field voltage-current characteristic curve will show characteristic changes, mainly manifested as an increase in voltage without a corresponding increase in current, and the slope of the curve changing from positive to negative.

[0004] Currently, back corona detection in electrostatic precipitators mainly relies on manual inspections and simple threshold alarms, which have the following shortcomings: strong detection lag, often only being discovered after back corona has developed significantly; single judgment criteria, relying solely on single parameter thresholds of voltage or current, making it difficult to accurately identify the early stages of back corona; crude suppression measures, usually employing a one-size-fits-all voltage reduction strategy, unable to adaptively adjust according to the severity of back corona; and lack of predictive capabilities, only able to respond passively, unable to provide early warnings or prevention. Summary of the Invention

[0005] The embodiments disclosed herein aim to at least solve one of the technical problems existing in the prior art, including lagging back corona detection, single judgment basis, and crude suppression measures, and provide a method and system for intelligent identification and adaptive suppression control of back corona in electrostatic precipitators.

[0006] One aspect of this disclosure provides a method for intelligent identification and adaptive suppression control of back corona discharge in an electrostatic precipitator, the control method comprising: Real-time acquisition of secondary voltage and secondary current in each electric field of the electrostatic precipitator; Based on the collected data, the voltage-current characteristic curves of each electric field are plotted in real time, and the slope and second derivative of the curves are calculated. When a negative value is detected in the slope or a sudden change occurs in the second derivative, it is preliminarily determined that the corresponding electric field has entered the back corona state. Fast Fourier transform is performed on the secondary current waveform to extract the amplitude and phase of the fundamental component, third harmonic, fifth harmonic and seventh harmonic, and the back corona index is calculated by combining the slope of the characteristic curve, the reference slope and the weighting coefficient. A multi-level determination strategy is adopted to confirm the back corona event; wherein, the first level of the multi-level determination strategy is based on the back corona index threshold, the second level is based on the state duration, and the third level is based on the consistency check of adjacent electric fields. The suppression strategy is automatically selected based on the severity of the back corona event; wherein, the suppression strategy includes reducing the supply voltage for mild back corona, entering pulse power supply mode and reducing the base DC voltage for moderate back corona, and entering intermittent pulse power supply mode for severe back corona. Monitor the electric field operating parameters, calculate the suppression efficiency, and when the suppression efficiency is lower than the preset efficiency threshold, adjust the weighting coefficient and recalculate the back corona index.

[0007] Furthermore, the real-time plotting of voltage-current characteristic curves for each electric field based on the collected data includes: Based on the sliding window method, the least squares method is used to perform curve fitting of the secondary voltage and secondary current using a second-order polynomial to obtain the fitting equation.

[0008] Furthermore, when the coefficients of the second-order terms of the fitted equation are less than a preset coefficient threshold, it is preliminarily determined that the corresponding electric field has entered the anti-corona state.

[0009] Furthermore, the anti-corona index is calculated using the following formula:

[0010] In the formula, The anti-corona index, The slope of the voltage-current characteristic curve. This is the baseline slope under normal operating conditions. For the fundamental component, , , These are the third, fifth, and seventh harmonics, respectively. , , These are the weighting coefficients. express….

[0011] Furthermore, the weighting coefficients are obtained from the operating parameters through a pre-trained BP neural network model; wherein the operating parameters include flue gas temperature, inlet dust concentration, coal ash content, and electric field operating time.

[0012] Furthermore, the first level of determination based on the anti-corona index threshold includes: when the anti-corona index is greater than a preset index threshold, it is determined to be a suspected anti-corona state; The second level is based on the duration of the state, including: when the suspected anti-corona state lasts for more than a preset time threshold, it is determined that the state has entered the anti-corona state; The third level of consistency verification based on adjacent electric fields includes: when the consistency of the back corona state of adjacent electric fields in the same dust collector exceeds a preset consistency threshold, it is determined to be a back corona state caused by changes in operating conditions. The multi-level determination strategy for confirming anti-corona events includes: when all three determination levels are met, it is confirmed as an anti-corona event.

[0013] Furthermore, the pulse peak voltage of the pulse power supply mode is 80%~90% of the rated voltage, the pulse width is 50μs~200μs, the pulse repetition frequency is 50Hz~500Hz, the pulse duty cycle is 5%~30%, and the base DC voltage is 40%~60% of the rated voltage.

[0014] Furthermore, the control method further includes: An anti-corona prediction model is established based on long-term operating data; wherein, the input parameters of the anti-corona prediction model include flue gas temperature, inlet dust concentration, coal ash content, boiler load, and current operating power ratio; the output of the anti-corona prediction model is the probability of anti-corona occurrence.

[0015] Another aspect of this disclosure provides an intelligent identification and adaptive suppression control system for back corona discharge in an electrostatic precipitator, used to implement the control method described above, the control system comprising: The data acquisition module is used to collect the secondary voltage and secondary current of each electric field of the electrostatic precipitator in real time; The curve analysis module is used to plot the voltage-current characteristic curves of each electric field in real time based on the collected data, and calculate the slope and second derivative of the curves; when a negative value is detected in the slope or a sudden change occurs in the second derivative, it is preliminarily determined that the corresponding electric field has entered the back corona state. The index calculation module is used to perform fast Fourier transform on the secondary current waveform, extract the amplitude and phase of the fundamental component, third harmonic, fifth harmonic and seventh harmonic, and calculate the back corona index by combining the slope of the characteristic curve, the reference slope and the weighting coefficient. A multi-level determination module is used to confirm the back corona event using a multi-level determination strategy; wherein, the first level of the multi-level determination strategy is based on the back corona index threshold, the second level is based on the state duration determination, and the third level is based on the consistency check determination of adjacent electric fields. The power supply control module is used to automatically select a suppression strategy based on the severity of the back corona event; wherein, the suppression strategy includes reducing the supply voltage when there is mild back corona, entering a pulse power supply mode and reducing the base DC voltage when there is moderate back corona, and entering an intermittent pulse power supply mode when there is severe back corona. The closed-loop adjustment module is used to monitor the electric field operating parameters, calculate the suppression efficiency, and adjust the weighting coefficient and recalculate the back corona index when the suppression efficiency is lower than the preset efficiency threshold.

[0016] Furthermore, the control system also includes a probability prediction module, which is used for: An anti-corona prediction model is established based on long-term operating data; wherein, the input parameters of the anti-corona prediction model include flue gas temperature, inlet dust concentration, coal ash content, boiler load, and current operating power ratio; the output of the anti-corona prediction model is the probability of anti-corona occurrence.

[0017] This disclosure discloses an intelligent identification and adaptive suppression control method and system for back corona in electrostatic precipitators. Through multi-parameter fusion of back corona index calculation and combined with voltage-current curve slope and harmonic analysis results, it can accurately identify the early stage of back corona. Employing a multi-level judgment strategy, it comprehensively considers the back corona index threshold, duration, and spatial consistency, avoiding misjudgments and missed judgments. It automatically selects the power supply mode according to the severity of back corona, achieving adaptive adjustment of suppression measures. This improves the accuracy of back corona detection and the effectiveness of suppression, ensuring the stable and efficient operation of the electrostatic precipitator. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating an embodiment of an intelligent identification and adaptive suppression control method for back corona discharge in an electrostatic precipitator. Figure 2 This is a schematic diagram of the structure of an intelligent identification and adaptive suppression control system for back corona discharge in an electrostatic precipitator, according to another embodiment of this disclosure. Detailed Implementation

[0019] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this disclosure.

[0020] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0021] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0022] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Therefore, the first component discussed below may be referred to as the second component without departing from the teachings of this disclosure. As used in this disclosure, the term "and / or" includes all combinations of any one and more of the associated listed items.

[0023] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of exemplary embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing this disclosure, and therefore cannot be used to limit the scope of protection of this disclosure.

[0024] like Figure 1 As shown, one embodiment of this disclosure provides a method for intelligent identification and adaptive suppression control of back corona in an electrostatic precipitator, comprising: Step S1: Real-time acquisition of secondary voltage and secondary current of each electric field of the electrostatic precipitator.

[0025] Specifically, the electrostatic field operating parameters are acquired in real time through voltage sensors, current sensors, temperature sensors, and data interfaces, and the secondary voltage of the high-voltage power supply for each electric field of the electrostatic precipitator is acquired simultaneously. Secondary current Output voltage and output current and spark rate and flue gas temperature The collected data, after digital filtering, can be stored in a real-time database.

[0026] Step S2: Based on the collected data, the voltage-current characteristic curves of each electric field are plotted in real time, and the slope and second derivative of the curves are calculated. When a negative value is detected in the slope or a sudden change occurs in the second derivative, it is preliminarily determined that the corresponding electric field has entered the back corona state.

[0027] Specifically, dynamic analysis of the voltage-current characteristic curves is performed. Based on the data collected in step S1, voltage-current data points are collected every 10 seconds using the sliding window method. After collecting 60 data points continuously, the least squares method is used to fit the second-order polynomial to the secondary voltage and secondary current curves, obtaining the fitting equation, thereby plotting the voltage-current characteristic curves of each electric field in real time. The slope of the curve is calculated. and second derivative When the slope is detected Negative values ​​or slopes Less than the reference slope under normal operating conditions or second derivative A sudden change occurs (second derivative under normal operating conditions) When ≈0), it is preliminarily determined that the electric field may have entered the reverse corona state.

[0028] The fitting equation is shown in the following formula:

[0029] The coefficients of the second-order terms in the formula This reflects the degree of nonlinearity of the electric field. Under normal operating conditions, the coefficients of the second-order terms... Approaching zero; when the electric field exhibits a back corona tendency, the coefficients of the second-order terms... It gradually becomes negative. Therefore, when the coefficient of the second-order term... Less than a preset coefficient threshold This indicates that the electric field is showing signs of saturation and can also serve as a preliminary basis for determining the risk of back corona discharge in the electric field.

[0030] Step S3: Perform a fast Fourier transform on the secondary current waveform to extract the amplitude and phase of the fundamental component, third harmonic, fifth harmonic and seventh harmonic, and calculate the back corona index by combining the slope of the characteristic curve, the reference slope and the weighting coefficient.

[0031] Specifically, waveform features are extracted for the secondary current. The waveform was subjected to a 1024-point Fast Fourier Transform (FFT) to extract the fundamental component. Third harmonic Fifth harmonic and the seventh harmonic The amplitude and phase were then calculated. The back corona index was subsequently calculated. As shown in the following formula:

[0032] In the formula, The anti-corona index, The slope of the voltage-current characteristic curve. This is the baseline slope under normal operating conditions. For the fundamental component, , , These are the third, fifth, and seventh harmonics, respectively. , , These are the weighting coefficients. express….

[0033] The weighting coefficient , , The training of the BP neural network, determined through pre-training, includes: training the BP neural network model based on a historical anti-corona event database; its input features are operating parameters, including flue gas temperature. Inlet dust concentration ash content of coal and electric field running time Its output is the optimal combination of weight coefficients, i.e. , , The value of the back corona index. Ultimately, this leads to the value of the back corona index. The accuracy of the calculation results in fitting the actual anti-corona state labels is over 95%.

[0034] Step S4: Use a multi-level decision strategy to confirm the back corona event; wherein, the first level of the multi-level decision strategy is based on the back corona index threshold, the second level is based on the state duration, and the third level is based on the consistency check of adjacent electric fields.

[0035] Specifically, based on the back corona index obtained in step S3 The anti-corona state is determined in multiple levels. The multi-level determination strategy specifically includes: Level 1, when the anti-corona index... Greater than the preset exponential threshold When the value is between 25 and 35, it is determined to be a suspected back corona discharge state; the second level is when the suspected back corona discharge state continues for more than a preset time threshold. When the time interval is 30s~60s, it is determined that the back corona state has been confirmed. In the third stage, the consistency of the back corona state of adjacent electric fields within the same dust collector is calculated. When the consistency exceeds a preset consistency threshold (e.g., 80%), it is determined that the back corona state is caused by a change in operating conditions. When it does not exceed the consistency threshold, it is determined that it is a local fault. When all three levels of determination meet the back corona conditions, it is confirmed as a back corona event and the suppression strategy in the next step S5 is triggered.

[0036] Step S5: Automatically select a suppression strategy based on the severity of the back corona event; wherein the suppression strategy includes reducing the supply voltage for mild back corona, entering a pulse power supply mode and reducing the base DC voltage for moderate back corona, and entering an intermittent pulse power supply mode for severe back corona.

[0037] Specifically, adaptive power supply mode switching is performed, and suppression strategies are automatically selected according to the severity of back corona, including: reducing the supply voltage to 85%~95% of the rated value when there is mild back corona; switching to pulse power supply mode and reducing the base DC voltage to 40%~60% of the rated value when there is moderate back corona; and entering intermittent pulse power supply mode when there is severe back corona.

[0038] The parameters for the pulse power supply mode are set as follows: pulse peak voltage. 80%~90% of the rated voltage; pulse width The pulse repetition frequency ranges from 50μs to 200μs. 50Hz~500Hz; pulse duty cycle 5%~30%; base DC voltage It is 40% to 60% of the rated voltage.

[0039] In some embodiments, when the back corona index If the value is in the range [25, 35), it is considered a mild back corona; when the back corona index... If the value is in the range [35, 50), it is considered a moderate back corona discharge; when the back corona index... A value of not less than 50 indicates severe back corona.

[0040] Step S6: Monitor the electric field operating parameters and calculate the suppression efficiency. When the suppression efficiency is lower than the preset efficiency threshold, adjust the weighting coefficient and recalculate the back corona index.

[0041] Specifically, after the suppression strategy in step S5 is executed, the electric field operating parameters are continuously monitored, and the suppression efficiency is calculated. The effect of anti-corona suppression was evaluated. When >50%, maintain the current suppression strategy; when When the level is less than 50%, the back corona index is automatically adjusted. Weighting coefficients in the calculation formula , , Recalculate the back corona index Then, a new suppression strategy is selected. If the suppression effect is poor for three consecutive cycles, meaning the suppression effectiveness rate is low for three consecutive computation cycles... If all values ​​are less than 50%, the expert diagnostic process can be triggered.

[0042] Step S7: Establish an anti-corona prediction model based on long-term operating data; wherein, the input parameters of the anti-corona prediction model include flue gas temperature, inlet dust concentration, coal ash content, boiler load, and current operating power ratio; the output of the anti-corona prediction model is the probability of anti-corona occurrence.

[0043] Specifically, anti-corona discharge prediction and prevention are carried out by establishing an anti-corona discharge prediction model based on long-term operational data. The input parameters include flue gas temperature. Inlet dust concentration ash content of coal Boiler load Compared to current operating power ratio When the anti-corona prediction model outputs the probability of anti-corona occurrence... When the voltage is >0.7, preventative suppression measures should be implemented in advance, reducing the supply voltage to 90%~95% of the rated value; when Released when <0.3.

[0044] This disclosure discloses an intelligent identification and adaptive suppression control method for back corona in electrostatic precipitators. Through multi-parameter fusion of back corona index calculations, combined with voltage-current curve slope and harmonic analysis results, it can accurately identify the early stages of back corona. A multi-level judgment strategy is adopted, comprehensively considering the back corona index threshold, duration, and spatial consistency to avoid misjudgments and missed judgments. The power supply mode is automatically selected based on the severity of back corona, achieving adaptive adjustment of suppression measures. A back corona prediction model is established, enabling early warning and preventative control of back corona. Parameter self-learning via a BP neural network allows for continuous optimization of the back corona identification and suppression strategy. This improves the accuracy of back corona detection and the effectiveness of suppression, ensuring the stable and efficient operation of the electrostatic precipitator.

[0045] like Figure 2 As shown, another embodiment of this disclosure provides an intelligent identification and adaptive suppression control system for back corona discharge in an electrostatic precipitator, used to implement the control method described in the previous embodiment. The control system includes: The data acquisition module 210 is used to collect the secondary voltage and secondary current of each electric field of the electrostatic precipitator in real time. The curve analysis module 220 is used to plot the voltage-current characteristic curves of each electric field in real time based on the collected data, and calculate the slope and second derivative of the curves; when a negative value is detected in the slope or a sudden change occurs in the second derivative, it is preliminarily determined that the corresponding electric field has entered the back corona state. The index calculation module 230 is used to perform fast Fourier transform on the secondary current waveform, extract the amplitude and phase of the fundamental component, third harmonic, fifth harmonic and seventh harmonic, and calculate the back corona index by combining the slope of the characteristic curve, the reference slope and the weighting coefficient. The multi-level determination module 240 is used to confirm the back corona event using a multi-level determination strategy; wherein, the first level of the multi-level determination strategy is based on the back corona index threshold, the second level is based on the state duration determination, and the third level is based on the consistency check determination of adjacent electric fields. The power supply control module 250 is used to automatically select a suppression strategy according to the severity of the back corona event; wherein, the suppression strategy includes reducing the supply voltage when there is mild back corona, entering a pulse power supply mode and reducing the base DC voltage when there is moderate back corona, and entering an intermittent pulse power supply mode when there is severe back corona. The closed-loop adjustment module 260 is used to monitor the electric field operating parameters, calculate the suppression efficiency, and adjust the weighting coefficient and recalculate the back corona index when the suppression efficiency is lower than the preset efficiency threshold.

[0046] For example, such as Figure 2 As shown, the control system further includes a probability prediction module 270, which is used for: An anti-corona prediction model is established based on long-term operating data; wherein, the input parameters of the anti-corona prediction model include flue gas temperature, inlet dust concentration, coal ash content, boiler load, and current operating power ratio; the output of the anti-corona prediction model is the probability of anti-corona occurrence.

[0047] Specifically, the intelligent identification and adaptive suppression control system for anti-corona discharge in an electrostatic precipitator according to an embodiment of this disclosure is used to implement the intelligent identification and adaptive suppression control method for anti-corona discharge in an electrostatic precipitator described in the above embodiments. The specific implementation process has been described in detail in the above embodiments and will not be repeated here.

[0048] It is understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of this disclosure, and this disclosure is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this disclosure, and these modifications and improvements are also considered to be within the scope of protection of this disclosure.

Claims

1. A method for intelligent identification and adaptive suppression control of back corona in an electrostatic precipitator, characterized in that, The control method includes: Real-time acquisition of secondary voltage and secondary current in each electric field of the electrostatic precipitator; Based on the collected data, the voltage-current characteristic curves of each electric field are plotted in real time, and the slope and second derivative of the curves are calculated. When a negative value is detected in the slope or a sudden change occurs in the second derivative, it is preliminarily determined that the corresponding electric field has entered the back corona state. Fast Fourier transform is performed on the secondary current waveform to extract the amplitude and phase of the fundamental component, third harmonic, fifth harmonic and seventh harmonic, and the back corona index is calculated by combining the slope of the characteristic curve, the reference slope and the weighting coefficient. A multi-level determination strategy is adopted to confirm the back corona event; wherein, the first level of the multi-level determination strategy is based on the back corona index threshold, the second level is based on the state duration, and the third level is based on the consistency check of adjacent electric fields. The suppression strategy is automatically selected based on the severity of the back corona event; wherein, the suppression strategy includes reducing the supply voltage for mild back corona, entering pulse power supply mode and reducing the base DC voltage for moderate back corona, and entering intermittent pulse power supply mode for severe back corona. Monitor the electric field operating parameters, calculate the suppression efficiency, and when the suppression efficiency is lower than the preset efficiency threshold, adjust the weighting coefficient and recalculate the back corona index.

2. The control method according to claim 1, characterized in that, The method of plotting the voltage-current characteristic curves of each electric field in real time based on the collected data includes: Based on the sliding window method, the least squares method is used to perform curve fitting of the secondary voltage and secondary current using a second-order polynomial to obtain the fitting equation.

3. The control method according to claim 2, characterized in that, When the coefficients of the second-order terms of the fitted equation are less than a preset coefficient threshold, it is preliminarily determined that the corresponding electric field has entered the anti-corona state.

4. The control method according to claim 1, characterized in that, The anti-corona index is calculated using the following formula: In the formula, The anti-corona index, The slope of the voltage-current characteristic curve. This is the baseline slope under normal operating conditions. For the fundamental component, , , These are the third, fifth, and seventh harmonics, respectively. , , These are the weighting coefficients. express….

5. The control method according to claim 4, characterized in that, The weighting coefficients are obtained from the operating parameters through a pre-trained BP neural network model; wherein the operating parameters include flue gas temperature, inlet dust concentration, coal ash content, and electric field operating time.

6. The control method according to claim 1, characterized in that, The first level is based on the anti-corona index threshold determination, including: when the anti-corona index is greater than the preset index threshold, it is determined to be a suspected anti-corona state; The second level of determination based on the duration of the state includes: when the suspected anti-corona state lasts for more than a preset time threshold, it is determined that the state has entered the anti-corona state; The third level of consistency verification based on adjacent electric fields includes: when the consistency of the back corona state of adjacent electric fields in the same dust collector exceeds a preset consistency threshold, it is determined to be a back corona state caused by changes in operating conditions. The multi-level determination strategy for confirming anti-corona events includes: when all three determination levels are met, it is confirmed as an anti-corona event.

7. The control method according to claim 1, characterized in that, The pulse peak voltage of the pulse power supply mode is 80%~90% of the rated voltage, the pulse width is 50μs~200μs, the pulse repetition frequency is 50Hz~500Hz, the pulse duty cycle is 5%~30%, and the base DC voltage is 40%~60% of the rated voltage.

8. The control method according to any one of claims 1 to 7, characterized in that, The control method further includes: An anti-corona prediction model is established based on long-term operating data; wherein, the input parameters of the anti-corona prediction model include flue gas temperature, inlet dust concentration, coal ash content, boiler load, and current operating power ratio; the output of the anti-corona prediction model is the probability of anti-corona occurrence.

9. A smart identification and adaptive suppression control system for back corona discharge in an electrostatic precipitator, used to implement the control method according to any one of claims 1 to 8, characterized in that, The control system includes: The data acquisition module is used to collect the secondary voltage and secondary current of each electric field of the electrostatic precipitator in real time; The curve analysis module is used to plot the voltage-current characteristic curves of each electric field in real time based on the collected data, and calculate the slope and second derivative of the curves; when a negative value is detected in the slope or a sudden change occurs in the second derivative, it is preliminarily determined that the corresponding electric field has entered the back corona state. The index calculation module is used to perform fast Fourier transform on the secondary current waveform, extract the amplitude and phase of the fundamental component, third harmonic, fifth harmonic and seventh harmonic, and calculate the back corona index by combining the slope of the characteristic curve, the reference slope and the weighting coefficient. A multi-level determination module is used to confirm the back corona event using a multi-level determination strategy; wherein, the first level of the multi-level determination strategy is based on the back corona index threshold, the second level is based on the state duration determination, and the third level is based on the consistency check determination of adjacent electric fields. The power supply control module is used to automatically select a suppression strategy based on the severity of the back corona event; wherein, the suppression strategy includes reducing the supply voltage when there is mild back corona, entering a pulse power supply mode and reducing the base DC voltage when there is moderate back corona, and entering an intermittent pulse power supply mode when there is severe back corona. The closed-loop adjustment module is used to monitor the electric field operating parameters, calculate the suppression efficiency, and adjust the weighting coefficient and recalculate the back corona index when the suppression efficiency is lower than the preset efficiency threshold.

10. The control system according to claim 9, characterized in that, The control system further includes a probability prediction module, which is used for: An anti-corona prediction model is established based on long-term operating data; wherein, the input parameters of the anti-corona prediction model include flue gas temperature, inlet dust concentration, coal ash content, boiler load, and current operating power ratio; the output of the anti-corona prediction model is the probability of anti-corona occurrence.

Images