A fuel cell waste heat recycling device

Abstract

The present invention relates to the technical field of heat utilization, and discloses a fuel cell waste heat recycling device, including: a fuel cell, a storage battery, a heat exchanger, a temperature sensing optical cable, a high-temperature cable, and a temperature processor. The heat exchanger is wound around the fuel cell and fixedly connected to the fuel cell. One end of the high-temperature cable is fixedly connected to the heat exchanger, and the other end of the high-temperature cable is fixedly connected to the storage battery. The high-temperature cable is used to transmit the electric energy of the heat exchanger. The temperature sensing optical cable is embedded inside the fuel cell, and the temperature sensing optical cable is arranged in a U shape inside the fuel cell. The temperature sensing optical cable is fixedly connected to the temperature processor, and the temperature processor is used to obtain the temperature data of the temperature sensing optical fiber. The present invention has the characteristics of good waste heat utilization and temperature monitoring by winding the heat exchanger around the fuel cell and collecting temperature data by the temperature processor.

Description

Technical Field

[0001] The present invention relates to the technical field of heat utilization, and more specifically, to a device for recycling waste heat of a fuel cell. Background Art

[0002] With the rapid development of the global economy, the energy consumption has increased sharply. Traditional fossil fuels such as oil and coal are becoming increasingly depleted, and the energy crisis is becoming more and more severe. With the progress of technology, fuel cells, as an efficient and environmentally friendly energy conversion device, are gradually becoming the key to solving the energy crisis and reducing carbon emissions. A fuel cell is a chemical device that directly converts the chemical energy of a fuel into electrical energy, also known as an electrochemical generator. It is the fourth generation of power generation technology after hydraulic power generation, thermal power generation, and nuclear power generation. A fuel cell is a device that directly converts the chemical energy of a fuel into electrical energy, and can continuously output electrical energy only by introducing fuel and an oxidant. However, when a fuel cell generates electrical energy, a large amount of heat is also generated.

[0003] Traditional devices cannot reasonably utilize the waste heat of fuel cells, resulting in waste of resources. If this heat is not effectively managed and utilized, it will not only reduce the efficiency of fuel cells, but also have a negative impact on the stability of fuel cells. In addition, the temperature distribution inside the fuel cell is crucial for its performance and lifespan. Traditional temperature acquisition faces inaccurate temperature acquisition and cannot obtain the accurate temperature value inside the fuel cell.

[0004] Therefore, how to provide a device for recycling waste heat of a fuel cell is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the present invention provides a device for recycling waste heat of a fuel cell, aiming to solve the problems of how to efficiently recover and utilize the heat generated by a fuel cell and accurately monitor the temperature inside the fuel cell.

[0006] The present invention provides a device for recycling waste heat of a fuel cell, comprising:

[0007] A fuel cell, a storage battery, a heat exchanger, a temperature sensing optical cable, a high-temperature cable, and a temperature processor;

[0008] The heat exchanger is wound around the fuel cell and fixedly connected to the fuel cell. One end of the high-temperature cable is fixedly connected to the heat exchanger, and the other end of the high-temperature cable is fixedly connected to the storage battery. The high-temperature cable is used to transmit the electrical energy of the heat exchanger;

[0009] The temperature sensing optical cable is embedded inside the fuel cell, is arranged in a U shape inside the fuel cell, and is fixedly connected to the temperature processor;

[0010] The temperature sensing optical cable includes a PE sheath, a carbon fiber filament bundle, and a temperature sensing optical fiber;

[0011] The PE sheath sheathes the carbon fiber filament bundle, and the carbon fiber filament bundle sheathes the temperature sensing optical fiber;

[0012] The temperature processor is used to obtain the temperature data of the temperature sensing optical fiber.

[0013] Further, the temperature processor sets a temperature acquisition system, and the temperature acquisition system includes:

[0014] A data acquisition unit, a temperature judgment unit, a temperature prediction unit, and a temperature processing unit;

[0015] The data acquisition unit is configured to collect the temperature data of the temperature sensing optical fiber and preprocess it to obtain an initial temperature value;

[0016] The temperature judgment unit is configured to compare the initial temperature value with historical data, and based on the comparison result, judge whether to correct the initial temperature value. When it is judged to correct the initial temperature value, a temperature data set is determined through a clustering algorithm, and the initial temperature value is corrected according to the temperature data set to obtain a corrected temperature value;

[0017] The temperature prediction unit is configured to establish a random forest model according to historical temperature value data and obtain a temperature prediction value according to the initial temperature value;

[0018] The temperature processing unit is configured to compare the corrected temperature value with the temperature prediction value, establish a temperature compensation model according to the comparison result, obtain a temperature compensation value according to the temperature compensation model, determine a temperature optimization coefficient according to the temperature compensation value, and optimize the corrected temperature value according to the temperature optimization coefficient to obtain a target temperature value, and the target temperature value is the product value of the corrected temperature value and the temperature optimization coefficient.

[0019] Further, when comparing the initial temperature value with historical data and judging whether to correct the initial temperature value based on the comparison result, it includes:

[0020] The historical data includes the minimum value of historical initial temperature data, the mean value of historical initial temperature data, historical initial temperature correction data, and historical correction factors, and the historical initial temperature correction data and the historical correction factors are in one-to-one correspondence;

[0021] When the initial temperature value is greater than or equal to the minimum value of the historical initial temperature data and greater than or equal to the mean value of the historical initial temperature data, it is judged not to correct the initial temperature value, and the initial temperature value is determined as the target temperature value;

[0022] When the initial temperature value is less than the minimum value of the historical initial temperature data, it is determined that the initial temperature value needs to be corrected.

[0023] Further, when determining the temperature data set by the clustering algorithm, it includes:

[0024] Taking the initial temperature value to be corrected and the historical data as the data set to be aggregated, extracting the historical correction factor corresponding to each data in the data set to be aggregated, determining that the expected number of clusters k is 3, and initializing the parameters of the Gaussian distribution;

[0025] Calculating the probability that each data in the data set to be aggregated belongs to each Gaussian distribution to obtain the responsibility value, obtaining the correction data set corresponding to the initial temperature value to be corrected according to the responsibility value, and taking the correction data set as the temperature data set.

[0026] Further, when correcting the initial temperature value according to the temperature data set to obtain the corrected temperature value, it includes:

[0027] Determining the correction factor of the initial temperature value to be corrected according to the mean value of the historical correction factors in the temperature data set;

[0028] The corrected temperature value is the product value of the initial temperature value to be corrected and the correction factor.

[0029] Further, when establishing a random forest model according to the historical temperature value data and obtaining the temperature prediction value according to the initial temperature value, it includes:

[0030] Dividing the historical temperature value data into a temperature training set and a temperature test set, using cross-validation and combining grid search to find the model establishment parameters of the random forest model, and establishing the random forest model;

[0031] Substituting the temperature training set into the random forest model to fit the random forest model, substituting the temperature test set into the fitted random forest model and obtaining the prediction accuracy of the temperature prediction value;

[0032] When the prediction accuracy reaches the preset accuracy threshold, the temperature prediction value at the current moment is obtained according to the initial temperature value.

[0033] Further, when comparing the corrected temperature value with the temperature prediction value and establishing a temperature compensation model according to the comparison result, it includes:

[0034] When the corrected temperature value is less than or equal to 1.5 times the temperature prediction value, it is determined that the corrected temperature value is not optimized, and the corrected temperature value is determined as the target temperature value;

[0035] When the corrected temperature value is greater than 1.5 times the temperature prediction value, it is determined that the corrected temperature value is optimized and a temperature compensation model is established.

[0036] Further, when determining that the corrected temperature value is optimized and a temperature compensation model is established, it includes:

[0037] Statistical historical corrected temperature value data and historical temperature prediction value data for optimizing all historical corrected temperature values, and the historical corrected temperature value data and the historical temperature prediction value data correspond one by one;

[0038] The temperature compensation model adopts a linear regression model, and the linear regression model is established by the following formula:

[0039] ;

[0040] Wherein, represents any item of historical corrected temperature value data, represents historical temperature prediction value data, represents the temperature compensation value, represents the intercept of the linear regression model.

[0041] Further, when obtaining the temperature compensation value according to the temperature compensation model, it includes:

[0042] Substitute all historical corrected temperature value data and all historical temperature prediction value data into the linear regression model one by one and perform difference calculation to eliminate the intercept of the linear regression model and obtain the temperature compensation value T.

[0043] Further, when determining the temperature optimization coefficient according to the temperature compensation value, it includes:

[0044] Preset a first preset optimization coefficient, a second preset optimization coefficient, and a third preset optimization coefficient;

[0045] When T≤2, the first preset optimization coefficient is used as the temperature optimization coefficient of the corrected temperature value;

[0046] When 2<T≤4, the second preset optimization coefficient is used as the temperature optimization coefficient of the corrected temperature value;

[0047] When 4<T, the third preset optimization coefficient is used as the temperature optimization coefficient of the corrected temperature value.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows: By winding the fuel cell with a heat exchanger and converting the waste heat into electrical energy for transmission to the storage battery, the utilization rate of the waste heat energy of the fuel cell is improved, and the efficient utilization of energy is realized. The temperature sensing optical cable is arranged in a U shape inside the fuel cell, and then the distributed temperature sensing optical cable is connected to the temperature processor to form a comprehensive optical fiber monitoring network, which improves the efficiency of the temperature sensing optical cable in monitoring temperature and real-time monitors the internal temperature of the fuel cell. It has the characteristics of being distributed and having a comprehensive coverage range, realizing the all-round monitoring of the inside of the fuel cell, and improving the accuracy and reliability of obtaining the internal temperature of the fuel cell in a high-temperature environment. The temperature processor analyzes the collected temperature data to accurately obtain the actual temperature value inside the fuel cell, realizing the automation and intelligence of the temperature monitoring of the fuel cell. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0050] Figure 1 is a schematic structural diagram of a fuel cell waste heat recycling device provided by an embodiment of the present invention;

[0051] Figure 2 is a schematic structural diagram of the inside of a fuel cell provided by an embodiment of the present invention;

[0052] Figure 3 is a schematic structural diagram of a temperature sensing optical cable provided by an embodiment of the present invention;

[0053] Figure 4 is a schematic structural diagram of a temperature processor provided by an embodiment of the present invention;

[0054] Figure 5 is a functional block diagram of a temperature acquisition system provided by an embodiment of the present invention.

[0055] In the figure, 1, fuel cell; 2, heat exchanger; 3, high-temperature cable; 4, storage battery; 5, temperature processor; 6, temperature sensing optical cable; 7, PE sheath; 8, temperature sensing optical fiber; 9, carbon fiber bundle. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0057] Referring to Figures 1-3 As shown, in some embodiments of the present application, a fuel cell waste heat recycling device includes: a fuel cell 1, a storage battery 4, a heat exchanger 2, a temperature sensing optical cable 6, a high-temperature cable 3, and a temperature processor 5; the heat exchanger 2 is wound around the fuel cell 1 and fixedly connected to the fuel cell 1, one end of the high-temperature cable 3 is fixedly connected to the heat exchanger 2, the other end of the high-temperature cable 3 is fixedly connected to the storage battery 4, and the high-temperature cable 3 is used to transmit the electric energy of the heat exchanger 2; the temperature sensing optical cable 6 is embedded inside the fuel cell 1, the temperature sensing optical cable 6 is arranged in a U shape inside the fuel cell 1, and the temperature sensing optical cable 6 is fixedly connected to the temperature processor 5; the temperature sensing optical cable 6 includes a PE sheath 7, a carbon fiber filament bundle 9, and a temperature sensing optical fiber 8; the PE sheath 7 sheaths the carbon fiber filament bundle 9, and the carbon fiber filament bundle 9 sheaths the temperature sensing optical fiber 8; the temperature processor 5 is used to obtain the temperature data of the temperature sensing optical fiber 8.

[0058] Specifically, the fuel cell 1 generates electrical energy through chemical reactions and releases a large amount of waste heat during the chemical process. The heat exchanger 2 is fixedly connected to the fuel cell 1 by a winding connection method, which not only enhances the compactness of the device but also improves the efficiency of the heat exchanger 2 in recovering the excess heat energy of the fuel cell 1. The waste heat generated by the fuel cell 1 is recovered by the heat exchanger 2, and the heat is transferred to the thermoelectric material inside the heat exchanger 2. The Seebeck effect occurs due to the temperature difference between the thermoelectric materials to generate electrical energy, and the electrical energy is transmitted to the storage battery 4 through the high-temperature cable 3. The storage battery 4 is used to store the electrical energy converted by the heat exchanger 2, thus achieving the purpose of recycling waste heat and energy conservation and emission reduction. The high-temperature cable 3 has high-temperature resistance and good electrical conductivity, enabling it to operate stably in the high-temperature environment generated by the fuel cell 1 and ensuring the transmission of electrical energy. The temperature-sensing optical cable 6 is embedded inside the fuel cell 1 and is arranged in a U shape inside the fuel cell 1. The diameter of the temperature-sensing optical cable 6 is 10 mm, and the weight is 90 kg / km. The temperature-sensing optical cable 6 includes a PE sheath 7, a carbon fiber filament bundle 9, and a temperature-sensing optical fiber 8. The temperature-sensing optical cable 6 has excellent high-temperature resistance and anti-interference capabilities. The PE sheath 7 plays an external protection role to prevent the high-temperature environment inside the fuel cell 1 from damaging the temperature-sensing optical fiber 8. The carbon fiber filament bundle 9 enhances the structural strength of the temperature-sensing optical cable 6, and the temperature-sensing optical fiber 8 is responsible for converting the internal temperature of the fuel cell 1 into temperature data. Through the U-shaped arrangement, the temperature-sensing optical fiber 8 inside the temperature-sensing optical cable 6 can not only cover all regions of the fuel cell 1 but also monitor the temperature changes inside the fuel cell 1 in real time and accurately, providing reliable data support for the health management of the fuel cell 1. At the same time, through the U-shaped arrangement, the temperature-sensing optical fiber 8 can also accurately locate the positions with abnormal internal temperatures of the fuel cell 1, helping to timely discover potential safety hazards. The temperature processor 5 is fixedly connected to the temperature-sensing optical cable 6 and is used to obtain the temperature data collected by the temperature-sensing optical fiber 8, so as to analyze and process it, providing data support for the operation of the fuel cell 1.

[0059] It can be understood that by continuously monitoring the temperature changes inside the fuel cell 1 through the temperature-sensing optical fiber 8 and transmitting them to the temperature processor 5 for data processing, the specific temperature value inside the fuel cell 1 can be accurately obtained, providing accurate temperature data for the health management of the fuel cell 1, ensuring that the fuel cell 1 operates within a safe and efficient working range, making the device have good energy efficiency improvement effects, excellent temperature control performance and stability, being able to effectively recover and utilize the waste heat of the fuel cell 1 in various application scenarios, and providing accurate temperature data inside the fuel cell 1.

[0060] Refer to Figures 4-5As shown, in some embodiments of the present application, the temperature processor 5 sets up a temperature acquisition system, which includes: a data acquisition unit, a temperature judgment unit, a temperature prediction unit, and a temperature processing unit; the data acquisition unit is configured to acquire the temperature data of the temperature sensing optical fiber 8 and preprocess it to obtain an initial temperature value; the temperature judgment unit is configured to compare the initial temperature value with historical data, and based on the comparison result, judge whether to correct the initial temperature value. When it is determined to correct the initial temperature value, a temperature data set is determined through a clustering algorithm, and the initial temperature value is corrected according to the temperature data set to obtain a corrected temperature value; the temperature prediction unit is configured to establish a random forest model based on the historical temperature value data and obtain a temperature prediction value according to the initial temperature value; the temperature processing unit is configured to compare the corrected temperature value with the temperature prediction value, establish a temperature compensation model according to the comparison result, obtain a temperature compensation value according to the temperature compensation model, determine a temperature optimization coefficient according to the temperature compensation value, and optimize the corrected temperature value according to the temperature optimization coefficient to obtain a target temperature value, where the target temperature value is the product value of the corrected temperature value and the temperature optimization coefficient.

[0061] Specifically, the initial temperature value is obtained through the preprocessing of temperature data, which improves the accuracy of obtaining the initial temperature value. The preprocessing includes data cleaning and standardization processing. Data cleaning removes the noise of temperature data and eliminates data redundancy, and standardization processing unifies the format of temperature data, so that the format of the initial temperature value remains unified, laying a data foundation for subsequent analysis. The temperature judgment unit compares the initial temperature value with historical data, and uses a clustering algorithm to determine the temperature data set and make corrections, effectively solving the problem of deviation in obtaining the internal temperature caused by accidental errors or environmental fluctuations of the temperature sensing optical fiber 8. The temperature prediction unit predicts the temperature prediction value by establishing a random forest model and combining historical temperature value data, providing a reference benchmark for obtaining an accurate temperature value. The temperature processing unit establishes a temperature compensation model and calculates the temperature compensation value according to the comparison result of the corrected temperature value and the temperature prediction value, thereby determining the temperature optimization coefficient. Through the dynamic temperature compensation mechanism, the system can adjust the deviation of the corrected temperature value in real time, ensuring the accuracy of obtaining the target temperature value.

[0062] It can be understood that the introduction of the temperature optimization coefficient improves the accuracy of the target temperature value. Through the clustering algorithm and random forest model in the temperature acquisition system, the system can flexibly adjust the temperature correction strategy according to different working environments and historical data, has good adaptability, can cope with the temperature changes inside the fuel cell 1, and thus obtains an accurate target temperature value.

[0063] In some embodiments of the present application, when comparing the initial temperature value with historical data and determining whether to correct the initial temperature value based on the comparison result, it includes: the historical data includes the minimum value of historical initial temperature data, the average value of historical initial temperature data, historical initial temperature correction data, and historical correction factors, and the historical initial temperature correction data and historical correction factors correspond one by one; when the initial temperature value is greater than or equal to the minimum value of historical initial temperature data and greater than or equal to the average value of historical initial temperature data, it is determined not to correct the initial temperature value, and the initial temperature value is determined as the target temperature value; when the initial temperature value is less than the minimum value of historical initial temperature data, it is determined to correct the initial temperature value.

[0064] It can be understood that using the average value of historical initial temperature data and the minimum value of historical initial temperature data as the judgment reference standard can reflect the deviation between the initial temperature value and historical data. When the initial temperature value is less than the minimum value of historical initial temperature data, it indicates that it has deviated from the normal historical range and an extreme situation has occurred. Dynamic correction reduces the interference and error of human judgment, enhances the adaptability of the system to different initial temperature values, and improves the adaptability and accuracy of the system.

[0065] In some embodiments of the present application, when determining the temperature data set through the clustering algorithm, it includes: using the initial temperature value to be corrected and historical data as the data set to be aggregated, extracting the historical correction factor corresponding to each data in the data set to be aggregated, determining the expected number of clusters k as 3, and initializing the parameters of the Gaussian distribution; calculating the probability that each data in the data set to be aggregated belongs to each Gaussian distribution to obtain the responsibility value, obtaining the correction data set corresponding to the initial temperature value to be corrected according to the responsibility value, and using the correction data set as the temperature data set.

[0066] In some embodiments of the present application, when correcting the initial temperature value based on the temperature data set to obtain the corrected temperature value, it includes: determining the correction factor of the initial temperature value to be corrected according to the average value of the historical correction factors in the temperature data set; the corrected temperature value is the product of the initial temperature value to be corrected and the correction factor.

[0067] It can be understood that by analyzing historical data through the clustering algorithm, the correction data set closest to the initial temperature value to be corrected is found, which improves the determination accuracy of the correction factor. Determining the average value of historical correction factors as the correction factor of the initial temperature value to be corrected ensures that the correction process conforms to the historical range, and the correction factor is obtained by combining historical multivariate data, reflecting the comprehensiveness of the obtained correction factor. The dynamic correction mechanism ensures that under different initial temperature values to be corrected, the correction factor can be adaptively found and the initial temperature value to be corrected can be corrected, reducing the dependence on human experience and judgment, reducing human judgment error and accidental error of the temperature sensing optical fiber 8, and improving the automation level and reliability of the system.

[0068] In some embodiments of the present application, when establishing a random forest model based on historical temperature value data and obtaining a temperature prediction value according to an initial temperature value, the following steps are included: dividing the historical temperature value data into a temperature training set and a temperature test set, using cross-validation combined with grid search to find the model establishment parameters of the random forest model, and establishing the random forest model; substituting the temperature training set into the random forest model to fit the random forest model, substituting the temperature test set into the fitted random forest model and obtaining the prediction accuracy rate of the temperature prediction value; when the prediction accuracy rate reaches a preset accuracy rate threshold, obtaining the temperature prediction value at the current moment according to the initial temperature value.

[0069] It can be understood that the historical temperature value data is divided into a temperature training set and a temperature test set, and 60% - 90% of the data is used as the temperature training set, and the rest is used as the temperature test set. This ensures that the temperature training set and the temperature test set cover various historical temperature value situations, thereby improving the generalization ability of the random forest model. The training through cross-validation and grid search ensures obtaining the appropriate parameters of the random forest model and the balance during the prediction process. Fitting the random forest model with the temperature training set improves the accuracy and stability of the random forest model's prediction. Substituting the temperature test set into the already trained random forest model and calculating the prediction accuracy rate of the random forest model, the prediction accuracy rate reflects the performance of the random forest model on unknown data and is a reference benchmark for evaluating the performance of the random forest model. After the random forest model reaches the preset accuracy rate threshold, the initial temperature value is substituted into the random forest model, thereby obtaining the temperature prediction value at the current moment.

[0070] In some embodiments of the present application, when comparing the corrected temperature value with the temperature prediction value and establishing a temperature compensation model according to the comparison result, the following steps are included: when the corrected temperature value is less than or equal to 1.5 times the temperature prediction value, it is determined that the corrected temperature value is not optimized, and the corrected temperature value is determined as the target temperature value; when the corrected temperature value is greater than 1.5 times the temperature prediction value, it is determined that the corrected temperature value is optimized and a temperature compensation model is established.

[0071] It can be understood that the temperature prediction value at the current moment is obtained through the random forest model and compared with the corrected temperature value, avoiding the situation of deviation of the corrected temperature value. When the corrected temperature value is greater than 1.5 times the temperature prediction value, it indicates that the correction degree of the initial temperature value is too large and there is a deviation from the temperature prediction value, and the corrected temperature value needs to be optimized. After correcting and optimizing the initial temperature value, the accuracy of the corrected temperature value is verified, ensuring the accuracy of obtaining the target temperature value.

[0072] In some embodiments of the present application, when determining to optimize the corrected temperature value and establish a temperature compensation model, it includes: statistically analyzing the historical corrected temperature value data and historical temperature prediction value data for optimizing all historical corrected temperature values, and the historical corrected temperature value data and historical temperature prediction value data correspond one by one; the temperature compensation model adopts a linear regression model, and the linear regression model is established by the following formula:

[0073] ;

[0074] Wherein, represents any item of historical corrected temperature value data, represents historical temperature prediction value data, represents the temperature compensation value, represents the intercept of the linear regression model.

[0075] In some embodiments of the present application, when obtaining the temperature compensation value according to the temperature compensation model, it includes: substituting all historical corrected temperature value data and all historical temperature prediction value data into the linear regression model one by one and performing difference calculation to eliminate the intercept of the linear regression model and obtain the temperature compensation value T.

[0076] It can be understood that statistically analyzing all historical corrected temperature value data and corresponding historical temperature prediction value data to be optimized for historical corrected temperature values, thereby establishing a linear regression model, reflects the comprehensiveness in the optimization process. The linear regression model can accurately reflect the relationship between historical corrected temperature value data and historical temperature prediction value data. By substituting all historical corrected temperature values and historical temperature prediction value data into the calculation one by one, the temperature compensation value is obtained, thereby eliminating the deviation of the corrected temperature value and improving the accuracy of the target temperature value.

[0077] In some embodiments of the present application, when determining the temperature optimization coefficient according to the temperature compensation value, it includes: presetting a first preset optimization coefficient, a second preset optimization coefficient, and a third preset optimization coefficient; when T≤2, then use the first preset optimization coefficient as the temperature optimization coefficient of the corrected temperature value; when 2<T≤4, then use the second preset optimization coefficient as the temperature optimization coefficient of the corrected temperature value; when 4<T, then use the third preset optimization coefficient as the temperature optimization coefficient of the corrected temperature value.

[0078] It can be understood that the first preset optimization coefficient is preferably 0.9, the second preset optimization coefficient is preferably 0.5, and the third preset optimization coefficient is preferably 0.3. Selecting the corresponding preset optimization coefficient according to the temperature compensation value can further achieve dynamic optimization of the corrected temperature value, ensure the accuracy of the optimization, and further ensure the accuracy of the target temperature value.

[0079] In summary, the beneficial effects of the present invention are as follows: Compared with the prior art, the beneficial effects of the present invention are as follows: By wrapping the fuel cell with a heat exchanger and converting the waste heat into electrical energy for transmission to the storage battery, the utilization rate of the waste heat energy of the fuel cell is improved, and the efficient utilization of energy is realized. The temperature sensing optical cable is arranged in a U shape inside the fuel cell, and then the distributed temperature sensing optical cable is connected to the temperature processor to form a comprehensive optical fiber monitoring network, which improves the efficiency of the temperature sensing optical cable in monitoring temperature and real-time monitors the internal temperature of the fuel cell. It has the characteristics of being distributed and having a comprehensive coverage range, realizes the all-round monitoring of the inside of the fuel cell, and improves the accuracy and reliability of obtaining the internal temperature of the fuel cell in a high-temperature environment. The temperature processor analyzes the collected temperature data to accurately obtain the actual temperature value inside the fuel cell, realizing the automation and intelligence of the temperature monitoring of the fuel cell.

[0080] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0082] These computer program instructions can also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable storage medium generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0083] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 in a block or a plurality of blocks.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A fuel cell waste heat recycling device, characterized in that: include: Fuel cells, batteries, heat exchangers, temperature sensing optical cables, high temperature cables and temperature processors; The heat exchanger is wound around the fuel cell and fixedly connected to the fuel cell, one end of the high-temperature cable is fixedly connected to the heat exchanger, and the other end of the high-temperature cable is fixedly connected to the battery. The high-temperature cable is used to transmit electric energy of the heat exchanger, recover waste heat generated by the fuel cell through the heat exchanger, transfer the heat to the thermoelectric material inside the heat exchanger, utilize the temperature difference between the thermoelectric materials to produce the Seebeck effect to generate electric energy, and transmit the electric energy to the battery through the high-temperature cable, and the battery is used to store the electric energy converted by the heat exchanger; The temperature sensing optical cable is embedded in the fuel cell, the temperature sensing optical cable is arranged in a U shape in the fuel cell, and the temperature sensing optical cable is fixedly connected to the temperature processor; The temperature sensing optical cable comprises a PE sheath, a carbon fiber bundle and a temperature sensing optical fiber; The PE sheath is sheathed with the carbon fiber bundle, and the carbon fiber bundle is sheathed with the temperature sensing optical fiber; The temperature processor is used to obtain temperature data of the temperature sensing optical fiber; The temperature processor is provided with a temperature acquisition system, and the temperature acquisition system comprises: Data acquisition unit, temperature judgment unit, temperature prediction unit and temperature processing unit; The data acquisition unit is configured to acquire temperature data of the temperature sensing optical fiber and pre-process and obtain an initial temperature value; The temperature judgment unit is configured to compare the initial temperature value with the historical data, and judge whether to correct the initial temperature value based on the comparison result, and when it is judged that the initial temperature value is to be corrected, determine the temperature data set by a clustering algorithm, and correct the initial temperature value according to the temperature data set to obtain a corrected temperature value; The temperature prediction unit is configured to establish a random forest model according to the historical temperature value data and obtain a temperature prediction value according to the initial temperature value; The temperature processing unit is configured to compare the corrected temperature value with the temperature prediction value, establish a temperature compensation model according to the comparison result, obtain a temperature compensation value according to the temperature compensation model, determine a temperature optimization coefficient according to the temperature compensation value, optimize the corrected temperature value according to the temperature optimization coefficient to obtain a target temperature value, and the target temperature value is the product of the corrected temperature value and the temperature optimization coefficient.

2. The fuel cell waste heat recycling device according to claim 1, characterized in that: When comparing the initial temperature value with the historical data and determining whether to correct the initial temperature value based on the comparison result, the method includes: The historical data includes a minimum value of historical initial temperature data, an average value of historical initial temperature data, historical initial temperature correction data and a historical correction factor, and the historical initial temperature correction data and the historical correction factor correspond to each other one by one; When the initial temperature value is greater than or equal to the minimum value of the historical initial temperature data and greater than or equal to the average value of the historical initial temperature data, it is determined that the initial temperature value is not to be corrected, and the initial temperature value is determined as the target temperature value; When the initial temperature value is less than the minimum value of the historical initial temperature data, it is determined that the initial temperature value is to be corrected.

3. The fuel cell waste heat recycling device according to claim 2, characterized in that: When determining the temperature data set through the clustering algorithm, including: The initial temperature value to be corrected and the historical data are used as the data set to be aggregated, and the historical correction factor corresponding to each data in the data set to be aggregated is extracted, the expected number of clusters k is determined to be 3, and the parameters of the Gaussian distribution are initialized; The probability that each data in the data set to be aggregated belongs to each Gaussian distribution is calculated to obtain a responsibility value, and a corrected data set corresponding to the initial temperature value to be corrected is obtained according to the responsibility value, and the corrected data set is used as the temperature data set.

4. The fuel cell waste heat recycling device according to claim 3, characterized in that: When the initial temperature value is corrected according to the temperature data set to obtain a corrected temperature value, the method includes: Determining, according to the average of the historical correction factors in the temperature data set, a correction factor for the initial temperature value to be corrected; The corrected temperature value is the product of the initial temperature value to be corrected and the correction factor.

5. The fuel cell waste heat recycling device according to claim 4, characterized in that: When a random forest model is established according to historical temperature value data and a temperature prediction value is obtained according to the initial temperature value, it includes: The historical temperature value data is divided into a temperature training set and a temperature test set, and a model establishment parameter of a random forest model is found by cross validation combined with a grid search to establish a random forest model; Substituting the temperature training set into the random forest model to fit the random forest model, substituting the temperature test set into the fitted random forest model to obtain the prediction accuracy of the temperature prediction value; When the prediction accuracy reaches a preset accuracy threshold, a temperature prediction value at the current moment is obtained according to the initial temperature value.

6. The fuel cell waste heat recycling device according to claim 5, characterized in that: When the corrected temperature value is compared with the predicted temperature value and a temperature compensation model is established according to the comparison result, the method includes: When the corrected temperature value is less than or equal to 1.5 times of the predicted temperature value, it is determined that the corrected temperature value is not to be optimized, and the corrected temperature value is determined as the target temperature value; When the corrected temperature value is greater than 1.5 times the predicted temperature value, it is determined that the corrected temperature value is to be optimized and a temperature compensation model is to be established.

7. The fuel cell waste heat recycling device according to claim 6, characterized in that: When determining to optimize the corrected temperature value and establish a temperature compensation model, it includes: Counting historical corrected temperature value data and historical temperature prediction value data optimized for all historical corrected temperature values, wherein the historical corrected temperature value data and the historical temperature prediction value data correspond to each other one by one; The temperature compensation model adopts a linear regression model, which is established by the following formula: ； Among them, T 1i Indicates any historical corrected temperature value data, T 2i represents the historical temperature prediction value data, a represents the temperature compensation value, and b represents the intercept of the linear regression model.

8. The fuel cell waste heat recycling device according to claim 7, characterized in that: When the temperature compensation value is obtained according to the temperature compensation model, it includes: All historical corrected temperature value data and all historical temperature prediction value data are substituted into the linear regression model one by one and difference calculation is performed to eliminate the intercept of the linear regression model and obtain the temperature compensation value T.

9. The fuel cell waste heat recycling device according to claim 8, characterized in that: When determining the temperature optimization coefficient according to the temperature compensation value, it includes: Presetting a first preset optimization coefficient, a second preset optimization coefficient, and a third preset optimization coefficient; When T≤2, the first preset optimization coefficient is used as the temperature optimization coefficient of the corrected temperature value; When 2<T≤4, the second preset optimization coefficient is used as the temperature optimization coefficient of the corrected temperature value; When 4<T, the third preset optimization coefficient is used as the temperature optimization coefficient of the corrected temperature value.

Images