Waste heat transmission efficiency detection method based on infrared image

Abstract

The invention relates to the field of waste heat transmission, in particular to a waste heat transmission efficiency detection method based on an infrared image. The method comprises the steps that the environment temperature and the environment humidity of a pipeline at any sampling moment and an infrared image of each wave band are acquired, and the noise degree of each wave band is calculated; for any wave band, obtaining an actual variance and an actual convolution kernel according to the noise degree, and filtering the infrared image by using the actual variance and the actual convolution kernel to obtain a filtered infrared image; and traversing to obtain a filtered infrared image of each wave band, taking the noise degree as a weight, and carrying out weighted summation on the filtered infrared images of the wave bands to obtain a fused infrared image, thereby completing transmission efficiency detection. According to the technical scheme, the precision of the waste heat transmission efficiency detection result can be improved.

Description

Technical Field

[0001] The present invention relates to the field of waste heat transmission, and more specifically, to a waste heat transmission efficiency detection method based on infrared images. Background Art

[0002] Energy consumption issues are increasingly becoming a global concern. In the process of energy utilization, the recovery and utilization of waste heat can not only significantly improve energy efficiency, but also play a vital role in reducing greenhouse gas emissions, reducing production costs, and protecting the environment. Waste heat utilization technology is increasingly used in metallurgy, chemical industry, machinery manufacturing, power generation and other fields, and is one of the key technologies to improve industrial energy efficiency.

[0003] Traditional waste heat detection technologies mostly rely on sensors, thermometers and other equipment, and common methods include temperature measurement and flow monitoring. However, these traditional methods often face large measurement errors or incomplete data in complex industrial environments and high-speed heat transfer processes. Especially in some high-temperature or difficult-to-reach areas, the deployment and monitoring of traditional sensors have great limitations. Infrared imaging technology has gradually become an emerging means of detecting waste heat transfer efficiency due to its advantages of non-contact measurement and real-time monitoring. The infrared thermal imager can obtain the thermal radiation information of the target object, thereby inferring the temperature distribution.

[0004] However, due to the presence of noise interference in different infrared images, simply analyzing images in a certain dimension often cannot fully reflect the actual situation of waste heat transfer, which may lead to distortion of temperature data; noise will not only cause deviations in temperature measurement and affect the accuracy of measurement results, but may also cover up subtle changes in the heat transfer process, resulting in inaccurate detection results of waste heat transfer efficiency. Summary of the invention

[0005] In order to solve the problem of inaccurate detection results of waste heat transfer efficiency, the present invention proposes a waste heat transfer efficiency detection method based on infrared images.

[0006] The invention discloses a waste heat transmission efficiency detection method based on infrared images, comprising: obtaining the ambient temperature, ambient humidity and infrared images of each band of a pipeline at any sampling moment, calculating the noise level of each band, wherein one sampling moment corresponds to a plurality of bands; for any band, obtaining the actual variance and the actual convolution kernel according to the noise level, filtering the infrared image by using the actual variance and the actual convolution kernel to obtain a filtered infrared image; traversing to obtain the filtered infrared image of each band, taking the noise level as a weight, performing weighted summation on the filtered infrared images of each band to obtain a fused infrared image, and completing the transmission efficiency detection.

[0007] By combining the ambient temperature, humidity and noise level of infrared images in each band, the filtering method of each band is intelligently adjusted to optimize the image processing effect. The appropriate filtering parameters are dynamically selected according to the noise characteristics of the band to accurately process the infrared image, reduce noise interference and effectively retain useful information. By weighted fusion of filtered images of different bands, not only can the image quality be improved and the details enhanced, but also the appropriate weight can be given to each band according to the noise level to ensure the clarity and information integrity of the fused image.

[0008] Preferably, the noise level includes: obtaining the central temperature and central humidity of any band in the history; the noise level satisfies the relationship: , Indicates the noise level, and Respectively represent the ambient temperature and ambient humidity at any sampling time, Indicates the core temperature, Indicates the central humidity, Represents a natural constant.

[0009] The image processing strategy can be dynamically adjusted according to the relative changes between the current environmental conditions and the historical environmental conditions to ensure the optimization of the noise suppression effect under different environmental conditions. This method improves the noise adaptability in the infrared image processing process.

[0010] Preferably, the noise level includes: obtaining a credible temperature range and a credible humidity range of any band in history, and obtaining a central temperature and a central humidity; the noise level satisfies the relationship: , Indicates the noise level, and Respectively represent the ambient temperature and ambient humidity at any sampling time, Indicates the core temperature, Indicates the central humidity, Indicates the credible temperature range, Indicates the credible humidity range, Represents a natural constant.

[0011] By introducing a credible temperature range and a credible humidity range, the sensitivity to noise can be flexibly adjusted under different environmental conditions. This effectively improves the adaptability to environmental changes, allowing the impact of noise to be accurately quantified and controlled, thereby reducing unnecessary noise interference during filtering and fusion, and retaining more effective information.

[0012] Preferably, the central temperature and central humidity include: obtaining all historical infrared images of any band in history, adding a label to each historical infrared image, the label is qualified or unqualified; the central point of the ambient temperature of all historical infrared images labeled as qualified is used as the central temperature, and the central point of the ambient humidity of all historical infrared images labeled as qualified is used as the central humidity.

[0013] Preferably, the center temperature and center humidity include: obtaining all historical infrared images of any band in the history, adding a label to each historical infrared image, the label is qualified or unqualified; the mode of the ambient temperatures of all historical infrared images labeled as qualified is used as the center temperature, and the mode of the ambient humidity of all historical infrared images labeled as qualified is used as the center humidity.

[0014] Preferably, the credible temperature range and credible humidity range include: taking the value range of the ambient temperature of all historical infrared images labeled as qualified as the credible temperature range, and taking the value range of the ambient humidity of all historical infrared images labeled as qualified as the credible humidity range.

[0015] Preferably, the obtaining of the actual variance and the actual convolution kernel includes: presetting the filter variance and the filter convolution kernel; taking the product of the noise level of any band and the filter variance as the actual variance, and taking the product of the noise level of any band and the filter convolution kernel as the actual convolution kernel.

[0016] The introduction of noise level allows the filter parameters to be flexibly adjusted according to the current environmental changes, so as to process bands with different noise intensities more reasonably. Specifically, bands with higher noise levels will use smaller actual variance and convolution kernels to reduce the impact of noise on the image, while bands with less noise can use larger parameters to better preserve the details of the image.

[0017] Preferably, the obtaining of the actual variance and the actual convolution kernel includes: presetting the filter variance, taking the product of the noise level of any band and the filter variance as the actual variance; and in response to the actual variance being enlarged by a preset multiple, the size of the actual convolution kernel is enlarged once.

[0018] Preferably, the fused infrared image is obtained to satisfy the relationship: , represents the fused infrared image, Indicates band The noise level, Indicates band The filtered infrared image of Represents a natural constant.

[0019] By introducing an exponential attenuation function of the noise level and assigning different weights to each band, the fused image can more accurately reflect the effective information of each band and suppress unnecessary noise interference. This weighted fusion method effectively improves the quality of the final image, ensures the retention of more important information, and reduces the distortion introduced by noise.

[0020] Preferably, the completion of the transmission efficiency detection includes: performing threshold segmentation on the fused infrared image to obtain the waste heat transfer area, calculating the average pixel value of the waste heat transfer area, obtaining the temperature of the waste heat transfer area based on the mapping relationship between the pixel value in the infrared image and the actual temperature, calculating the actual heat transfer amount based on the temperature of the waste heat transfer area, and taking the ratio of the actual heat transfer amount to the theoretical heat transfer amount as the transmission efficiency to complete the transmission efficiency detection.

[0021] Beneficial effects of the present invention: The present invention can more accurately evaluate the waste heat transmission status in the pipeline by combining the changes in ambient temperature and humidity and image processing technology. The use of infrared image processing technology can effectively extract and analyze the waste heat transmission area. By processing the noise of infrared images, background interference is reduced and irrelevant factors are eliminated, thereby improving the clarity and accuracy of the image. Weighted fusion technology can combine image information from different angles to obtain more comprehensive and accurate temperature distribution data. Threshold segmentation helps to distinguish different temperature areas and accurately capture the waste heat transmission area.

[0022] The present invention can more accurately identify the heat transfer path, thereby providing more accurate heat transfer calculation, optimizing energy utilization efficiency and effectively reducing energy loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a method for detecting waste heat transfer efficiency based on infrared images according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments.

[0025] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0026] Reference Figure 1 The waste heat transfer efficiency detection method based on infrared images includes steps S1 to S3, which are described in detail below.

[0027] S1, obtain the ambient temperature, ambient humidity and infrared image of each band of the pipeline at any sampling time, and calculate the noise level of each band, where one sampling time corresponds to several bands.

[0028] In one embodiment, a temperature sensor and a humidity sensor are installed near the pipeline responsible for waste heat transmission to detect the ambient temperature and humidity in real time and ensure that the collection of the ambient temperature and humidity is synchronous, that is, starts and ends at the same time.

[0029] Install infrared equipment to obtain several infrared images at any sampling time. It should be noted that when collecting infrared images, infrared images of different bands should be collected at the same sampling time, that is, one sampling time corresponds to multiple bands, and each band corresponds to an infrared image. This is because infrared light of different bands shows different collection effects under different environmental conditions. For example, infrared light of the mid-band can obtain higher-quality images in a high-temperature and high-humidity environment, while infrared light of other bands is easily interfered by more noise in such an environment, resulting in poor image quality. Therefore, collecting ambient temperature and humidity data can help judge the quality of infrared images of different bands and provide more accurate environmental background information for subsequent analysis.

[0030] The central temperature and central humidity of any band in history are obtained, including obtaining all historical infrared images of any band in history, and adding a label to each historical infrared image, the label is qualified or unqualified. The label is obtained in the following way: the technicians in this field evaluate the shooting quality of each historical infrared image in combination with the actual situation, and use the evaluation result as a label, the evaluation result includes qualified or unqualified.

[0031] The center point of the ambient temperature of all historical infrared images with qualified labels is taken as the center temperature, and the center point of the ambient humidity of all historical infrared images with qualified labels is taken as the center humidity.

[0032] The noise level satisfies the relationship: , Indicates the noise level, and Respectively represent the ambient temperature and ambient humidity at any sampling time, Indicates the core temperature, Indicates the central humidity, Represents a natural constant.

[0033] It should be explained that at the same sampling moment, the ambient temperature and humidity remain constant, that is, the ambient temperature and humidity corresponding to all bands at that moment are the same. However, infrared images of different bands have different adaptation ranges to ambient temperature and humidity, which are called the credible temperature range and credible humidity range of the band. Each band has an optimal ambient temperature and humidity value in the historical data, which is called the central temperature and central humidity of the band. The central temperature and central humidity of each band are different, and these values ​​vary between different bands.

[0034] In order to evaluate the quality of an infrared image of a band, the difference between the current ambient temperature and the central temperature of the band, as well as the difference between the current ambient humidity and the central humidity of the band can be compared. If the difference between the temperature and humidity of the current environment and the central value of the band is small, it means that the current environmental conditions are suitable for infrared imaging of the band, and the quality and credibility of the infrared image are high. On the contrary, if the difference is large, it may lead to poor image quality and reduced credibility.

[0035] In one embodiment, the noise level includes: The credible temperature range and credible humidity range of any band in the history are obtained. The credible temperature range and credible humidity range include: taking the value range of the ambient temperature of all historical infrared images labeled as qualified as the credible temperature range, and taking the value range of the ambient humidity of all historical infrared images labeled as qualified as the credible humidity range.

[0036] Get the core temperature and core humidity.

[0037] The noise level satisfies the relationship: , Indicates the noise level, and Respectively represent the ambient temperature and ambient humidity at any sampling time, Indicates the core temperature, Indicates the central humidity, Indicates the credible temperature range, Indicates the credible humidity range, Represents a natural constant.

[0038] The further the ambient temperature and humidity at the current sampling time are from the optimal adaptation environment of a certain band, the more likely it is that the infrared image quality of this band will be unstable and the more noise will increase. This is because the infrared image of each band has an optimal response range to specific environmental conditions. If it deviates from this range, the signal-to-noise ratio of the image will decrease, resulting in more obvious noise, which in turn affects the reliability of the infrared image.

[0039] In one embodiment, the center temperature and center humidity include: obtaining all historical infrared images of any band in the history, adding a label to each historical infrared image, the label is qualified or unqualified; the mode of the ambient temperature of all historical infrared images labeled as qualified is used as the center temperature, and the mode of the ambient humidity of all historical infrared images labeled as qualified is used as the center humidity.

[0040] S2, for any band, obtain the actual variance and the actual convolution kernel according to the noise level, and use the actual variance and the actual convolution kernel to filter the infrared image to obtain a filtered infrared image.

[0041] In one embodiment, Gaussian filtering is a commonly used image processing technique, which is mainly used to remove noise and smooth images. In Gaussian filtering, convolution kernel and variance are two key parameters, wherein variance directly affects the calculation of standard deviation, and standard deviation determines the smoothness of Gaussian kernel. Specifically, the larger the standard deviation, the stronger the smoothing effect of Gaussian kernel, and the details of the image will be further blurred or lost. In this way, Gaussian filtering can effectively remove high-frequency noise, but it may also cause loss of details in the image, especially when the image contains important texture or edge information. Therefore, the selection of variance needs to be adjusted according to the actual situation to balance the relationship between noise removal and detail retention. If the variance is set too large, the image will become too blurred and lose too many details; and if the variance is too small, the noise may not be effectively removed, affecting the clarity of the image.

[0042] Preset the filter variance and filter convolution kernel; take the product of the noise level of any band and the filter variance as the actual variance, and take the product of the noise level of any band and the filter convolution kernel as the actual convolution kernel.

[0043] The infrared image of any band is filtered according to the true variance and the true convolution kernel to obtain the filtered infrared image.

[0044] In one embodiment, obtaining the actual variance and the actual convolution kernel includes: The filter variance is preset, and the product of the noise level of any band and the filter variance is taken as the actual variance; in response to the actual variance being enlarged by a preset multiple, the size of the actual convolution kernel is enlarged once.

[0045] For example, the variance can be 1, 2, 3, 4, etc. from small to large, and the size of the convolution kernel is generally 3 times 3, 5 times 5, 7 times 7, etc., so there is a mapping relationship between the variance and the convolution kernel, that is, when the variance is 1, 2, 3, the size of the convolution kernel is 3 times 3, when the variance is 4 to 12, the size of the convolution kernel is 5 times 5, and so on, to obtain the convolution kernel size corresponding to different variances. Therefore, after obtaining the true variance, the true convolution kernel can be obtained.

[0046] S3, traverse to obtain the filtered infrared image of each band, take the noise level as the weight, perform weighted summation on the filtered infrared images of each band to obtain the fused infrared image, and complete the transmission efficiency detection.

[0047] In one embodiment, the fused infrared image is obtained to satisfy the relationship: , represents the fused infrared image, Indicates band The noise level, Indicates band The filtered infrared image of Represents a natural constant.

[0048] Bands with higher noise levels are given smaller weights, while bands with lower noise levels are given larger weights, so that band data with clearer signals and less noise are preferentially retained when fusing images.

[0049] Perform threshold segmentation on the fused infrared image to obtain the waste heat transfer area, calculate the average pixel value of the waste heat transfer area, obtain the temperature of the waste heat transfer area based on the mapping relationship between the pixel value in the infrared image and the actual temperature, calculate the actual heat transfer amount based on the temperature of the waste heat transfer area, and take the ratio of the actual heat transfer to the theoretical heat transfer amount as the transmission efficiency to complete the transmission efficiency detection.

[0050] It should be noted that, for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of this application, which are all within the scope of protection of this application. Therefore, the scope of protection of the patent of this application shall be based on the attached claims.

Claims

1. A method for detecting waste heat transfer efficiency based on infrared images, characterized in that: include: Obtain the ambient temperature, ambient humidity and infrared images of each band of the pipeline at any sampling time, and calculate the noise level of each band, where one sampling time corresponds to several bands; For any band, the actual variance and the actual convolution kernel are obtained according to the noise level, and the infrared image is filtered using the actual variance and the actual convolution kernel to obtain a filtered infrared image; The filtered infrared images of each band are obtained by traversing, and the noise level is used as the weight to perform weighted summation on the filtered infrared images of each band to obtain a fused infrared image to complete the transmission efficiency detection.

2. The method for detecting waste heat transfer efficiency based on infrared images according to claim 1, characterized in that: The noise levels include: Get the central temperature and central humidity of any band in the history; The noise level satisfies the relationship: , Indicates the noise level, and Respectively represent the ambient temperature and ambient humidity at any sampling time, Indicates the core temperature, Indicates the central humidity, Represents a natural constant.

3. The method for detecting waste heat transfer efficiency based on infrared images according to claim 1, characterized in that: The noise levels include: Get the credible temperature range and credible humidity range of any band in the history, and get the central temperature and central humidity; The noise level satisfies the relationship: , Indicates the noise level, and Respectively represent the ambient temperature and ambient humidity at any sampling time, Indicates the core temperature, Indicates the central humidity, Indicates the credible temperature range, Indicates the credible humidity range, Represents a natural constant.

4. The method for detecting waste heat transfer efficiency based on infrared images according to claim 2 or 3, characterized in that: The core temperature and core humidity include: Obtain all historical infrared images of any band in history, and add a label to each historical infrared image, with the label being qualified or unqualified; The center point of the ambient temperature of all historical infrared images with qualified labels is taken as the center temperature, and the center point of the ambient humidity of all historical infrared images with qualified labels is taken as the center humidity.

5. The method for detecting waste heat transfer efficiency based on infrared images according to claim 2 or 3, characterized in that: The core temperature and core humidity include: Obtain all historical infrared images of any band in history, and add a label to each historical infrared image, with the label being qualified or unqualified; The mode of the ambient temperatures of all historical infrared images with qualified labels is taken as the central temperature, and the mode of the ambient humidity of all historical infrared images with qualified labels is taken as the central humidity.

6. The method for detecting waste heat transfer efficiency based on infrared images according to claim 3 is characterized in that: The credible temperature range and credible humidity range include: The value range of the ambient temperature of all historical infrared images with qualified labels is taken as the credible temperature range, and the value range of the ambient humidity of all historical infrared images with qualified labels is taken as the credible humidity range.

7. The method for detecting waste heat transfer efficiency based on infrared images according to claim 1, characterized in that: The obtaining of the actual variance and the actual convolution kernel comprises: Preset filter variance and filter convolution kernel; The product of the noise level in any band and the filter variance is taken as the actual variance, and the product of the noise level in any band and the filter convolution kernel is taken as the actual convolution kernel.

8. The method for detecting waste heat transfer efficiency based on infrared images according to claim 1, characterized in that: The obtaining of the actual variance and the actual convolution kernel comprises: The filter variance is preset, and the product of the noise level in any band and the filter variance is taken as the actual variance; In response to the actual variance being enlarged by a preset multiple, the size of the actual convolution kernel is enlarged once.

9. The method for detecting waste heat transfer efficiency based on infrared images according to claim 1, characterized in that: The obtained fused infrared image satisfies the relationship: , represents the fused infrared image, Indicates band The noise level, Indicates band The filtered infrared image of Represents a natural constant.

10. The method for detecting waste heat transfer efficiency based on infrared images according to claim 1, characterized in that: The transmission efficiency detection includes: Perform threshold segmentation on the fused infrared image to obtain the waste heat transfer area, calculate the average pixel value of the waste heat transfer area, obtain the temperature of the waste heat transfer area based on the mapping relationship between the pixel value in the infrared image and the actual temperature, calculate the actual heat transfer amount based on the temperature of the waste heat transfer area, and take the ratio of the actual heat transfer to the theoretical heat transfer amount as the transmission efficiency to complete the transmission efficiency detection.

Images