Energy-saving control method and system of electric dust remover

Abstract

The invention relates to the technical field of electric precipitator control, and discloses an energy-saving control method and system for an electric precipitator, and the method comprises the steps: obtaining dust data, generating a spatial distribution diagram, and calculating a baseline value in combination with a concentration threshold value; calculating dust change data based on the distribution map, and generating a difference value in combination with the baseline value and a change threshold value; comparing the difference value with a difference threshold value, generating a boundary adjustment signal and dividing a control region to form a coordinate set; acquiring real-time dust data according to the coordinate set, and generating power supply parameters in combination with the distribution threshold; determining a power supply parameter set through deviation calculation and optimization processing; obtaining efficiency parameters according to the power supply parameter set, generating an adjustment parameter set in combination with an efficiency threshold, extracting regional feature parameters, and re-dividing boundaries in combination with a feature threshold to generate an updating scheme; according to the updating scheme, dust data are obtained again, clustering analysis is carried out, and an electric field adjusting instruction is output to complete energy-saving control. According to the method, the dust removal efficiency and the energy consumption are optimal through multi-region cooperative power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of electrostatic precipitator control, and particularly to an energy-saving control method and system for an electrostatic precipitator. Background Art

[0002] With the continuous improvement of industrial flue gas purification standards and the normalization of dynamic fluctuations in operating conditions, the electrostatic precipitation system needs to simultaneously maximize the dust removal efficiency and dynamically optimize the energy consumption under the condition of intensified spatio-temporal heterogeneity of parameters such as dust concentration and particle size distribution. However, the differences in dust charging characteristics, the non-linear characteristics of the electric field strength distribution, and the multi-region coupling effect make it difficult to construct an accurate mapping relationship between real-time operating condition data and dynamic regulation targets, and the traditional control system faces the bottleneck of insufficient global optimization ability.

[0003] In an existing technology, the electrostatic precipitator adopts a rigid control framework based on fixed geometric partitioning, and applies unified voltage / current parameters to each partition by predefining the horizontal or vertical regional division boundaries. Such methods rely on historical experience to set the partition scale and power supply intensity. Although they can simplify the system design, due to the lack of full consideration of the characteristics of dust, the power supply strategy and dust removal requirements are mismatched in high-dynamic scenarios.

[0004] The existing technology cannot adapt to the dynamic distribution of dust and the differences in real-time operating conditions due to the adoption of fixed partitioning and unified power supply parameters, resulting in low dust removal efficiency and high energy consumption, and there is a problem that the system cannot dynamically generate a multi-region collaborative power supply scheme that takes into account both the dust removal efficiency and the optimal energy consumption under complex operating conditions. Summary of the Invention

[0005] The present invention provides an energy-saving control method and system for an electrostatic precipitator, aiming to solve the problem of being unable to dynamically generate a multi-region collaborative power supply scheme that takes into account both the dust removal efficiency and the optimal energy consumption.

[0006] In the first aspect, to solve the above technical problems, the present invention provides an energy-saving control method for an electrostatic precipitator, including:

[0007] Obtain the original data set of dust, generate a spatial distribution map of the dust according to the original data set and perform regional division, and calculate the characteristic baseline data set in combination with a preset concentration threshold;

[0008] Based on the spatial distribution map, calculate the change data of the dust distribution, and generate a regional difference value in combination with the characteristic baseline data set and a preset change threshold;

[0009] Compare the regional difference value with a preset difference threshold, generate an adjustment signal for the regional boundary according to the comparison result, divide the electric field control region in combination with the spatial distribution map, and generate a boundary coordinate set;

[0010] Obtain real-time dust data according to the set of boundary coordinates, calculate the differential distribution data of each electric field control area, generate a voltage adjustment signal in combination with a preset distribution threshold, and determine the current distribution value;

[0011] According to the voltage adjustment signal and the current distribution value, perform deviation calculation to obtain voltage deviation distribution data, and perform optimization processing to determine the power supply parameter set;

[0012] Obtain dust removal efficiency parameters according to the power supply parameter set, and perform power supply parameter adjustment in combination with a preset efficiency parameter threshold to obtain an adjusted power supply parameter set;

[0013] Obtain characteristic parameters according to the adjusted power supply parameter set, and perform re-partitioning of boundary coordinates in combination with a preset characteristic threshold to obtain an updated partitioning scheme;

[0014] According to the updated partitioning scheme, re-obtain dust data and perform clustering analysis to determine the operating state of the dust collector and obtain an adjustment instruction for electric field control.

[0015] As an optional implementation manner, generating a spatial distribution map of dust from the original data set and performing area partitioning, and calculating the characteristic baseline value of dust in each area in combination with a preset concentration threshold to obtain a characteristic baseline data set, including:

[0016] The original data set includes dust concentration data and particle size distribution data of dust, historical concentration data, historical particle size distribution data, and corresponding timestamps;

[0017] Extract a certain number of sampling data from the original data set, perform grid partitioning on the sampling data and use the Kriging algorithm for interpolation calculation to obtain the estimated value of each grid point, and visualize the estimated value to generate a spatial distribution map;

[0018] According to the concentration data and particle size distribution values in the spatial distribution map, perform area partitioning in combination with a preset concentration threshold and a preset particle size threshold to obtain multiple characteristic partitions of dust;

[0019] If the concentration data in the characteristic partition is greater than the concentration threshold, obtain the spatial distribution map corresponding to the characteristic partition, and use a convolutional neural network to extract features from the spatial distribution map to obtain the distribution characteristics of the abnormal area;

[0020] According to the distribution characteristics of the abnormal area, combine the sampling data of the characteristic partition with the historical working condition database for matching, and calculate the compensation baseline value of the concentration;

[0021] If the concentration data within the characteristic partition is less than the concentration threshold, obtain the historical concentration data of the characteristic partition, and calculate the average concentration within the moving time window as the statistical baseline value of the concentration;

[0022] The moving time window is obtained by setting the window length and sliding step based on the historical concentration data and time stamps;

[0023] Combine the compensation baseline value and the statistical baseline value to form the characteristic baseline data set of the dust.

[0024] As an alternative implementation, calculate the change data of the dust distribution based on the spatial distribution map, and combine the characteristic baseline data set with a preset change threshold to generate a regional difference value, including:

[0025] Based on the dust data in the spatial distribution map, calculate the increase or decrease rate of the concentration data per unit time using the difference method to generate concentration change data, and statistically calculate the absolute difference in particle size within adjacent time periods to generate particle size offset data;

[0026] The concentration change data and the particle size offset data together constitute the distribution change data of the dust;

[0027] If the distribution change data is greater than the preset change threshold or deviates from the corresponding baseline value, determine the corresponding area as an abnormal area, and calculate the regional difference value of the abnormal area;

[0028] If the distribution change data is less than the preset change threshold or is within the corresponding baseline value, determine the corresponding area as a normal area, and the regional difference value is 0.

[0029] As an alternative implementation, compare the regional difference value with a preset difference threshold, generate an adjustment signal for the regional boundary based on the comparison result, and combine the spatial distribution map to divide the electric field control area to generate a boundary coordinate set, including:

[0030] Compare the regional difference value of each area with the preset difference threshold. If the regional difference value is greater than the difference threshold, generate an adjustment signal for this area and record the coordinates of this area as abnormal coordinates;

[0031] If the regional difference value is less than the difference threshold, generate an adjustment signal for this area and record the coordinates of this area as normal coordinates;

[0032] According to the adjustment signal, the system extracts all the abnormal coordinates and normal coordinates, and combines the spatial distribution map to divide the electric field control area to generate the boundary coordinate set of multiple independent electric field control areas.

[0033] As an alternative implementation, obtaining real-time dust data according to the set of boundary coordinates, calculating differential distribution data for each electric field control region, generating a voltage adjustment signal in combination with a preset distribution threshold, and determining current allocation values includes:

[0034] The real-time dust data includes real-time dust concentration values and real-time particle size distribution values;

[0035] Preprocess the real-time dust data to eliminate noise interference to obtain noise-reduced dust data, and calculate differential distribution data based on the noise-reduced dust data;

[0036] If the differential distribution data is greater than a preset differential threshold, trigger a voltage adjustment mechanism and generate a voltage adjustment signal;

[0037] According to the voltage adjustment signal, calculate the current allocation values for each electric field control region through a preset rule of current allocation;

[0038] If the differential distribution data is less than a preset differential threshold, the dust collector continues to operate normally;

[0039] According to the voltage adjustment signal, calculate the current allocation values for each electric field control region through a preset rule of current allocation;

[0040] Calculate the current allocation values for each electric field control region when the dust collector operates normally according to the rated voltage and rated power of the dust collector.

[0041] As an alternative implementation, performing deviation calculation based on the voltage adjustment signal and the current allocation values to obtain voltage deviation distribution data, and performing optimization processing to determine a set of power supply parameters includes:

[0042] Obtain monitoring data on the actual working conditions of the dust collector, and calculate the power supply voltage and power supply current for each electric field control region in combination with the voltage adjustment signal and the current allocation values to obtain a set of power supply parameters;

[0043] According to the set of power supply parameters, calculate the deviation value of the power supply voltage in combination with the working condition change rate in the monitoring data, and determine the deviation distribution data of the regional voltage;

[0044] According to the deviation distribution data, determine the fluctuation range data of the power supply current, and judge the change trend of the matching degree between the power supply parameters and the working conditions in combination with a preset fluctuation threshold to generate trend distribution data;

[0045] Based on the trend distribution data, establish a mapping relationship between the power supply matching degree and the power supply parameters to obtain a first mapping data set;

[0046] If the first mapping data set is greater than a preset first mapping threshold, a genetic algorithm is used to optimize the power supply voltage and power supply current to obtain a preliminary power supply parameter set.

[0047] As an optional implementation manner, obtaining the dust removal efficiency parameter according to the power supply parameter set, and combining with a preset efficiency parameter threshold to adjust the power supply parameters to obtain an adjusted power supply parameter set, includes:

[0048] If the dust removal efficiency parameter is higher than a preset efficiency parameter threshold, a particle swarm optimization algorithm is used to update the power supply parameter set to obtain an updated power supply parameter set;

[0049] According to the updated power supply parameter set, a new dust removal efficiency parameter is obtained and denoted as an efficiency update parameter, and a support vector machine algorithm is used to analyze the efficiency update parameter to obtain efficiency change data;

[0050] Based on the efficiency change data, a mapping relationship between the power supply parameters of each region and the dust removal efficiency is established to obtain a second mapping data set;

[0051] If the second mapping data set is greater than a preset second mapping threshold, the power supply parameters are iteratively adjusted according to the change direction to obtain an adjusted power supply parameter set.

[0052] As an optional implementation manner, according to the updated division scheme, re-obtaining dust data and performing clustering analysis to determine the operating state of the dust collector to obtain an adjustment instruction for electric field control, includes:

[0053] Based on the updated division scheme, the dust concentration, particle size distribution data and environmental interference value of each region of the electrostatic precipitator are collected in real time to generate a real-time data set, and the real-time power supply current and power supply voltage are obtained to generate electric field management parameters;

[0054] According to the real-time data set, the power supply matching degree and regional difference value of each region are calculated to obtain matching degree data;

[0055] If the power supply matching degree in the matching degree data is higher than a preset matching degree threshold, the electric field management parameters are adjusted based on an adaptive particle swarm optimization algorithm to generate a management parameter set;

[0056] According to the management parameter set, the updated dust concentration and particle size distribution data are obtained, and an updated data set is generated in combination with the environmental interference value;

[0057] The K-means clustering algorithm is used to classify the regional difference values in the updated data set to obtain a classification result set;

[0058] According to the classification result set, a fuzzy logic control algorithm is used to determine the change trend of the operating state of the dust collector, and a state data set is obtained;

[0059] According to the state data set, a power supply voltage adjustment amount and a power supply current adjustment amount are generated, and at the same time, an adjustment instruction is output to perform electric field control on the dust collector, completing energy-saving control.

[0060] In a second aspect, the present invention provides an energy-saving control system for an electrostatic precipitator, including:

[0061] A data acquisition module, configured to acquire the original data set of dust, generate a spatial distribution map of the dust according to the original data set and perform regional division, and calculate and obtain a characteristic baseline data set in combination with a preset concentration threshold;

[0062] A regional difference value acquisition module, configured to calculate the change data of the dust distribution based on the spatial distribution map, and generate a regional difference value in combination with the characteristic baseline data set and a preset change threshold;

[0063] A boundary coordinate set acquisition module, configured to compare the regional difference value with a preset difference threshold, generate an adjustment signal for the regional boundary according to the comparison result, divide the electric field control area in combination with the spatial distribution map, and generate a boundary coordinate set;

[0064] An adjustment signal generation module, configured to acquire real-time dust data according to the boundary coordinate set, calculate the difference distribution data of each electric field control area, generate a voltage adjustment signal in combination with a preset distribution threshold, and determine the current distribution value;

[0065] A power supply parameter set module, configured to perform deviation calculation according to the voltage adjustment signal and the current distribution value, obtain voltage deviation distribution data, and perform optimization processing to determine a power supply parameter set;

[0066] An adjusted power supply parameter set module, configured to obtain a dust removal efficiency parameter according to the power supply parameter set, perform power supply parameter adjustment in combination with a preset efficiency parameter threshold, and obtain an adjusted power supply parameter set;

[0067] An updated division scheme module, configured to obtain characteristic parameters according to the adjusted power supply parameter set, perform re-division of the boundary coordinates in combination with a preset characteristic threshold, and obtain an updated division scheme;

[0068] An energy-saving control module, according to the updated division scheme, re-acquires dust data and performs clustering analysis to determine the operating state of the dust collector, and obtains an adjustment instruction for electric field control.

[0069] In a third aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the energy-saving control method of an electrostatic precipitator described in the first aspect above.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] (1) By constructing a dust spatial distribution map of the electrostatic precipitator, the present invention uses the differential algorithm to analyze the concentration change rate and particle size offset, and combines the intelligent comparison of the dynamic threshold and the characteristic baseline to accurately generate the regional difference value. This technology breaks through the limitations of traditional monitoring methods. Through the dynamic analysis of concentration and particle size characteristics, it realizes the accurate positioning of abnormal dust deposition areas. The generation of the difference value integrates the historical data trend and fluctuation characteristics, effectively avoiding misjudgment caused by monitoring lag, and adaptively matching different working condition parameters, providing accurate support for the zonal power supply strategy, and finally achieving the coordinated improvement of the energy consumption optimization and dust removal efficiency of the electrostatic precipitator.

[0072] (2) Based on the boundary coordinate set, the present invention obtains the dust distribution data in real time, constructs a voltage adjustment signal set for multi-field zoning through the differential distribution data, and accurately calculates the current distribution value of each region. This technology breaks through the extensive mode of unified power supply for the whole area of traditional electrostatic precipitators. It adopts a zoning control algorithm that links the dust concentration gradient and the threshold, and converts the real-time monitoring data into a quantifiable voltage / current parameter combination. By dynamically matching the dust distribution characteristics, it generates an adapted enhanced power supply signal for high-load areas to maintain the dust removal efficiency, and outputs the optimal energy-saving parameter combination for low-load areas. This mechanism realizes a millimeter-level response of the power supply strategy to the dust distribution, achieving an accurate balance between the improvement of dust removal efficiency and the reduction of ineffective energy consumption.

[0073] (3) The present invention dynamically updates the power supply parameter set through the particle swarm optimization algorithm, analyzes the performance change data in combination with the support vector machine, and constructs a quantitative mapping model between the power supply parameters and the dust removal performance. When the mapping data exceeds the threshold, the iterative algorithm is used to continuously optimize the voltage / current combination, forming a closed-loop control mechanism of "parameter update - performance feedback - strategy iteration". This technology correlates and models the discrete parameters with the dust removal performance, ensuring both the scientific nature of parameter adjustment and the accurate matching of dynamic changes in working conditions. While maintaining the emission stability, it realizes the optimal configuration of energy consumption, and finally achieves the intelligent optimization of the power supply strategy of the electrostatic precipitator and the refinement of energy efficiency management.

[0074] (4) The present invention re-acquires dust data and performs clustering analysis, calculates the regional power supply matching degree and difference value to accurately identify the operating state. When the matching degree is higher than the threshold, the adaptive particle swarm optimization algorithm is used to dynamically adjust the electric field management parameters, and the updated regional difference values are classified by combining K-means clustering to form a classification result set. Further, the fuzzy logic control algorithm is used to analyze the classification results to determine the change trend of the dust collector operating state, and finally optimize parameters such as the supply voltage and control instructions are generated to achieve precise adjustment of the electric field parameters. The multi-algorithm linkage converts environmental interference and real-time working condition data into dynamic control strategies, improves the dust removal efficiency and power utilization efficiency, and enhances the adaptability and stability of the system to complex working conditions. Description of the Drawings

[0075] Figure 1 is a schematic flow chart of an energy-saving control method for an electrostatic precipitator provided by an embodiment of the present invention;

[0076] Figure 2 is a schematic structural diagram of an energy-saving control system for an electrostatic precipitator provided by an embodiment of the present invention. Detailed Embodiments

[0077] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0078] To solve the above problems, referring to Figure 1 , the first embodiment of the present invention provides an energy-saving control method for an electrostatic precipitator, including the following steps:

[0079] S1, obtain the original data set of dust, generate a spatial distribution map of the dust according to the original data set and perform regional division, and calculate the characteristic baseline data set in combination with a preset concentration threshold;

[0080] S2, based on the spatial distribution map, calculate the change data of the dust distribution, and generate a regional difference value in combination with the characteristic baseline data set and a preset change threshold;

[0081] S3, compare the regional difference value with a preset difference threshold, generate an adjustment signal for the regional boundary according to the comparison result, and divide the electric field control area in combination with the spatial distribution map to generate a boundary coordinate set;

[0082] S4, obtain real-time dust data according to the boundary coordinate set, calculate the difference distribution data of each electric field control area, generate a voltage adjustment signal in combination with a preset distribution threshold, and determine the current distribution value;

[0083] S5. Based on the voltage adjustment signal and the current distribution value, perform deviation calculation to obtain voltage deviation distribution data, and perform optimization processing to determine the power supply parameter set.

[0084] S6. Obtain the dust removal efficiency parameters according to the power supply parameter set, and combine with the preset efficiency parameter threshold to adjust the power supply parameters to obtain the adjusted power supply parameter set.

[0085] S7. Obtain the characteristic parameters according to the adjusted power supply parameter set, and combine with the preset characteristic threshold to re-divide the boundary coordinates to obtain the updated division scheme.

[0086] S8. According to the updated division scheme, re-obtain the dust data and perform clustering analysis to determine the operating state of the dust collector and obtain the adjustment instruction for electric field control.

[0087] In step S1, obtain the original dataset of dust, generate a spatial distribution map of dust according to the original dataset and perform regional division, and combine with the preset concentration threshold to calculate and obtain the characteristic baseline dataset.

[0088] In one implementation, the obtaining the original dataset of dust, generating a spatial distribution map of dust according to the original dataset and performing regional division, and combining with the preset concentration threshold to calculate and obtain the characteristic baseline dataset includes:

[0089] Obtain the original dataset of dust. The original dataset includes dust concentration data, particle size distribution data, historical concentration data, historical particle size distribution data and corresponding timestamps. The dust concentration data is obtained by a laser scattering sensor, and the specific characteristics are the current concentration value, the concentration change rate and the historical average concentration. The particle size distribution data is measured by an optical particle size analyzer, and the specific characteristics are the median particle size, the particle size distribution width and the particle proportion. The historical concentration data and the historical particle size distribution data are obtained from the dust collector database. The timestamps are synchronously recorded in the database by the system clock.

[0090] Extract a certain number of sampling data from the original dataset, perform grid division on the sampling data and perform interpolation calculation using the Kriging algorithm to obtain the estimated value of each grid point, and visualize the estimated value to generate a spatial distribution map.

[0091] According to the concentration data and particle size distribution values in the spatial distribution map, combine with the preset concentration threshold and the preset particle size threshold to perform regional division to obtain multiple characteristic partitions of dust.

[0092] Further, based on the concentration data and particle size distribution values in the spatial distribution map, combined with a preset concentration threshold and a preset particle size threshold, regional division is performed to obtain characteristic partitions of multiple dusts, including:

[0093] Traverse each grid point, and based on the estimated concentration value and the estimated particle size value of the current point, combined with the preset concentration threshold and the preset particle size threshold, determine the partition category to which it belongs. The partition categories include low-concentration area, medium-concentration area, high-concentration area, fine-particle area, medium-particle area, and coarse-particle area. The estimated concentration value is denoted as C1, the estimated particle size value is denoted as D1, the concentration threshold range is denoted as C2~C3, and the particle size threshold is denoted as D2~D3. When C1 is less than C2 and D1 is less than D2, the grid point is classified into the low-concentration fine-particle area. When C1 is less than C2 and D1 is between D2 and D3, the grid point is classified into the low-concentration medium-particle area. When C1 is less than C2 and D1 is greater than D3, the grid point is classified into the low-concentration coarse-particle area. When C1 is between C2 and C2 and D1 is less than D2, the grid point is classified into the medium-concentration fine-particle area. When C1 is between C2 and C2 and D1 is between D2 and D3, the grid point is classified into the medium-concentration medium-particle area. When C1 is between C2 and C2 and D1 is greater than D3, the grid point is classified into the medium-concentration coarse-particle area. When C1 is greater than C3 and D1 is less than D2, the grid point is classified into the high-concentration fine-particle area. When C1 is greater than C3 and D1 is between D2 and D3, the grid point is classified into the high-concentration medium-particle area. When C1 is greater than C3 and D1 is greater than D3, the grid point is classified into the high-concentration coarse-particle area.

[0094] If the concentration data in the characteristic partition is greater than the concentration threshold, obtain the spatial distribution map corresponding to the characteristic partition, and use a convolutional neural network to extract the characteristic of the abnormal area distribution from the spatial distribution map;

[0095] Specifically, when the concentration data in the characteristic partition exceeds the preset concentration threshold, extract the spatial distribution image of the concentration data from the spatial distribution map corresponding to the characteristic partition. The image resolution is consistent with the grid division, and each pixel value corresponds to the estimated concentration value after Kriging interpolation. The processing process of the convolutional neural network is as follows:

[0096] Take the spatial distribution image as the input, input it into the convolutional layer and pooling layer of the neural network to extract the global features of the feature map. Map the feature vector to a 1024-dimensional hidden layer, the activation function is ReLU, use semantic segmentation to output a pixel-level abnormal probability map, and mark the coordinates and geometric range of the abnormal area. Analyze the continuous abnormal pixels to generate independent abnormal area bounding boxes, and the output result is the characteristic of the abnormal area distribution, including the coordinates of the abnormal area, concentration mean / variance, gradient direction, and duration.

[0097] According to the abnormal area distribution characteristics, match the sampling data of the characteristic partition with the historical working condition database, and calculate the compensation baseline value of the concentration;

[0098] If the concentration data in the characteristic partition is less than the concentration threshold, obtain the historical concentration data of the characteristic partition, and calculate the average concentration within the moving time window as the statistical baseline value of the concentration;

[0099] Take the compensation baseline value and the statistical baseline value as a vector in the vector set to form the characteristic baseline data set of the dust.

[0100] Furthermore, perform grid division on the sampling data and use the Kriging algorithm for interpolation calculation to obtain the estimated value of each grid point, including:

[0101] According to the target area to which the sampling data belongs, divide the monitoring space into equally spaced rectangular grids (such as 1m×1m), and each grid point corresponds to a unique geographical coordinate, forming a regular grid matrix covering the entire domain of the electrostatic precipitator;

[0102] For each grid point, select a preset number (such as 10) of sampling points in its neighborhood, construct a covariance matrix, and solve the weight coefficients based on the Kriging equations;

[0103] Weighted sum the weight coefficients and the observed values of the corresponding sampling points to obtain the estimated value of the grid point, and repeat this process to complete the interpolation calculation of all grid points;

[0104] The calculation of the estimated value:

[0105]

[0106] Among them, represents the estimated value of the sampling point x i , λ i represents the Kriging weight coefficient corresponding to x i , Z(x i ) represents the observed value of x i , and n represents the number of sampling points;

[0107] It should be noted that visualize the estimated value and use visualization tools such as three-dimensional surface diagrams, contour diagrams, and heat maps to generate spatial distribution diagrams.

[0108] Furthermore, the step of calculating the compensation baseline value of the concentration by matching the sampling data of the characteristic partition with the historical working condition database according to the abnormal area distribution characteristics includes:

[0109] Extract the characteristic parameters of the abnormal area from the spatial distribution map, where the characteristic parameters include the concentration change rate, concentration time series data, and morphological parameters;

[0110] Perform tagging processing on the historical working condition database to construct a multi-dimensional feature index: working condition features, dust characteristics, and morphological space characteristics;

[0111] For the concentration time series data, use the DTW algorithm to calculate the similarity between the characteristic parameters of the current abnormal area and the historical working conditions, and use the Mahalanobis distance to quantify the multi-dimensional feature similarity;

[0112] Select the top K historical working conditions with the highest similarity, obtain the distribution weights according to the similarity, and the compensation baseline value is the weighted average result:

[0113]

[0114] The weight calculation formula is:

[0115]

[0116] Among them, C com represents the concentration compensation baseline value, λ i represents the weight of the i-th historical data, C his represents the baseline concentration value of the i-th matching historical working condition, d i represents the Mahalanobis distance between the current abnormal area and the i-th historical working condition, and α represents the adjustment coefficient to control the sensitivity of the weight to the distance.

[0117] It should be noted that the value of K is determined by analyzing the similarity distribution and data volume of the historical working conditions, combined with the elbow method, cross-validation, or statistical calculation (such as taking the square root of the total number of historical working conditions).

[0118] Furthermore, obtain the historical concentration data of the characteristic partition, and calculate the concentration mean within the moving time window as the statistical baseline value of the concentration, including:

[0119] Sort the historical concentration data into historical concentration time series data according to the time stamp, and set the length and sliding step of the moving time window;

[0120] For each time point, intercept the data subset within the window, and calculate the arithmetic mean of the concentration within the window as the statistical baseline value:

[0121]

[0122] Among them, C b (t i ) represents the statistical baseline value at time point t i , C jis the concentration value at the j-th time point within the window, and n is the number of valid data points within the window.

[0123] In step S2, based on the spatial distribution map, calculate the change data of the dust distribution, and combine the characteristic baseline data set with a preset change threshold to generate a regional difference value.

[0124] In one implementation, the calculating the change data of the dust distribution based on the spatial distribution map, combining the characteristic baseline data set with a preset change threshold to generate a regional difference value includes:

[0125] According to the dust data in the spatial distribution map, calculate the increase or decrease rate of the concentration data per unit time based on the difference method to generate concentration change data, and statistically calculate the absolute difference in particle size within adjacent time periods to generate particle size offset data;

[0126] The concentration change data and the particle size offset data together constitute the distribution change data of the dust;

[0127] If the distribution change data is greater than the preset change threshold or deviates from the corresponding baseline value, determine the corresponding area as an abnormal area, and calculate the regional difference value of the abnormal area;

[0128] If the distribution change data is less than the preset change threshold or is within the corresponding baseline value, determine the corresponding area as a normal area, and the regional difference value is 0.

[0129] Further, calculate the increase or decrease rate of the concentration data per unit time based on the difference method, and the calculation formula is expressed as:

[0130]

[0131] where R ij,t represents the concentration change rate at the grid point (i,j) per unit time, C ij,t represents the dust concentration at the grid point (i,j) at time t, Δt represents the data sampling time interval, and k represents the number of time windows for smoothing processing;

[0132] Further, the formula for calculating the regional difference value of the abnormal area is:

[0133]

[0134] where V diff (i,j) represents the quantization value of the regional abnormality degree at the grid point (i,j), that is, the difference value, ε represents the weight coefficient of the concentration change rate in the difference value, T Ris denoted as the concentration change rate threshold, β is denoted as the weight coefficient of the particle size deviation in the difference value, and the weight coefficients ε and β satisfy ε + β = 1, ΔD i,j,t is denoted as the deviation amount of the real-time particle size distribution from the historical baseline at the grid point (i, j), B D is denoted as the historical baseline value, ΔT D is denoted as the particle size deviation tolerance threshold.

[0135] In step S3, compare the regional difference value with a preset difference threshold to generate an adjustment signal for the regional boundary, and combine the spatial distribution map to divide the electric field control region and generate a set of boundary coordinates.

[0136] In one implementation, the comparing the regional difference value with a preset difference threshold to generate an adjustment signal for the regional boundary, and combining the spatial distribution map to divide the electric field control region and generate a set of boundary coordinates includes:

[0137] Compare the regional difference value of each region with a preset difference threshold. If the regional difference value is greater than the difference threshold, generate an adjustment signal for this region and record the coordinates of this region as abnormal coordinates;

[0138] If the regional difference value is less than the difference threshold, generate an adjustment signal for this region and record the coordinates of this region as normal coordinates;

[0139] It should be noted that the adjustment signal is a control instruction generated by the system based on the comparison result of the regional difference value and the threshold, and is used to guide the division and boundary adjustment of the electric field control region, and includes coordinates and status identifiers;

[0140] According to the adjustment signal, the system extracts all the abnormal coordinates and the normal coordinates, and combines the spatial distribution map to divide the electric field control region and generate a set of boundary coordinates for multiple independent electric field control regions.

[0141] In an example, the steps of dividing the electric field control region are as follows:

[0142] Perform spatial grouping on the discrete points in the abnormal coordinate set to generate multiple independent abnormal region clusters; for example, if multiple grid points are marked as abnormal due to excessive pollution concentration, these points are aggregated into one or more clusters, and each cluster represents an independent abnormal region;

[0143] Calculate the minimum convex polygon boundary for the coordinate points of each abnormal cluster to generate a closed polygon vertex sequence. This step converts the discrete abnormal points into clear geometric boundaries. For example, the scattered dust points are connected into a regular or polygonal area range;

[0144] For the normal region, the scattered normal coordinate points are merged into a continuous large region, and then the outer contour boundary is extracted to form a closed polygon. For example, the scattered normal grid points are integrated into a complete regional boundary;

[0145] For the abnormal region, the high-voltage power supply area is independently divided for each abnormal cluster, and for the normal region, it is divided into a low-energy consumption operation area.

[0146] It should be noted that the abnormal coordinates include the spatial coordinates of all grid points in the abnormal region, and the normal coordinates include the spatial coordinates of all grid points in the normal region.

[0147] In step S4, according to the boundary coordinate set, real-time dust data is obtained, the differential distribution data of each electric field control area is calculated, a voltage adjustment signal is generated in combination with a preset distribution threshold, and the current distribution value is determined.

[0148] In one implementation manner, the obtaining the corresponding real-time dust data according to the boundary coordinate set, calculating the differential distribution data of each electric field control area, generating a voltage adjustment signal in combination with a preset differential threshold, and determining the current distribution value includes:

[0149] The real-time dust data includes a real-time dust concentration value and a real-time particle size distribution value;

[0150] The real-time dust data is preprocessed to eliminate noise interference to obtain noise-reduced dust data, and real-time regional difference values are calculated based on the noise-reduced dust data to obtain real-time differential distribution data;

[0151] If the differential distribution data is greater than a preset differential threshold, a voltage adjustment mechanism is triggered and a voltage adjustment signal is generated;

[0152] According to the voltage adjustment signal, the current distribution values of each electric field control area are calculated through a preset rule of current distribution;

[0153] If the differential distribution data is less than a preset differential threshold, the dust collector continues to work normally;

[0154] The current distribution values of each electric field control area when the dust collector works normally are calculated according to the rated voltage and rated power of the dust collector.

[0155] It should be noted that the voltage adjustment signal is a voltage adjustment amount generated according to the ratio of the difference value exceeding the threshold, and the preset rule is a demand distribution rule, that is, the current is distributed according to the voltage adjustment amount to satisfy power balance. The calculation formula of the current distribution value is expressed as:

[0156]

[0157] Wherein, I i,jThe current distribution value represented as the region (i,j), P b Represented as the baseline power, ΔU i,j The voltage adjustment amount represented as the region (i,j), I ref Represented as the rated current of the electric field;

[0158] In one example, the steps of preprocessing the real-time dust data to eliminate noise interference are as follows: collecting the dust concentration value and particle size distribution value in the electric field control area through a real-time dust monitoring system, and preprocessing the data using a moving average filtering algorithm. The moving window is set to 5 minutes and the step size is 30 seconds to eliminate noise interference.

[0159] In step S5, according to the voltage adjustment signal and the current distribution value, a deviation calculation is performed to obtain voltage deviation distribution data, and optimization processing is carried out to determine the power supply parameter set.

[0160] In one implementation, the performing a deviation calculation according to the voltage adjustment signal and the current distribution value, obtaining voltage deviation distribution data, and performing optimization processing to determine the power supply parameter set includes:

[0161] Obtaining the monitoring data of the actual working condition of the dust collector, combining the voltage adjustment signal and the current distribution value, calculating the power supply voltage and power supply current of each electric field control area, and obtaining the power supply parameter set;

[0162] It should be noted that the power supply parameter set is a combination of the power supply voltage and the power supply current, such as [3.1kV / 1.4A, 3.4kV / 1.7A, 2.9kV / 1.2A]

[0163] According to the power supply parameter set, combining the working condition change rate in the monitoring data to calculate the deviation value of the power supply voltage, and determining the deviation distribution data of the regional voltage; further, the calculation formula of the deviation value of the power supply voltage is expressed as:

[0164]

[0165] Wherein, ΔU ％ Represents the deviation value of the power supply voltage, U actual,i Represents the power supply voltage of the i-th region, U nom,i Represents the detected voltage of the i-th region, and the deviation distribution data is D = {ΔU ％,1 , ΔU ％,2 , …, ΔU ％,n}.

[0166] According to the deviation distribution data, determining the fluctuation range data of the power supply current, combining the preset fluctuation threshold to judge the change trend of the matching degree between the power supply parameters and the working condition, and generating trend distribution data;

[0167] Furthermore, the calculation formula for the fluctuation range data is expressed as:

[0168] ΔI range,i = m·ΔU ％,i

[0169] Wherein, ΔI range,i represents the current fluctuation amount in the i-th region, m represents the current-voltage sensitivity coefficient (describing the influence of voltage deviation on current fluctuation), and ΔU ％,i represents the deviation distribution data in the i-th region.

[0170] It should be noted that the deviation distribution data is formed and distributed in different regions or time points, reflecting the matching degree between the power supply parameters and the working conditions. The fluctuation range data indicates that when the power supply voltage deviates due to changes in working conditions (such as fluctuations in dust concentration) (such as too high or too low voltage setting), it will directly cause the current to change accordingly. For example, if the voltage in a certain region is increased due to deviation, and the actual working condition is that the dust decreases, the current may fluctuate significantly (such as suddenly increasing from 100A to 150A) due to too strong an electric field. The system captures this current change caused by voltage deviation; furthermore, the acquisition of the trend distribution data is obtained as follows: comparing the actual fluctuation range of the current with a preset fluctuation threshold (such as allowing a fluctuation of ±10%). If the fluctuation exceeds the threshold, it indicates that the power supply parameters (voltage / current) do not match the current working conditions (such as too high voltage setting resulting in unstable current). By continuous monitoring, observing whether this mismatch is gradually deteriorating (such as an expanding fluctuation range) or improving (such as a shrinking fluctuation range), so as to generate the trend distribution data;

[0171] In an example, the generation of the trend distribution data is expressed as: if the fluctuation range at a subsequent time point is greater than the fluctuation range at the previous time point, it is considered that the matching degree is gradually deteriorating, such as: If the fluctuation range at a subsequent time point is less than the fluctuation range at the previous time point, it is considered that the matching degree is gradually improving, such as:

[0172] Recording the change trend of the fluctuation range in the form of a time series to form the trend distribution data:

[0173]

[0174] Wherein, T D represents the trend distribution data, represents the fluctuation range data at the t1 moment in the i-th region, and Status1 represents the matching degree status at the corresponding moment, with values of "deteriorating", "improving", or "stable".

[0175] Based on the trend distribution data, establish the mapping relationship between the power supply matching degree and the power supply parameters to obtain the first mapping data set;

[0176] It should be noted that the establishment of the mapping relationship is specifically manifested as transforming the relationship between the power supply parameters (voltage, current) and the operating condition matching degree into a queryable "parameter - matching degree" data set; for example, in the power supply parameter combination (8 kV / 120 A), the fluctuation range is ±10 A (not exceeding the standard, with a stable trend), and the score is 90 points;

[0177] If the first mapping data set is greater than the preset first mapping threshold, the genetic algorithm is used to optimize the power supply voltage and power supply current to obtain a preliminary power supply parameter set.

[0178] It should be noted that if the first mapping data set is less than the preset first mapping threshold, the power supply parameter set is the preliminary power supply parameter set.

[0179] It should be noted that the process of optimizing using the genetic algorithm is expressed as: converting the voltage and current parameters into "chromosomes" (such as binary or numerical forms), generating multiple groups of random parameter combinations (such as 100 groups) to form an initial population. For each group of parameters, simulate its operating effect under the current operating condition (such as predicting the current fluctuation range), combine with the preset threshold (such as allowing a fluctuation of ±10%), and calculate the matching degree score (such as the smaller the fluctuation, the higher the score). Retain the parameter combinations with high matching degrees (such as retaining the top 20% of the high - score combinations), randomly select two groups of parameters, exchange some parameter values to generate new combinations, and slightly adjust some parameters (such as adjusting the voltage from 8 kV to 8.2 kV) to explore new solutions. Repeat the above process until the termination condition is met (such as the number of iterations reaches 100 times or the matching degree no longer improves), and select the parameter combination with the highest matching degree from the final population to form a preliminary power supply parameter set.

[0180] Furthermore, according to the voltage adjustment signal and the current distribution value, combined with the monitoring data of the actual operating condition of the dust collector, calculate the power supply voltage and power supply current of each electric field control area, including:

[0181] The monitoring data of the actual operating condition includes real - time dust concentration, ambient temperature, ambient humidity, etc.;

[0182] The calculation formula for the power supply voltage is expressed as:

[0183] U(i,j) = U base +ΔU i,j ·f(T,H)

[0184] The calculation formula for the power supply current is expressed as:

[0185]

[0186] where U(i,j) represents the power supply voltage of area (i,j), U baseDenoted as the reference voltage value, f(T, H) is denoted as the temperature and humidity correction factor, I′(i, j) is denoted as the power supply current of region (i, j), C base Denoted as the reference concentration value, C scale Denoted as the concentration scaling factor.

[0187] In step S6, according to the power supply parameter set, obtain the dust removal efficiency parameter, combine it with the preset efficiency parameter threshold, adjust the power supply parameters, and obtain the adjusted power supply parameter set.

[0188] In one implementation, the obtaining the dust removal efficiency parameter according to the power supply parameter set, combining it with the preset efficiency parameter threshold, and adjusting the power supply parameters to obtain the adjusted power supply parameter set includes:

[0189] If the dust removal efficiency parameter is higher than the preset efficiency parameter threshold, then use the particle swarm optimization algorithm to update the power supply parameter set to obtain the updated power supply parameter set;

[0190] According to the updated power supply parameter set, obtain the new dust removal efficiency parameter and denote it as the efficiency update parameter, and use the support vector machine algorithm to analyze the efficiency update parameter to obtain the efficiency change data;

[0191] It should be noted that the dust removal efficiency parameter includes the dust deposition amount and the electric field response time. The dust deposition amount is obtained by the dust concentration sensor installed at the outlet of the dust collector to monitor the dust content in the discharged gas in real time, and combined with the dust content before entering the dust collector (sensors are also set at the inlet), calculate the captured dust amount, dust deposition amount = (inlet dust concentration - outlet dust concentration) × treatment air volume. The electric field response time uses the monitoring system to record the time point of each working condition change and the time point when the dust collector starts to respond, and the difference between the two is the electric field response time.

[0192] It should be noted that the analysis process of the support vector machine algorithm is as follows: Input the parameters of the updated power supply parameter set (such as voltage 8.2 kV, current 130 A) and the corresponding dust removal efficiency (such as 15% reduction in dust) into the SVM model. Use the historical dust removal efficiency data and power supply parameters to train the SVM to identify the association pattern between parameters and efficiency.

[0193] When there is a new power supply parameter set, input these new parameters into the trained SVM model to predict the expected dust removal efficiency under this parameter configuration. According to the output of the SVM model, compare the efficiency indicators before and after adjustment (such as the percentage of dust reduction), and calculate the change amount of the efficiency, which is the efficiency change data. For example, if the original dust reduction rate was 15% and it becomes 20% after adjusting the parameters, the efficiency change data may include "+5%".

[0194] Based on the performance change data, establish the mapping relationship between the power supply parameters of each region and the dust removal performance to obtain the second mapping data set;

[0195] It should be noted that the establishment of the mapping relationship is specifically manifested as transforming the relationship between the power supply parameters (voltage, current) and the performance change data into a queryable "power supply parameter - performance data" data set; for example, in the power supply parameter combination (8.2 kV / 130 A), the corresponding dust performance parameter is 5%, that is, {(8.2 kV / 130 A), 5%}.

[0196] If the second mapping data set is greater than the preset second mapping threshold, iteratively adjust the power supply parameters according to the change direction to obtain the adjusted power supply parameter set;

[0197] It should be noted that if the predicted performance of the second mapping data set exceeds the preset threshold, it indicates that there is still room for optimization. According to the SVM prediction trend, determine the parameter adjustment direction (for example, the voltage needs to continue to increase to further reduce dust); combined with safety limits (such as the voltage upper limit), control the adjustment amplitude (such as ±0.1 kV each time), and repeat the process until the performance change stabilizes or reaches the target, and output the adjusted power supply parameter set;

[0198] Furthermore, the particle swarm optimization algorithm is used to update the power supply parameter set to obtain the updated power supply parameter set, including:

[0199] According to the power supply parameter set, randomly generate m groups of candidate parameters (U, I), and each parameter combination is called a "particle". Evaluate the dust removal performance of the particles, and preferentially reduce the dust deposition amount and shorten the electric field response time;

[0200] If the dust deposition amount or the response time exceeds the preset threshold, the score is reduced. The higher the score, the better the parameter combination (U, I). The best parameter combination of each particle in its own historical iteration is called the individual optimum, and the parameter combination with the highest score in the entire particle swarm is called the global optimum;

[0201] The particles move in the direction of the individual optimum and the global optimum, and the speed is controlled by the inertia weight and the learning factor. Adjust the voltage and current values according to the updated speed to generate new candidate parameters;

[0202] After the iteration is completed, the global optimum parameters are the updated power supply parameter set (U new , I new ).

[0203] In step S7, according to the adjusted power supply parameter set, obtain the characteristic parameters of the region, and combine the preset characteristic threshold to re-divide the boundary coordinates to obtain the updated division scheme.

[0204] In one implementation, obtaining the characteristic parameters of the area according to the adjusted power supply parameter set, and combining with the preset characteristic threshold to re-divide the boundary coordinates to obtain an updated division scheme, including:

[0205] Based on the adjusted power supply parameter set, re-collect the real-time dust concentration, particle size distribution and boundary displacement data of the area, and generate a characteristic parameter set;

[0206] Compare the characteristic parameter set with the preset characteristic threshold to identify the difference area;

[0207] It should be noted that the comparison between the characteristic parameters and the threshold is as follows: Compare the real-time dust concentration value with the preset concentration threshold (such as "≤50mg / m 3 "), if the dust concentration in a certain area exceeds the threshold (such as measured 60mg / m 3 ), it is marked as an area with "exceeded concentration";

[0208] Compare the real-time particle size distribution data with the preset distribution range (such as "0.1-10μm"), if the particle size in a certain area is abnormal (such as a large number of 15μm particles appear), it is marked as an area with "abnormal particle size";

[0209] Compare the real-time boundary displacement data with the displacement threshold (such as "±5cm"). If the displacement exceeds the range (such as the displacement of a certain area reaches 8cm), it is marked as an area with "exceeded displacement";

[0210] If there are multiple parameter abnormalities in a certain area (such as exceeded dust concentration and exceeded displacement), it is preferentially marked as a high-priority difference area;

[0211] According to the difference area, use the dynamic boundary division algorithm to adjust the coordinate boundary of the electric field control area to generate an updated division scheme;

[0212] It should be noted that the dynamic boundary division algorithm includes adaptive region segmentation based on gradient change or boundary offset compensation based on fuzzy logic.

[0213] Furthermore, according to the difference area, using the dynamic boundary division algorithm to adjust the coordinate boundary of the electric field control area to generate an updated division scheme, including:

[0214] According to the difference area, through the dust concentration difference between adjacent difference areas, identify the high-gradient boundary to obtain the concentration gradient distribution characteristics. For example, the dust concentrations of area A and area B are 60mg / m 3 and 30mg / m 3 , and the concentration gradient at the boundary between the two is 30mg / m 3 , which is much higher than other areas, then it is marked as a high-gradient boundary.

[0215] Analyze the direction, amplitude, and temporal variation trend of the boundary displacement based on the boundary of the differential region, determine whether it is caused by air flow disturbance, temperature change, or equipment vibration, and obtain the characteristics of the boundary offset law. The distribution law of the differential region consists of the concentration gradient distribution characteristics and the boundary offset law characteristics.

[0216] Use spatial statistical methods (such as gradient analysis method) to quantify the distribution law of the differential region. According to the distribution law of the differential region, adjust the coordinate boundary of the electric field control region using the gradient threshold method and the fuzzy logic compensation method.

[0217] The gradient threshold method and the fuzzy logic compensation method include:

[0218] Perform gradient operation on the spatial distribution map of dust concentration, and extract the regions with drastic concentration changes (such as the junction of the capture transfer region and the separation region). Set the concentration gradient threshold according to historical operating condition data or empirical formulas, use the center line of the high-gradient region as the new boundary, and generate smooth boundary coordinates through linear interpolation or spline curve fitting. Convert the boundary displacement amount (such as ±5% coordinate offset), displacement direction (X / Y axis components), and displacement rate into fuzzy sets (such as "small offset", "medium offset", "large offset"). According to the fuzzy sets, establish fuzzy rules, such as "the displacement amount is a large offset" and "the direction is perpendicular to the separation interface", then "the boundary compensation amount = displacement amount × preset weight parameter", and obtain the fuzzy inference result.

[0219] Convert the fuzzy inference result into a specific boundary coordinate compensation value, and generate the updated boundary coordinates.

[0220] Integrate the boundary coordinates and power supply parameters combination of the dynamic boundary division algorithm into an updated division scheme.

[0221] In step S8, according to the updated division scheme, re-obtain the dust data and perform clustering analysis to determine the operating state of the dust collector, and obtain the adjustment instruction for electric field control.

[0222] In one implementation, according to the updated division scheme, combined with the environmental interference value, perform clustering analysis to determine the operating state of the dust collector, output the adjustment instruction for fine control of the electric field, and complete the energy-saving control, including:

[0223] Based on the updated division scheme, collect the dust concentration, particle size distribution data, and environmental interference value of each region of the electrostatic precipitator in real time, and generate a real-time data set;

[0224] According to the real-time data set, calculate the power supply matching degree and regional difference value of each region to obtain the matching degree data;

[0225] It should be noted that the regional difference value represents the quantification of the differences in dust concentration and particle size distribution between adjacent or different electric field control regions. The concentration difference is obtained by calculating the absolute value or standardized value of the concentration difference between adjacent regions. The particle size difference is obtained through the standard deviation or chi-square test of the particle size distribution. The concentration difference and particle size difference are weighted and summed to form the regional difference value. The matching degree data includes the power supply matching degree of each region and the regional difference value.

[0226] If the power supply matching degree in the matching degree data is higher than the preset matching degree threshold, the electric field management parameters are adjusted based on the adaptive particle swarm optimization algorithm to generate a set of management parameters.

[0227] It should be noted that the steps of adjusting the electric field management parameters based on the adaptive particle swarm optimization algorithm are as follows: According to the electric field management parameters, m groups of candidate parameters (U, I, F,...) are randomly generated, and each parameter combination is called a "particle". The electric field control ability of the system is evaluated, and the electric field response time is preferentially shortened.

[0228] If the electric field response time exceeds the preset threshold, the score is reduced. The higher the score, the better the parameter combination (U, I, F,...). The best parameter combination of each particle in its own historical iteration is called the individual optimum, and the parameter combination with the highest score in the entire particle swarm is called the global optimum.

[0229] The particles move in the directions of the individual optimum and the global optimum. The speed is controlled by the inertia weight and learning factor. The power supply voltage, power supply current, power supply frequency, etc. are adjusted according to the updated speed to generate new candidate parameters.

[0230] After the iteration is completed, the global optimum parameters are the updated power supply parameter set (U new , I new , F new ,...);

[0231] It should be noted that the management parameters mentioned in the adjustment of the management parameters by the adaptive particle swarm optimization algorithm refer to the electric field control parameters that need to be optimized during the operation of the electrostatic precipitator, such as power supply voltage, power supply current, power supply frequency, dust concentration, particle size distribution data, and temperature compensation coefficient.

[0232] According to the set of management parameters, the updated dust concentration and particle size distribution data are obtained, and an updated data set is generated in combination with the environmental interference value.

[0233] It should be noted that after obtaining the updated dust concentration, particle size distribution data, and environmental interference value, the power supply matching degree and regional difference value of each electric field control region are recalculated.

[0234] The K-means clustering algorithm is used to classify the regional difference values of each region obtained by recalculation to obtain a classification result set.

[0235] According to the classification result set, the fuzzy logic control algorithm is used to determine the change trend of the operating state of the dust collector, and a state data set is obtained;

[0236] According to the state data set, the power supply voltage adjustment amount and the power supply current adjustment amount are generated, and at the same time, an adjustment instruction is output to perform electric field control on the dust collector, completing energy-saving control.

[0237] In an example, the determination of the change trend of the operating state of the dust collector by using the fuzzy logic control algorithm can be described as follows: the fuzzy rule is set as "if the difference value is less than 0.2, the state is optimized; if the difference value is greater than 0.2, the state is adjusted", and the state of each area [optimized, adjusted, optimized, optimized,...] is output;

[0238] It should be noted that when the state is optimized, the adjustment direction is to maintain the current voltage or make a fine adjustment, and the adjustment amount is optimized within a small range according to the "optimal voltage range" in the historical data; when the state is optimized, the adjustment direction is to dynamically adjust according to the direction of the difference value (such as increasing the voltage when the concentration increases and decreasing the voltage when the concentration decreases), and the adjustment amount is that the greater the difference value, the greater the adjustment amplitude, and the final value is the current value plus the adjustment amount;

[0239] For different electric field control areas, a specific instruction format is generated, and the PWM signal is sent through the PLC or the embedded controller to adjust the voltage, and the final power supply value is input to the corresponding area;

[0240] Furthermore, the calculation formula of the power supply matching degree is:

[0241]

[0242] Among them, M represents the power supply matching degree, V actual,i represents the actual power supply parameter value of the i-th dimension, V optimal,i represents the theoretical optimal power supply parameter value of the i-th dimension, and n represents the power supply parameter dimension;

[0243] Furthermore, the K-means clustering algorithm is used to classify the regional difference values of each recomputed area, and a classification result set is obtained, including:

[0244] The regional difference values of each area are divided into K clusters (such as high-difference area, medium-difference area, low-difference area) to guide the electric field partition control;

[0245] Randomly select K samples as the initial clustering centers, and for each sample x i Calculate its distance from all the center points and assign it to the nearest cluster to obtain the assignment result;

[0246] According to the allocation result, recalculate the center points of each cluster. If the change in the center points is less than the threshold or the maximum number of iterations is reached, stop the iteration; otherwise, repeat steps 2-3. Take the output result of the iterative calculation as the classification result set.

[0247] Refer to Figure 2 , the second embodiment of the present invention provides an energy-saving control system for an electrostatic precipitator, including:

[0248] A 101 data acquisition module, configured to acquire the original data set of dust, generate a spatial distribution map of the dust based on the original data set and perform regional division, and calculate a characteristic baseline data set in combination with a preset concentration threshold;

[0249] A 102 regional difference value acquisition module, configured to calculate the change data of the dust distribution based on the spatial distribution map, and generate a regional difference value in combination with the characteristic baseline data set and a preset change threshold;

[0250] A 103 boundary coordinate set acquisition module, configured to compare the regional difference value with a preset difference threshold, generate an adjustment signal for the regional boundary according to the comparison result, divide the electric field control region in combination with the spatial distribution map, and generate a boundary coordinate set;

[0251] A 104 adjustment signal generation module, configured to acquire real-time dust data according to the boundary coordinate set, calculate the difference distribution data of each electric field control region, generate a voltage adjustment signal in combination with a preset distribution threshold, and determine the current allocation value;

[0252] A 105 power supply parameter set module, configured to perform deviation calculation according to the voltage adjustment signal and the current allocation value, obtain voltage deviation distribution data, and perform optimization processing to determine the power supply parameter set;

[0253] A 106 adjusted power supply parameter set module, configured to acquire the dust removal efficiency parameter according to the power supply parameter set, perform power supply parameter adjustment in combination with a preset efficiency parameter threshold, and obtain an adjusted power supply parameter set;

[0254] A 107 updated division scheme module, configured to acquire the characteristic parameter according to the adjusted power supply parameter set, perform redivision of the boundary coordinates in combination with a preset characteristic threshold, and obtain an updated division scheme;

[0255] A 108 energy-saving control module, according to the updated division scheme, re-acquire the dust data and perform clustering analysis to determine the operating state of the dust collector and obtain an adjustment instruction for the electric field control.

[0256] It should be noted that the energy-saving control system of an electrostatic precipitator provided by the embodiments of the present invention is used to execute all the process steps of the energy-saving control method of an electrostatic precipitator in the above embodiments. The working principles and beneficial effects of the two correspond one by one, so they will not be elaborated here.

[0257] In summary, the present invention provides an energy-saving control method for an electrostatic precipitator. Compared with the prior art, the present invention has the following beneficial effects:

[0258] The present invention constructs a dust spatial distribution map of the electrostatic precipitator, analyzes the dynamic changes of concentration and particle size in combination with the differential algorithm, and accurately generates regional difference values by means of the intelligent comparison between the dynamic threshold and the characteristic baseline, breaking through the limitations of traditional monitoring methods and realizing millimeter-level positioning of abnormal dust deposition areas. Based on the real-time dust distribution data, a combined voltage / current parameter for multi-field zoning is constructed, and a zoning control algorithm with concentration gradient and threshold linkage is adopted to strengthen power supply in high-load areas and optimize energy saving in low-load areas, forming a dynamic matching mechanism between dust distribution characteristics and power supply strategies. By using the particle swarm optimization algorithm and support vector machine modeling to construct a quantitative mapping relationship between power supply parameters and dust removal efficiency, and combining with the iterative algorithm to form a closed-loop control system of "parameter update - efficiency feedback - strategy iteration", and introducing clustering analysis and fuzzy logic control to predict the trend and classify and optimize the operating state. The multi-algorithm collaboration converts environmental interference and working condition data into dynamic control strategies, while ensuring emission stability, realizing optimal energy consumption allocation, improving dust removal efficiency and adapting to complex working conditions, and finally achieving multi-dimensional collaborative synergy of intelligent optimization of zoned power supply, refined energy efficiency management and system stability of the electrostatic precipitator.

[0259] The embodiments of the present invention also provide an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an energy-saving control program for an electrostatic precipitator. When the processor executes the computer program, the steps in the above embodiments of the energy-saving control method based on an electrostatic precipitator are implemented, such as Figure 1 step S1 shown. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiments are implemented, such as the 101 data acquisition module.

[0260] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0261] The electronic device can be a computing device such as a desktop computer, notebook, palm computer, and smart tablet, etc. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0262] The so-called processor can be a Central Processing Unit (CPU), or it can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the electronic device and connects all parts of the entire electronic device through various interfaces and lines.

[0263] The memory can be used to store the computer programs and / or modules. The processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0264] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0265] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0266] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An energy-saving control method for an electrostatic precipitator, characterized in that: include: Obtaining an original data set of dust, generating a spatial distribution map of dust according to the original data set and performing regional division, and calculating a characteristic baseline data set in combination with a preset concentration threshold; Based on the spatial distribution map, calculate the change data of dust distribution, combine the characteristic baseline data set with a preset change threshold, and generate a regional difference value; Compare the regional difference value with a preset difference threshold, generate an adjustment signal for the regional boundary according to the comparison result, divide the electric field control area in combination with the spatial distribution map, and generate a boundary coordinate set; Acquire real-time dust data according to the boundary coordinate set, calculate differential distribution data of each electric field control area, generate a voltage adjustment signal in combination with a preset distribution threshold, and determine a current distribution value; According to the voltage adjustment signal and the current distribution value, deviation calculation is performed to obtain voltage deviation distribution data, and optimization processing is performed to determine a power supply parameter set; Acquire dust removal efficiency parameters according to the power supply parameter set, and adjust the power supply parameters in combination with a preset efficiency parameter threshold to obtain an adjusted power supply parameter set; Acquire characteristic parameters according to the adjusted power supply parameter set, and re-divide the boundary coordinates in combination with a preset characteristic threshold to obtain an updated division scheme; According to the update division scheme, the dust data is reacquired and cluster analysis is performed to determine the operating status of the dust collector and obtain adjustment instructions for the electric field control.

2. The energy-saving control method for an electrostatic precipitator according to claim 1, characterized in that: The generating of the spatial distribution map of dust according to the original data set and performing regional division, combined with the preset concentration threshold, and calculating the characteristic baseline data set, includes: The original data set includes dust concentration data and particle size distribution data, historical concentration data, historical particle size distribution data and corresponding timestamps of dust; Extracting a certain amount of sampled data from the original data set, gridding the sampled data and performing interpolation calculation using a Kriging algorithm to obtain an estimated value for each grid point, visualizing the estimated value, and generating a spatial distribution map; According to the concentration data and the particle size distribution value in the spatial distribution diagram, combined with a preset concentration threshold and a preset particle size threshold, regional division is performed to obtain multiple dust characteristic partitions; If the concentration data in the characteristic partition is greater than the concentration threshold, a spatial distribution map corresponding to the characteristic partition is obtained, and a convolutional neural network is used to extract features from the spatial distribution map to obtain distribution characteristics of the abnormal area; According to the distribution characteristics of the abnormal area, the sampling data of the characteristic partition is matched with the historical operating condition database to calculate the compensation baseline value of the concentration; If the concentration data in the characteristic partition is less than the concentration threshold, the historical concentration data of the characteristic partition is obtained, and the concentration mean value in the moving time window is calculated as the statistical baseline value of the concentration; The moving time window is obtained by setting the window length and the sliding step size according to the historical concentration data and the timestamp; The compensated baseline value is combined with the statistical baseline value to form a characteristic baseline data set of dust.

3. The energy-saving control method for an electrostatic precipitator according to claim 2, characterized in that: The step of calculating the change data of dust distribution based on the spatial distribution map and combining the characteristic baseline data set with a preset change threshold to generate a regional difference value includes: According to the dust data in the spatial distribution diagram, the increase or decay rate of the concentration data per unit time is calculated based on the difference method to generate concentration change data, and the absolute difference of the particle size in adjacent time periods is counted to generate particle size deviation data; The concentration change data and the particle size deviation data together constitute the dust distribution change data; If the distribution change data is greater than a preset change threshold or a baseline value corresponding to the offset, the corresponding area is determined to be an abnormal area, and a regional difference value of the abnormal area is calculated; If the distribution change data is smaller than a preset change threshold or is within a corresponding baseline value, the corresponding area is determined to be a normal area, and the area difference value is 0.

4. The energy-saving control method for an electrostatic precipitator according to claim 1, characterized in that: The step of comparing the regional difference value with a preset difference threshold, generating an adjustment signal for the regional boundary according to the comparison result, dividing the electric field control region in combination with the spatial distribution map, and generating a boundary coordinate set includes: Compare the regional difference value of each region with a preset difference threshold, and if the regional difference value is greater than the difference threshold, generate an adjustment signal for the region, and record the regional coordinates as abnormal coordinates; If the area difference value is less than the difference threshold, an adjustment signal for the area is generated, and the coordinates of the area are recorded as normal coordinates; According to the adjustment signal, the system extracts all the abnormal coordinates and the normal coordinates, divides the electric field control area in combination with the spatial distribution map, and generates boundary coordinate sets of multiple independent electric field control areas.

5. The energy-saving control method for an electrostatic precipitator according to claim 1, characterized in that: The real-time dust data is acquired according to the boundary coordinate set, the difference distribution data of each electric field control area is calculated, a voltage adjustment signal is generated in combination with a preset distribution threshold, and a current distribution value is determined, including: The real-time dust data includes real-time dust concentration value and real-time particle size distribution value; Preprocessing the real-time dust data to eliminate noise interference to obtain noise-reduced dust data, and calculating regional difference values ​​based on the noise-reduced dust data to obtain difference distribution data; If the difference distribution data is greater than a preset distribution threshold, a voltage adjustment mechanism is triggered and a voltage adjustment signal is generated; According to the voltage adjustment signal, the current distribution value of each electric field control area is calculated by using a preset rule of current distribution; If the difference distribution data is less than the preset distribution threshold, the dust collector continues to work normally; The current distribution value of each electric field control area when the dust collector is working normally is calculated based on the rated voltage and rated power of the dust collector.

6. The energy-saving control method for an electrostatic precipitator according to claim 5, characterized in that: The step of performing deviation calculation according to the voltage adjustment signal and the current distribution value to obtain voltage deviation distribution data, and performing optimization processing to determine a power supply parameter set includes: Acquire monitoring data of the actual working condition of the dust collector, calculate the power supply voltage and power supply current of each electric field control area in combination with the voltage adjustment signal and the current distribution value, and obtain a power supply parameter set; According to the power supply parameter set and in combination with the operating condition change rate in the monitoring data, the deviation value of the power supply voltage is calculated to determine the deviation distribution data of the regional voltage; Determine the fluctuation range data of the power supply current according to the deviation distribution data, judge the matching change trend of the power supply parameter and the working condition in combination with the preset fluctuation threshold, and generate trend distribution data; Based on the trend distribution data, a mapping relationship between power supply matching degree and power supply parameters is established to obtain a first mapping data set; If the first mapping data set is greater than a preset first mapping threshold, a genetic algorithm is used to optimize the power supply voltage and the power supply current to obtain a preliminary power supply parameter set.

7. The energy-saving control method for an electrostatic precipitator according to claim 1, characterized in that: The step of obtaining the dust removal efficiency parameter according to the power supply parameter set and adjusting the power supply parameter in combination with a preset efficiency parameter threshold to obtain an adjusted power supply parameter set includes: If the dust removal efficiency parameter is higher than a preset efficiency parameter threshold, the power supply parameter set is updated using a particle swarm optimization algorithm to obtain an updated power supply parameter set; According to the updated power supply parameter set, new dust removal efficiency parameters are obtained and recorded as efficiency update parameters, and the efficiency update parameters are analyzed using a support vector machine algorithm to obtain efficiency change data; Based on the performance change data, a mapping relationship between the power supply parameters of each area and the dust removal efficiency is established to obtain a second mapping data set; If the second mapping data set is greater than a preset second mapping threshold, the power supply parameters are iteratively adjusted according to the change direction to obtain an adjusted power supply parameter set.

8. The energy-saving control method for an electrostatic precipitator according to claim 1, characterized in that: The method of reacquiring dust data and performing cluster analysis according to the updated division scheme to determine the operating state of the dust collector and obtain an adjustment instruction for the electric field control includes: Based on the update division scheme, dust concentration, particle size distribution data and environmental interference value of each area of ​​the electrostatic precipitator are collected in real time to generate a real-time data set, obtain real-time power supply current and power supply voltage, and generate electric field management parameters; According to the real-time data set, the power supply matching degree and regional difference value of each area are calculated to obtain matching degree data; If the power supply matching degree in the matching degree data is higher than a preset matching degree threshold, adjusting the electric field management parameters based on an adaptive particle swarm optimization algorithm to generate a management parameter set; According to the management parameter set, obtaining updated dust concentration and particle size distribution data, and generating an updated data set in combination with the environmental interference value; Using a K-means clustering algorithm to classify the regional difference values ​​in the updated data set to obtain a classification result set; According to the classification result set, a fuzzy logic control algorithm is used to determine the change trend of the dust collector operation state to obtain a state data set; According to the state data set, a supply voltage adjustment amount and a supply current adjustment amount are generated, and an adjustment instruction is output at the same time to perform electric field control on the dust collector to complete energy-saving control.

9. An energy-saving control system for an electrostatic precipitator, characterized in that: include: A data acquisition module is used to acquire an original data set of dust, generate a spatial distribution map of dust according to the original data set and perform regional division, and calculate a characteristic baseline data set in combination with a preset concentration threshold; A regional difference value acquisition module, used to calculate the change data of dust distribution based on the spatial distribution map, and generate a regional difference value by combining the characteristic baseline data set with a preset change threshold; A boundary coordinate set acquisition module, used to compare the regional difference value with a preset difference threshold, generate an adjustment signal of the regional boundary according to the comparison result, divide the electric field control area in combination with the spatial distribution map, and generate a boundary coordinate set; An adjustment signal generation module is used to obtain real-time dust data according to the boundary coordinate set, calculate the difference distribution data of each electric field control area, generate a voltage adjustment signal in combination with a preset distribution threshold, and determine a current distribution value; A power supply parameter set module, used to perform deviation calculation according to the voltage adjustment signal and the current distribution value to obtain voltage deviation distribution data, and perform optimization processing to determine a power supply parameter set; A power supply parameter set adjustment module is used to obtain dust removal efficiency parameters according to the power supply parameter set, and adjust the power supply parameters in combination with a preset efficiency parameter threshold to obtain an adjusted power supply parameter set; An updating partitioning scheme module is used to obtain characteristic parameters according to the adjusted power supply parameter set, and to re-divide the boundary coordinates in combination with a preset characteristic threshold value to obtain an updated partitioning scheme; The energy-saving control module reacquires the dust data and performs cluster analysis according to the update division scheme, determines the operating status of the dust collector, and obtains adjustment instructions for the electric field control.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the energy-saving control method for the electrostatic precipitator according to any one of claims 1 to 8.

Images