CN111307480A - Embedded heat pipe-based heat transfer management system, method and storage medium - Google Patents

Abstract

The invention belongs to the technical field of heat transfer management of heat pipes, and discloses a heat transfer management system, method and storage medium based on an embedded heat pipe. Loss data; according to the detected value, the central control module controls the heat transfer efficiency calculation module, and the calculation program calculates the heat transfer efficiency data of the heat pipe; controls the fault diagnosis module to diagnose the fault of the heat pipe connected to the battery through the diagnostic circuit; according to the heat transfer efficiency and battery fault data As a result, the heat pipe life is predicted using the prediction program by the heat pipe life prediction module. Through the fault diagnosis module, the invention can diagnose the short circuit and liquid leakage of the battery in the initial stage of the occurrence of the short circuit and before the high temperature occurs, and accurately predict the maximum temperature rise problem caused by the short circuit.

Description

A heat transfer management system, method and storage medium based on embedded heat pipe

technical field

The invention belongs to the technical field of heat transfer management of heat pipes, and in particular relates to a heat transfer management system, method and storage medium based on embedded heat pipes.

Background technique

Heat pipe technology has been widely used in aerospace, military and other industries before. Since it was introduced into the radiator manufacturing industry, people have changed the design thinking of traditional radiators and got rid of the need to rely solely on high-volume motors to obtain better heat dissipation. The single heat dissipation mode adopts heat pipe technology, so that even if the radiator adopts a low-speed and low-air volume motor, it can still obtain satisfactory results, so that the noise problem that plagues air-cooled heat dissipation can be well solved, opening up a new world in the heat dissipation industry. However, the existing heat transfer management system based on the embedded heat pipe cannot accurately diagnose the battery failure connected by the heat pipe; at the same time, the heat conduction performance of the heat pipe cannot be accurately tested.

To sum up, the existing problems in the prior art are: the existing embedded heat pipe heat transfer management system cannot accurately diagnose the battery failure connected by the heat pipe; meanwhile, the heat conduction performance of the heat pipe cannot be accurately tested.

SUMMARY OF THE INVENTION

In view of the problems existing in the prior art, the present invention provides a heat transfer management system, method and storage medium based on an embedded heat pipe.

The present invention is realized in this way, a heat transfer management system based on embedded heat pipe, the heat transfer management system based on embedded heat pipe includes:

The temperature detection module is connected with the central control module, and is used to detect the temperature data of the heat pipe through the temperature sensor; the process of processing the collected signal by the temperature detection module is: detecting the temperature change through the sensitive element, and using the conversion element to convert the signal; conversion; The completed signal is transmitted to the processing circuit; the processing circuit denoises and amplifies the collected signal to obtain a signal without noise; the signal without noise is transmitted to the central control module; the process of denoising the collected signal through the processing circuit is as follows: Perform wavelet decomposition on the collected temperature signal to obtain various scale coefficients of the temperature data; perform threshold processing on the temperature data according to each scale coefficient of the temperature data; after the processing is completed, use wavelet reconstruction to obtain a signal without noise;

The heat loss detection module is connected with the central control module and is used to detect the heat loss data of the heat pipe through the heat pipe monitoring equipment;

The central control module is connected with the temperature detection module, the heat loss detection module, the heat transfer efficiency calculation module, the fault diagnosis module, the heat pipe test module, the heat pipe life prediction module and the display module, and is used to control the normal operation of each module through the main control computer; The control module extracts corresponding data features according to the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results; establishes a corresponding training set according to the extracted data features; and combines the heat pipe temperature data, heat pipe loss data, heat pipe Heat transfer efficiency data and fault diagnosis results, establish a corresponding test set; calculate the difference between the object to be tested and the training set, and within the range of the difference, select the attributes of N training objects as the neighbors of the test data; Classify the test data according to the attributes of N training objects;

The heat transfer efficiency calculation module, connected with the central control module, is used to calculate the heat transfer efficiency data of the heat pipe through the calculation program;

The fault diagnosis module is connected with the central control module, and is used for diagnosing the fault of the heat pipe connected to the battery through the diagnosis circuit;

The heat pipe test module, connected with the central control module, is used to test the thermal conductivity of the heat pipe through the test equipment;

The heat pipe life prediction module, connected with the central control module, is used to predict the heat pipe life through the prediction program; according to the detected heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the above data is stored in the database , to accumulate data and analyze; after the data accumulation and analysis is completed, determine the model and characteristics of the heat pipe failure; predict the service life of the heat pipe according to the model and characteristics of the heat pipe failure;

The display module, connected with the central control module, is used to display the detected heat pipe temperature, heat loss data, heat transfer efficiency, diagnosis result, test result and life prediction result through the display.

Another object of the present invention is to provide an embedded heat pipe-based heat transfer management method using the embedded heat pipe-based heat transfer management system, and the embedded heat pipe-based heat transfer management method includes:

Step 1, test the thermal conductivity of the heat pipe by using the test equipment in the heat pipe test module;

Step 2, in the process of testing the thermal conductivity of the heat pipe, the temperature detection module detects the temperature data of the heat pipe through the temperature sensor, and the heat loss detection module detects the heat loss data of the heat pipe through the heat pipe monitoring equipment;

Step 3, according to the detected value, the central control module controls the heat transfer efficiency calculation module, and the calculation program calculates the heat transfer efficiency data of the heat pipe; controls the fault diagnosis module to diagnose the fault of the heat pipe connected to the battery through the diagnostic circuit;

Step 4, according to the heat transfer efficiency and the battery failure data results, use the prediction program to predict the life of the heat pipe through the heat pipe life prediction module;

Step 5, the central control module controls the display module to display the detected heat pipe temperature, heat loss data, heat transfer efficiency, diagnosis result, test result, and life prediction result by using the display.

Further, in the step 1, the test method of the heat pipe test module is as follows:

Prepare a heat pipe test device, the heat pipe test device includes a constant temperature water tank, a heat pipe positioning fixture and a tester, the constant temperature water tank is filled with hot water of a constant temperature, and the heat pipe positioning fixture is movably installed above the constant temperature water tank , which is used to clamp and fix the first ends of these heat pipes, the tester is connected to the heat pipe positioning fixture, and is used to measure the temperature of the first ends of these heat pipes;

When the heat pipe positioning fixture is in the first active position, the first ends of the heat pipes are clamped and fixed on the heat pipe positioning fixture, and the second ends of the heat pipes are suspended above the water surface of the hot water. ; Then put the heat pipe positioning fixture in the second active position, make the second end of the heat pipe immersed in hot water for heating and start timing; after immersing these heat pipes in hot water for a period of time, read through the tester At this time, the temperature of the first end of each heat pipe, if the temperature of the first end of a heat pipe is higher than a certain value, it can be judged that the thermal conductivity of the heat pipe meets the requirements.

Further, in the second step, the temperature detection module processes the collected signals as follows:

The temperature conversion is detected by the sensitive element, and the signal is converted by the conversion element; the converted signal is transmitted to the processing circuit;

The processing circuit denoises and amplifies the collected signal to obtain a signal without noise; the signal without noise is transmitted to the central control module.

Further, the process of denoising the collected signal through the processing circuit is as follows:

Perform wavelet decomposition on the collected temperature signal to obtain the scale coefficients of the temperature data;

According to the scale coefficients of the temperature data, threshold processing is performed on the temperature data; after the processing is completed, wavelet reconstruction is used to obtain a signal without noise.

Further, in the third step, the process of classifying the data by the central control module is as follows:

According to the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the corresponding data features are extracted; according to the extracted data features, a corresponding training set is established; and the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer data are extracted. Efficiency data and fault diagnosis results, establish corresponding test sets;

Calculate the difference between the object to be tested and the training set, and within the range of the difference, select the attributes of N training objects as the nearest neighbors of the test data;

The test data is classified according to the attributes of the N training objects.

Further, in the step 3, the process of fusing the data detected by the multiple temperature sensors by the central control module is as follows:

The central control module receives data information transmitted by multiple temperature sensors, and uses corresponding algorithms to extract corresponding technical features;

According to the extracted technical features, establish a representative feature vector;

The feature vector is processed by pattern recognition, and the detection target is described and calibrated; the corresponding correlation is established according to the content of the description and calibration; at the same time, the data is synthesized by the fusion algorithm.

Further, in the step 3, the fault diagnosis module diagnosis method is as follows:

Step a, configure the upper computer diagnostic parameters to open the upper computer and initialize the sampling frequency f, current threshold value Is, and power threshold value Cs;

In step b, the host computer monitors the current signal I in real time through the current sensor. If I<Is, the host computer continues to monitor the current signal in real time through the current sensor, and repeats step b. If I≥Is, the external short-circuit fault diagnosis and Maximum temperature rise prediction mechanism, enter step c;

The cth step, the host computer collects and stores the current signal Ii at the tith moment according to the sampling frequency f, calculates the electricity C released by the external short circuit, and the calculation relationship is as follows:

where N is the number of samples after an external short circuit occurs;

The dth step is to diagnose whether the external short circuit causes battery leakage. If C≥Cs, the battery is diagnosed as not leaking, and the result is displayed on the host computer interface, and the e-th step is entered. If C<Cs, Then it is diagnosed as liquid leakage, the result is displayed on the interface of the host computer, and the f-th step is entered;

The e-th step, the first neural network process, the upper computer inputs the electricity C calculated in the c-th step into the pre-established and trained BP neural network 1, and obtains the output of the BP neural network 1, The output is the predicted value ΔTmax of the maximum temperature rise of the external short-circuit fault of the battery;

The fth step, the second neural network process, the upper computer inputs the electricity C calculated in the cth step into the pre-established and trained BP second neural network, and obtains the BP second neural network. The output is the predicted value ΔTmax of the maximum temperature rise of the external short-circuit fault of the battery.

Further, the establishment and training process of the BP first neural network and the BP second neural network specifically includes the following steps:

(1) determine the training samples of the BP first neural network and the BP second neural network;

(2) establishing described BP first neural network and BP second neural network;

(3) training the BP first neural network and the BP second neural network respectively;

(4) Determine the best BP first neural network and BP second neural network.

Further, in the step 4, the process of predicting the life of the heat pipe by the heat pipe life prediction module is as follows:

According to the detected heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the above data is stored in the database, and the data is accumulated and analyzed;

After the data accumulation analysis is completed, the model and characteristics of the heat pipe failure are determined;

Predict the service life of heat pipes based on the models and characteristics of heat pipe failures.

The advantages and positive effects of the present invention are as follows: the present invention can diagnose the short circuit and liquid leakage of the battery at the initial stage of the short circuit occurrence and before the high temperature occurs, and accurately predict the problem of the maximum temperature rise caused by the short circuit through the fault diagnosis module. It provides a good foundation for the protection and further intervention of the external short-circuit fault of the power battery; at the same time, the first end of the heat pipes is clamped and fixed to the heat pipe positioning fixture through the heat pipe test module, and the second end is suspended on the hot water. The heat pipe positioning fixture is then pivoted to the second active position, and the second end of the heat pipe is immersed in hot water to heat and start timing; after heating the second end of the heat pipe for a period of time, the test is passed. The meter reads the temperature of the first end of each heat pipe at this time; if the temperature of the first end of a heat pipe is higher than a certain value, it can be judged that the thermal conductivity of the heat pipe meets the requirements, thereby greatly improving the accuracy of the heat pipe thermal conductivity test. .

Description of drawings

FIG. 1 is a schematic diagram of a heat transfer management system based on an embedded heat pipe provided by an embodiment of the present invention.

In the figure: 1. Temperature detection module; 2. Heat loss detection module; 3. Central control module; 4. Heat transfer efficiency calculation module; 5. Fault diagnosis module; 6. Heat pipe test module; 7. Heat pipe life prediction module; 8 , Display module.

FIG. 2 is a flowchart of a method for heat transfer management based on an embedded heat pipe provided by an embodiment of the present invention.

Detailed ways

In order to further understand the content, characteristics and effects of the present invention, the following embodiments are exemplified and described in detail below with the accompanying drawings.

The structure of the present invention will be described in detail below with reference to the accompanying drawings.

As shown in FIG. 1 , the embedded heat pipe-based heat transfer management system provided by the embodiment of the present invention includes: a temperature detection module 1, a heat loss detection module 2, a central control module 3, a heat transfer efficiency calculation module 4, a fault diagnosis module 5, A heat pipe test module 6 , a heat pipe life prediction module 7 , and a display module 8 .

The temperature detection module 1 is connected to the central control module 3, and is used for detecting the temperature data of the heat pipe through the temperature sensor.

The heat loss detection module 2 is connected to the central control module 3, and is used for detecting the heat loss data of the heat pipe through the heat pipe monitoring equipment.

The central control module 3 is connected to the temperature detection module 1, the heat loss detection module 2, the heat transfer efficiency calculation module 4, the fault diagnosis module 5, the heat pipe test module 6, the heat pipe life prediction module 7, and the display module 8, and is used to pass the main control module. The machine controls each module to work normally.

The heat transfer efficiency calculation module 4 is connected with the central control module 3, and is used for calculating the heat transfer efficiency data of the heat pipe through a calculation program.

The fault diagnosis module 5 is connected to the central control module 3, and is used for diagnosing the fault of the heat pipe connected to the battery through the diagnosis circuit.

The heat pipe test module 6 is connected to the central control module 3 and is used for testing the thermal conductivity of the heat pipe through the test equipment.

The heat pipe life prediction module 7 is connected to the central control module 3 and is used for predicting the heat pipe life through a prediction program.

The display module 8, connected to the central control module 3, is used to display the detected heat pipe temperature, heat loss data, heat transfer efficiency, diagnosis results, test results, and life prediction results through the display.

As shown in FIG. 2, the embedded heat pipe-based heat transfer management method provided by the embodiment of the present invention includes:

S101: Test the thermal conductivity of the heat pipe by using the test equipment in the heat pipe test module.

S102: In the process of testing the thermal conductivity of the heat pipe, the temperature detection module detects the temperature data of the heat pipe through the temperature sensor, and the heat loss detection module detects the heat loss data of the heat pipe through the heat pipe monitoring device.

S103: According to the detected value, the central control module controls the heat transfer efficiency calculation module, and the calculation program calculates the heat transfer efficiency data of the heat pipe. The control fault diagnosis module diagnoses the fault of the heat pipe connected to the battery through the diagnosis circuit.

S104: According to the results of the heat transfer efficiency and the battery failure data, the heat pipe life prediction module uses a prediction program to predict the heat pipe life.

S105: The central control module controls the display module to display the detected heat pipe temperature, heat loss data, heat transfer efficiency, diagnosis result, test result, and life prediction result by using the display.

The present invention will be further described below in conjunction with specific embodiments.

Example 1

The process of processing the collected signals by the temperature detection module 1, which is connected to the central control module 3 and used for detecting the temperature data of the heat pipe through the temperature sensor, is as follows:

The temperature change is detected by the sensitive element, and the signal is converted by the conversion element. The converted signal is passed to the processing circuit.

The processing circuit denoises and amplifies the collected signal to obtain a signal without noise. The noise-free signal is passed to the central control module.

The process of denoising the collected signal through the processing circuit is as follows:

The collected temperature signal is decomposed by wavelet, and the scale coefficients of the temperature data are obtained.

According to each scale coefficient of the temperature data, threshold processing is performed on the temperature data. After the processing is completed, wavelet reconstruction is used to obtain a signal without noise.

The invention provides a temperature detection module 1, a heat loss detection module 2, a heat transfer efficiency calculation module 4, a fault diagnosis module 5, a heat pipe test module 6, a heat pipe life prediction module 7, and a display module 8. The process of classifying data by the central control module 3, which controls the normal operation of each module, is as follows:

According to the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the corresponding data features are extracted. According to the extracted data features, a corresponding training set is established. And a corresponding test set is established based on the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results.

Calculate the difference between the object to be tested and the training set, and within the range of the difference, select the attributes of N training objects as the nearest neighbors of the test data.

The test data is classified according to the attributes of the N training objects.

Example 2

The invention provides a temperature detection module 1, a heat loss detection module 2, a heat transfer efficiency calculation module 4, a fault diagnosis module 5, a heat pipe test module 6, a heat pipe life prediction module 7, and a display module 8. The central control module 3 that controls the normal operation of each module, in order to prevent errors in the process of measuring the temperature of the heat pipe by a single temperature sensor. Multiple temperature sensors are required to measure the temperature in the heat pipe. Multiple temperature sensors transmit the detected data to the central control module 3, and the process of fusing the data detected by multiple temperature sensors is as follows:

The central control module receives data information transmitted by multiple temperature sensors, and uses corresponding algorithms to extract corresponding technical features.

According to the extracted technical features, a representative feature vector is established.

The feature vector is processed by pattern recognition, and the detection target is described and calibrated. According to the content of the description and calibration, establish the corresponding correlation. At the same time, the fusion algorithm is used to synthesize the data.

Example 3

The fault diagnosis method in the fault diagnosis module 5 provided by the present invention is as follows:

Step a, configure the upper computer diagnostic parameters to turn on the upper computer and initialize the sampling frequency f, the current threshold value Is, and the power threshold value Cs.

In step b, the host computer monitors the current signal I in real time through the current sensor. If I<Is, the host computer continues to monitor the current signal in real time through the current sensor, and repeats step b. If I≥Is, the external short-circuit fault diagnosis and Maximum temperature rise prediction mechanism, go to step c.

The cth step, the host computer collects and stores the current signal Ii at the tith moment according to the sampling frequency f, calculates the electricity C released by the external short circuit, and the calculation relationship is as follows:

where N is the number of samples after an external short circuit occurs.

The dth step is to diagnose whether the external short circuit causes battery leakage. If C≥Cs, the battery is diagnosed as not leaking, and the result is displayed on the host computer interface, and the e-th step is entered. If C<Cs, Then, it is diagnosed that liquid leakage occurs, the result is displayed on the interface of the host computer, and the step f is entered.

The e-th step, the first neural network process, the upper computer inputs the electricity C calculated in the c-th step into the pre-established and trained BP neural network 1, and obtains the output of the BP neural network 1, The output is the predicted value ΔTmax of the maximum temperature rise of the external short-circuit fault of the battery.

The fth step, the second neural network process, the upper computer inputs the electricity C calculated in the cth step into the pre-established and trained BP second neural network, and obtains the BP second neural network. The output is the predicted value ΔTmax of the maximum temperature rise of the external short-circuit fault of the battery.

Example 4

The establishment and training process of the BP first neural network and the BP second neural network provided by the present invention specifically include the following steps:

(1) Determine the training samples of the BP first neural network and the BP second neural network.

(2) Establish the BP first neural network and the BP second neural network.

(3) The BP first neural network and the BP second neural network are trained respectively.

(4) Determine the best BP first neural network and BP second neural network.

The test method of the heat pipe test module 6 provided by the present invention is as follows:

Prepare a heat pipe test device, the heat pipe test device includes a constant temperature water tank, a heat pipe positioning fixture and a tester, the constant temperature water tank is filled with hot water of a constant temperature, and the heat pipe positioning fixture is movably installed above the constant temperature water tank , which is used to clamp and fix the first ends of the heat pipes, the tester is connected to the heat pipe positioning fixture, and is used to measure the temperature of the first ends of the heat pipes.

When the heat pipe positioning fixture is in the first active position, the first ends of the heat pipes are clamped and fixed on the heat pipe positioning fixture, and the second ends of the heat pipes are suspended above the water surface of the hot water. . Then, the heat pipe positioning fixture is placed in the second active position, and the second end of the heat pipe is immersed in hot water to heat and start timing. After soaking these heat pipes in hot water for a period of time, the temperature of the first end of each heat pipe is read out by the tester. If the temperature of the first end of a certain heat pipe is higher than a certain value, it can be judged that the The thermal conductivity meets the requirements.

The heat pipe life prediction module 7, which is connected to the central control module 3 and used for predicting the heat pipe life through a prediction program, provided by the present invention, predicts the heat pipe life as follows:

According to the detected heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the above data is stored in the database, and the data is accumulated and analyzed.

After the data accumulation analysis is completed, the model and characteristics of the failure of the heat pipe are determined.

Predict the service life of heat pipes based on the models and characteristics of heat pipe failures.

Example 5

When the present invention works, firstly, the heat conduction performance of the heat pipe is tested by using the test equipment in the heat pipe test module 6 . In the process of testing the thermal conductivity of the heat pipe, the temperature detection module 1 detects the temperature data of the heat pipe through the temperature sensor, and the heat loss detection module 2 detects the heat loss data of the heat pipe through the heat pipe monitoring device. According to the detected value, the central control module 3 controls the heat transfer efficiency calculation module, and the calculation program calculates the heat transfer efficiency data of the heat pipe. The control failure diagnosis module 5 diagnoses the failure of the heat pipe connected to the battery through the diagnosis circuit. According to the heat transfer efficiency and battery failure data results, the heat pipe life prediction module 7 uses a prediction program to predict the heat pipe life. The central control module 3 controls the display module to display the detected heat pipe temperature, heat loss data, heat transfer efficiency, diagnosis results, test results, and life prediction results by using the display.

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented in whole or in part in the form of a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer may be a general purpose computer, special purpose computer, computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server or data center Transmission to another website site, computer, server, or data center by wire (eg, coaxial cable, fiber optic, digital subscriber line (DSL), or wireless (eg, infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that includes an integration of one or more available media. The usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (SSD)), among others.

The above is only the preferred embodiment of the present invention, and does not limit the present invention in any form. Any simple modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention belong to the present invention. within the scope of the technical solution of the invention.

Claims (10)

1. A heat transfer management system based on an embedded heat pipe, wherein the heat transfer management system based on an embedded heat pipe comprises: The temperature detection module is connected with the central control module, and is used to detect the temperature data of the heat pipe through the temperature sensor; the process of processing the collected signal by the temperature detection module is: detecting the temperature change through the sensitive element, and using the conversion element to convert the signal; conversion; The completed signal is transmitted to the processing circuit; the processing circuit denoises and amplifies the collected signal to obtain a signal without noise; the signal without noise is transmitted to the central control module; the process of denoising the collected signal through the processing circuit is as follows: Perform wavelet decomposition on the collected temperature signal to obtain various scale coefficients of the temperature data; perform threshold processing on the temperature data according to each scale coefficient of the temperature data; after the processing is completed, use wavelet reconstruction to obtain a signal without noise; The heat loss detection module is connected with the central control module and is used to detect the heat loss data of the heat pipe through the heat pipe monitoring equipment; The central control module is connected with the temperature detection module, the heat loss detection module, the heat transfer efficiency calculation module, the fault diagnosis module, the heat pipe test module, the heat pipe life prediction module and the display module, and is used to control the normal operation of each module through the main control computer; The control module extracts corresponding data features according to the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results; establishes a corresponding training set according to the extracted data features; and combines the heat pipe temperature data, heat pipe loss data, heat pipe Heat transfer efficiency data and fault diagnosis results, establish a corresponding test set; calculate the difference between the object to be tested and the training set, and within the range of the difference, select the attributes of N training objects as the neighbors of the test data; Classify the test data according to the attributes of N training objects; The heat transfer efficiency calculation module, connected with the central control module, is used to calculate the heat transfer efficiency data of the heat pipe through the calculation program; The fault diagnosis module is connected with the central control module, and is used for diagnosing the fault of the heat pipe connected to the battery through the diagnosis circuit; The heat pipe test module, connected with the central control module, is used to test the thermal conductivity of the heat pipe through the test equipment; The heat pipe life prediction module, connected with the central control module, is used to predict the heat pipe life through the prediction program; according to the detected heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the above data is stored in the database , to accumulate data and analyze; after the data accumulation and analysis is completed, determine the model and characteristics of the heat pipe failure; predict the service life of the heat pipe according to the model and characteristics of the heat pipe failure; The display module, connected with the central control module, is used to display the detected heat pipe temperature, heat loss data, heat transfer efficiency, diagnosis result, test result and life prediction result through the display. 2. An embedded heat pipe-based heat transfer management method using the embedded heat pipe-based heat transfer management system of claim 1, wherein the embedded heat pipe-based heat transfer management method comprises: Step 1, test the thermal conductivity of the heat pipe by using the test equipment in the heat pipe test module; Step 2, in the process of testing the thermal conductivity of the heat pipe, the temperature detection module detects the temperature data of the heat pipe through the temperature sensor, and the heat loss detection module detects the heat loss data of the heat pipe through the heat pipe monitoring equipment; Step 3, according to the detected value, the central control module controls the heat transfer efficiency calculation module, and the calculation program calculates the heat transfer efficiency data of the heat pipe; controls the fault diagnosis module to diagnose the fault of the heat pipe connected to the battery through the diagnostic circuit; Step 4, according to the heat transfer efficiency and the battery failure data results, use the prediction program to predict the life of the heat pipe through the heat pipe life prediction module; Step 5, the central control module controls the display module to display the detected heat pipe temperature, heat loss data, heat transfer efficiency, diagnosis result, test result, and life prediction result by using the display. 3. The heat transfer management method based on embedded heat pipes as claimed in claim 2, wherein in the step 1, the test method of the heat pipe test module is as follows: Prepare a heat pipe test device, the heat pipe test device includes a constant temperature water tank, a heat pipe positioning fixture and a tester, the constant temperature water tank is filled with hot water of a constant temperature, and the heat pipe positioning fixture is movably installed above the constant temperature water tank , which is used to clamp and fix the first ends of these heat pipes, the tester is connected to the heat pipe positioning fixture, and is used to measure the temperature of the first ends of these heat pipes; When the heat pipe positioning fixture is in the first active position, the first ends of the heat pipes are clamped and fixed on the heat pipe positioning fixture, and the second ends of the heat pipes are suspended above the water surface of the hot water. ; Then put the heat pipe positioning fixture in the second active position, make the second end of the heat pipe immersed in hot water for heating and start timing; after immersing these heat pipes in hot water for a period of time, read through the tester At this time, the temperature of the first end of each heat pipe, if the temperature of the first end of a heat pipe is higher than a certain value, it can be judged that the thermal conductivity of the heat pipe meets the requirements. 4. The heat transfer management method based on an embedded heat pipe as claimed in claim 2, wherein in the second step, the temperature detection module processes the collected signals as follows: The temperature conversion is detected by the sensitive element, and the signal is converted by the conversion element; the converted signal is transmitted to the processing circuit; The processing circuit de-noises and amplifies the collected signal to obtain a signal without noise; the signal without noise is transmitted to the central control module; The process of denoising the collected signal through the processing circuit is as follows: Perform wavelet decomposition on the collected temperature signal to obtain the scale coefficients of the temperature data; According to the scale coefficients of the temperature data, threshold processing is performed on the temperature data; after the processing is completed, wavelet reconstruction is used to obtain a signal without noise. 5. The heat transfer management method based on an embedded heat pipe as claimed in claim 2, wherein in the step 3, the process of classifying the data by the central control module is: According to the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the corresponding data features are extracted; according to the extracted data features, a corresponding training set is established; and the heat pipe temperature data, heat pipe loss data, heat pipe heat transfer data are extracted. Efficiency data and fault diagnosis results, establish corresponding test sets; Calculate the difference between the object to be tested and the training set, and within the range of the difference, select the attributes of N training objects as the nearest neighbors of the test data; The test data is classified according to the attributes of the N training objects. 6. The method for heat transfer management based on embedded heat pipes as claimed in claim 2, wherein in the step 3, the process that the central control module fuses the data detected by the multiple temperature sensors is: The central control module receives data information transmitted by multiple temperature sensors, and uses corresponding algorithms to extract corresponding technical features; According to the extracted technical features, establish a representative feature vector; The feature vector is processed by pattern recognition, and the detection target is described and calibrated; the corresponding correlation is established according to the content of the description and calibration; at the same time, the data is synthesized by the fusion algorithm. 7. The heat transfer management method based on embedded heat pipes as claimed in claim 2, wherein in the step 3, the fault diagnosis module diagnosis method is as follows: Step a, configure the upper computer diagnostic parameters to open the upper computer and initialize the sampling frequency f, current threshold value Is, and power threshold value Cs; In step b, the host computer monitors the current signal I in real time through the current sensor. If I<Is, the host computer continues to monitor the current signal in real time through the current sensor, and repeats step b. If I≥Is, the external short-circuit fault diagnosis and Maximum temperature rise prediction mechanism, enter step c; The cth step, the host computer collects and stores the current signal Ii at the tith moment according to the sampling frequency f, calculates the electricity C released by the external short circuit, and the calculation relationship is as follows: where N is the number of samples after an external short circuit occurs; The dth step is to diagnose whether the external short circuit causes battery leakage. If C≥Cs, the battery is diagnosed as not leaking, and the result is displayed on the host computer interface, and the e-th step is entered. If C<Cs, Then it is diagnosed as liquid leakage, the result is displayed on the interface of the host computer, and the f-th step is entered; The e-th step, the first neural network process, the upper computer inputs the electricity C calculated in the c-th step into the pre-established and trained BP neural network 1, and obtains the output of the BP neural network 1, The output is the predicted value ΔTmax of the maximum temperature rise of the external short-circuit fault of the battery; The fth step, the second neural network process, the upper computer inputs the electricity C calculated in the cth step into the pre-established and trained BP second neural network, and obtains the BP second neural network. output, the output is the predicted value ΔTmax of the maximum temperature rise of the external short-circuit fault of the battery; The establishment and training process of the BP first neural network and the BP second neural network specifically includes the following steps: (1) determine the training samples of the BP first neural network and the BP second neural network; (2) establishing described BP first neural network and BP second neural network; (3) training the BP first neural network and the BP second neural network respectively; (4) Determine the best BP first neural network and BP second neural network. 8. The heat transfer management method based on an embedded heat pipe according to claim 2, wherein in the step 4, the prediction process of the life of the heat pipe by the heat pipe life prediction module is: According to the detected heat pipe temperature data, heat pipe loss data, heat pipe heat transfer efficiency data and fault diagnosis results, the above data is stored in the database, and the data is accumulated and analyzed; After the data accumulation analysis is completed, the model and characteristics of the heat pipe failure are determined; Predict the service life of heat pipes based on the models and characteristics of heat pipe failures. 9. A computer program product stored on a computer-readable medium, comprising a computer-readable program that, when executed on an electronic device, provides a user input interface to implement an embedded-based embedded system as claimed in any one of claims 2-8 Heat pipe heat transfer management method. 10. A computer-readable storage medium storing instructions, when the instructions are executed on a computer, causing the computer to execute the embedded heat pipe-based heat transfer management method according to any one of claims 2-8.

Images