A method, device and equipment for constructing an EGTM degradation model

Abstract

The application provides a method, device and equipment for constructing an EGTM degradation model. The method comprises: obtaining EGTM time series data in an interval between two adjacent water washes; determining the frequency of EGTM in different temperature intervals in the water wash interval according to the EGTM time series data, taking the temperature interval as the division basis; determining the cumulative probability distribution diagram of EGTM in the water wash interval according to the frequency of EGTM; dividing the cumulative probability distribution diagram of EGTM according to a probability threshold, and constructing the EGTM degradation model of the engine in the water wash interval according to the division result. The EGTM degradation model constructed by the method can accurately judge the degradation law of the engine after water washing.

Description

Technical Field

[0001] This invention relates to the field of information processing technology, and in particular to a method, apparatus and equipment for constructing an EGTM decay model. Background Technology

[0002] The exhaust gas temperature margin (EGTM) at full power during takeoff is a crucial parameter characterizing engine performance and a significant indicator of remaining engine life on the wing. EGTM refers to the difference between the exhaust gas temperature margin (EGT) at full power and the exhaust gas temperature red line (EGTRedline) in the engine manual. As engine service time increases, the exhaust gas temperature (EGT) gradually rises, leading to a decrease in EGTM. A smaller EGTM results in a decline in various engine performance indicators, such as increased fuel consumption and failure rate, higher aircraft operating costs, and reduced safety. To restore EGTM, airlines use a water-washing method to improve engine performance. Water washing involves cleaning the engine's air passages, removing deposits from the compressor blades, thereby restoring thrust and EGTM, reducing fuel consumption, preventing blade pitting, and extending engine life on the wing.

[0003] Therefore, a well-planned water washing maintenance program can maximize engine lifespan while maintaining low operating costs. However, a prerequisite for a well-planned water washing maintenance program is a thorough understanding of the engine's recovery effect after water washing and its subsequent degradation patterns. The appropriate EGTM (engine aging process time) after water washing should be determined based on these factors.

[0004] Currently, airlines directly judge the recovery effect and degradation pattern of the engine based on the original EGTM sequence of the engine after water washing. However, due to a series of factors such as the influence of the external environment, different engine operating conditions, deviations in the EEC control law, different pilot operation methods, and sensor monitoring errors, the time series data of the EGTM after water washing has a large nonlinear disturbance, which affects the accurate judgment of the degradation pattern of the engine after water washing. Summary of the Invention

[0005] This invention provides a method, apparatus, and equipment for constructing an EGTM degradation model, which addresses the shortcomings of existing technologies where airlines directly determine the degradation pattern of engines based on the original EGTM sequence after water washing, and enables accurate determination of the degradation pattern of engines after water washing.

[0006] This invention provides a method for constructing an EGTM decay model, comprising: Acquire EGTM time-series data within the interval between two adjacent water washing cycles; Based on the temperature interval, the frequency of EGTM occurrence in different temperature intervals within the washing interval is determined according to the EGTM time series data. The cumulative probability distribution of EGTM within a washing interval is determined based on the frequency of EGTM occurrence in different temperature intervals. The cumulative probability distribution map of the EGTM is divided according to the probability threshold, and the EGTM decay model of the engine within the water washing interval is constructed based on the division results.

[0007] According to a method for constructing an EGTM decay model provided by the present invention, the step of dividing the cumulative probability distribution map of the EGTM according to a probability threshold and constructing the EGTM decay model of the engine within the water washing interval based on the division result includes: Set the EGTM value when the cumulative probability equals the probability threshold θ as the minimum decline value, and set the EGTM value when the cumulative probability equals 1-θ as the maximum recovery value; The EGTM within the range corresponding to the minimum decay value is defined as the decay zone of the engine; The EGTM within the range that is greater than or equal to the minimum decay value and less than or equal to the maximum recovery value is defined as the fluctuation zone of the engine. The EGTM within the range corresponding to the maximum recovery value is defined as the engine's recovery zone; Based on the engine's degradation zone, fluctuation zone, and recovery zone, an EGTM degradation model of the engine is constructed within the water washing interval.

[0008] According to a method for constructing an EGTM degradation model provided by the present invention, the step of constructing the EGTM degradation model of the engine within the water washing interval based on the degradation zone, fluctuation zone, and recovery zone of the engine includes: Extract the corresponding modeling points from the decay region, fluctuation region, and recovery region respectively; Based on the modeling points, a linear EGTM decay model of the engine is constructed within the water washing interval.

[0009] According to a method for constructing an EGTM decay model provided by the present invention, the extraction of corresponding modeling points from the decay zone, fluctuation zone, and recovery zone includes: Extract the minimum decay value from the decay region and extract several points corresponding to the maximum recovery value of EGTM from the fluctuation region as modeling points; Using the EGTM before this water wash as the modeling starting point and the modeling point corresponding to the first time the EGTM reaches its maximum recovery value as the modeling ending point, a recovery segment of the linear EGTM decay model is constructed. The fluctuation segment of the linear EGTM decay model is constructed by taking the point corresponding to the first time EGTM reaches its maximum recovery value as the modeling starting point and the point corresponding to the last time EGTM reaches its maximum recovery value as the modeling ending point. Using the point corresponding to the last EGTM reaching the maximum recovery value as the modeling starting point and the extracted minimum decay value as the modeling ending point, the decay segment of the linear EGTM decay model is constructed. A linear EGTM decay model is constructed based on the recovery segment, fluctuation segment, and decay segment.

[0010] A method for constructing an EGTM decay model according to the present invention includes: Acquire EGTM timing data of the engine during the full water washing phase; The EGTM timing data of the full water washing section is divided into several water washing intervals based on the water washing maintenance date. The linear EGTM decay model for the corresponding water washing interval is determined based on the EGTM time series data within each water washing interval. The linear EGTM decay model for the full washing section is determined based on the linear EGTM decay model corresponding to each washing interval.

[0011] According to the method for constructing an EGTM decay model provided by the present invention, the probability threshold θ = 7.5%.

[0012] The present invention also provides an apparatus for constructing an EGTM decay model, comprising: an acquisition unit for acquiring EGTM time-series data within the interval between two adjacent water washings; The acquisition unit is used to acquire EGTM time-series data within the interval between two adjacent water washing cycles; The determination unit is used to determine the frequency of EGTM occurrence in different temperature intervals within the current washing interval based on the EGTM time series data, using temperature intervals as the dividing criteria. The determining unit is also used to determine the cumulative probability distribution map of EGTM within the washing interval based on the frequency of EGTM occurrence within different temperature intervals. The construction unit is used to divide the cumulative probability distribution map of the EGTM according to the probability threshold, and to construct the EGTM decay model of the engine within the water washing interval based on the division result.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for constructing the EGTM decay model as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for constructing the EGTM decay model as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements a method for constructing an EGTM decay model as described above.

[0016] The present invention provides a method, apparatus, and device for constructing an EGTM decay model. This method uses temperature intervals as a dividing line to obtain the frequency of EGTM time-series data changes within two adjacent water washing intervals. Based on the frequency of EGTM occurrences within different temperature intervals, it determines the cumulative probability distribution map of EGTM within each water washing interval. Finally, it uses a probability threshold to divide the cumulative probability distribution map of EGTM to construct an EGTM decay model. This allows the decay model constructed using this method to extract key features that characterize the decay pattern of the original EGTM sequence, and simplifies the highly nonlinear EGTM sequence, which is affected by numerous parameters, into a piecewise linear decay model. This achieves the goal of accurately and efficiently judging the decay pattern after engine water washing. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the construction method of the EGTM decay model provided by this invention; Figure 2 This is a timing diagram of EGTM within a certain water washing interval; Figure 3 Probability distribution of EGTM during the second water washing interval; Figure 4 Calibration plot for modeling points of the EGTM decay model; Figure 5 Line graph of the EGTM decay model; Figure 6 The timing diagram of EGTM before partitioning; Figure 7 The timing diagram of the partitioned EGTM; Figure 8 For the EGTM decay model of the full water washing section; Figure 9This is a flowchart illustrating the construction process of the EGTM linear decay model of this invention. Figure 10 The EGTM decay model is used during the fourteenth water washing interval; Figure 11 The graph shows the EGTM degradation model evaluation during the fourteenth water washing interval; Figure 12 Evaluation of the EGTM degradation model for the full water washing section of the engine; Figure 13 Box plot of K-value for the EGTM linear decay model; Figure 14 Bar chart of the envelope area within the three-wash section; Figure 15 A schematic diagram of the structure of the EGTM decay model construction device provided by the present invention; Figure 16 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] Figure 1 The flowchart of the method for constructing the EGTM decay model provided by this invention is as follows: Figure 1 As shown, the method includes: Step 101: Obtain EGTM timing data within the interval between two adjacent water washing cycles.

[0021] Step 102: Based on the temperature interval, determine the frequency of EGTM occurrence in different temperature intervals within the washing interval according to the EGTM time series data.

[0022] Specifically, an aircraft acquires an EGT value once during a single flight mission. This EGT value is typically acquired after the aircraft has stabilized. Water washing, on the other hand, is usually performed after several flights (90 flights), meaning there are several EGT values ​​between two water washes. Therefore, by acquiring the EGTM time-series data (the frequency of EGTM occurrences) between two adjacent water washes, the overall distribution of EGTM within that water wash interval can be reflected.

[0023] Figure 2To obtain the EGTM time sequence diagram within a certain washing interval, the EGTM sequences within two adjacent washing intervals are first extracted. This embodiment of the invention takes the second washing interval as an example. Figure 2 As shown, the frequency of EGTM occurrence within the washing interval is statistically analyzed with an interval of 0.5K to reflect the overall distribution of EGTM within the washing interval.

[0024] Step 103: Determine the cumulative probability distribution of EGTM within the washing interval based on the frequency of EGTM occurrence in different temperature intervals.

[0025] Specifically, there are two methods that can be used to calculate the cumulative probability distribution of EGTM within the washing interval.

[0026] The first method: Calculate the empirical distribution curve of EGTM within the washing interval using formula (1), such as... Figure 3 The curve outline is shown in the figure. Figure 3 The probability distribution of EGTM during the second washing interval. The upper confidence boundary of this empirical distribution is calculated using equation (2), and the lower confidence boundary is calculated using equation (3). This represents the confidence level, where n is the total number of samples. The two dashed lines in the figure represent the upper and lower confidence boundaries for a 95% confidence level.

[0027] (1) (2) (3) in, represents the cumulative probability that EGTM is less than x; k represents the EGTM that is less than or equal to x; （k） The probability density function of EGTM is represented by the following: represents the confidence level; n represents the total number of samples.

[0028] The second method: The kernel distribution is a nonparametric representation of the probability density function (pdf) of a random variable. The kernel distribution can be used when the parametric distribution cannot adequately describe the data, or when it is desirable to avoid making assumptions about the distribution of the data. The kernel distribution is defined by a smoothing function and a bandwidth value, with the bandwidth value controlling the smoothness of the resulting density curve. The kernel density estimator is the probability density function pdf of the random variable. For any real value x, the formula for the kernel density estimator is given by equation (4). express.

[0029] First, the probability density of EGTM is calculated using equation (4), where the Gaussian kernel function is used (5). Then, the cumulative probability distribution function of EGTM within the washing interval is calculated by combining equations (6) and (7), as follows: Figure 3 The solid curve in the figure is shown.

[0030] (4) (5) (6) (7) in, The probability density function of EGTM is represented by the following: This represents bandwidth, which is set to 4 here; Indicates EGTM; Indicates EGTM samples; Represents the Gaussian kernel function; The cumulative probability function of EGTM is represented by ; Equation (4) represents the probability density function of EGTM.

[0031] As can be seen, the cumulative probability distribution curve obtained by probability density fitting using method two highly overlaps with the empirical distribution curve obtained by method one, and both are basically within the confidence interval. Therefore, the cumulative probability distribution of EGTM within the washing interval can be obtained by any method.

[0032] Step 104: Divide the cumulative probability distribution map of the EGTM according to the probability threshold, and construct the EGTM decay model of the engine within the water washing interval based on the division results.

[0033] The following explains how to divide the cumulative probability distribution map of the EGTM according to the probability threshold, and how to construct the EGTM decay model of the engine within the water washing interval based on the division results.

[0034] The EGTM value when the cumulative probability equals the probability threshold θ is set as the minimum decay value, and the EGTM value when the cumulative probability equals 1-θ is set as the maximum recovery value. The EGTM values ​​within the interval corresponding to the minimum decay value are defined as the engine decay zone. The EGTM values ​​within the interval corresponding to the minimum decay value and the maximum recovery value are defined as the engine fluctuation zone. The EGTM values ​​within the interval corresponding to the maximum recovery value are defined as the engine recovery zone. Based on the engine decay zone, fluctuation zone, and recovery zone, an EGTM decay model of the engine within this water washing interval is constructed.

[0035] Specifically, a probability threshold θ is set, and the EGTM value when the cumulative probability equals θ is set as the minimum decline value, while the EGTM value when the cumulative probability equals 1-θ is set as the maximum recovery value. Figure 3As shown by the two rectangles, EGTM is divided into three regions: the decay region = {EGTM | EGTM < minimum decay value}, the fluctuation region = {EGTM | minimum decay value ≤ EGTM ≤ maximum recovery value}, and the recovery region = {EGTM | EGTM > maximum recovery value}. Figure 3 The image shows three different regions from left to right.

[0036] The following explains how to construct the EGTM decay model of the engine within the water washing interval based on the engine's decay zone, fluctuation zone, and recovery zone.

[0037] Extract the corresponding modeling points from the decay zone, fluctuation zone, and recovery zone respectively; construct a linear EGTM decay model of the engine within the water washing interval based on the modeling points.

[0038] The extraction of corresponding modeling points from the decay zone, fluctuation zone, and recovery zone includes: extracting the minimum decay value from the decay zone and extracting several points corresponding to the maximum recovery value of EGTM from the fluctuation zone as modeling points; using the EGTM before this wash as the modeling starting point and the modeling point corresponding to the first time EGTM reaches the maximum recovery value as the modeling ending point to construct the recovery segment of the linear EGTM decay model; using the point corresponding to the first time EGTM reaches the maximum recovery value as the modeling starting point and the point corresponding to the last time extracted EGTM reaches the maximum recovery value as the modeling ending point to construct the fluctuation segment of the linear EGTM decay model; using the point corresponding to the last time extracted EGTM reaches the maximum recovery value as the modeling starting point and the extracted minimum decay value as the modeling ending point to construct the decay segment of the linear EGTM decay model; and constructing the linear EGTM decay model based on the recovery segment, fluctuation segment, and decay segment.

[0039] The following example uses two points corresponding to the maximum recovery value of EGTM extracted from the fluctuation zone as modeling points for illustration.

[0040] Specifically, Figure 4 The point calibration plot for the EGTM decay model, such as Figure 4 As shown, the extracted minimum decay value and maximum recovery value are correlated with the EGTM time series within the washing interval. The figure marks the four most important modeling points for establishing the EGTM decay model: EGTM before washing, the first time EGTM reaches its maximum recovery value, the third to last time EGTM reaches its maximum recovery value, and the point of minimum decay value for EGTM. (Connections...) Figure 4 The four calibration points yielded three line segments: a recovery segment, a fluctuation segment, and a decline segment. Figure 5 , Figure 5 This is a line graph of the EGTM decay model. From... Figure 5It can be seen that the EGTM decay model has changed from a nonlinear model to a linear model.

[0041] The above explains how to construct an EGTM decay model within a single water washing interval. The following explains how to construct an EGTM decay model for all water washing intervals.

[0042] First, acquire the EGTM time-series data of the engine during the full water washing phase; second, divide the EGTM time-series data of the full water washing phase into EGTM time-series data of several water washing intervals according to the water washing maintenance date; finally, determine the linear EGTM decay model of the corresponding water washing interval based on the EGTM time-series data within each water washing interval, and determine the linear EGTM decay model of the full water washing phase based on the linear EGTM decay model corresponding to each water washing interval.

[0043] Specifically, the following explanation uses the CFM56-7B turbofan engine of a Boeing 737-800 as an example.

[0044] First, the original EGTM sequence was divided into data segments according to the date of water washing and maintenance. Figure 6 This is the timing diagram of EGTM before partitioning. Figure 7 To obtain the EGTM timing diagram after partitioning, the EGTM sequences within the remaining 17 water wash intervals of this engine are... Figure 5 The linear decay model is constructed in the same manner as shown, and the results are obtained. Figure 8 , Figure 8 The EGTM decay model is used for the full water washing section.

[0045] Figure 9 The flowchart for constructing the EGTM linear decay model of this invention is as follows: Figure 9 As shown, the method for constructing the EGTM linear decay model of the present invention includes: First, the frequency of EGTM occurrence within two adjacent water washing intervals is counted. Then, the probability density division state of EGTM is determined based on the occurrence frequency of EGTM. Finally, the EGTM decay model of the entire water washing segment is reconstructed based on the division state.

[0046] The accuracy of the characterization of the EGTM decay model constructed using the method of this invention is evaluated below.

[0047] Taking the data from the fourteenth water wash interval of the engine as an example, the modeling effect is as follows: Figure 10 As shown, Figure 10The figure shows the EGTM decay model within the fourteenth wash interval. EGTM_Model_initial(14) represents the initial point of the EGTM decay model within the fourteenth wash interval, which is the termination point of the decay model within the previous wash interval. EGTM_Model_final(14) represents the termination point of the EGTM decay model within the fourteenth wash interval, and min_EGTM_Real(14) represents the minimum value of the original EGTM within the fourteenth wash interval. Min_Baseline(14) represents the baseline value of EGTM within the fourteenth wash interval, which can be obtained from equation (8), i.e., the minimum value among the initial point of the decay model, the termination point of the decay model, and the minimum point of the original EGTM. (10) Figure 11 The graph shows the EGTM degradation model evaluation within the fourteenth wash interval, as shown below. Figure 11 As shown, the envelope regions of the original EGTM and the linear decay model are established with respect to the baseline, as follows: Figure 11 As shown in the figure. Among them, the area enclosed by the original EGTM time series and the baseline is A1, and the area enclosed by the linear decay model and the baseline is A2. The derivation formulas of A1 and A2 are shown in equations (9) and (10), where i represents the i-th wash, EGTM_Real represents the original EGTM, EMI(EGTM_Model_Initial) represents the initial value of the decay model EGTM; EMR(EGTM_Model_Recover) represents the recovery value of the decay model EGTM; KP(EGTM_Model_RecoverRate) represents the recovery rate of the decay model EGTM; EMD(EGTM_Model_Degration) represents the decay value of the decay model EGTM; KD(EGTM_Model_Degration) represents the decay rate of the decay model EGTM. K is the decay model evaluation index, as shown in equation (11). It can be seen that the smaller the value of K, the smaller the time series error between the constructed linear decay model and the original EGTM, and the better it can characterize the recovery effect and decay trend of the original EGTM after washing. (9) (10) (11) Figure 12 To evaluate the performance of the EGTM degradation model for the full water washing section of the engine, from Figure 12 It can be seen that the linear decay model constructed using the method of this invention has a very small time series error compared with the original EGTM, indicating that the linear decay model constructed using the method of this invention can accurately characterize the recovery effect and decay trend of the original EGTM after water washing.

[0048] The following explains how to determine the probability threshold θ.

[0049] Linear decay models were constructed using different probability thresholds θ in the full water washing section data of multiple engines, and the aforementioned K value was used as the evaluation index. Due to table size limitations, only some evaluation results are shown here, as detailed in Tables 1 to 6. As can be seen from Table 6, when θ is 7.5%, the average value of the K value evaluation index of the full water washing section linear decay model is the smallest, and the modeling effect is the best. Therefore, the probability threshold θ = 7.5% was selected to construct the EGTM linear decay model.

[0050] Table 1. Evaluation results when θ is 5%.

[0051] Table 2 shows the evaluation results when θ is 7.5%.

[0052] Table 3 Evaluation results when θ is 10%

[0053] Table 4 shows the evaluation results when θ is 12.5%.

[0054] Table 5 shows the evaluation results when θ is 15%.

[0055] Table 6. Mean values ​​of K-value evaluation index for the linear decay model of the full washing section.

[0056] Figure 13 Box plots of the K-values ​​for the EGTM linear decay model were constructed using probability threshold θ=7.5% on full-water washing section data from six different CFM56-7B turbofan engines. The box plots of the K-values ​​for each engine's full-water washing section are shown below. Figure 13 As shown, degradation models A2 and A1 are constructed for the 1st, 8th, and 15th water washing stages of each engine, respectively. Figure 14 As shown, Figure 14 A bar chart of the envelope area within the three washing sections, from Figure 14 It can be seen that the mean and variance of the degradation model K evaluation index built on different engines are small, and the modeling area A2 of the degradation model has a small error compared with the original EGTM envelope area A1, which proves the effectiveness of the linear degradation model constructed by the method of this invention.

[0057] The apparatus for constructing the EGTM decay model provided by the present invention will be described below. The apparatus for constructing the EGTM decay model described below can be referred to in correspondence with the method for constructing the EGTM decay model described above.

[0058] Figure 15 This is a schematic diagram of the structure of the EGTM decay model construction device provided by the present invention, as shown below. Figure 15 As shown, the device includes: Acquisition unit 1501 is used to acquire EGTM time series data within the interval between two adjacent water washing cycles; The determining unit 1502 is used to determine the frequency of EGTM occurrence in different temperature intervals within the current washing interval based on the EGTM time series data, using temperature intervals as the dividing basis. The determining unit 1502 is also used to determine the cumulative probability distribution map of EGTM within the washing interval based on the frequency of EGTM occurrence within different temperature intervals. The construction unit 1503 is used to divide the cumulative probability distribution map of the EGTM according to the probability threshold, and to construct the EGTM decay model of the engine within the water washing interval based on the division result.

[0059] Figure 16 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 16 As shown, the electronic device may include: a processor 810, a communication interface 1620, a memory 1630, and a communication bus 1640, wherein the processor 1610, the communication interface 1620, and the memory 1630 communicate with each other through the communication bus 1640. The processor 1610 can call logical instructions in the memory 1630 to execute a method for constructing an EGTM decay model, the method including: Acquire EGTM time-series data within the interval between two adjacent water washing cycles; Based on the temperature interval, the frequency of EGTM occurrence in different temperature intervals within the washing interval is determined according to the EGTM time series data. The cumulative probability distribution of EGTM within a washing interval is determined based on the frequency of EGTM occurrence in different temperature intervals. The cumulative probability distribution map of the EGTM is divided according to the probability threshold, and the EGTM decay model of the engine within the water washing interval is constructed based on the division results.

[0060] Furthermore, the logical instructions in the aforementioned memory 1630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the construction method of the EGTM decay model provided by the above methods.

[0062] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the construction method of the EGTM decay model provided by the above methods.

[0063] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing an EGTM decay model, characterized in that, include: Acquire EGTM time-series data within the interval between two adjacent water washing cycles; Based on the temperature interval, the frequency of EGTM occurrence in different temperature intervals within the washing interval is determined according to the EGTM time series data. The cumulative probability distribution of EGTM within a washing interval is determined based on the frequency of EGTM occurrence in different temperature intervals. The cumulative probability distribution map of the EGTM is divided according to the probability threshold, and the EGTM decay model of the engine within the water washing interval is constructed based on the division results. The step of dividing the cumulative probability distribution map of the EGTM according to a probability threshold, and constructing the EGTM decay model of the engine within the water washing interval based on the division results includes: Set the EGTM value when the cumulative probability equals the probability threshold θ as the minimum decline value, and set the EGTM value when the cumulative probability equals 1-θ as the maximum recovery value; The EGTM within the range corresponding to the minimum decay value is defined as the decay zone of the engine; The EGTM within the range that is greater than or equal to the minimum decay value and less than or equal to the maximum recovery value is defined as the fluctuation zone of the engine. The EGTM within the range corresponding to the maximum recovery value is defined as the engine's recovery zone; Based on the engine's decay zone, fluctuation zone, and recovery zone, an EGTM decay model of the engine is constructed within the water washing interval. The construction of the EGTM decay model of the engine within the water washing interval based on the engine's decay zone, fluctuation zone, and recovery zone includes: Extract the corresponding modeling points from the decay region, fluctuation region, and recovery region respectively; Based on the modeling points, a linear EGTM decay model of the engine is constructed within the water washing interval.

2. The method for constructing the EGTM decay model according to claim 1, characterized in that, The extraction of corresponding modeling points from the decay region, fluctuation region, and recovery region includes: Extract the minimum decay value from the decay region and extract several points corresponding to the maximum recovery value of EGTM from the fluctuation region as modeling points; Using the EGTM before this water wash as the modeling starting point and the modeling point corresponding to the first time the EGTM reaches its maximum recovery value as the modeling ending point, a recovery segment of the linear EGTM decay model is constructed. The fluctuation segment of the linear EGTM decay model is constructed by taking the point corresponding to the first time EGTM reaches its maximum recovery value as the modeling starting point and the point corresponding to the last time EGTM reaches its maximum recovery value as the modeling ending point. Using the point corresponding to the last EGTM reaching the maximum recovery value as the modeling starting point and the extracted minimum decay value as the modeling ending point, the decay segment of the linear EGTM decay model is constructed. A linear EGTM decay model is constructed based on the recovery segment, fluctuation segment, and decay segment.

3. The method for constructing the EGTM decay model according to claim 2, characterized in that, include: Acquire EGTM timing data of the engine during the full water washing phase; The EGTM timing data of the full water washing section is divided into several water washing intervals based on the water washing maintenance date. The linear EGTM decay model for the corresponding water washing interval is determined based on the EGTM time series data within each water washing interval. The linear EGTM decay model for the full washing section is determined based on the linear EGTM decay model corresponding to each washing interval.

4. The method for constructing the EGTM decay model according to claim 1, characterized in that, The probability threshold θ = 7.5%.

5. An apparatus for constructing the EGTM decay model according to claim 1, characterized in that, include: The acquisition unit is used to acquire EGTM time-series data within the interval between two adjacent water washing cycles; The determination unit is used to determine the frequency of EGTM occurrence in different temperature intervals within the current washing interval based on the EGTM time series data, using temperature intervals as the dividing criteria. The determining unit is also used to determine the cumulative probability distribution map of EGTM within the washing interval based on the frequency of EGTM occurrence within different temperature intervals. The construction unit is used to divide the cumulative probability distribution map of the EGTM according to the probability threshold, and to construct the EGTM decay model of the engine within the water washing interval based on the division result.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for constructing the EGTM decay model as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method for constructing the EGTM decay model as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for constructing the EGTM decay model as described in any one of claims 1 to 4.

Images