Air cooling unit automatic spraying control system and method capable of reducing back pressure in segmented mode

Abstract

The invention discloses an air cooling unit automatic spraying control system and method capable of reducing backpressure in a segmented mode. The system comprises a data acquisition module, a dirt recognition module, a control module and a spraying module. The data acquisition module is used for acquiring real-time meteorological data and unit operation data, and the unit operation data comprises real-time load data and cooling fin temperature data; the dirt identification module is used for collecting image data of the radiating fins and carrying out dirt identification and positioning on the image data to obtain dirt information; the control module is used for generating a segmented spraying scheme based on the real-time meteorological data, the unit operation data and the dirt information; and the spraying module is used for spraying, cleaning and cooling the cooling fins based on the segmented spraying scheme so as to reduce the back pressure of the air cooling unit. Through regular automatic spraying, cleaning and cooling, the system can effectively reduce the back pressure of the air cooling unit, reduce the energy consumption, improve the operation efficiency of the unit, reduce the requirement for manual cleaning and reduce the maintenance cost.

Description

Technical Field

[0001] The invention belongs to the technical field of thermal power generation, and in particular relates to an automatic spray control system and method for an air-cooling unit capable of reducing back pressure in stages. Background Art

[0002] As a key equipment in industrial cooling systems, air-cooling units are widely used in the power industry. Traditional air-cooling units mainly rely on the surface area of ​​the heat sink fins to increase the heat exchange efficiency to achieve the purpose of cooling. However, with the long-term operation of the equipment and the influence of abnormal climate, dust, dirt and other sediments will gradually accumulate on the surface of the heat sink fins. These substances will significantly reduce the heat exchange efficiency of the fins, increase the back pressure of the air-cooling unit, reduce the power supply efficiency, and may shorten the service life of the equipment. At present, the cleaning of the heat sink fins mainly relies on manual or semi-automatic methods for regular cleaning, which consumes a lot of water resources, and regular cleaning increases the maintenance cost of the equipment, and the cleaning interval is difficult to accurately control.

[0003] Although some automated cleaning technologies have been proposed and applied, most systems still have problems such as low intelligence, poor adaptability, and high energy consumption. In addition, existing automated systems often lack real-time monitoring and evaluation of cleaning effects and cannot be optimized and adjusted according to the actual conditions of the fins. Therefore, it is necessary to develop an artificial intelligence-based segmented cooling and dust removal spray system and method for air-cooled unit heat dissipation fins to overcome the limitations of existing technologies and achieve a more efficient, intelligent, and environmentally friendly cleaning process. Summary of the invention

[0004] The present invention aims to solve the deficiencies of the prior art and provides the following solutions:

[0005] An automatic spray control system for an air-cooling unit capable of reducing back pressure in stages, comprising: a data acquisition module, a dirt identification module, a control module and a spray module;

[0006] The data acquisition module is used to collect real-time meteorological data and unit operation data, and the unit operation data includes real-time load data and heat sink fin temperature data;

[0007] The dirt recognition module is used to collect image data of the heat sink, and perform dirt recognition and positioning on the image data to obtain dirt information;

[0008] The control module is used to generate a segmented spraying plan based on the real-time meteorological data, the unit operation data and the fouling information;

[0009] The spray module is used to spray, clean and cool the heat dissipation fins based on the segmented spray scheme to reduce the back pressure of the air-cooling unit.

[0010] Preferably, the data acquisition module includes: a meteorological data acquisition unit, a unit load data acquisition unit, and a fin temperature acquisition unit;

[0011] The meteorological data collection unit is used to collect real-time meteorological data;

[0012] The unit load data collection unit is used to collect real-time load data;

[0013] The fin temperature collection unit is used to collect the temperature data of the heat dissipation fins.

[0014] Preferably, the dirt recognition module includes: an image acquisition unit, an image processing unit and a dirt recognition and positioning unit;

[0015] The image acquisition unit is used to acquire the image data of the heat dissipation fin;

[0016] The image processing unit is used to process the image data to obtain a processed image;

[0017] The dirt identification and positioning unit is used to identify dirt features in the processed image and locate the position of the identified dirt to obtain the dirt information.

[0018] Preferably, the image processing unit comprises: a noise filtering subunit, a size correction subunit and an image enhancement subunit;

[0019] The noise filtering subunit is used to eliminate the noise in the image data to obtain a denoised image;

[0020] The size correction subunit adjusts the image size of the denoised image to obtain a corrected image;

[0021] The image enhancement subunit is used to enhance the contrast and clarity of the corrected image to obtain the processed image.

[0022] Preferably, the control module includes: a model building unit, a data analysis unit and a scheduling unit;

[0023] The model building unit is used to build an initial spray task analysis model, and train the initial spray task analysis model using historical meteorological data, historical unit operation data and historical spray task data to obtain a spray task analysis model;

[0024] The data analysis unit uses the spray task analysis model to analyze the real-time meteorological data, the unit operation data and the processed image data to generate the segmented spray plan;

[0025] The scheduling unit is used to control the spray module to spray and clean the heat dissipation fins based on the spray scheme, so as to reduce the back pressure of the air cooling unit.

[0026] The present invention also provides an automatic spray control method for an air-cooling unit capable of reducing back pressure in stages, the method being applied to any of the above-mentioned systems and comprising the following steps:

[0027] S1. Collecting real-time meteorological data and unit operation data, the unit operation data includes real-time load data and cooling fin temperature data;

[0028] S2. Collect image data of the heat sink, and identify and locate dirt on the image data to obtain dirt information;

[0029] S3. Generate a segmented spraying scheme based on the real-time meteorological data, the unit operation data and the fouling information;

[0030] S4. Based on the segmented spraying scheme, the heat dissipation fins are sprayed, cleaned and cooled to reduce the back pressure of the air-cooling unit.

[0031] Preferably, the S1 comprises:

[0032] Use meteorological sensors to collect real-time meteorological data;

[0033] Use power load collection equipment to collect real-time load data;

[0034] The temperature data of the heat dissipation fins is collected by using a temperature sensor.

[0035] Preferably, S2 includes:

[0036] collecting the image data of the heat dissipation fin;

[0037] Processing the image data to obtain a processed image;

[0038] The dirt features are identified in the processed image, and the position of the identified dirt is located to obtain the dirt information.

[0039] Preferably, the processing method comprises:

[0040] Eliminating noise in the image data to obtain a denoised image;

[0041] Adjusting the image size of the denoised image to obtain a corrected image;

[0042] The contrast and clarity of the corrected image are enhanced to obtain the processed image.

[0043] Preferably, S3 includes:

[0044] An initial spray task analysis model is constructed, and the initial spray task analysis model is trained using historical meteorological data, historical unit operation data, and historical spray task data to obtain a spray task analysis model;

[0045] Analyzing the real-time meteorological data, the unit operation data and the processed image data using the spray task analysis model to generate the segmented spray plan;

[0046] Based on the spraying scheme, the spraying module is controlled to spray and clean the heat dissipation fins to reduce the back pressure of the air cooling unit.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention collects real-time meteorological data and unit operation data through the data acquisition module. The system can monitor and respond to changes in the external environment and unit status more accurately. At the same time, it uses historical data to train the spray task analysis model, and performs real-time data analysis on the monitored data to generate a segmented spray plan, reduce human intervention, and improve the scientificity and rationality of decision-making; at the same time, through regular automated spray cleaning and cooling, the system can effectively reduce the back pressure of the air-cooled unit, reduce energy consumption, improve the operating efficiency of the unit, reduce the need for manual cleaning, and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0050] Figure 1 Schematic diagram of the system structure of an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Embodiment 1

[0054] In this embodiment, if Figure 1 As shown, an automatic spray control system for an air-cooling unit capable of reducing back pressure in stages includes: a data acquisition module, a dirt identification module, a control module and a spray module.

[0055] The data acquisition module is used to collect real-time meteorological data and unit operation data, and the unit operation data includes real-time load data and heat sink fin temperature data.

[0056] The data acquisition module includes: a meteorological data acquisition unit, a unit load data acquisition unit, and a fin temperature acquisition unit. The meteorological data acquisition unit is used to collect real-time meteorological data; the unit load data acquisition unit is used to collect real-time load data; and the fin temperature acquisition unit is used to collect heat dissipation fin temperature data.

[0057] In this embodiment, the meteorological data acquisition unit can use a high-precision meteorological sensor array to monitor key meteorological parameters such as temperature, humidity, wind speed, wind direction, rainfall, etc. in real time, and the data is transmitted to the control module in real time through wireless communication. The unit load data acquisition unit can use smart meters and load monitors to monitor the power consumption, current, voltage and other parameters of the unit in real time to ensure the accuracy and real-time nature of the data. The fin temperature acquisition unit can use thermocouples or infrared thermal imagers to monitor the temperature of the heat sink fins at multiple points to ensure the comprehensiveness and accuracy of the temperature data.

[0058] The dirt recognition module is used to collect image data of the heat sink, and perform dirt recognition and positioning on the image data to obtain dirt information.

[0059] The dirt recognition module includes: an image acquisition unit, an image processing unit and a dirt recognition and positioning unit. The image acquisition unit is used to collect image data of the heat sink fins. In this embodiment, the image acquisition unit can use several drones equipped with high-definition industrial cameras to divide the heat sink fins of the air cooling tower into several sections. Each drone is responsible for image acquisition of a single fin segment and sets segment position labels for the collected images.

[0060] The image processing unit is used to process the image data to obtain a processed image. The image processing unit includes: a noise filtering subunit, a size correction subunit and an image enhancement subunit; the noise filtering subunit is used to eliminate the noise in the image data to obtain a denoised image; the size correction subunit is used to adjust the image size of the denoised image to obtain a corrected image; the image enhancement subunit is used to enhance the contrast and clarity of the corrected image to obtain a processed image. In this embodiment, the noise filtering subunit uses Gaussian filtering to remove noise in the image:

[0061]

[0062] Among them, I filtered (x, y) represents the denoised pixel value, I(x, y) represents the pixel value of the original image at the coordinate (x, y), σ represents the standard deviation of the Gaussian kernel, M represents the size of the Gaussian kernel, N represents the total number of elements in the kernel, and i and j represent natural numbers starting from 0. The size correction subunit uses bilinear interpolation to scale the denoised image and calculates the new pixel value by weighted averaging the four nearest neighbor pixels. The image enhancement subunit first grayscales the corrected image and calculates the number of times each gray level k appears in the image, that is, the histogram H(k); then the histogram H(k) is normalized to obtain the probability density function p(k):

[0063]

[0064] Among them, I×J is the total number of pixels in the image; then the cumulative distribution function P(k) is calculated according to the probability density function p(k):

[0065]

[0066] Among them, n and m represent natural numbers starting from 0; finally, a mapping function is constructed to map each pixel I′(x, y) of the corrected image to a new grayscale level to obtain the mapped pixel I″(x, y), completing the image enhancement:

[0067] I"(x,y)=round(L-1×(1-P(I′ (x,y) )))

[0068] Among them, L represents the maximum value of the gray level, and the round function represents rounding.

[0069] The dirt identification and positioning unit is used to identify dirt features in the processed image, locate the position of the identified dirt, and obtain dirt information. In this embodiment, the Canny operator is used to identify the edges in the image to obtain several dirt-like contours, and then these contours are feature-recognized according to the set dirt features (including color, texture, and shape), and the dirt is determined to be within the contours, and the dirt is marked. At the same time, the segment where the dirt is located is determined according to the segment position label of the original image, and the position of the dirt in the fin of the segment is determined according to the coordinate information when the drone takes the image, and the dirt identification and positioning is completed.

[0070] The control module is used to generate a segmented spraying plan based on real-time meteorological data, unit operation data and fouling information.

[0071] The control module includes: a model building unit, a data analysis unit and a scheduling unit. The model building unit is used to build an initial spray task analysis model, and use historical meteorological data, unit historical operation data and historical spray task data to train the initial spray task analysis model to obtain a spray task analysis model; the data analysis unit uses the spray task analysis model to analyze real-time meteorological data, unit operation data and processed image data to generate a segmented spray plan; the scheduling unit is used to control the spray module to spray and clean the heat sink fins based on the spray plan to reduce the back pressure of the air-cooled unit.

[0072] In this embodiment, the initial spray task analysis model in the model building unit can adopt a machine learning model, including: a data input layer, a feature extraction layer, a feature fusion layer, an intermediate processing layer, a decision layer and an output layer. The data input receives real-time meteorological data, unit operation data and pre-processed image data from the data acquisition module; the feature extraction layer is used to identify the features in the meteorological data that affect the spray effect, such as temperature, humidity, wind speed, etc., and analyzes the unit load, heat sink fin temperature, historical spraying figures and other data to extract features related to unit performance and cleanliness; the feature fusion layer integrates features from different sources to form a comprehensive feature vector; the intermediate processing layer includes multiple hidden layers for further feature extraction and nonlinear transformation; the decision layer uses classification or regression algorithms based on the fused feature vector to predict the optimal solution for the spray task; the output layer outputs a segmented spray solution, including the location, time, water volume, etc. of the spray. The training process of the model includes: (1) cleaning, standardizing and normalizing the collected meteorological data, unit operation data and image data, selecting and constructing features that affect the spraying task based on domain knowledge, and using these data to build a training data set; (2) setting model parameters, such as network structure, learning rate, optimizer, etc., to initialize the model; (3) using the training data set to train the model, adjusting the model parameters through the back propagation algorithm to minimize the prediction error, then evaluating the model performance, adjusting the model structure or parameters to prevent overfitting, and finally performing a final evaluation of the model to ensure the generalization ability of the model; (4) regularly using new data to update and optimize the model to adapt to environmental changes and improve system performance.

[0073] The data analysis unit uses the spraying task analysis model to analyze the real-time meteorological data to confirm the approximate date for spraying. When the temperature exceeds 35 degrees, it is judged as a high temperature state. At the same time, it is judged whether the operating power of the unit has increased based on the unit operation data. If the conditions of high temperature state and increased operating power are met at the same time, a short-term spraying plan is formulated. On the other hand, the spraying task analysis model is used to analyze the processed image data to obtain the location information of the dirt, and then a segmented spraying plan is formulated based on the dirt location and future meteorological data.

[0074] The spray module is used to spray, clean and cool the heat sink fins based on a segmented spray scheme to reduce the back pressure of the air-cooled unit.

[0075] Embodiment 2

[0076] In this embodiment, an automatic spray control method for an air-cooling unit capable of reducing back pressure in stages includes the following steps:

[0077] S1. Collect real-time meteorological data and unit operation data, the unit operation data includes real-time load data and heat sink fin temperature data.

[0078] S1 includes: using meteorological sensors to collect real-time meteorological data; using power load collection equipment to collect real-time load data; and using temperature sensors to collect heat sink fin temperature data.

[0079] S2. Collect image data of the heat sink fins, and perform dirt identification and positioning on the image data to obtain dirt information.

[0080] S2 includes: collecting image data of the heat sink fins; processing the image data to obtain a processed image; identifying dirt features in the processed image, and locating the position of the identified dirt to obtain dirt information.

[0081] The processing method includes: eliminating noise in image data to obtain a denoised image; adjusting the image size of the denoised image to obtain a corrected image; and enhancing the contrast and clarity of the corrected image to obtain a processed image.

[0082] S3. Generate a segmented spraying plan based on real-time meteorological data, unit operation data and fouling information.

[0083] S3 includes: constructing an initial spray task analysis model, and training the initial spray task analysis model using historical meteorological data, historical unit operation data and historical spray task data to obtain a spray task analysis model; using the spray task analysis model to analyze real-time meteorological data, unit operation data and processed image data to generate a segmented spray plan; based on the spray plan, controlling the spray module to spray and clean the heat sink fins to reduce the back pressure of the air-cooled unit.

[0084] S4. Based on the segmented spraying scheme, the heat sink fins are sprayed, cleaned and cooled to reduce the back pressure of the air-cooled unit.

[0085] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. An automatic spray control system for air-cooling units capable of reducing back pressure in stages, characterized in that: include: Data acquisition module, dirt identification module, control module and spray module; The data acquisition module is used to collect real-time meteorological data and unit operation data, and the unit operation data includes real-time load data and heat sink fin temperature data; The dirt recognition module is used to collect image data of the heat sink, and perform dirt recognition and positioning on the image data to obtain dirt information; The control module is used to generate a segmented spraying plan based on the real-time meteorological data, the unit operation data and the fouling information; The spray module is used to spray, clean and cool the heat dissipation fins based on the segmented spray scheme to reduce the back pressure of the air-cooling unit.

2. According to claim 1, an automatic spray control system for air-cooling units capable of reducing back pressure in stages, characterized in that: The data acquisition module includes: a meteorological data acquisition unit, a unit load data acquisition unit, and a fin temperature acquisition unit; The meteorological data collection unit is used to collect real-time meteorological data; The unit load data collection unit is used to collect real-time load data; The fin temperature collection unit is used to collect the temperature data of the heat dissipation fins.

3. According to claim 1, an automatic spray control system for air-cooling units capable of reducing back pressure in stages, characterized in that: The dirt recognition module includes: an image acquisition unit, an image processing unit and a dirt recognition and positioning unit; The image acquisition unit is used to acquire the image data of the heat dissipation fin; The image processing unit is used to process the image data to obtain a processed image; The dirt identification and positioning unit is used to identify dirt features in the processed image and locate the position of the identified dirt to obtain the dirt information.

4. According to claim 3, an automatic spray control system for air-cooling units capable of reducing back pressure in stages, characterized in that: The image processing unit includes: a noise filtering subunit, a size correction subunit and an image enhancement subunit; The noise filtering subunit is used to eliminate the noise in the image data to obtain a denoised image; The size correction subunit adjusts the image size of the denoised image to obtain a corrected image; The image enhancement subunit is used to enhance the contrast and clarity of the corrected image to obtain the processed image.

5. According to claim 3, an automatic spray control system for air-cooling units capable of reducing back pressure in stages, characterized in that: The control module includes: a model building unit, a data analysis unit and a scheduling unit; The model building unit is used to build an initial spray task analysis model, and train the initial spray task analysis model using historical meteorological data, historical unit operation data and historical spray task data to obtain a spray task analysis model; The data analysis unit analyzes the real-time meteorological data, the unit operation data and the processed image data using the spray task analysis model to generate the segmented spray plan; The scheduling unit is used to control the spray module to spray and clean the heat dissipation fins based on the spray scheme, so as to reduce the back pressure of the air cooling unit.

6. An automatic spray control method for air-cooling unit capable of reducing back pressure in stages, the method being applied to the system according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. Collecting real-time meteorological data and unit operation data, the unit operation data includes real-time load data and cooling fin temperature data; S2. Collect image data of the heat sink, and identify and locate dirt on the image data to obtain dirt information; S3. Generate a segmented spraying scheme based on the real-time meteorological data, the unit operation data and the fouling information; S4. Based on the segmented spraying scheme, the heat dissipation fins are sprayed, cleaned and cooled to reduce the back pressure of the air-cooling unit.

7. According to claim 6, an automatic spray control method for stepwise back pressure reduction of an air cooling unit is characterized in that: The S1 includes: Use meteorological sensors to collect real-time meteorological data; Use power load collection equipment to collect real-time load data; The temperature data of the heat dissipation fins is collected by using a temperature sensor.

8. According to claim 6, an automatic spray control method for air-cooling unit capable of reducing back pressure in stages, characterized in that: The S2 includes: collecting the image data of the heat dissipation fin; Processing the image data to obtain a processed image; The dirt features are identified in the processed image, and the position of the identified dirt is located to obtain the dirt information.

9. The automatic spray control method for stepwise back pressure reduction of an air cooling unit according to claim 8, characterized in that: The processing method includes: Eliminating noise in the image data to obtain a denoised image; Adjusting the image size of the denoised image to obtain a corrected image; The contrast and clarity of the corrected image are enhanced to obtain the processed image.

10. The automatic spray control method for stepwise back pressure reduction of an air cooling unit according to claim 8, characterized in that: The S3 includes: An initial spray task analysis model is constructed, and the initial spray task analysis model is trained using historical meteorological data, historical unit operation data, and historical spray task data to obtain a spray task analysis model; Analyzing the real-time meteorological data, the unit operation data and the processed image data using the spray task analysis model to generate the segmented spray plan; Based on the spraying scheme, the spraying module is controlled to spray and clean the heat dissipation fins to reduce the back pressure of the air cooling unit.

Images