Method for predicting ambient temperature of aircraft platform

Abstract

The present invention provides a method for predicting the ambient temperature of an aircraft platform, which comprises the following specific steps: using a cluster analysis algorithm to divide n groups of temperature response values ​​in the aircraft into m temperature subsets u m , and determine the temperature subset u m S that generates heat exchange m subsets; create each temperature subset u m With adjacent S m The heat balance equation of each temperature subset u is determined based on the heat transfer analysis. m The influencing factors of each item in the corresponding heat balance equation are expressed using the influencing factors of each item to obtain each temperature subset u m Heat transfer model; each temperature subset u m The influencing factors involved in each item in the corresponding heat transfer model are divided into different types, and the optimized heat transfer model is obtained through optimization; the model parameter identification is used to obtain each temperature subset u m The present invention improves the prediction accuracy of the ambient temperature of the aircraft platform by constructing a temperature prediction model that is consistent with the laws of physical changes.

Description

Technical Field

[0001] The present invention relates to the field of aviation engineering, and in particular to a method for predicting the ambient temperature of an aircraft platform. Background Art

[0002] Temperature is the main reason that affects the performance of aviation equipment and induces failures. Environmental factors such as high temperature, low temperature and rapid temperature changes will have various adverse effects on equipment. At the same time, temperature is also a "multiplier" of other environmental effects. For example, the rate of metal corrosion will be accelerated in a high temperature environment. For aircraft, a variety of factors such as aerodynamic heating during flight, radiant heating of the aircraft's outer surface by the sun, and self-heating of internal electronic equipment make the temperature environment of the aircraft platform more severe. Therefore, it is necessary to accurately determine the platform's ambient temperature during the development stage and carry out design and test verification work accordingly, which is an important prerequisite for ensuring aircraft safety and equipment use.

[0003] At present, the most effective way to determine the ambient temperature of an aircraft platform is to conduct actual temperature measurement. However, due to factors such as cost and safety, the sample size of the measured data is relatively small, and it is usually impossible to measure the temperature extremes of the aircraft platform environment. Therefore, the commonly used engineering solution is to establish a heat transfer model between the aircraft state parameters and the platform temperature response based on the existing measured data, and then predict the temperature extremes.

[0004] Since the platform ambient temperature of an aircraft is affected by many factors such as the aircraft's flight altitude, flight speed, internal heat source, and the presence or absence of environmental control, and the degree of influence of each factor varies in different regions, the accuracy of the traditional heat transfer model that only considers temperature changes cannot meet the prediction requirements. It is necessary to establish a corresponding heat transfer model based on the thermal environment characteristics of different regions, so as to achieve accurate prediction of the platform ambient temperature. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a method for predicting the ambient temperature of an aircraft platform. First, according to the distances between the temperature response values ​​of the aircraft, a cluster analysis algorithm is used to divide n groups of temperature response values ​​into m temperature subsets u m , establish each temperature subset u m With adjacent S m The heat balance equation of a heat subset is then calculated, and the heat transfer model is divided into trend change terms and stable terms through heat transfer analysis. Finally, the trend change terms are converted into variables, and the constant terms are extracted and incorporated into the stable terms, so as to construct a temperature prediction model that is consistent with the real physical change law, reduce the prediction error of the traditional model, and improve the prediction accuracy of the model.

[0006] The present invention provides a method for predicting the ambient temperature of an aircraft platform, and the specific implementation steps are as follows:

[0007] S1. Arrange n groups of temperature measuring points in different areas of the target cabin of the aircraft, and measure n groups of temperature response values ​​T1~T after the aircraft performs a mission cycle. n ;

[0008] S2, according to the distances between the temperature response values ​​of the aircraft measured in step S1, using a cluster analysis algorithm, divide the n groups of temperature response values ​​into m temperature subsets u m , the specific expression is:

[0009] U=u1∪u2…∪u m ;

[0010] S3. Determine the temperature subset u obtained in step S2 in the space domain of the aircraft. m S that generates heat exchange m Subsets;

[0011] S4. Establish each temperature subset u of the aircraft m With adjacent S m The heat balance equation of the subset is expressed as follows:

[0012] Q m =Q0+Q E +Q1+Q2+…+Q s

[0013] In the formula, Q m refers to the temperature subset u m The heat increment in the temperature subset u is Q0, which is transferred from the external natural environment to the temperature subset u. m The heat, Q E is the temperature subset u m Heat generated by internal electronic equipment, Q1, Q2, ..., Q s The adjacent S m subsets and temperature subset u m heat exchange;

[0014] S5. According to the heat transfer analysis of the aircraft, determine each temperature subset u m The corresponding heat balance equations are Q0, Q E , Q1, Q2, …, Q s The influencing factors of each item are expressed by using the influencing factors of each item to obtain each temperature subset u m The heat transfer model is expressed as follows:

[0015] Q m =A0(Δt0)+A1(Δt1)+A2(Δt2)+…+A s (Δt s)+C

[0016] In the formula, A s is the heat transfer coefficient, s = 0, 1, ..., m; Δt (s) is the temperature change, s = 0, 1, ..., m; C is a constant;

[0017] S6. According to each temperature subset u m The variation trend of the measured temperature data in the m The corresponding heat transfer model divides the types of influencing factors into stable terms and trend change terms;

[0018] S7. According to the type of influencing factors classified in step S6, the heat transfer model of step S5 is optimized, and the linear correlation coefficient of each item in the heat transfer model equivalent to the temperature change of the target cabin of the aircraft is calculated, and the expression of the optimized heat transfer model is obtained as follows:

[0019] Q m =C0+C1k1(Δt1)+C2(Δt2)+C3k i +…+C s (Δt s );

[0020] In the formula, C s are diffusion coefficients, k i is the measured temperature data, i=1,2,…;

[0021] S8, using the temperature measured data to perform parameter identification on the heat transfer equation in step S7 to obtain a temperature prediction model;

[0022] S9. Input relevant parameters of the aircraft in the mission state into the temperature prediction model to realize the prediction of the aircraft platform ambient temperature.

[0023] Preferably, in step S2, the cluster analysis algorithm takes a certain distance between all temperature response values ​​as a threshold, divides temperature response values ​​less than the threshold into subsets, and divides temperature response values ​​greater than the threshold into different subsets, ensuring that the distance between temperature response values ​​in each subset is less than the threshold, and the distance between each subset is greater than the threshold.

[0024] Preferably, the temperature subset u m The number of is less than or equal to the number of temperature measurement points.

[0025] Preferably, in step S5, in step S5, Q0, Q E , Q1, Q2, …, Q s The influencing factors include the influencing factors of heat conduction and the influencing factors of convection heat transfer.

[0026] Preferably, the Q E The term is represented by the constant C.

[0027] Preferably, in step S6, the stable items are items whose values ​​are stable within one mission cycle, including the length, thickness and volume of the aircraft.

[0028] Preferably, in step S6, the trend change item is an item that changes with a fixed regularity corresponding to changes in one or more parameters of the aircraft, including convection heat transfer coefficient, thermal conductivity coefficient and constant-pressure heat capacity.

[0029] Preferably, the relevant parameters include the altitude during the flight, the Mach number during the flight and the natural ambient temperature.

[0030] Compared with the prior art, the present invention has the following advantages:

[0031] 1. The present invention divides the heat transfer model into trend change terms and stable terms through heat transfer analysis. Considering the changing law of each physical quantity in the trend change term with the flight state, the trend change term is converted into a variable mode; the constant term is extracted and incorporated into the stable term, thereby constructing a temperature prediction model that is more consistent with the real physical change law, reducing the prediction error of the traditional model and improving the prediction accuracy of the model.

[0032] 2. The present invention adopts cluster analysis method to analyze the temperature measured data, classifies the temperature measured data with the same attribute, ensures that the temperature measured data in the same area has the highest similarity, and the temperature measured data in different areas has the lowest similarity, effectively mines the intrinsic attributes of the temperature measured data, and ensures the rationality of the temperature partition. On this basis, the corresponding heat transfer equation is used to fit and regress the temperature measured data of each area, effectively improving the modeling efficiency and model prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1A and Figure 1B They are respectively prediction effect test diagrams of the aircraft in the method for predicting the ambient temperature of the aircraft platform of the present invention;

[0034] Figure 2 is an error distribution diagram of an aircraft in the method for predicting the ambient temperature of an aircraft platform of the present invention;

[0035] Figure 3 The present invention is a flow chart of a method for predicting the ambient temperature of an aircraft platform. DETAILED DESCRIPTION

[0036] In order to fully describe the technical content, objectives and effects of the present invention, the following will be described in detail with reference to the accompanying drawings.

[0037] The method used to predict the ambient temperature of the aircraft platform is implemented as follows: Figure 3 As shown:

[0038] S1. Arrange n groups of temperature measuring points in different areas of the target cabin of the aircraft, and measure n groups of temperature response values ​​after the aircraft performs a mission cycle, i.e., T1~T n .

[0039] S2, according to the distances between the temperature response values ​​of the aircraft measured in step S1, using a cluster analysis algorithm, divide the n groups of temperature response values ​​into m temperature subsets u m , the temperature subset u m The number is less than or equal to the number of temperature measurement points. The specific expression is:

[0040] U=u1∪u2…∪u m

[0041] Specifically, the cluster analysis algorithm refers to the analysis process of grouping objects into multiple classes composed of similar objects, which belongs to unsupervised learning. Further, in a preferred embodiment of the present invention, a certain distance between all temperature response values ​​is used as a threshold, and temperature response values ​​less than the threshold are divided into subsets, and temperature response values ​​greater than the threshold are divided into different subsets, ensuring that the distance between temperature response values ​​in each subset is less than the threshold, and the distance between each subset is greater than the threshold.

[0042] S3. Determine the temperature subset u obtained in step S2 in the space domain of the aircraft. m S that generates heat exchange m A subset of collections.

[0043] S4. Establish each temperature subset u of the aircraft m With adjacent S m The heat balance equation of the subset is expressed as follows:

[0044] Q m =Q0+Q E +Q1+Q2+…+Q s

[0045] In the formula, Q m refers to the temperature subset u m The heat increment in the temperature subset u is Q0, which is transferred from the external natural environment to the temperature subset u. m The heat, Q E is the temperature subset u m Heat generated by internal electronic equipment, Q1, Q2, ..., Q s The adjacent S m subsets and temperature subset um heat exchange.

[0046] Specifically, the heat balance equation refers to the transfer of heat between two or more systems with different temperatures until the temperatures of the systems are equal.

[0047] S5. According to the heat transfer analysis of the aircraft, determine each temperature subset u m The corresponding heat balance equations are Q0, Q E , Q1, Q2, …, Q s The influencing factors of each item are used to express it, and each temperature subset u is obtained m The heat transfer model is expressed as follows:

[0048] Q m =A0(Δt0)+A1(Δt1)+A2(Δt2)+…+A s (Δt s )+C

[0049] In the formula, A s is the heat transfer coefficient, s = 0, 1, ..., m; Δt (s) is the temperature change, s = 0, 1, …, m, and C is a constant.

[0050] Specifically, each item is expressed by the influencing factors, including the forms of heat conduction and convection heat transfer. E The term is represented by the constant C.

[0051] S6. According to each temperature subset u m The variation trend of the measured temperature data in the m The influencing factors involved in each item in the corresponding heat transfer model are divided into different types, including stable items and trend change items.

[0052] Furthermore, stable items are items whose values ​​are stable within a mission cycle, including the length, thickness and volume of the aircraft. Trend change items are items that change with a fixed regularity as one or more parameters of the aircraft change, including convection heat transfer coefficient, thermal conductivity coefficient and constant pressure heat capacity.

[0053] S7. According to the type of influencing factors classified in step S6, the heat transfer model of step S5 is optimized, the linear correlation coefficient of each item in the heat transfer model equivalent to the temperature change of the target cabin of the aircraft is calculated, and the items with linear correlation coefficients less than 0.7 are eliminated, and the expression of the optimized heat transfer model is obtained as follows:

[0054] Q m =C0+C1k1(Δt1)+C2(Δt2)+C3k i +…+Cs (Δt s );

[0055] In the formula, C s are diffusion coefficients, k i , i=1,2,…, are the measured temperature data.

[0056] S8, using the temperature measured data to perform parameter identification on the heat transfer equation in step S7 to obtain a temperature prediction model;

[0057] S9. Input relevant parameters of the aircraft in the mission state into the temperature prediction model to realize temperature prediction.

[0058] In a preferred embodiment of the present invention, the relevant parameters include the altitude during the flight, the Mach number during the flight, and the natural environment temperature. Model parameter identification refers to determining the various unknowns in the heat transfer model based on the temperature measured data by using methods such as multiple regression.

[0059] The following is a further description of a method for predicting the ambient temperature of an aircraft platform according to the present invention in conjunction with an embodiment:

[0060] S1. Arrange 30 sets of temperature measuring points in different areas of the aircraft target cabin, and measure 30 sets of temperature response values ​​after the aircraft performs a mission cycle, i.e., T1~T 30 .

[0061] S2. Based on the distances between the temperature response values ​​of the aircraft measured in step S1, the cluster analysis algorithm is used to divide the 30 groups of temperature response values ​​into 8 temperature subsets, where the cohesion of the measured data in each set is the highest and the separation between different sets is the largest, thereby realizing the partitioning of the temperature environment of the aircraft. The partitioning results are shown in Table 1.

[0062] Table 1 Aircraft temperature environment zoning results

[0063] Serial number Temperature zone compartment number Partition point collection 1 Section 1 <![CDATA[u1={T1}]]> 2 Section 2 <![CDATA[u2={T2,T3}]]> 3 Section 3 <![CDATA[u3={T4,T5,T6}]]> 4 Section 4 <![CDATA[u4={T7,T8}]]> 5 Section 5 <![CDATA[u5={T9,T 10 ,T 11 ,T 12 ,T 13 ,T 14 ,T 15 ,T 16 ,T 17 ,T 18 }]]> 6 Section 6 <![CDATA[u6={T 19 ,T 20 ,T 21 ,T 22 ,T 23 ,T 24 }]]> 7 Section 7 <![CDATA[u7={T 25 ,T 26 ,T 28 }]]> 8 Section 8 <![CDATA[u8={T 27 ,T 30 }]]>

[0064] S3. In the space domain of the aircraft, determine the temperature partitions adjacent to the temperature subsets u1 to u8 obtained in step S2, and obtain S8 subsets of heat exchange. The specific division results are shown in Table 2.

[0065] Table 2 Adjacent region set

[0066]

[0067]

[0068] S4. Establish heat balance equations for the temperature subsets u1 to u8 of the aircraft and the adjacent heat subsets S1 to S8. Taking u2 as an example, its heat flow balance equation is as follows:

[0069] Q2=Q0+Q1+Q3+Q E

[0070] Where Q2 is the heat change of u2, Q0 is the heat transferred from the external natural environment (including aerodynamic heating) to u2, Q1 is the heat transferred from u1 to u2, Q3 is the heat transferred from u3 to u2, Q E The heat generated by the electronic devices inside the u1.

[0071] S5. According to the heat transfer analysis of the aircraft, determine the various terms Q0, Q E , Q1, Q2 and Q3, and use the influencing factors of each item to express the heat transfer model of the temperature subset u2. The specific expression is:

[0072] A2ΔT2=A0(T r -T1)+A1(T1-T2)+A3(T3-T2)+C

[0073] Where A2 is the comprehensive heat transfer coefficient of area u2, A2 = F(T2, V), V is the volume of area u2; A0 is the heat transfer coefficient between the aircraft surface recovery temperature and area u2, A0 = F(h1, h2, λ, δ), h1, h2 are the heat transfer coefficients between the inner and outer surfaces of area u2 and the air, λ is the thermal conductivity, δ is the skin thickness, T r is the skin surface recovery temperature, T r =F(H,Ma,T0), T0 is the natural environment temperature outside the aircraft; A1 is the heat transfer coefficient between area u1 and area u2, A1 = F(T2,V 21 ,h u1 ,h u2 ,λ 21 ,δ 21 ), V 21 is the volume of air exchanged between area u2 and area u1, h u1 is the convection heat transfer coefficient between the u1 side wall plate and the air, h u2 is the convection heat transfer coefficient between the u2 side wall plate and the air, λ 21 is the thermal conductivity of the wall between region u2 and region u1, δ 21 is the thickness of the wall between area u2 and area u1; A3 is the heat transfer coefficient between area u3 and area u2, A3=F(T2,V 23 ,h u3 ,h u2 ,λ 23 ,δ23 ); C is a constant, representing the constant heating power of the electronic equipment.

[0074] S6. According to the change trend of the measured temperature data in the temperature subset u2, the influencing factors involved in each item in the heat transfer model corresponding to each temperature subset u2 are divided into different types, including stable items and trend change items. The specific operation steps are as follows:

[0075] Stable terms are generally physical parameters or parameters that are not affected much by temperature, including δ in A0 and V in A1. 21 ,λ 21 ,δ 21 , V in A2, V in A3 23 ,λ 23 ,δ 23 And C, etc.

[0076] Trend change items, parameters that are greatly affected by temperature or change with the aircraft's flight status, including h1, h2, λ in A0, h in A1 u1 ,h u2 , h in A3 u3 ,h u2 In addition, T r , T1, T2 and T3 are also variables, but they can be obtained through measured data or calculation.

[0077] S7. According to the type of influencing factors classified in step S6, the heat transfer model of step S5 is optimized, the trend change term is decomposed, and then merged with the stable term, the linear correlation coefficient of each term in the heat transfer model equivalent to the temperature change of the target cabin of the aircraft is calculated, and the terms with linear correlation coefficients less than 0.7 are eliminated, and the heat transfer model expression after optimization in the u2 region is obtained as follows:

[0078] k2ΔT2=C0+C1k1(T r (t)-T2(t))+C2(T1(t)-T2(t))+C3(T3(t)-T2(t))+C4k-C5ΔT2

[0079] Where, C0~C5 are the combined stable terms and can be approximately regarded as constants; k1=F(T2), k2=F(h,λ), which can be calculated from the measured data.

[0080] S8. Use the temperature measured data to perform parameter identification on the heat transfer equation in step S7, obtain the temperature prediction model, and obtain the diffusion term coefficients C0 to C5 of the heat transfer model. After calculation, the values ​​of C0 to C5 are shown in Table 3.

[0081] Table 3 Model parameter calculation results

[0082] parameter <![CDATA[C0]]> <![CDATA[C1]]> <![CDATA[C2]]> <![CDATA[C3]]> <![CDATA[C4]]> <![CDATA[C5]]> Quantity -0.0011 0.013 6.99e-05 3.35e-04 0.0038 -0.0030

[0083] Through the above calculations, the expression of the temperature prediction model of the temperature subset u2 in the aircraft can be obtained, and the accuracy of the temperature prediction model is verified.

[0084] T2 (n+1) (t) = (-0.0011 + (0.013k1 (T r (n) (t)-T2 (n) (t))+(6.99e-05)(T1 (n) (t)-T2 (n) (t))

[0085] +(3.35e-04)(T3 (n) (t)-T2 (n) (t))+0.0038k1+(-0.0030+k2)T2 (n) (t)) / (-0.0030+k2)

[0086] In the formula, the superscripts n and n+1 represent the nth moment and n+1th moment respectively.

[0087] S9. Input the relevant parameters of the aircraft in the mission state into the temperature prediction model to achieve temperature prediction. Use the temperature measured data that are not involved in the modeling as a test sample to verify the accuracy of the heat transfer model. Take a flight of the target cabin of the aircraft as an example. The temperature environment prediction error at each time from takeoff to landing is as follows: Figure 1A and Figure 1B As shown. During the entire flight process, this method is applied to establish a temperature prediction model, and the heat transfer model is divided into a trend change term and a stable term. Considering the change law of each physical quantity in the trend change term with the flight state, the trend change term is converted into a variable pattern; the constant term is extracted and incorporated into the stable term, so as to construct a temperature prediction model that is more consistent with the actual physical change law. The maximum prediction error is only 1.7°C, and the prediction curve is highly consistent with the actual data change. It effectively mines the intrinsic properties of the measured temperature data, ensures the rationality of the temperature zoning, eliminates the problem of prediction lag in traditional work, and makes the prediction close to the actual service environment, which greatly improves the accuracy of temperature environment prediction. The absolute error of the prediction of nearly 150,000 sample data is statistically analyzed, as shown in Figure 2 As shown in the error distribution diagram, it can be seen that the prediction accuracy of the heat transfer model of the present invention meets the actual requirements and effectively improves the modeling efficiency and model prediction accuracy.

[0088] The embodiments described above are only descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for predicting the ambient temperature of an aircraft platform, characterized in that: The specific implementation steps are as follows: S1. Arrange n groups of temperature measuring points in different areas of the target cabin of the aircraft, and measure n groups of temperature response values ​​T1~T after the aircraft performs a mission cycle. n ; S2, according to the distances between the temperature response values ​​of the aircraft measured in step S1, using a cluster analysis algorithm, divide the n groups of temperature response values ​​into m temperature subsets u m , the specific expression is: U=u1∪u2…∪u m ; S3. Determine the temperature subset u obtained in step S2 in the space domain of the aircraft. m S that generates heat exchange m Subsets; S4. Establish each temperature subset u of the aircraft m With adjacent S m The heat balance equation of the subset is expressed as follows: Q m =Q0+Q E +Q1+Q2+…+Q s In the formula, Q m refers to the temperature subset u m The heat increment in the temperature subset u is Q0, which is transferred from the external natural environment to the temperature subset u. m The heat, Q E is the temperature subset u m Heat generated by internal electronic equipment, Q1, Q2, ..., Q s The adjacent S m subsets and temperature subset u m heat exchange; S5. According to the heat transfer analysis of the aircraft, determine each temperature subset u m The corresponding heat balance equations are Q0, Q E , Q1, Q2, …, Q s The influencing factors of each item are expressed by using the influencing factors of each item to obtain each temperature subset u m The heat transfer model is expressed as follows: Q m =A0(Δt0)+A1(Δt1)+A2(Δt2)+…+A s (Δt s )+C In the formula, A s is the heat transfer coefficient, s = 0, 1, ..., m; Δt s is the temperature change, s = 0, 1, ..., m; C is a constant; S6. According to each temperature subset u m The variation trend of the measured temperature data in the m The corresponding heat transfer model divides the types of influencing factors into stable terms and trend change terms; S7. According to the type of influencing factors classified in step S6, the heat transfer model of step S5 is optimized, and the linear correlation coefficient of each item in the heat transfer model equivalent to the temperature change of the target cabin of the aircraft is calculated, and the expression of the optimized heat transfer model is obtained as follows: Q m =C0+C1k1(Δt1)+C2(Δt2)+C3k i +…+C s (Δt s ) In the formula, C s are diffusion coefficients, k i is the measured temperature data, i=1,2,…; S8, using the temperature measured data to perform parameter identification on the heat transfer equation in step S7 to obtain a temperature prediction model; S9. Input relevant parameters of the aircraft in the mission state into the temperature prediction model to realize the prediction of the aircraft platform ambient temperature.

2. The method for predicting the ambient temperature of an aircraft platform according to claim 1, characterized in that: In step S2, the cluster analysis algorithm takes a certain distance between all temperature response values ​​as a threshold, divides temperature response values ​​less than the threshold into subsets, and divides temperature response values ​​greater than the threshold into different subsets, ensuring that the distance between temperature response values ​​in each subset is less than the threshold, and the distance between each subset is greater than the threshold.

3. The method for predicting the ambient temperature of an aircraft platform according to claim 1 or 2, characterized in that: The temperature subset u m The number of is less than or equal to the number of temperature measurement points.

4. The method for predicting the ambient temperature of an aircraft platform according to claim 1, characterized in that: In step S5, Q0, Q E , Q1, Q2, …, Q s The influencing factors include the influencing factors of heat conduction and the influencing factors of convection heat transfer.

5. The method for predicting the ambient temperature of an aircraft platform according to claim 1 or 4, characterized in that: The Q E The term is represented by the constant C.

6. The method for predicting the ambient temperature of an aircraft platform according to claim 1, characterized in that: In step S6 , the stable items are items whose values ​​are stable within a mission cycle, including the length, thickness and volume of the aircraft.

7. The method for predicting the ambient temperature of an aircraft platform according to claim 1 or 6, characterized in that: In step S6, the trend change item is an item that changes with a fixed regularity corresponding to changes in one or more parameters of the aircraft, and includes a convective heat transfer coefficient, a heat conduction coefficient, and a constant-pressure heat capacity.

8. The method for predicting the ambient temperature of an aircraft platform according to claim 1, characterized in that: The relevant parameters include the altitude during the flight, the Mach number during the flight, and the natural environment temperature.

Images