A collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device

Abstract

The present invention discloses a collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device, which relates to the technical field of collaborative optimization of thermal management and includes the following steps: collecting thermal management collaborative optimization data including the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data, and preprocessing the collected data; using the generated heat dissipation optimization scheme and fluid flow optimization scheme to respectively construct a heat dissipation optimization model and a fluid flow optimization model; coordinating the output results of the heat dissipation optimization model and the fluid flow optimization model to optimize the thermal management of the high-precision optical fiber pipeline detection device. The present invention constructs a heat dissipation monitoring model and a fluid flow monitoring model through a multiple linear regression algorithm, and then obtains a heat dissipation optimization coefficient and a fluid flow optimization coefficient, solving the problem that it is difficult to monitor the temperature of the optical fiber pipeline detection device from multiple angles in the prior art, which in turn affects the collaborative optimization effect of its thermal management system.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal management collaborative optimization, and particularly relates to a collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device. Background Art

[0002] With the rapid development of technology, high-precision optical fiber pipeline detection devices are widely used in fields such as oil, natural gas, and electricity. They can accurately detect the status of optical fiber pipelines, timely discover potential faults, and ensure the safe operation of the pipelines. However, during the operation of high-precision optical fiber pipeline detection devices, due to the continuous operation of internal electronic components and the light emission and heat generation of light sources, a large amount of heat will be generated. If these heats cannot be effectively managed, the excessive temperature will seriously affect the optical performance of the optical fibers in the high-precision optical fiber pipeline detection device, resulting in the attenuation and distortion of detection signals, reducing the detection accuracy. At the same time, high temperature will also accelerate the aging of electronic components, shorten their service life, increase the maintenance cost and failure risk of the device. Existing thermal management systems often only design for a single heat dissipation method and do not fully consider the synergistic effect of each heat dissipation link. For example, relying solely on air cooling is difficult to meet the heat dissipation requirements under high-power operation; or only using liquid cooling, but due to unreasonable layout, it cannot fully cover heat-sensitive areas. Therefore, it is extremely urgent to develop a collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device, aiming to comprehensively use various heat dissipation means to improve the overall efficiency of the thermal management system to ensure the stable and efficient operation of the high-precision optical fiber pipeline detection device;

[0003] Although there have been great progress in the direction of thermal management in the existing technology, there are still some problems to be optimized. It is difficult for the existing technology to monitor the temperature of the optical fiber pipeline detection device from multiple angles, which in turn affects the collaborative optimization effect of its thermal management system. Therefore, how to optimize the thermal monitoring process and further promote the collaborative optimization of heat dissipation and fluid, and strengthen the thermal management of the high-precision optical fiber pipeline detection device is the problem we need to solve. Summary of the Invention

[0004] To achieve the above object, the present invention is realized through the following technical solutions: A collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device includes the following steps:

[0005] Step 1: Collect thermal management collaborative optimization data including the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data, and preprocess the collected data to provide data support for the implementation of subsequent steps;

[0006] Step 2: Monitor the temperature of the optical fiber pipeline detection device through the preprocessed temperature data of the optical fiber pipeline detection device and the environmental data, and then obtain the heat generation coefficient, providing data preparation for constructing a heat dissipation monitoring model;

[0007] Step 3: Using the preprocessed cooling medium data, calculate the corrosion degree of the cooling medium, and combine the heat generation coefficient with the preprocessed cooling medium data to construct a heat dissipation monitoring model;

[0008] Step 4: Through the preprocessed environmental data, combined with the multiple linear regression algorithm, construct a fluid flow monitoring model;

[0009] Step 5: Based on the output results of the heat dissipation monitoring model and the fluid flow monitoring model, generate a heat dissipation optimization plan and a fluid flow optimization plan respectively;

[0010] Step 6: Using the generated heat dissipation optimization plan and fluid flow optimization plan, construct a heat dissipation optimization model and a fluid flow optimization model respectively;

[0011] Step 7: Collaborate the output results of the heat dissipation optimization model and the fluid flow optimization model to optimize the thermal management of the high-precision optical fiber pipeline detection device, solving the problem that it is difficult to monitor the temperature of the optical fiber pipeline detection device from multiple angles in the prior art, which in turn affects the collaborative optimization effect of its thermal management system.

[0012] A further improvement of the technical solution of the present invention lies in: in the above Step 1, the process of collecting the thermal management collaborative optimization data includes:

[0013] Collect the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data through the thermal management unit of the high-precision optical fiber pipeline detection device. Among them, different types of collection devices are deployed in the thermal management unit, and these collection devices include temperature sensors, pressure sensors, vortex flow meters, thermal conductivity testers, pH meters, ion chromatographs, anemometers, and pitot tubes;

[0014] The temperature data of the optical fiber pipeline detection device includes the temperatures of the heating components and the radiator in the optical fiber pipeline detection device; the cooling medium data includes the temperature, pressure, flow rate, thermal conductivity, pH value, and chloride ion content of the cooling medium; the environmental data includes the ambient temperature where the optical fiber pipeline detection device is located, as well as the wind speed and pressure in the air duct;

[0015] Perform data cleaning and data standardization processing on the collected thermal management collaborative optimization data, set the timestamps of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data respectively, and adjust the timestamps of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data to achieve the synchronization of the collection times of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data;

[0016] Integrate the cooling medium data and environmental data to generate a thermal management collaborative optimization dataset, and divide the thermal management collaborative optimization dataset into a training set and a test set, and the ratio of the training set to the test set is 7:3.

[0017] A further improvement of the technical solution of the present invention lies in: in the second step, the process of obtaining the heat generation coefficient includes:

[0018] Calculate the temperature difference between the heat generating component and the radiator, the temperature difference between the heat generating component and the environment where the optical fiber pipeline detection device is located, and the temperature difference between the radiator and the environment where the optical fiber pipeline detection device is located;

[0019] Assign weights to the temperature difference between the heat generating component and the radiator, the temperature difference between the heat generating component and the environment where the optical fiber pipeline detection device is located, and the temperature difference between the radiator and the environment where the optical fiber pipeline detection device is located, respectively;

[0020] Combined with the weighted summation method, obtain the heat generation coefficient, and integrate the heat generation coefficient into the thermal management collaborative optimization dataset, wherein the process of obtaining the heat generation coefficient includes:

[0021]

[0022] Wherein, F is the heat generation coefficient; , and are the weights of the temperature difference between the heat generating component and the radiator, the temperature difference between the heat generating component and the environment where the optical fiber pipeline detection device is located, and the temperature difference between the radiator and the environment where the optical fiber pipeline detection device is located, respectively; , and are the temperature difference between the heat generating component and the radiator, the temperature difference between the heat generating component and the environment where the optical fiber pipeline detection device is located, and the temperature difference between the radiator and the environment where the optical fiber pipeline detection device is located, respectively.

[0023] A further improvement of the technical solution of the present invention lies in: in the third step, the calculation process of the corrosion degree of the cooling medium includes:

[0024] According to the pH value of the cooling medium, assign a corresponding pH value corrosion degree coefficient. When the pH value of the cooling medium is less than 7, the assigned pH value corrosion degree coefficient is equal to ; when the pH value of the cooling medium is equal to 7, the assigned pH value corrosion degree coefficient is equal to ; when the pH value of the cooling medium is greater than 7, the assigned pH value corrosion degree coefficient is equal to ;

[0025] Use the chloride ion content of the cooling medium to calculate the chloride ion content corrosion degree coefficient, and its calculation process is as follows:

[0026]

[0027] Among them, is the corrosion degree coefficient of chloride ion content, is the chloride ion content of the cooling medium;

[0028] The corrosion degree of the cooling medium is calculated by multiplying the corrosion degree coefficient of pH value and the corrosion degree coefficient of chloride ion content, and the corrosion degree of the cooling medium is integrated into the heat management collaborative optimization dataset.

[0029] A further improvement of the technical solution of the present invention lies in that: in the step three, the construction process of the heat dissipation monitoring model includes:

[0030] Extract the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient from the heat management collaborative optimization dataset;

[0031] Using the training set data, combined with the multiple linear regression algorithm, taking the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient as inputs and the heat dissipation optimization coefficient as the output, learn the linear relationship between the cooling medium data, the corrosion degree of the cooling medium, the heat generation coefficient, and the heat dissipation optimization coefficient, and train the heat dissipation monitoring model;

[0032] Input the test set data into the heat dissipation monitoring model, adjust the intercept term and regression coefficient of the heat dissipation monitoring model, optimize the performance of the heat dissipation monitoring model, obtain the final heat dissipation monitoring model, combine the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient, output the corresponding heat dissipation optimization coefficient, and integrate the heat dissipation optimization coefficient into the heat management collaborative optimization dataset;

[0033] The expression of this heat dissipation monitoring model is as follows:

[0034]

[0035] Among them, is the heat dissipation optimization coefficient; , , , , and are the regression coefficients of the temperature, pressure, flow rate, thermal conductivity, corrosion degree, and heat generation coefficient of the cooling medium respectively; , , , , and are the temperature, pressure, flow rate, thermal conductivity, corrosion degree, and heat generation coefficient of the cooling medium respectively.

[0036] A further improvement of the technical solution of the present invention lies in that: in the step four, the construction process of the fluid flow monitoring model includes:

[0037] Extract the environmental data from the heat management collaborative optimization dataset. Combine the training set data with the multiple linear regression algorithm. Use the environmental data as the input and the fluid flow optimization coefficient as the output to learn the linear relationship between the environmental data and the fluid flow optimization coefficient, and train the fluid flow monitoring model;

[0038] Input the test set data into the fluid flow monitoring model, adjust the intercept term and regression coefficients of the fluid flow monitoring model, optimize the performance of the fluid flow monitoring model, obtain the final fluid flow monitoring model, combine the environmental data, output the corresponding fluid flow optimization coefficient, and integrate the fluid flow optimization coefficient into the heat management collaborative optimization dataset;

[0039] The expression of the fluid flow monitoring model is:

[0040]

[0041] Where L is the fluid flow optimization coefficient, , and are the regression coefficients of the environmental temperature, the wind speed in the air duct, and the pressure in the air duct where the optical fiber pipeline detection device is located respectively, , and are the environmental temperature, the wind speed in the air duct, and the pressure in the air duct where the optical fiber pipeline detection device is located respectively, and are the intercept term and error term of the fluid flow monitoring model.

[0042] A further improvement of the technical solution of the present invention is that in the fifth step, the generation process of the heat dissipation optimization scheme and the fluid flow optimization scheme includes:

[0043] According to the heat dissipation optimization coefficient, divide the heat dissipation performance into high heat dissipation performance, medium heat dissipation performance, and low heat dissipation performance. When the heat dissipation optimization coefficient is in the range of 0 to 0.4, the heat management system of the optical fiber pipeline detection device corresponds to high heat dissipation performance; when the heat dissipation optimization coefficient is in the range of 0.4 to 0.6, the heat management system of the optical fiber pipeline detection device corresponds to medium heat dissipation performance; when the heat dissipation optimization coefficient is greater than 0.6, the heat management system of the optical fiber pipeline detection device corresponds to low heat dissipation performance;

[0044] Allocate heat dissipation optimization schemes for high heat dissipation performance, medium heat dissipation performance, and low heat dissipation performance respectively, number the heat dissipation optimization schemes, and integrate the heat dissipation optimization scheme numbers into the heat management collaborative optimization dataset;

[0045] Specifically, when the thermal management system of the optical fiber pipeline detection device has high heat dissipation performance, the heat sink is polished to reduce its surface roughness, and flow guide fins are added to the edge of the heat sink, and the properties of the cooling medium are monitored and maintained regularly; when the thermal management system of the optical fiber pipeline detection device has medium heat dissipation performance, the quantity and spacing of the heat sinks are adjusted, the cooling medium is improved, an intelligent flow controller is installed, and the rotation speed of the cooling pump is adjusted according to the internal temperature change of the high-precision optical fiber pipeline detection device to increase the flow rate of the cooling medium and strengthen the temperature monitoring of the high-precision optical fiber pipeline detection device and its environment; when the thermal management system of the optical fiber pipeline detection device has low heat dissipation performance, the heat sink is completely replaced, the internal heat pipe layout of the high-precision optical fiber pipeline detection device is re-planned, a high-performance cooling medium is switched, a liquid cooling plate is added, etc., so as to generate corresponding heat dissipation optimization schemes for different heat dissipation optimization coefficients;

[0046] According to the fluid flow optimization coefficient, the fluid flow performance is divided into high fluid flow performance, medium fluid flow performance and low fluid flow performance. When the fluid flow optimization coefficient is between 0 and 0.3, the thermal management system of the optical fiber pipeline detection device corresponds to high fluid flow performance; when the fluid flow optimization coefficient is between 0.3 and 0.7, the thermal management system of the optical fiber pipeline detection device corresponds to medium fluid flow performance; when the fluid flow optimization coefficient is greater than 0.7, the thermal management system of the optical fiber pipeline detection device corresponds to low fluid flow performance;

[0047] Fluid flow optimization schemes are respectively assigned to high fluid flow performance, medium fluid flow performance and low fluid flow performance, the fluid flow optimization schemes are numbered, and the fluid flow optimization scheme numbers are integrated into the thermal management collaborative optimization dataset.

[0048] Specifically, when the thermal management system of the optical fiber pipeline detection device has high fluid flow performance, the support and fixing devices of the pipeline are checked, the pipeline is smoothed, and the fan is maintained according to a strict maintenance cycle; when the thermal management system of the optical fiber pipeline detection device has medium fluid flow performance, the pipeline is locally cleaned and repaired, the pipeline connection parts are checked and improved, the blade angle of the fan is finely adjusted according to the actual flow rate and pressure, and high-precision flow sensors and pressure sensors are installed to monitor the flow rate and pressure of the fluid in real time; when the thermal management system of the optical fiber pipeline detection device has high fluid flow performance, the pipeline material and specifications are replaced, the pipeline routing is re-planned, and a higher-performance fan is used for operation, so as to generate corresponding fluid flow optimization schemes for different fluid flow optimization coefficients.

[0049] A further improvement of the technical solution of the present invention lies in that: in the fifth step, the construction process of the heat dissipation optimization model includes:

[0050] Extract the heat dissipation optimization coefficient and the heat dissipation optimization scheme number from the thermal management collaborative optimization dataset;

[0051] Using the training set data and combining with the neural network algorithm, taking the heat dissipation optimization coefficient as the input and the heat dissipation optimization plan number as the output, learning the non-linear relationship between the heat dissipation optimization coefficient and the heat dissipation optimization plan number, and training the heat dissipation optimization model;

[0052] Input the test set data into the heat dissipation optimization model, compare the output result of the heat dissipation optimization model with the actual heat dissipation optimization plan number, adjust the parameters of the heat dissipation optimization model, optimize the performance of the heat dissipation optimization model, obtain the final heat dissipation optimization model, and combine with the heat dissipation optimization coefficient to output the corresponding heat dissipation optimization plan number.

[0053] A further improvement of the technical solution of the present invention lies in: in step six, the construction process of the fluid flow optimization model includes:

[0054] Extract the fluid flow optimization coefficient and the fluid flow optimization plan number from the thermal management collaborative optimization dataset;

[0055] Combining the training set data with the convolutional neural network algorithm, taking the fluid flow optimization coefficient as the input and the fluid flow optimization plan number as the output, learning the non-linear relationship between the fluid flow optimization coefficient and the fluid flow optimization plan number, and training the fluid flow optimization model;

[0056] Input the test set data into the fluid flow optimization model, compare the fluid flow optimization model with the actual fluid flow optimization plan number, adjust the parameters of the fluid flow optimization model, optimize the fluid flow optimization model, obtain the final fluid flow optimization model, and combine with the fluid flow optimization coefficient to output the corresponding fluid flow optimization plan number.

[0057] A further improvement of the technical solution of the present invention lies in: in step seven, the process of optimizing the thermal management of the high-precision optical fiber pipeline detection device includes:

[0058] According to the heat dissipation optimization plan number output by the heat dissipation optimization model, match the corresponding heat dissipation optimization plan;

[0059] According to the fluid flow optimization plan number output by the fluid flow optimization model, match the corresponding fluid flow optimization plan;

[0060] Collaboratively execute the heat dissipation optimization plan and the fluid flow optimization plan to optimize the thermal management of the high-precision optical fiber pipeline detection device.

[0061] The beneficial effects of the present invention are as follows: In a method for collaborative optimization of a thermal management system of a high-precision optical fiber pipeline detection device in the present invention, compared with the method for collaborative optimization of a thermal management system of a traditional high-precision optical fiber pipeline detection device, the data acquisition technology, temperature monitoring technology, heat dissipation and fluid collaborative optimization technology, and machine learning algorithms in the method of the present invention are closely combined with modern information technology to accurately capture the temperature data, cooling medium data, and environmental data of the optical fiber pipeline detection device, and then obtain the heat generation coefficient and the corrosion degree of the cooling medium. Through the multiple linear regression algorithm, a heat dissipation monitoring model and a fluid flow monitoring model are constructed, and then the heat dissipation optimization coefficient and the fluid flow optimization coefficient are obtained, achieving the evaluation of the heat dissipation and fluid flow performance, solving the problem that it is difficult to monitor the temperature of the optical fiber pipeline detection device from multiple angles in the prior art, which in turn affects the collaborative optimization effect of its thermal management system, ensuring that the method in the present invention can refine the dynamic monitoring standard of a method for collaborative optimization of a thermal management system of a high-precision optical fiber pipeline detection device within a more accurate range, making the monitored data a more accurate indicator under the same conditions. The research and application of this method significantly enhance the degree of intelligence in the collaborative optimization process of the thermal management system of the high-precision optical fiber pipeline detection device. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0063] Figure 1 It is a flowchart of a method for collaborative optimization of a thermal management system of a high-precision optical fiber pipeline detection device according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0065] As Figure 1 shown, the present invention provides a method for collaborative optimization of a thermal management system of a high-precision optical fiber pipeline detection device, which consists of the following steps:

[0066] Step 1: Collect the thermal management collaborative optimization data including the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data, and preprocess the collected data to provide data support for the implementation of the subsequent steps;

[0067] Step 2: Monitor the temperature of the optical fiber pipeline detection device through the preprocessed temperature data of the optical fiber pipeline detection device and the environmental data, and then obtain the heat generation coefficient, providing data preparation for constructing the heat dissipation monitoring model;

[0068] Step 3: Use the preprocessed cooling medium data to calculate the corrosion degree of the cooling medium, and combine the heat generation coefficient with the preprocessed cooling medium data to construct the heat dissipation monitoring model;

[0069] Step 4: Through the preprocessed environmental data, combined with the multiple linear regression algorithm, construct the fluid flow monitoring model;

[0070] Step 5: Based on the output results of the heat dissipation monitoring model and the fluid flow monitoring model, generate the heat dissipation optimization plan and the fluid flow optimization plan respectively;

[0071] Step 6: Use the generated heat dissipation optimization plan and fluid flow optimization plan to construct the heat dissipation optimization model and the fluid flow optimization model respectively;

[0072] Step 7: Collaborate the output results of the heat dissipation optimization model and the fluid flow optimization model to optimize the thermal management of the high-precision optical fiber pipeline detection device, solving the problem that it is difficult to monitor the temperature of the optical fiber pipeline detection device from multiple angles in the prior art, which in turn affects the collaborative optimization effect of its thermal management system.

[0073] In Step 1, the process of collecting the thermal management collaborative optimization data includes:

[0074] Collect the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data through the thermal management unit of the high-precision optical fiber pipeline detection device. Among them, different types of collection devices are deployed in the thermal management unit, and these collection devices include temperature sensors, pressure sensors, vortex flow meters, thermal conductivity testers, pH meters, ion chromatographs, anemometers, and pitot tubes;

[0075] The temperature data of the optical fiber pipeline detection device includes the temperatures of the heat-generating components and the radiator in the optical fiber pipeline detection device; the cooling medium data includes the temperature, pressure, flow rate, thermal conductivity, pH value, and chloride ion content of the cooling medium; the environmental data includes the ambient temperature where the optical fiber pipeline detection device is located and the wind speed and pressure in the air duct;

[0076] Clean and standardize the collected data for collaborative optimization of thermal management. Set the timestamps for the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data respectively. Adjust the timestamps of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data to synchronize the acquisition times of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data;

[0077] Integrate the cooling medium data and the environmental data to generate a dataset for collaborative optimization of thermal management, and divide the dataset for collaborative optimization of thermal management into a training set and a test set. The ratio of the training set to the test set is 7:3.

[0078] In step two, the process of obtaining the heat generation coefficient includes:

[0079] Calculate the temperature differences between the heat-generating component and the radiator, between the heat-generating component and the environment where the optical fiber pipeline detection device is located, and between the radiator and the environment where the optical fiber pipeline detection device is located;

[0080] Assign weights to the temperature differences between the heat-generating component and the radiator, between the heat-generating component and the environment where the optical fiber pipeline detection device is located, and between the radiator and the environment where the optical fiber pipeline detection device is located respectively;

[0081] Using the weighted summation method, obtain the heat generation coefficient and integrate the heat generation coefficient into the dataset for collaborative optimization of thermal management. Among them, the process of obtaining the heat generation coefficient includes:

[0082]

[0083] Among them, F is the heat generation coefficient; , and are the weights of the temperature differences between the heat-generating component and the radiator, between the heat-generating component and the environment where the optical fiber pipeline detection device is located, and between the radiator and the environment where the optical fiber pipeline detection device is located respectively; , and are the temperature differences between the heat-generating component and the radiator, between the heat-generating component and the environment where the optical fiber pipeline detection device is located, and between the radiator and the environment where the optical fiber pipeline detection device is located respectively.

[0084] In step three, the calculation process of the corrosion degree of the cooling medium includes:

[0085] According to the pH value of the cooling medium, assign the corresponding pH value corrosion degree coefficient. When the pH value of the cooling medium is less than 7, the assigned pH value corrosion degree coefficient is equal to ; when the pH value of the cooling medium is equal to 7, the assigned pH value corrosion degree coefficient is equal to ; when the pH value of the cooling medium is greater than 7, the assigned pH corrosion coefficient is equal to ;

[0086] Calculate the chloride ion content corrosion coefficient using the chloride ion content of the cooling medium. The calculation process is as follows:

[0087]

[0088] Where, is the chloride ion content corrosion coefficient, is the chloride ion content of the cooling medium;

[0089] Calculate the corrosion degree of the cooling medium by multiplying the pH corrosion coefficient and the chloride ion content corrosion coefficient, and integrate the corrosion degree of the cooling medium into the thermal management collaborative optimization dataset.

[0090] In step three, the construction process of the heat dissipation monitoring model includes:

[0091] Extract the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient from the thermal management collaborative optimization dataset;

[0092] Using the training set data, combined with the multiple linear regression algorithm, take the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient as inputs, and the heat dissipation optimization coefficient as the output, learn the linear relationship between the cooling medium data, the corrosion degree of the cooling medium, the heat generation coefficient, and the heat dissipation optimization coefficient, and train the heat dissipation monitoring model;

[0093] Input the test set data into the heat dissipation monitoring model, adjust the intercept term and regression coefficients of the heat dissipation monitoring model, optimize the performance of the heat dissipation monitoring model, obtain the final heat dissipation monitoring model, combine the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient, output the corresponding heat dissipation optimization coefficient, and integrate the heat dissipation optimization coefficient into the thermal management collaborative optimization dataset;

[0094] The expression of this heat dissipation monitoring model is as follows:

[0095]

[0096] Where, is the heat dissipation optimization coefficient; , , , , and are the regression coefficients of the temperature, pressure, flow rate, thermal conductivity, corrosion degree, and heat generation coefficient of the cooling medium respectively; , , , , and are respectively the temperature, pressure, flow rate, thermal conductivity, corrosion degree of the cooling medium, and the heat generation coefficient.

[0097] In step four, the construction process of the fluid flow monitoring model includes:

[0098] Extract the environmental data from the thermal management collaborative optimization dataset, combine the training set data with the multiple linear regression algorithm, use the environmental data as the input, and the fluid flow optimization coefficient as the output, learn the linear relationship between the environmental data and the fluid flow optimization coefficient, and train the fluid flow monitoring model;

[0099] Input the test set data into the fluid flow monitoring model, adjust the intercept term and regression coefficient of the fluid flow monitoring model, optimize the performance of the fluid flow monitoring model, obtain the final fluid flow monitoring model, combine the environmental data, output the corresponding fluid flow optimization coefficient, and integrate the fluid flow optimization coefficient into the thermal management collaborative optimization dataset;

[0100] The expression of this fluid flow monitoring model is:

[0101]

[0102] where L is the fluid flow optimization coefficient, , and are respectively the regression coefficients of the environmental temperature where the optical fiber pipeline detection device is located, the wind speed in the air duct, and the pressure in the air duct, , and are respectively the environmental temperature where the optical fiber pipeline detection device is located, the wind speed in the air duct, and the pressure in the air duct, and are the intercept term and error term of the fluid flow monitoring model.

[0103] In step five, the generation process of the heat dissipation optimization plan and the fluid flow optimization plan includes:

[0104] According to the heat dissipation optimization coefficient, divide the heat dissipation performance into high heat dissipation performance, medium heat dissipation performance, and low heat dissipation performance. When the heat dissipation optimization coefficient is between 0 and 0.4, the thermal management system of the optical fiber pipeline detection device corresponds to high heat dissipation performance; when the heat dissipation optimization coefficient is between 0.4 and 0.6, the thermal management system of the optical fiber pipeline detection device corresponds to medium heat dissipation performance; when the heat dissipation optimization coefficient is greater than 0.6, the thermal management system of the optical fiber pipeline detection device corresponds to low heat dissipation performance;

[0105] Allocate heat dissipation optimization plans for high heat dissipation performance, medium heat dissipation performance, and low heat dissipation performance respectively, number the heat dissipation optimization plans, and integrate the heat dissipation optimization plan numbers into the thermal management collaborative optimization dataset;

[0106] Specifically, when the thermal management system of the optical fiber pipeline detection device has high heat dissipation performance, the heat sink is polished to reduce its surface roughness, and flow guide fins are added to the edge of the heat sink, and the properties of the cooling medium are monitored and maintained regularly; when the thermal management system of the optical fiber pipeline detection device has medium heat dissipation performance, the quantity and spacing of the heat sinks are adjusted, the cooling medium is improved, an intelligent flow controller is installed, and the rotation speed of the cooling pump is adjusted according to the internal temperature change of the high-precision optical fiber pipeline detection device to increase the flow rate of the cooling medium and strengthen the temperature monitoring of the high-precision optical fiber pipeline detection device and its environment; when the thermal management system of the optical fiber pipeline detection device has low heat dissipation performance, the heat sink is completely replaced, the internal heat pipe layout of the high-precision optical fiber pipeline detection device is re-planned, a high-performance cooling medium is switched, and a liquid cooling plate is added, etc., so as to generate corresponding heat dissipation optimization schemes for different heat dissipation optimization coefficients;

[0107] According to the fluid flow optimization coefficient, the fluid flow performance is divided into high fluid flow performance, medium fluid flow performance and low fluid flow performance. When the fluid flow optimization coefficient is between 0 and 0.3, the thermal management system of the optical fiber pipeline detection device corresponds to high fluid flow performance; when the fluid flow optimization coefficient is between 0.3 and 0.7, the thermal management system of the optical fiber pipeline detection device corresponds to medium fluid flow performance; when the fluid flow optimization coefficient is greater than 0.7, the thermal management system of the optical fiber pipeline detection device corresponds to low fluid flow performance;

[0108] Fluid flow optimization schemes are respectively assigned to high fluid flow performance, medium fluid flow performance and low fluid flow performance, the fluid flow optimization schemes are numbered, and the fluid flow optimization scheme numbers are integrated into the thermal management collaborative optimization dataset.

[0109] Specifically, when the thermal management system of the optical fiber pipeline detection device has high fluid flow performance, the support and fixing devices of the pipeline are checked, the pipeline is smoothed, and the fan is maintained according to a strict maintenance cycle; when the thermal management system of the optical fiber pipeline detection device has medium fluid flow performance, the pipeline is locally cleaned and repaired, the pipeline connection parts are checked and improved, the blade angle of the fan is finely adjusted according to the actual flow rate and pressure, and high-precision flow sensors and pressure sensors are installed to monitor the flow rate and pressure of the fluid in real time; when the thermal management system of the optical fiber pipeline detection device has high fluid flow performance, the pipeline material and specification are replaced, the pipeline layout is re-planned, and a higher-performance fan is used for operation, so as to generate corresponding fluid flow optimization schemes for different fluid flow optimization coefficients.

[0110] In step five, the construction process of the heat dissipation optimization model includes:

[0111] Extract the heat dissipation optimization coefficient and the heat dissipation optimization scheme number from the thermal management collaborative optimization dataset;

[0112] Using the training set data and combining with the neural network algorithm, taking the heat dissipation optimization coefficient as the input and the heat dissipation optimization plan number as the output, learning the non-linear relationship between the heat dissipation optimization coefficient and the heat dissipation optimization plan number, and training the heat dissipation optimization model;

[0113] Input the test set data into the heat dissipation optimization model, compare the output result of the heat dissipation optimization model with the actual heat dissipation optimization plan number, adjust the parameters of the heat dissipation optimization model, optimize the performance of the heat dissipation optimization model, obtain the final heat dissipation optimization model, and combine with the heat dissipation optimization coefficient to output the corresponding heat dissipation optimization plan number.

[0114] In step six, the construction process of the fluid flow optimization model includes:

[0115] Extract the fluid flow optimization coefficient and the fluid flow optimization plan number from the thermal management collaborative optimization dataset;

[0116] Combining the training set data with the convolutional neural network algorithm, taking the fluid flow optimization coefficient as the input and the fluid flow optimization plan number as the output, learning the non-linear relationship between the fluid flow optimization coefficient and the fluid flow optimization plan number, and training the fluid flow optimization model;

[0117] Input the test set data into the fluid flow optimization model, compare the fluid flow optimization model with the actual fluid flow optimization plan number, adjust the parameters of the fluid flow optimization model, optimize the fluid flow optimization model, obtain the final fluid flow optimization model, and combine with the fluid flow optimization coefficient to output the corresponding fluid flow optimization plan number.

[0118] In step seven, the process of optimizing the thermal management of the high-precision optical fiber pipeline detection device includes:

[0119] According to the heat dissipation optimization plan number output by the heat dissipation optimization model, match the corresponding heat dissipation optimization plan;

[0120] According to the fluid flow optimization plan number output by the fluid flow optimization model, match the corresponding fluid flow optimization plan;

[0121] Collaboratively execute the heat dissipation optimization plan and the fluid flow optimization plan to optimize the thermal management of the high-precision optical fiber pipeline detection device.

[0122] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device, characterized in that: It includes the following steps: Step 1: Collect the thermal management collaborative optimization data including the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data, and preprocess the collected data; Step 2: Monitor the temperature of the optical fiber pipeline detection device through the preprocessed temperature data of the optical fiber pipeline detection device and the environmental data, and then obtain the heat generation coefficient; Step 3: Use the preprocessed cooling medium data to calculate the corrosion degree of the cooling medium, and combine the heat generation coefficient with the preprocessed cooling medium data to construct a heat dissipation monitoring model; Step 4: Through the preprocessed environmental data, combine with the multiple linear regression algorithm to construct a fluid flow monitoring model; Step 5: Based on the output results of the heat dissipation monitoring model and the fluid flow monitoring model, generate a heat dissipation optimization plan and a fluid flow optimization plan respectively; Step 6: Use the generated heat dissipation optimization plan and fluid flow optimization plan to construct a heat dissipation optimization model and a fluid flow optimization model respectively; Step 7: Collaborate the output results of the heat dissipation optimization model and the fluid flow optimization model to optimize the thermal management of the high-precision optical fiber pipeline detection device.

2. The collaborative optimization method of the thermal management system of a high-precision optical fiber pipeline detection device according to claim 1, characterized in that: In the said Step 1, the collection process of the thermal management collaborative optimization data includes: Collect the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data through the thermal management unit of the high-precision optical fiber pipeline detection device; The temperature data of the optical fiber pipeline detection device includes the temperatures of the heating components and the radiator in the optical fiber pipeline detection device; the cooling medium data includes the temperature, pressure, flow rate, thermal conductivity, pH value, and chloride ion content of the cooling medium; the environmental data includes the ambient temperature where the optical fiber pipeline detection device is located and the wind speed and pressure in the air duct; Perform data cleaning and data standardization processing on the collected thermal management collaborative optimization data, set the timestamps of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data respectively, and adjust the timestamps of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data to achieve the synchronization of the collection times of the temperature data of the optical fiber pipeline detection device, the cooling medium data, and the environmental data; Integrate the cooling medium data and the environmental data to generate a thermal management collaborative optimization data set, and divide the thermal management collaborative optimization data set into a training set and a test set.

3. The collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device according to claim 2, wherein: In the said Step 2, the process of obtaining the heat generation coefficient includes: Calculate the temperature difference between the heating component and the radiator, the temperature difference between the heating component and the environment where the optical fiber pipeline detection device is located, and the temperature difference between the radiator and the environment where the optical fiber pipeline detection device is located; Assign weights to the temperature difference between the heating component and the radiator, the temperature difference between the heating component and the environment where the optical fiber pipeline detection device is located, and the temperature difference between the radiator and the environment where the optical fiber pipeline detection device is located respectively; Combine the weighted summation method to obtain the heat generation coefficient, and integrate the heat generation coefficient into the thermal management collaborative optimization data set.

4. The collaborative optimization method of the thermal management system of a high-precision optical fiber pipeline detection device according to claim 3, wherein: In the said Step 3, the calculation process of the corrosion degree of the cooling medium includes: According to the pH value of the cooling medium, assign the corresponding pH corrosion coefficient. When the pH value of the cooling medium is less than 7, the assigned pH corrosion coefficient is equal to ; when the pH value of the cooling medium is equal to 7, the assigned pH corrosion coefficient is equal to ; when the pH value of the cooling medium is greater than 7, the assigned pH corrosion coefficient is equal to ; Calculate the chloride ion content corrosion degree coefficient using the chloride ion content of the cooling medium. Then, obtain the corrosion degree of the cooling medium by multiplying the pH value corrosion degree coefficient by the chloride ion content corrosion degree coefficient, and integrate the corrosion degree of the cooling medium into the thermal management collaborative optimization dataset.

5. The collaborative optimization method of the thermal management system of a high-precision optical fiber pipeline detection device according to claim 4, wherein: In step three, the construction process of the heat dissipation monitoring model includes: Extract the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient from the thermal management collaborative optimization dataset; Using the training set data and combining with the multiple linear regression algorithm, take the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient as inputs, and the heat dissipation optimization coefficient as the output, learn the linear relationship between the cooling medium data, the corrosion degree of the cooling medium, the heat generation coefficient, and the heat dissipation optimization coefficient, and train the heat dissipation monitoring model; Input the test set data into the heat dissipation monitoring model, adjust the intercept term and regression coefficient of the heat dissipation monitoring model, optimize the performance of the heat dissipation monitoring model, obtain the final heat dissipation monitoring model, combine the cooling medium data, the corrosion degree of the cooling medium, and the heat generation coefficient, output the corresponding heat dissipation optimization coefficient, and integrate the heat dissipation optimization coefficient into the thermal management collaborative optimization dataset.

6. The collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device according to claim 5, characterized in that: In step four, the construction process of the fluid flow monitoring model includes: Extract the environmental data from the thermal management collaborative optimization dataset, combine the training set data with the multiple linear regression algorithm, take the environmental data as the input, and the fluid flow optimization coefficient as the output, learn the linear relationship between the environmental data and the fluid flow optimization coefficient, and train the fluid flow monitoring model; Input the test set data into the fluid flow monitoring model, adjust the intercept term and regression coefficient of the fluid flow monitoring model, optimize the performance of the fluid flow monitoring model, obtain the final fluid flow monitoring model, combine the environmental data, output the corresponding fluid flow optimization coefficient, and integrate the fluid flow optimization coefficient into the thermal management collaborative optimization dataset.

7. The collaborative optimization method for the thermal management system of a high-precision optical fiber pipeline detection device according to claim 6, characterized in that: In step five, the generation process of the heat dissipation optimization plan and the fluid flow optimization plan includes: According to the heat dissipation optimization coefficient, divide the heat dissipation performance into high heat dissipation performance, medium heat dissipation performance, and low heat dissipation performance. When the heat dissipation optimization coefficient is between 0 and 0.4, the thermal management system of the optical fiber pipeline detection device corresponds to high heat dissipation performance; when the heat dissipation optimization coefficient is between 0.4 and 0.6, the thermal management system of the optical fiber pipeline detection device corresponds to medium heat dissipation performance; when the heat dissipation optimization coefficient is greater than 0.6, the thermal management system of the optical fiber pipeline detection device corresponds to low heat dissipation performance; Allocate heat dissipation optimization plans for high heat dissipation performance, medium heat dissipation performance, and low heat dissipation performance respectively, number the heat dissipation optimization plans, and integrate the heat dissipation optimization plan numbers into the thermal management collaborative optimization dataset; According to the fluid flow optimization coefficient, the fluid flow performance is divided into high fluid flow performance, medium fluid flow performance, and low fluid flow performance. When the fluid flow optimization coefficient is between 0 and 0.3, the corresponding thermal management system of the optical fiber pipeline detection device has high fluid flow performance; when the fluid flow optimization coefficient is between 0.3 and 0.7, the corresponding thermal management system of the optical fiber pipeline detection device has medium fluid flow performance; when the fluid flow optimization coefficient is greater than 0.7, the corresponding thermal management system of the optical fiber pipeline detection device has low fluid flow performance; Fluid flow optimization schemes are respectively assigned to high fluid flow performance, medium fluid flow performance, and low fluid flow performance, the fluid flow optimization schemes are numbered, and the fluid flow optimization scheme numbers are integrated into the thermal management collaborative optimization dataset.

8. The collaborative optimization method of the thermal management system of a high-precision optical fiber pipeline detection device according to claim 7, wherein: In step five mentioned above, the construction process of the heat dissipation optimization model includes: Extract the heat dissipation optimization coefficient and the heat dissipation optimization scheme number from the thermal management collaborative optimization dataset; Using the training set data and combining with the neural network algorithm, taking the heat dissipation optimization coefficient as the input and the heat dissipation optimization scheme number as the output, learn the non-linear relationship between the heat dissipation optimization coefficient and the heat dissipation optimization scheme number, and train the heat dissipation optimization model; Input the test set data into the heat dissipation optimization model, compare the output result of the heat dissipation optimization model with the actual heat dissipation optimization scheme number, adjust the parameters of the heat dissipation optimization model, optimize the performance of the heat dissipation optimization model, obtain the final heat dissipation optimization model, and combine with the heat dissipation optimization coefficient to output the corresponding heat dissipation optimization scheme number.

9. The collaborative optimization method of the thermal management system of a high-precision optical fiber pipeline detection device according to claim 8, characterized in that: In step six mentioned above, the construction process of the fluid flow optimization model includes: Extract the fluid flow optimization coefficient and the fluid flow optimization scheme number from the thermal management collaborative optimization dataset; Combining the training set data and the convolutional neural network algorithm, taking the fluid flow optimization coefficient as the input and the fluid flow optimization scheme number as the output, learn the non-linear relationship between the fluid flow optimization coefficient and the fluid flow optimization scheme number, and train the fluid flow optimization model; Input the test set data into the fluid flow optimization model, compare the fluid flow optimization model with the actual fluid flow optimization scheme number, adjust the parameters of the fluid flow optimization model, optimize the fluid flow optimization model, obtain the final fluid flow optimization model, and combine with the fluid flow optimization coefficient to output the corresponding fluid flow optimization scheme number.

10. The collaborative optimization method of the thermal management system of a high-precision optical fiber pipeline detection device according to claim 9, characterized in that: In step seven mentioned above, the process of optimizing the thermal management of the high-precision optical fiber pipeline detection device includes: Match the corresponding heat dissipation optimization scheme according to the heat dissipation optimization scheme number output by the heat dissipation optimization model; Match the corresponding fluid flow optimization scheme according to the fluid flow optimization scheme number output by the fluid flow optimization model; Collaboratively execute the heat dissipation optimization scheme and the fluid flow optimization scheme to optimize the thermal management of the high-precision optical fiber pipeline detection device.

Images