A type of scale-resistant closed-loop cooling tower

Abstract

This invention relates to the field of cooling tower technology, specifically disclosing a closed-loop cooling tower for preventing scaling, including coils and a water distribution detection system. The water distribution detection system includes a wind speed sensor, an infrared thermal imager, and an edge processor. The wind speed sensor collects wind speed data inside the cooling tower; the infrared thermal imager collects thermal images of the coil surface; the edge processor converts the thermal images into temperature data, inputs the wind speed and temperature data into a pre-set AI model, and obtains prediction results for coil scaling from the AI ​​model. The prediction results include estimated scaling location and estimated scaling time. The edge processor also determines whether the estimated scaling time is less than a time threshold; if it is, it generates a warning message. The technical solution of this invention can predict coil scaling in advance.

Description

Technical Field

[0001] This invention relates to the field of cooling tower technology, and in particular to a closed-loop cooling tower for preventing scaling. Background Technology

[0002] A closed-circuit cooling tower is a device used to cool water or other liquids, including spray nozzles, coils, and packing layers. The liquid to be cooled flows inside the coils. Cooling water is sprayed from the spray nozzles and flows through the coils, absorbing heat from the coil surface, thus cooling the coils and consequently the liquid inside.

[0003] To increase the contact area between the coils and cooling water and enhance cooling efficiency, as many coils as possible are often installed within a limited space. This can easily lead to situations where the cooling water cannot cover the outer surface of the coils, resulting in dry spots and subsequent scale buildup. Scale on the coil surface acts as an insulating layer, hindering heat conduction between the coil and the cooling medium, reducing heat exchange efficiency and weakening cooling capacity. Scale also makes the coil surface rough and uneven, increasing the difficulty of cleaning and maintenance. Furthermore, scale affects the protective layer on the coil surface, exposing the coil's metal materials to a corrosive environment. Over time, this can lead to coil corrosion and damage, and even the formation of corrosion products, further contaminating the cooling water system.

[0004] Because the coils are arranged in layers, during inspections, only the scaling on the surface layer of the coils can usually be observed. The scaling on the inner coils can only be understood after disassembly. This results in a lag in the inspection of the inside of the coils, and by the time a problem is discovered, it has often reached a very serious stage.

[0005] Therefore, a closed-loop cooling tower that can predict scaling in advance is needed to prevent scaling. Summary of the Invention

[0006] This invention provides a closed-loop cooling tower that prevents scaling, enabling early prediction of scaling conditions on the coils.

[0007] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0008] A scale-resistant closed-loop cooling tower includes coils and a water distribution detection system, which includes a wind speed sensor, an infrared thermal imager, and an edge processor.

[0009] Wind speed sensors are used to collect wind speed data inside cooling towers;

[0010] Infrared thermal imagers are used to acquire thermal images of the surface layer of the coil.

[0011] The edge processor is also used to convert thermal imaging images into temperature data, input wind speed data and temperature data into a pre-set AI model, and obtain prediction results of coil scaling from the AI ​​model; the prediction results include the estimated scaling location and the estimated scaling time.

[0012] The edge processor is also used to determine whether the estimated scaling time is less than a time threshold; if it is, it generates a warning message.

[0013] The basic principles and beneficial effects of the scheme are as follows:

[0014] The varying degrees of coolant adhesion on the coil surface lead to different surface temperatures. Areas with uniform coolant adhesion are cooler than those without, and areas with faster coolant flow are cooler than those with slower flow. Faster-flowing areas receive more coolant, making it easier for the coolant to flow into the next coil layer, reducing the likelihood of scaling on that layer. Internal airflow helps to propel coolant across the coil, further reducing scaling. Therefore, the surface temperature of the coil and the airflow velocity directly influence whether scaling occurs.

[0015] This solution uses an anemometer to collect wind speed data inside the cooling tower and an infrared thermal imager to capture thermal images of the coil surface. An edge processor then converts these thermal images into temperature data. This data is input into a pre-built AI model to predict coil scaling. The predictions include the estimated location and timing of scaling. Therefore, this solution can detect and predict scaling before it occurs, providing advance guidance for cooling tower maintenance and cleaning.

[0016] The edge processor not only handles data processing and conversion but also makes judgments based on the estimated scaling time. If the estimated scaling time is less than a set time threshold, it will generate an early warning message. This early warning function makes the operation monitoring of the cooling tower more intelligent and proactive. When scaling is severe or time is of the essence, operators can take timely measures to avoid the impact of scaling, such as reduced heat dissipation efficiency and increased energy consumption.

[0017] In summary, this invention, by introducing a water distribution detection system and fully utilizing equipment such as wind speed sensors and infrared thermal imagers, combined with the predictive capabilities of AI models, can predict scaling conditions on cooling tower coils in advance, achieving effective scaling monitoring and early warning functions. This innovative design makes cooling tower maintenance more efficient and reliable, helps extend equipment lifespan, and reduces energy consumption, thus possessing broad application prospects in industrial production.

[0018] Furthermore, it also includes a model training module, which is used to acquire a dataset, including historical wind speed data, historical thermal imaging images, the location of scale buildup on the coil corresponding to the historical thermal imaging images, and the scale buildup time.

[0019] The model training module is also used to build training and test sets based on the dataset; train the AI ​​model based on the training set, evaluate the performance of the AI ​​model based on the test set, and deploy the trained AI model to the edge processor.

[0020] The model training module acquires datasets including historical wind speed data, historical thermal imaging images, the locations of scale buildup on the coils corresponding to the historical thermal imaging images, and the time of scale buildup. This rich dataset provides ample samples and labels for training the AI ​​model, enabling it to more accurately learn the relationship between wind speed, coil surface temperature, and the internal structure of the coil.

[0021] The model training module divides the dataset into training and testing sets. The AI ​​model is trained on the training set and then evaluated on the testing set. This training and evaluation process ensures the efficiency and accuracy of the AI ​​model, enabling it to better meet the needs of scaling prediction in real-world scenarios.

[0022] The trained AI model will be deployed to an edge processor, meaning it can run in real time on-site at the cooling tower. The AI ​​model deployed on the edge processor can quickly process collected wind speed data and infrared thermal imaging images, thereby predicting coil scaling and providing early warnings in a timely manner, offering crucial decision support for maintenance personnel.

[0023] Furthermore, the coil includes multiple layers of straight pipes and bends connecting the ends of the straight pipes; the location of scaling includes the number of layers and rows of the scaling straight pipes, and the distance from the end of the straight pipes.

[0024] It facilitates accurate location of scale buildup.

[0025] Furthermore, the temperature data includes the temperature value and the position of the corresponding top straight pipe.

[0026] This facilitates the detection of temperature at every point on the top straight pipe.

[0027] Furthermore, the straight tube is provided with several annular protrusions evenly distributed along its length.

[0028] The annular protrusions divide the straight pipe into several independent sections, which helps the water flow to converge between two annular protrusions, reducing the probability of scaling. At the same time, each section can also serve as a temperature monitoring area, facilitating temperature monitoring and subsequent determination of the location of scaling.

[0029] Furthermore, it also includes a blower for blowing air and a spray system for distributing water to the coil; the wind speed sensor is fixed below the blower; the spray system includes a main water supply pipe and several branch water supply pipes connected to the main water supply pipe, the branch water supply pipes are arranged parallel to the length direction of the coil, and several first nozzles are evenly arranged on the branch water supply pipes.

[0030] Furthermore, a first solenoid valve is also installed on the main water supply pipe;

[0031] It also includes a horizontal sliding mechanism and a controller;

[0032] The horizontal sliding mechanism is located above the coil, and the infrared thermal imager is fixed on the horizontal sliding mechanism;

[0033] The controller is used to close the first solenoid valve at preset intervals, move the horizontal sliding mechanism to a predetermined position, and control the infrared thermal imager to capture thermal images of the coil. The controller is also used to open the first solenoid valve after the image capture is completed.

[0034] Furthermore, there are at least two predetermined positions, and the controller is used to control the horizontal sliding mechanism to move sequentially to each of the preset predetermined positions during the first shot.

[0035] Furthermore, the edge processor is also used to acquire local thermal imaging images captured at a predetermined location, and stitch all the local thermal imaging images into a complete thermal imaging image. Attached Figure Description

[0036] Figure 1 This is a logic block diagram of an embodiment of an anti-scaling closed-loop cooling tower.

[0037] Figure 2 This is a top view of a second embodiment of an anti-scaling closed cooling tower. Detailed Implementation

[0038] The following detailed description illustrates the specific implementation method:

[0039] The markings in the accompanying drawings of the instruction manual include: main water supply pipe 1, branch water supply pipe 2, servo motor 3, reducer 4, lead screw 5, and nut seat 6.

[0040] Example 1

[0041] like Figure 1 As shown, this embodiment of a scale-resistant closed-loop cooling tower includes a coil and a water distribution detection system. The coil includes multiple layers of straight pipes and bends connecting the ends of the straight pipes. Several annular protrusions are evenly arranged along the length of the straight pipes.

[0042] The water distribution detection system includes a wind speed sensor, an infrared thermal imager, an edge processor, and a model training module.

[0043] An anemometer is used to collect wind speed data inside the cooling tower; an infrared thermal imager is used to collect thermal images of the coil surface. In the thermal images, the coil surface displays different colors due to different temperatures.

[0044] The model training module is used to acquire the training dataset, which includes historical wind speed data, historical thermal imaging images, the location of scale buildup on the coils corresponding to the historical thermal imaging images, and the time of scale buildup. The module also constructs training and testing sets based on the dataset; trains the AI ​​model using the training set, evaluates the AI ​​model's performance using the testing set, and deploys the trained AI model to the edge processor.

[0045] Specifically, historical wind speed data and historical thermal imaging data were acquired using wind speed sensors and infrared thermal imagers, respectively. The location and timing of scale buildup on the coil were collected by staff, labeled, and uploaded. The thermal imaging images needed to be converted into temperature data, including the temperature value and the corresponding position of the top straight pipe. The scale location included the layer number, row number, and distance from the end of the straight pipe. In this embodiment, the left end of the straight pipe was considered to be at distance 0. In other words, the layer number corresponds to the Z-axis coordinate in the three-dimensional coordinate system, the row number corresponds to the X-axis coordinate, and the distance from the end of the straight pipe corresponds to the Y-axis coordinate. The specific scale location on the coil can be determined using the layer number, row number, and distance from the end of the straight pipe. In this embodiment, 80% of the dataset was used for training and 20% for validation.

[0046] The edge processor is also used to acquire new wind speed data and thermal imaging images, crop the thermal imaging images to retain the portion corresponding to the coil, convert the cropped thermal imaging images into temperature data, and input the wind speed and temperature data into a pre-set AI model to obtain prediction results of coil scaling. The prediction results include the estimated scaling location and the estimated scaling time. To ensure the accuracy of the prediction results, this embodiment requires consistent water quality; that is, the water quality when obtaining the training dataset should be consistent with the actual water quality during testing. If the water quality is inconsistent, a water treatment device needs to be installed.

[0047] The edge processor is also used to determine whether the estimated scaling time is less than a time threshold. If it is, a warning message is generated. In this embodiment, the time threshold is 30 days. In this embodiment, the warning message can be pushed outwards via a network, such as to the control center or the mobile phones of designated personnel.

[0048] Example 2

[0049] The difference between this embodiment and Embodiment 1 is that this embodiment also includes a blower and a spray system for distributing water to the coil. A wind speed sensor is fixed below the blower. The spray system includes a main water supply pipe 1 and several branch water supply pipes 2 connected to the flange of the main water supply pipe 1. The branch water supply pipes 2 are arranged parallel to the length direction of the coil, and several first nozzles are evenly arranged on the branch water supply pipes 2. In this embodiment, a first solenoid valve is also provided on the main water supply pipe 1.

[0050] like Figure 2 As shown, it also includes a horizontal sliding mechanism and a controller;

[0051] The horizontal sliding mechanism is located above the coil, and the infrared thermal imager is fixed on the horizontal sliding mechanism.

[0052] Specifically, the horizontal sliding mechanism includes a servo motor 3, a reducer 4, a lead screw 5, and a nut seat 6 that cooperates with the lead screw 5; the lead screw 5 is located between the branch water supply pipes 2, and the lead screw 5 is parallel to the branch water supply pipes 2. In this embodiment, the lead screw 5 is located in the middle position of the branch water supply pipes 2.

[0053] The servo motor 3 and the reducer 4 are fixed on one side of the closed cooling tower shell. The output shaft of the servo motor 3 is fixedly connected to the input end of the reducer 4, and the output end of the reducer 4 is fixedly connected to one end of the lead screw 5. The other end of the lead screw 5 is rotatably connected to the other side of the closed cooling tower shell.

[0054] The infrared thermal imager is fixed on the nut seat 6, and the infrared thermal imager is facing the coil.

[0055] The first solenoid valve, servo motor 3, and infrared thermal imager are all electrically connected to the controller, which is in turn electrically connected to the edge processor.

[0056] In this embodiment, under inspection mode, the controller closes the first solenoid valve at preset intervals, then starts the servo motor 3 to move the nut seat 6 to a predetermined position, controlling the infrared thermal imager to capture a thermal image of the coil. The controller also controls the first solenoid valve to open after the image capture is complete. In this embodiment, the captured thermal image covers the entire upper surface of the coil, allowing the nut seat 6 to move to the middle position of the coil. In other embodiments, if the captured thermal image only covers part of the coil, the coil is divided into several sections. A partial thermal image is captured at a predetermined position, then another partial thermal image is captured at the next predetermined position. Finally, all the partial thermal images are stitched together to form a complete thermal image. During infrared thermal image capture, briefly stopping the first nozzle sprays water can prevent water mist from affecting the image.

[0057] Example 3

[0058] The difference between this embodiment and embodiment two is that in this embodiment, there are at least two predetermined positions. The controller is used to control the nut seat to move sequentially to each of the preset predetermined positions during the first shooting. The preset predetermined positions are determined by the staff.

[0059] The edge processor is also used to acquire new thermal imaging images. After converting the thermal imaging images into temperature data, it filters out the temperature value corresponding to the straight pipe directly below the lead screw. If there is no straight pipe directly below the lead screw, this embodiment considers the straight pipes on both sides directly below the lead screw as the straight pipes directly below the lead screw.

[0060] The edge processor is also used to sort the filtered temperature values ​​in descending order; select the temperature value with the largest value, determine the corresponding straight pipe position, mark it as the first straight pipe position, and map the position of the lead screw above the first straight pipe position to the position of the lead screw as the first predetermined position;

[0061] The edge processor is also used to determine the covered and uncovered areas of the thermal imaging image at the first predetermined location, select the straight pipe position with the highest temperature value in the uncovered area and mark it as the second straight pipe position, determine the second predetermined location based on the second straight pipe position, and so on until the thermal imaging image fully covers the coil.

[0062] The controller is used to control the nut seat to move sequentially to each predetermined position during non-first-time shooting, and to control the infrared thermal imager to capture local thermal imaging images of the coil.

[0063] The edge processor is also used to stitch all the local thermal images together into a complete thermal image.

[0064] After the first nozzle stops spraying water, the absence of sprayed cooling water reduces its impact on the infrared thermal imager. However, the coil continues to heat up, and the cooling water adhering to its surface continues to evaporate, forming water vapor that affects the infrared thermal imager's capture. In this embodiment, a predetermined position is determined based on the location with the highest temperature below the lead screw. Since a higher temperature indicates less adhering cooling water and less water vapor, capturing images at this location reduces the impact of water vapor on the image. Simultaneously, it allows the center of the infrared thermal imager to be aligned with the high-temperature location, further improving the imaging effect. Since subsequent analysis focuses on the high-temperature location, this minimizes its impact on the overall thermal image acquisition.

[0065] The above are merely embodiments of the present invention. The invention is not limited to the fields covered by these embodiments. Commonly known structures and characteristics in the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are able to access all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A scale-resistant closed-loop cooling tower, comprising coils, characterized in that, It also includes a water distribution detection system, which includes a wind speed sensor, an infrared thermal imager, and an edge processor; Wind speed sensors are used to collect wind speed data inside cooling towers; Infrared thermal imagers are used to acquire thermal images of the surface layer of the coil. The edge processor is also used to convert thermal imaging images into temperature data, input wind speed data and temperature data into a pre-set AI model, and obtain prediction results of coil scaling from the AI ​​model; the prediction results include the estimated scaling location and the estimated scaling time. The edge processor is also used to determine whether the estimated scaling time is less than a time threshold; if it is, it generates a warning message.

2. The anti-scaling closed-loop cooling tower according to claim 1, characterized in that: It also includes a model training module, which is used to acquire a dataset, including historical wind speed data, historical thermal imaging images, the location of scale buildup on the coil corresponding to the historical thermal imaging images, and the scale buildup time. The model training module is also used to build training and test sets based on the dataset; train the AI ​​model based on the training set, evaluate the performance of the AI ​​model based on the test set, and deploy the trained AI model to the edge processor.

3. The anti-scaling closed-loop cooling tower according to claim 2, characterized in that: The coil includes multiple layers of straight pipes and bends connecting the ends of the straight pipes; the location of scaling includes the number of layers and rows of the scaling straight pipes and the distance from the end of the straight pipes.

4. The anti-scaling closed-loop cooling tower according to claim 3, characterized in that: The temperature data includes the temperature value and the position of the corresponding top straight pipe.

5. The anti-scaling closed-loop cooling tower according to claim 4, characterized in that: The straight tube has several annular protrusions evenly arranged along its length.

6. The anti-scaling closed-loop cooling tower according to claim 5, characterized in that: It also includes a blower for blowing air and a spray system for distributing water to the coil; the wind speed sensor is fixed below the blower; the spray system includes a main water supply pipe and several branch water supply pipes connected to the main water supply pipe, the branch water supply pipes are arranged parallel to the length direction of the coil, and several first nozzles are evenly arranged on the branch water supply pipes.

7. The anti-scaling closed-loop cooling tower according to claim 6, characterized in that: The main water supply pipe is also equipped with a first solenoid valve; It also includes a horizontal sliding mechanism and a controller; The horizontal sliding mechanism is located above the coil, and the infrared thermal imager is fixed on the horizontal sliding mechanism; The controller is used to close the first solenoid valve at preset intervals, move the horizontal sliding mechanism to a predetermined position, and control the infrared thermal imager to capture thermal images of the coil. The controller is also used to open the first solenoid valve after the image capture is completed.

8. The anti-scaling closed-loop cooling tower according to claim 7, characterized in that: There are at least two predetermined positions, and the controller is used to control the horizontal sliding mechanism to move sequentially to each of the preset predetermined positions during the first shot.

9. The anti-scaling closed-loop cooling tower according to claim 8, characterized in that: The edge processor is also used to acquire local thermal imaging images captured at predetermined locations and stitch all the local thermal imaging images into a complete thermal imaging image.

Images