End-to-end prediction method for dust collection efficiency of wet dust collector

Abstract

The invention discloses an end-to-end prediction method for the dust removal efficiency of a wet dust collector, and the method comprises the steps: firstly obtaining an actual pressure fluctuation signal, dividing the actual pressure fluctuation signal into a plurality of intervals according to the size of the dust removal efficiency, and selecting actual pressure fluctuation signal segments corresponding to the actual dust removal efficiency in different intervals through the actual pressure fluctuation signal corresponding to the actual dust removal efficiency; respectively converting the signal segments in different intervals into images by adopting two conversion methods; fusing the images by adopting different image feature fusion methods to form an image data set; a set network model is adopted to train different image data sets of each interval, then different initial discrimination models are formed, discrimination weights of the different initial discrimination models in each interval are dynamically calculated according to accuracy rates of the different initial discrimination models in each interval, performance advantages of each model in a specific interval are utilized to the maximum extent, and the discrimination accuracy of the different initial discrimination models in the specific interval is improved. And a dust removal efficiency fusion prediction model is obtained, so that high-precision and high-robustness dust removal efficiency monitoring is realized.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of monitoring the dust removal efficiency of a wet dust collector, and in particular to an end-to-end prediction method for the dust removal efficiency of a wet dust collector. BACKGROUND

[0002] A wet dust collector is one of the core equipment for dust prevention and control in the industrial and mining industries, and real-time and accurate monitoring of its operating efficiency is crucial for ensuring the effectiveness of emission reduction. Currently, the most accurate method for measuring the dust removal efficiency of a wet dust collector is to directly measure the changes in dust concentration in the environment and then calculate the required dust removal efficiency after corresponding analysis. Although this method is accurate, it is complex to calculate and requires regular calibration of dust monitoring equipment, making it impossible to achieve real-time monitoring. Existing online real-time monitoring and identification mainly rely on the identification of the internal gas-liquid two-phase flow state (flow pattern) or the analysis of the physical properties of the washing medium, and then indirectly infer the dust removal efficiency through empirical correlations. Specifically, existing technical solutions mainly fall into two categories: First, a pressure sensor is installed on the pipeline of the dust collector to collect one-dimensional pressure fluctuation signals, and a signal processing or machine learning model is used to identify the internal flow pattern, thereby indirectly evaluating the efficiency. However, the gas-liquid flow in a wet dust collector is extremely complex, and there is a high degree of overlap and non-single mapping relationship between the flow pattern and the dust removal efficiency. For example, under the same flow pattern, due to factors such as bubble size distribution and liquid film fluctuation, the dust removal efficiency can fluctuate by more than ±50%, resulting in a principle error in the method based on flow pattern inference, which makes it difficult to meet the demand for accurate monitoring.

[0003] Second, an indirect analysis method based on visual images: high-speed cameras and other means are used to obtain internal flow images, and image information entropy and other characteristic parameters are used to establish a correlation with the efficiency. Although this method is intuitive, it relies heavily on expensive and fragile optical equipment, which is difficult to operate stably for a long time in harsh industrial environments such as dust, humidity, and vibration. Moreover, it is significantly affected by lighting conditions, and the cost of system deployment and maintenance is high, which restricts its large-scale application.

[0004] In summary, existing technologies essentially belong to the indirect mapping path of "signal / image → flow pattern or gas holdup → efficiency", which has two fundamental bottlenecks: Principle error: the correlation model between the intermediate variable (such as flow pattern) and the target variable (dust removal efficiency) itself has errors and poor adaptability.

[0005] Limitations in feature extraction: neither traditional signal processing nor single image conversion methods can fully and robustly extract deep spatio-temporal and frequency domain coupling features directly related to dust removal efficiency. For the non-linear and non-stationary pressure signals specific to wet dust collectors, existing feature mining methods lack depth and breadth, resulting in a low upper limit for model accuracy.

[0006] Therefore, how to provide a new dust removal efficiency discrimination method, which can screen out the most effective feature combination from multiple image modalities, and construct an end-to-end prediction architecture coupled with process depth to process one-dimensional pressure signals, so as to realize high-precision and high-robustness dust removal efficiency monitoring, is the research direction required by the present application. SUMMARY

[0007] In view of the problems existing in the prior art, the present application provides an end-to-end prediction method for dust removal efficiency of a wet dust collector, which converts one-dimensional pressure signals into images and fusion processing by selecting a specific model, and adopts a partition interval weight distribution strategy, which can screen out the most effective feature combination from multiple image modalities, and then maximize the performance advantages of each model in a specific area, so as to realize high-precision and high-robustness dust removal efficiency monitoring.

[0008] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: an end-to-end prediction method for dust removal efficiency of a wet dust collector, comprising the following steps: Step one, pressure signal acquisition and real dust removal efficiency calculation: start the wet dust collector to work in the current environment, and acquire the real-time pressure signals of the inlet and outlet of the wet dust collector for a period of time; at the same time, acquire the real-time dust concentration in the current environment for a period of time, which is used to calculate the real dust removal efficiency.

[0009] Step two, pressure signal preprocessing: correct the real-time pressure signals of the inlet and outlet obtained in step one to obtain the actual pressure fluctuation signals inside the wet dust collector; divide multiple different intervals according to the size of the dust removal efficiency, select the actual pressure fluctuation signal segment corresponding to the real dust removal efficiency in different intervals according to the actual pressure fluctuation signal corresponding to the real dust removal efficiency in step one; and adopt a sliding window method to intercept the actual pressure fluctuation signal segment in different intervals for subsequent data processing.

[0010] Step three, converting pressure signals into images: at least two conversion methods are selected to convert the actual pressure fluctuation signal segments in different intervals obtained in step two into images, so that at least two images are obtained for each interval.

[0011] Step four, image fusion: different image feature fusion methods are adopted to fuse the multiple images obtained in step three, and image data sets fused by different methods are obtained for each interval.

[0012] Step five, dust removal efficiency discrimination model construction: after the network model is trained by using different image data sets in each interval, different initial discrimination models are formed, and then the dust removal efficiency discriminated by different initial discrimination models is obtained, and the discrimination results are compared with whether the corresponding real dust removal efficiency is in the same interval, so as to obtain the dust removal efficiency discrimination accuracy of each initial discrimination model in each interval; according to the accuracy of each initial discrimination model in each interval, the discrimination weight of different initial discrimination models in each interval is dynamically calculated, so as to obtain the final dust removal efficiency fusion prediction model, realize the selection and integration of the regional optimal model, and improve the overall prediction consistency.

[0013] Step six, dust removal efficiency monitoring: the wet dust collector continuously removes dust from the current environment, and after repeating steps one to five, the dust removal efficiency of the wet dust collector and its corresponding interval are continuously output by the dust removal efficiency fusion prediction model, so as to realize the continuous monitoring of the dust removal efficiency.

[0014] Further, in step one, the real-time dust concentration in the current environment is obtained by using the particulate matter concentration sampler, and the real dust removal efficiency of the wet dust collector is calculated according to the real-time dust concentration change.

[0015] Further, in step two, the actual pressure fluctuation signal inside the wet dust collector is obtained, and the specific process is as follows: the real-time pressure signals of the inlet and outlet are subtracted to obtain the actual pressure fluctuation signal inside the wet dust collector.

[0016] Further, in step two, different intervals are divided, specifically: according to the dust removal efficiency from small to large, the intervals are divided into low-efficiency zone, primary-efficiency zone, medium-efficiency zone and high-efficiency zone.

[0017] Further, in step three, two conversion methods are selected, which are symmetric point mode (SDP) and pseudo image coding (PIE). The two conversion methods are used because the symmetric point mode can generate symmetric leaflet images rich in spatial correlation features, and the pseudo image coding can generate gray scale images rich in time-frequency features, which form effective complementation in feature expression and improve the accuracy of subsequent discrimination of dust removal efficiency.

[0018] Further, in step four, three image feature fusion methods are used, including weighted average fusion (WAF), simple splicing fusion (ISF) and regional gradient fusion (RGAF). The image data sets formed by the three image fusion methods have different advantages in different intervals.

[0019] Furthermore, the network model set in step five is a convolutional neural network (CNN) model, and the backbone network of the model adopts a lightweight residual structure to balance computational efficiency and feature extraction depth; after training with three image datasets, WAF-CNN initial discrimination model, ISF-CNN initial discrimination model and RGAF-CNN initial discrimination model are formed respectively.

[0020] Furthermore, the dust removal efficiency fusion prediction model obtained in step five is specifically as follows: Define binary characteristic function , ∈[different initial discriminant model labels], ∈ [different intervals]), if the data identified by a certain initial discrimination model belongs to the target interval. ,but =1, otherwise =0; for the interval The calculation is as follows: Where P n Here, n represents the weight values ​​for different initial discriminant models, and n is the number of initial discriminant models. Then, the output rules of the dust removal efficiency fusion prediction model are established so that when the model outputs dust removal efficiency for different intervals, it will select the initial discrimination model with the highest weighting value for output. Specifically: First, if different initial discrimination models output the same dust removal efficiency in the same interval, the dust removal efficiency fusion prediction model directly outputs the dust removal efficiency as the dust removal efficiency of that interval. Otherwise, calculate the weighted voting score E according to the above formula. k If E k If E ≥ Ekmin, then the dust removal efficiency of the corresponding initial discrimination model is output as the dust removal efficiency for that interval; finally, if E k If <Ekmin, then the dust removal efficiency of the initial discrimination model with the highest weighted value is output as the dust removal efficiency of that interval; Based on the above output rules, a dust removal efficiency discrimination model is established, and the prediction results of the fusion model are output.

[0021] Compared with the prior art, the present invention has the following advantages: 1. High-precision end-to-end prediction: This invention employs the synergistic effect formed by feature selection and fusion: it selects Symmetric Point Pattern (SDP) and Pseudo Image Encoding (PIE) as two image conversion methods that are physically complementary and synergistic in performance in the field of pressure signal to image feature extraction (i.e., SDP is good at capturing spatial structure correlation, and PIE is good at expressing time-frequency features). Image fusion is then performed through a weighted average fusion (WAF) strategy. Experiments using different models have confirmed that this specific combination produces a synergistic enhancement effect, effectively extracting deep features strongly correlated with dust removal efficiency. The overall prediction accuracy of the WAF-CNN model is improved to 97.5%, an accuracy that cannot be achieved using any single image conversion method or other known combinations.

[0022] 2. Strong Robustness: This invention employs the inherent redundancy and architectural design of multimodal fusion. Due to the inherent information redundancy and complementarity of the constructed multimodal feature fusion images, especially when facing noise and data loss, different image modalities have different sensitivities to interference. The prediction model constructed by this invention performs excellently under complex working conditions. Under conditions of high noise and high data loss, the performance degradation is much lower than that of a single model, which proves the effectiveness and stability of the prediction model formed by this fusion architecture in industrial settings.

[0023] 3. Accurate Adaptability Across All Operating Conditions: This invention proposes a regional dynamic weighted fusion mechanism, dividing the dust removal efficiency into intervals and deeply coupling it with the performance of each initial identification model within different intervals. Higher weights are assigned to models with higher accuracy within a particular interval to establish a dust removal efficiency fusion prediction model. This prediction model achieves a qualitative leap in model decision-making from "global optimum" to "regional optimum." This method effectively solves the "weakest link effect" of a single model in certain dust removal efficiency intervals, achieving synergistic optimization and balanced improvement of accuracy across different dust removal efficiency intervals. This effect is unattainable by traditional static model fusion methods that are detached from specific processes.

[0024] 4. Novel Technical Framework: The method of this invention bypasses the intermediate step of existing manifold identification and constructs a complete and closed technical framework of "one-dimensional pressure signal → multimodal image feature screening and fusion → dynamic weight decision based on different intervals → direct output of dust removal efficiency". This framework breaks through the traditional technical bias of relying on "indirect mapping" in this field, and provides a brand-new technical path for solving the problem of fundamental errors. Attached Figure Description

[0025] Figure 1 This is a flowchart of the model fusion strategy and dust removal efficiency range prediction result discrimination in this invention.

[0026] Figure 2This is a comparison chart of the accuracy of different conversion methods in the embodiment of the present invention for judging dust removal efficiency.

[0027] Figure 3 This is a schematic diagram illustrating the process of fusing multimodal features of PIE and SDP features into an image dataset according to an embodiment of the present invention.

[0028] Figure 4 This is a comparison chart of the accuracy of different initial discrimination models in judging dust removal efficiency in embodiments of the present invention. Detailed Implementation

[0029] The present invention will be further described below.

[0030] Example: A 5000 m³ / h wet scrubber needs to monitor the PM2.5 concentration in the current environment. 2.5 The dust removal process, employing the method of this invention to determine dust removal efficiency, includes the following steps: Step 1: Pressure Signal Acquisition and Actual Dust Removal Efficiency Calculation: High-frequency pressure sensors are installed at the inlet and outlet of the wet scrubber (the inlet sensor is positioned close to the scrubber, and the outlet sensor is positioned before the negative pressure fan exhaust port and after the scrubber outlet). A data acquisition module is used to collect pressure signals in real-time under all operating conditions at a sampling frequency of 1024Hz, with 5120 sampling points. The wet scrubber is then turned on to perform dust removal operations in the current environment, and the real-time pressure signals at the inlet and outlet are acquired and maintained for a period of time. Particulate matter concentration samplers are installed at the inlet and outlet of the wet scrubber, and the inlet and outlet dust concentrations are simultaneously measured under the corresponding operating conditions during this period to calculate the actual dust removal efficiency under the corresponding pressure signal conditions.

[0031] Step 2: Pressure Signal Preprocessing: The difference between the real-time inlet and outlet pressure signals obtained in Step 1 is used as the actual pressure fluctuation signal inside the wet scrubber; based on PM... 2.5 The dust removal efficiency is divided into several different ranges, specifically: based on the dust removal efficiency from low to high, the ranges are: 0-80% is the low-efficiency range, 80%-90% is the primary efficiency range, 90%-97% is the medium efficiency range, and 97%-100% is the high-efficiency range. Using the actual pressure fluctuation signal corresponding to the actual dust removal efficiency from step one, the actual pressure fluctuation signal segments corresponding to different ranges of actual dust removal efficiency are selected. A sliding window method is then used to extract the actual pressure fluctuation signal segments within different ranges for subsequent data processing.

[0032] Step 3: Converting pressure signals into images: Two conversion methods were selected: Symmetric Point Pattern (SDP) and Pseudo Image Encoding (PIE). These two methods were chosen because SDP generates symmetrical leaf-shaped images rich in spatial correlation features, while PIE generates grayscale images rich in time-frequency features. The two methods effectively complement each other in feature representation, improving the accuracy of subsequent dust removal efficiency determination. To verify the effectiveness of the two conversion methods selected in this embodiment, Gram angle field (GAF), Markov transition field (MTF), relative position matrix (RPM), SDP, and PIE methods were used to fuse the two images obtained in Step 3, respectively. Image datasets fused using different methods were obtained for each interval. Three types of machine learning models—Convolutional Neural Network (CNN), Decision Tree (DT), and Support Vector Machine (SVM)—were used to train and validate the different image datasets. A raw time series model (TS) based on a Long Short-Term Memory (LSTM) network was set as a control group. Figure 2 As shown, this is a comparison chart of the accuracy of different conversion methods in determining dust removal efficiency from images. Figure 2 It can be seen that the accuracy of the dust removal efficiency output by the model formed after training the CNN model using the image converted by Symmetric Point Pattern (SDP) and Pseudo Image Coding (PIE) is much higher than that of other conversion methods (94.7% and 94.9%, respectively). Therefore, these two conversion methods are used to convert the actual pressure fluctuation signal segments in different intervals obtained in step two into images, so that two images are obtained for each interval.

[0033] Step 4, Image Fusion: Three image feature fusion methods—Weighted Average Fusion (WAF), Simple Sequin Fusion (ISF), and Region Gradient Fusion (RGAF)—are used to fuse the multiple images obtained in Step 3, resulting in image datasets fused using different methods for each interval. The image datasets generated by these three image fusion methods each have different advantages in different intervals. To verify their effectiveness, this embodiment uses four fusion methods—Simple Sequin Fusion (ISF), Weighted Average Fusion (WAF), Region Gradient Fusion (RGAF), and Wavelet Transform Fusion (WTIF)—to generate multimodal feature fusion image datasets that fuse PIE and SDP features. The specific process is as follows: Figure 3 As shown in the figure. A comparative analysis was conducted using the MCNN multi-stream network architecture. To evaluate the generality of the fusion strategy, all fused image datasets were validated using Convolutional Neural Networks (CNN), Decision Trees (DT), and Support Vector Machines (SVM). The CNN backbone network employed a lightweight residual structure to balance computational efficiency and feature extraction depth. The results are shown in the figure. Figure 4As shown in the figure, the multimodal images constructed using spatial domain fusion methods such as WAF, ISF, and RGAF can effectively inherit and enhance image features, with the WAF-CNN model achieving the highest accuracy of 97.5%. Therefore, these three image feature fusion methods were chosen to obtain three image datasets.

[0034] Step 5: Construction of Dust Removal Efficiency Discrimination Model: Based on the verification results of Step 4, among the three models—Convolutional Neural Network (CNN), Decision Tree (DT), and Support Vector Machine (SVM)—the CNN model has the highest accuracy after training. Therefore, the CNN model is trained using different image datasets for each interval to form different initial discrimination models (i.e., WAF-CNN initial discrimination model, ISF-CNN initial discrimination model, and RGAF-CNN initial discrimination model). The dust removal efficiency is then obtained by different initial discrimination models. The discrimination results are compared with the corresponding real dust removal efficiency to determine whether they are in the same interval. The dust removal efficiency discrimination accuracy of each discrimination model in each interval is shown in Table 1.

[0035] Table 1. Accuracy of the three models in each dust removal efficiency range (%) Based on the accuracy of different initial discrimination models in each interval, the discrimination weight of different initial discrimination models in each interval is dynamically calculated, thereby obtaining the final dust removal efficiency fusion prediction model. This achieves the selection and integration of the optimal model for the region, improving the overall prediction consistency. Specifically: Based on the test accuracy of the three models in four types of regions, the weights of each model are calculated independently for each region. Taking the fusion prediction of inefficient regions as an example: Similarly, the weights for the intermediate-efficiency zone, high-efficiency zone, and extreme zone are calculated based on the model accuracy corresponding to each zone.

[0036] Define binary characteristic function , ∈ [different initial discriminant model labels], ∈ [different intervals]), if the data identified by a certain initial discrimination model belongs to the target interval. ,but =1, otherwise =0; for the interval The calculation is as follows: Where Pn denoted by , where represents the weight values ​​for different initial discriminant models, and n represents the number of initial discriminant models.

[0037] Then, the output rules of the dust removal efficiency fusion prediction model are established so that when the model outputs dust removal efficiency for different intervals, it will select the initial discrimination model with the highest weighting value for output. Specifically: First, if the three initial discrimination models output the same dust removal efficiency in the same interval, the dust removal efficiency fusion prediction model directly outputs that dust removal efficiency as the dust removal efficiency for that interval.

[0038] Otherwise, calculate the weighted voting score E according to the above formula. k If E k If E ≥ Ek min, then the dust removal efficiency of the corresponding initial discrimination model is output as the dust removal efficiency for that interval; finally, if E k If Ek min < Ek min, then the dust removal efficiency of the initial discrimination model with the highest weighted value is output as the dust removal efficiency of that interval.

[0039] Otherwise, calculate the weighted voting score E according to the above formula. k If E k ≥Ek min, taking the inefficient region as an example, Ek min=0.671, then the dust removal efficiency corresponding to the initial discrimination model is output as the dust removal efficiency of that region; finally, if E k If the value is less than Ekmin, then the dust removal efficiency of the initial discrimination model with the highest weighted value (RGAF-CNN in this embodiment is the inefficient region) is taken as the dust removal efficiency of that region. Following the above output rules, a dust removal efficiency discrimination model is established, and the prediction result of the fusion model is output.

[0040] After obtaining the predictive model of the current environment through this embodiment, only high-frequency pressure sensors need to be installed in industrial sites with the same environment. The host computer executes the above processing flow and outputs E in real time. k The values ​​and their corresponding ranges are used to ensure continuous monitoring and optimal accuracy of dust removal efficiency.

[0041] Robustness verification of the prediction model in this embodiment: Noise data with a signal-to-noise ratio (SNR) of 25-45 dB and data missing ratios of 5%-25% were added to the time series data of the original pressure signal, and the recognition accuracy of each model was verified to obtain the corresponding recognition accuracy. Under different noise levels and data missing ratios, the prediction model in this embodiment exhibits strong robustness. Within the SNR range of 25-45 dB, the accuracy of the prediction model in this embodiment remains between 68.3% and 98.9%; when the data missing ratio is 5%-25%, the accuracy of the prediction model in this embodiment remains between 79.7% and 97.5%. This indicates that the prediction model in this embodiment can effectively cope with data fluctuations and noise interference under complex working conditions.

[0042] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for end-to-end prediction of dust removal efficiency in a wet scrubber, characterized in that, Includes the following steps: Step 1: Pressure signal acquisition and calculation of actual dust removal efficiency: Start the wet scrubber in the current environment to perform dust removal, and acquire the real-time pressure signals at the inlet and outlet of the wet scrubber for a period of time; at the same time, acquire the real-time dust concentration in the current environment during this period of time to calculate the actual dust removal efficiency. Step 2, Pressure Signal Preprocessing: Correct the real-time pressure signals at the inlet and outlet obtained in Step 1 to obtain the actual pressure fluctuation signal inside the wet scrubber; divide the scrubber into multiple different intervals according to the dust removal efficiency; select the actual pressure fluctuation signal segment corresponding to the actual dust removal efficiency in different intervals based on the actual pressure fluctuation signal corresponding to the actual dust removal efficiency in Step 1; and use the sliding window method to extract the actual pressure fluctuation signal segment in different intervals for subsequent data processing. Step 3: Convert pressure signal into image: Select at least two conversion methods to convert the actual pressure fluctuation signal segments in different intervals obtained in Step 2 into images, so that at least two images are obtained for each interval; Step 4, Image Fusion: Different image feature fusion methods are used to fuse the various images obtained in Step 3, and image datasets fused by different methods are obtained for each interval; Step 5: Construction of dust removal efficiency discrimination model: The network model is trained using different image datasets in each interval to form different initial discrimination models. The dust removal efficiency is then obtained by different initial discrimination models. The discrimination results are compared with the corresponding real dust removal efficiency to determine whether they are in the same interval. This allows us to obtain the dust removal efficiency discrimination accuracy of different discrimination models in each interval. Based on the accuracy of different initial discrimination models in each interval, the discrimination weight of different initial discrimination models in each interval is dynamically calculated to obtain the final dust removal efficiency fusion prediction model. Step Six: Dust Removal Efficiency Monitoring: The wet scrubber continuously removes dust from the current environment. After repeating steps one to five, the dust removal efficiency of the wet scrubber and its corresponding range are continuously output through the dust removal efficiency fusion prediction model, thereby achieving continuous monitoring of dust removal efficiency.

2. The end-to-end prediction method for dust removal efficiency of a wet scrubber according to claim 1, characterized in that, In step one, a particulate matter concentration sampler is used to obtain the real-time dust concentration in the current environment, and the actual dust removal efficiency of the wet scrubber is calculated based on the real-time dust concentration changes.

3. The end-to-end prediction method for dust removal efficiency of a wet scrubber according to claim 1, characterized in that, Step two involves obtaining the actual pressure fluctuation signal inside the wet scrubber. Specifically, the difference between the real-time pressure signals at the inlet and outlet is used as the actual pressure fluctuation signal inside the wet scrubber.

4. The end-to-end prediction method for dust removal efficiency of a wet scrubber according to claim 1, characterized in that, In step two, the different zones are divided as follows: based on the dust removal efficiency, the zones are divided into low-efficiency zone, primary-efficiency zone, medium-efficiency zone, and high-efficiency zone in ascending order.

5. The end-to-end prediction method for dust removal efficiency of a wet scrubber according to claim 1, characterized in that, In step three, two conversion methods were selected: symmetric point mode and pseudo-image encoding.

6. The end-to-end prediction method for dust removal efficiency of a wet scrubber according to claim 1, characterized in that, In step four, three image feature fusion methods are used: weighted average fusion, simple stitching fusion, and regional gradient fusion.

7. The end-to-end prediction method for dust removal efficiency of a wet scrubber according to claim 6, characterized in that, The network model set in step five is a convolutional neural network model, and the backbone network of the model adopts a lightweight residual structure to balance computational efficiency and feature extraction depth. After training with three image datasets, WAF-CNN initial discrimination model, ISF-CNN initial discrimination model and RGAF-CNN initial discrimination model are formed respectively.

8. The end-to-end prediction method for dust removal efficiency of a wet scrubber according to claim 1, characterized in that, The step five involves obtaining the dust removal efficiency fusion prediction model, specifically as follows: Define binary characteristic function , ∈[different initial discriminant model labels], ∈ [different intervals]), if the dust removal efficiency determined by an initial discrimination model belongs to the target interval ,but =1, otherwise =0; for the interval The calculation is as follows: Where P n Here, n represents the weight values ​​for different initial discriminant models, and n is the number of initial discriminant models. Then, the output rules of the dust removal efficiency fusion prediction model are established so that when the model outputs dust removal efficiency for different intervals, it will select the initial discrimination model with the highest weighting value for output. Specifically: First, if different initial discrimination models output the same dust removal efficiency in the same interval, the dust removal efficiency fusion prediction model directly outputs the dust removal efficiency as the dust removal efficiency of that interval. Otherwise, calculate the weighted voting score E according to the above formula. k If E k If E ≥ Ekmin, then the dust removal efficiency of the corresponding initial discrimination model is output as the dust removal efficiency for that interval; finally, if E k If <Ekmin, then the dust removal efficiency of the initial discrimination model with the highest weighted value is output as the dust removal efficiency of that interval; Based on the above output rules, a dust removal efficiency discrimination model is established, and the prediction results of the fusion model are output.

Images