A deep learning-based heat transfer component fault diagnosis system

Abstract

The application discloses a kind of heat transfer component fault diagnosis systems based on deep learning, including six big modules.Model training data management module is according to the design morphing threshold of different heat transfer components, divide its normal operating period and functional failure period, collect morphing variable and operating time and store as data set;Life prediction and health assessment module constructs model using data set, predicts the time of target component to reach morphing threshold;Morphing characteristic perception module collects target component data, obtains a morphing variable value;Intelligent maintenance strategy screening module calls strategy library to screen adaptive scheme and enters training set;Maintenance effect verification module interval prediction time calculates secondary morphing variable after maintenance, and compares with threshold value;Self-learning strategy optimization module according to comparison result, effective scheme is included in preferred set, and invalid scheme then enters screening set for artificial judgment.The system realizes the intelligent diagnosis and maintenance optimization of heat transfer component fault.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault diagnosis, more particularly, the present application relates to a heat transfer component fault diagnosis system based on deep learning. BACKGROUND

[0002] The existing heat transfer component fault diagnosis system mostly adopts multi-source data fusion learning.

[0003] Firstly, the data pool is cooperatively constructed. The real-time monitoring pool built by the system covers multiple types of key parameters, including dynamic physical quantities, chemical characteristics and environmental parameters. The historical case library is classified in three dimensions according to the deformation threshold "component type-failure mode-working condition", and a large number of complete records are stored, including the whole life cycle monitoring curve from the commissioning of the component to the failure.

[0004] Then, the deformation threshold cross-domain data association mining mechanism is established. Through the association algorithm, the system automatically identifies the hidden association between the data, including strong association rules and time sequence association. The strong association rule refers to the high confidence of the occurrence of a certain fault under a certain parameter combination; the time sequence association reflects the time sequence relationship between the parameter change trend and the fault risk improvement. In the data fusion process, the evidence theory is used to process conflicting data, and the influence of measurement error is reduced through credibility allocation, thereby improving the accuracy of feature mapping.

[0005] Finally, the deformation threshold edge computing and cloud cooperation architecture is established. In order to solve the problem of data transmission delay in industrial field, the system completes the preprocessing of real-time data such as outlier elimination and normalization at the edge node, and then only uploads the key feature values to the cloud for fusion analysis with the historical case library. This architecture can improve the data processing efficiency and ensure that the association rules can respond within milliseconds when dealing with sudden working conditions, thereby ensuring their effectiveness.

[0006] 1. Traditional methods are mostly limited to judging the current fault and cannot predict the fault time. This makes it often only passive maintenance after the fault occurs, which can easily cause unplanned shutdown, disrupt production rhythm, reduce production efficiency, and is difficult to ensure production continuity and stability.

[0007] 2. The traditional method needs to manually identify the failure threshold of each component. Different personnel may give different standards based on their own experience and the process is tedious and prone to error, which will waste a lot of time.

[0008] 3. The traditional model needs to observe the entire failure period of the component. For components with long service life, the observation period is too long, which will consume a lot of time and effort, seriously slowing down the model development efficiency, leading to the model not being applied in time, making it difficult to quickly meet the needs of equipment maintenance for the model, and affecting the timeliness and effectiveness of maintenance work. SUMMARY

[0009] In order to overcome the above-mentioned defects of the prior art, the present application provides a heat transfer component fault diagnosis system based on deep learning, which solves the problems raised in the above background art by the following scheme.

[0010] A heat transfer component fault diagnosis system based on deep learning, comprising a model training data management module: based on different heat transfer component design deformation thresholds, the heat transfer components are divided into normal operation period and functional failure period according to the deformation amount of the heat transfer components, the deformation amount of a certain number of heat transfer components is calculated and its running time is recorded, and it is transmitted and stored in the data set;

[0011] A life prediction and health assessment module: using the information in the data set to build a prediction model, and predicting the time when the target heat transfer component reaches the deformation threshold;

[0012] A deformation feature perception module: data acquisition is performed on the target heat transfer component to obtain a one-time deformation value of the heat transfer component;

[0013] An intelligent maintenance strategy screening module: a preset maintenance strategy library is called to screen out a maintenance scheme that adapts to the process flow, and this scheme is entered into the training set;

[0014] A maintenance effect verification module: the deformation amount of the heat transfer component after maintenance is calculated again at intervals to obtain a second deformation value, and the second deformation value is compared with the deformation threshold;

[0015] A self-learning strategy optimization module: if the second deformation value is less than the deformation threshold, the maintenance scheme is included in the optimal scheme set; if the second deformation value is greater than the deformation threshold, the maintenance is included in the screening set for manual judgment.

[0016] Preferably, the model training data management module reads the current wear amount D w and the running time t w of the heat transfer component of the same model as the target heat transfer component to establish a data set.

[0017] Preferably, the present example selects a weibull model to judge the time when the heat transfer component reaches the deformation threshold, and uses a power law model to verify the prediction result.

[0018] Preferably, a double camera is used to collect images of the surface points of the heat transfer component.

[0019] The present application has the advantages of

[0020] 1. The present application predicts the failure time, gives the relevant personnel enough time to prepare in advance, can purchase spare parts and arrange maintenance personnel in time, thereby effectively reducing the probability of unplanned shutdown and ensuring the continuity and stability of production.

[0021] 2. This invention uses a standardized method to set thresholds, avoiding the standard differences caused by the lack of unified standards in traditional methods due to manual identification, greatly simplifying the threshold setting process and saving a lot of time.

[0022] 3. This invention establishes a database to train the model based on the current wear, without needing to observe the entire failure cycle, which greatly shortens the model training cycle and enables usable models to be obtained more quickly. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the overall structure of the present invention.

[0024] Figure 2 This is a schematic diagram of the system architecture of the present invention.

[0025] Figure 3 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] like Figure 1 The system shown is a deep learning-based fault diagnosis system for heat transfer components. It performs two deformation calculations on the target heat transfer component at intervals of model prediction time. If the second deformation does not reach the predicted value after using the maintenance plan, it proves that the maintenance plan is not a high-quality maintenance plan. If the second deformation reaches the predicted value after using the maintenance plan, it proves that the maintenance plan is not a poor-quality maintenance plan.

[0028] like Figure 2 The system shown is a deep learning-based fault diagnosis system for heat transfer components, including a model training data management module, a life prediction and health assessment module, a deformation feature perception module, an intelligent maintenance strategy screening module, a maintenance effect verification module, and a self-learning strategy optimization module.

[0029] like Figure 3 The system shown is a deep learning-based fault diagnosis system for heat transfer components. It establishes a model using the current wear of heat transfer components of the same model as the target heat transfer component. It calculates the individual theoretical life and the group theoretical life of the same model heat transfer components separately. If the error between the individual theoretical life and the group theoretical life is within a reasonable range, the model is successfully established.

[0030] The model training data management module designs a deformation threshold based on different heat transfer components, divides the heat transfer components into normal operation period and functional failure period according to the deformation variable of the heat transfer components, calculates the deformation variable of a certain number of heat transfer components and records the running time, and transmits and stores to the data set. Different deformation thresholds are designed for different heat transfer components, and the calculation formula is,

[0031] Deformation threshold , the deformation threshold unit is m, wherein △T is the difference between the highest temperature generated in the production process of the heat transfer component and the temperature at the end of the process, the unit is ℃; α is the material expansion coefficient, the elongation per unit length when the material rises by 1K temperature, the unit is ℃ -1 ; L is the material gap diameter of the heat transfer component, the unit is m; E cff is the effective elastic modulus, which represents the actual stiffness of the material at the working temperature, the unit is Pa, which is measured by high temperature tensile test or referred to the material manual; σ is the allowable stress of the material, which represents the maximum allowable stress of the material for long-term safe operation at the working temperature, avoids plastic deformation or fracture, reflects the ability of the material to resist deformation and the sensitivity of the material to thermal deformation, the unit is Pa; S is the safety factor, which reflects the safety redundancy of engineering design, is used to avoid structural failure caused by accidental factors such as material performance fluctuation, working condition deviation, calculation error, etc. According to the importance classification of components, the key path components take 2.0-2.5, and the non-key components take 1.5-1.8; r is the structure correction coefficient, which reflects the influence of the structure form of the heat transfer component on the deformation sensitivity, the straight pipe takes 1.0, the elbow pipe takes 1.2-1.5, and increases with the decrease of the curvature radius, the special-shaped component takes 1.5-2.0. When the sample quantity of the same type of heat transfer component is sufficient, usually ≥ 30, the multi-sample parallel collection mode is adopted, and the data representativeness is improved through the difference comparison between samples. When the sample quantity of the same type is insufficient, < 10, the collection period of single sample is prolonged, and the key stage collection frequency is encrypted to construct longitudinal time series data chain.

[0032] The life prediction and health assessment module uses the information in the data set to build a prediction model and predict the time when the target heat transfer component reaches the deformation threshold; the data set is used to establish a prediction model to predict the time when the total deformation variable of the target heat transfer component reaches the deformation threshold, and the model establishment steps are as follows,

[0033] S1, modeling target determination and sample data collection: calling the information in the data set, reading the current wear D w of the heat transfer component of the same type as the target heat transfer component and the running time t w ;

[0034] S2, power-law wear model establishment: the power-law wear model is used to describe the objective law that the wear D(t) of a certain product evolves with the growth of time t. The formula is D(t) represents the wear of the heat transfer component at time t; t is the actual operating time; k is the wear coefficient, characterizing the trend of wear rate change; the smaller k is, the more wear-resistant the material; m is the wear index, characterizing the trend of wear rate change; γ is the wear latency, representing the stage where wear is negligible in the early stage of equipment operation. Calculate the parameters У, k, and m in the power-law wear model. Collect at least three sets of operating times and corresponding wear samples, denoted as {(D1, t1), (D2, t2), ..., (D... w , t w Taking the natural logarithm of both sides of the formula, we can transform it into a linear equation. Let Y = lnD(t), X = ln(t−γ), and A = lnk, then the linear equation is Y = A + mX. Calculate the corresponding Xi = ln(t-γ) and Yi = lnD(t), fit the linear equation using the least squares method, and obtain the goodness-of-fit R. 2 Adjust D(t), the value of t, and repeat the calculation until R... 2 Maximum, usually R 2 The value of γ must be ≥0.9 for it to be optimal. The slope of the linear equation is m, and the intercept is A=lnk. Substituting different values ​​of D(t) and t, we can calculate the values ​​of k and m.

[0035] S3. Individual Theoretical Life Calculation: After calculating parameters k, γ, and m, the power-law model is mathematically transformed to obtain the single-sample theoretical life formula, completing the conversion from wear index to time index; the formula is: The deformation threshold D will be set. max Substituting D0, we obtain the time t0 for a single heat transfer component to reach the deformation threshold. Multiple sets of t0 are collected to form a lifetime dataset {t}. a , t b , t c , ..., t n};

[0036] S4. Population Theoretical Lifetime Calculation: The cumulative distribution function and reliability function of the Weibull distribution are introduced to quantify the statistical distribution characteristics of the population lifetime; the formula for the cumulative distribution function is... , representing the proportion of samples in the population with lifetime ≤ t; the reliability function is: , representing the proportion of samples in the population with lifespan > t; where β is the shape parameter and η is the scale parameter; the lifespan dataset {t a , t b , t c , ..., t n The data are arranged in ascending order to obtain an ordered lifetime dataset {t1, t2, t3, ..., t}. max}; and calculate the specific values ​​of parameters γ, β, and η based on the data; using median rank

[0037] Algorithm calculation , i is the order number. By twice logarithmic transformation, the cumulative distribution function is transformed into a linear equation ,

[0038] First logarithmic change ,

[0039] Second logarithmic change Let Let , a linear equation is established Based on the linear regression result corresponding to the optimal gamma: the slope a = beta, the intercept b = -beta * ln eta, beta and eta are calculated.

[0040] S5, model verification and eligibility determination: extract the specific quantile life to calculate the group theoretical life t q , individual theoretical life t0 is compared, and the difference is within a reasonable range. The relative difference between the group theoretical life and the individual theoretical life is calculated

[0041] In this example, the relative difference is less than 15%, so the model is correct. If the error is greater than 15%, reselect the data in the data set for modeling.

[0042] The deformation feature perception module collects data of the target heat transfer component to obtain a first deformation value of the heat transfer component; the deformation of the target heat transfer component is based on a digital image method, and the surface of the unused heat transfer component needs to be pretreated;

[0043] First, a discrete feature point system with stable recognition performance needs to be designed. The positions of the points are uniformly distributed macroscopically, but each local area is random. The ideal point should cover 3-5 pixels, and the spacing between points should be at least 2-3 times the diameter of the point to ensure that each subset contains enough unique point features. For high-temperature working conditions, the marker point material needs to be consistent with the component body to avoid marker point falling off due to the difference in thermal expansion coefficient. In a humid environment, the dot matrix area needs to be passivated to improve corrosion resistance and ensure no obvious rust within 1 year.

[0044] Before the experiment, obtain waste or small samples of the same material as the heat transfer component. Perform laser marking tests on them, systematically adjusting laser power, speed, frequency, pulse width, and marking frequency. Laser dot marking is used to matte finish the heat transfer component. First, eliminate the interference of light reflection. The surface of the heat transfer component usually has a mirror reflection, which can cause the dot-marked area in the image to appear overexposed or have light spots, hiding the edge features of the dot mark and affecting the accuracy of subsequent wear measurement in the image. Second, enhance the contrast. The matte surface can highlight the gray difference between the dot mark and the background, making it easier for the image recognition algorithm to accurately extract the position and shape of the mark, providing a reliable image basis for subsequent wear calculation based on mark displacement or deformation. The surface of the heat transfer component that has been matte finished uses laser direct marking technology to create a dot matrix structure on the surface of the heat transfer component, serving as a reference mark for subsequent displacement measurement.

[0045] Use a camera to capture dot matrix images at different time intervals. Select a high-speed camera with appropriate field of view and resolution. Use a fixed-focus lens to reduce focal plane changes. Select a filter with a center wavelength that matches the wavelength of the illumination light source, allowing only the illumination light to pass through, greatly suppressing the interference of the high-temperature component's own radiation, thereby improving the image signal-to-noise ratio and reducing image distortion caused by air thermal disturbance. Use a high-precision ceramic calibration board to capture reference images at room temperature and under no load. Collect at least 20 images from multiple angles to ensure that the calibration error is less than 0.02 pixels. Start the production line and apply the heat load according to the predetermined program. Synchronously trigger the dual-camera to capture images at the preset frequency.

[0046] For a certain mark point, calculate the three-dimensional coordinate displacement of the mark point before and after the time interval through image matching algorithm.

[0047] Take the surface of the heat transfer component at room temperature and under no load as the reference. The dot matrix image captured at this time is the standard. The three-dimensional coordinate of the mark point is marked as P0=(X0, Y0, Z0),

[0048] For the pre-processed laser dot matrix, extract the point information. Use the gray contrast of the matte finish to automatically segment the mark point area through Otsu algorithm. Sub-pixel positioning: perform ellipse fitting on the segmented area to calculate the sub-pixel coordinates of the point.

[0049] For the left and right camera images at the same time, use binocular disparity and calibration parameters to calculate the three-dimensional coordinates of the mark point in the world coordinate system:

[0050] ,

[0051] ,

[0052] ,

[0053] Where B is the binocular baseline distance, which is the straight-line distance between the optical centers of the left and right cameras. It is an inherent hardware parameter of the binocular vision system and needs to be obtained through precise measurement. It directly affects the accuracy of depth calculation. The longer the baseline, the higher the depth resolution for distant objects; f x d represents the focal length of the left camera in the x-direction, in pixels, determined by camera calibration. It reflects the scaling ratio by which the lens projects a point in three-dimensional space onto a two-dimensional image plane. The larger the focal length, the more pronounced the parallax change at the same depth. d represents the left-right parallax, i.e., the x-coordinate u of the same marker point in the left camera image. l x-coordinate u in the right camera image r The difference, expressed in pixels, is the core basis for depth acquisition in binocular vision and a key intermediate variable for 3D coordinate calculation; c x The x-coordinate of the principal point of the left camera, i.e., the x-coordinate of the intersection of the optical principal axis and the image sensor plane, is expressed in pixels and is determined by camera calibration. It serves as the reference point for converting pixel coordinates to world coordinates and is used to eliminate the influence of image center offset on coordinate calculations; v l The y-axis pixel coordinates of the marker point in the left camera image, in pixels, are also obtained through sub-pixel localization; c y The y-coordinate of the principal point of the left camera, in pixels, is determined by camera calibration and is related to c. x Similarly, it is used to correct the coordinate reference in the vertical direction; f y f is the focal length of the left camera in the y-direction, in pixels. Since camera sensor pixels may not be square, f... y with f x They may differ and need to be obtained through calibration to ensure the accuracy of the vertical coordinate calculation.

[0054] The displacements at this point are ΔX = X − X0, ΔY = Y − Y0, and ΔZ = Z − Z0. Based on these displacements, the total deformation of the heat transfer component can be calculated as follows: The total deformation of the heat transfer component... The unit is meters (m). The total deformation L of the heat transfer component is substituted into the Weibull model for calculation to obtain the predicted time when the deformation value of the heat transfer component reaches the deformation threshold.

[0055] The intelligent maintenance strategy screening module calls a preset maintenance strategy library, screens out an adaptive maintenance scheme, and enters this scheme into a training set; the strategy library stores maintenance schemes according to three dimensions of process flow types, component characteristics, and running time lengths, is divided into high-temperature and high-pressure working conditions, intermittent running working conditions, and corrosive medium working conditions according to process flows, is associated with metal materials, non-metal materials, straight pipes, and bent pipes according to component characteristics, and matches corresponding maintenance means in combination with the three types of situations. The execution scheme with the highest adaptation degree is entered into the training set in a fixed format, and fields include: basic information, input data, and execution results: the basic information includes a scheme ID, an application component ID, an execution time, and process flow parameters; the input data includes cumulative running time length before maintenance, predicted running time to a threshold value, and component characteristic data; the execution results are to be supplemented, and subsequent secondary verification modules fill in running state data after maintenance and threshold value comparison results.

[0056] The maintenance effect verification module calculates a secondary deformation variable value of the heat transfer component after maintenance at an interval system prediction time, compares the secondary deformation variable value with a deformation threshold value, calculates a total deformation variable of the current heat transfer component in the same way, and compares the total deformation variable with the deformation threshold value. According to the life extension ratio value, the maintenance scheme is classified.

[0057] The self-learning strategy optimization module determines whether the current maintenance strategy is effective, if the secondary deformation variable value is less than the deformation threshold value, the current maintenance scheme is included in an optimized scheme set; if the secondary deformation variable value is greater than the deformation threshold value, the maintenance is included in a screening set for manual judgment. For the scheme with an excessive secondary deformation variable, a manual judgment form is generated, including basic information such as component model, maintenance scheme ID, and running working condition parameters; abnormal analysis including deformation variable curve comparison before and after maintenance and normal curve of the same type component at the same period, to determine whether the invalid maintenance is caused by working condition mutation, whether the maintenance parameters need to be adjusted, and whether it is a defect of the scheme itself. After the manual judgment result is entered, the system automatically includes the adjusted scheme in a verification set, and preferentially arranges the next maintenance test. The scheme with a life extension ratio less than 1, especially less than 0.5, is the first recommended for routine maintenance.

[0058] Secondly, only structures related to the disclosed embodiments are involved in the drawings of the disclosed embodiments, other structures can be referred to the general design, and the same embodiments and different embodiments of the present application can be combined with each other under the condition of no conflict;

[0059] Finally, the above only describes preferred embodiments of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A deep learning-based heat transfer component failure diagnosis system, characterized by, The model training data management module includes: based on the design of different heat transfer components deformation threshold, according to the heat transfer component deformation will be divided into normal operation period and functional failure period, a certain number of heat transfer components to calculate its deformation and record its running time, transmission and storage to the data set; The data set is used to establish a prediction model to predict the time required for the total deformation of the target heat transfer component to reach the deformation threshold, and the model establishment steps are as follows, S1, modeling target determination and sample data acquisition: call the information in the data set, read the current wear amount D of the heat transfer component of the same model as the target heat transfer component w and its running time t w ; S2, power law wear model is established: the power law wear model is used for describing the objective law that the wear D(t) of a product increases with time t, and the formula is , D(t) is the wear of the heat transfer component at time t; t is the actual running time; k is the wear coefficient, which represents the change trend of the wear rate, the smaller k is, the more wear-resistant the material is; m is the wear index, which represents the change trend of the wear rate; γ is the wear incubation period, which represents the stage that the wear amount in the initial stage of equipment operation can be ignored; S3, individual theoretical life calculation: after calculating the parameters k, γ, m, the power law model is mathematically transformed to obtain a single sample theoretical life formula, and the conversion from wear index to time index is completed; the formula is The deformation threshold D max is set a , t b , t c ,..., t n}; S4, Population Theory Life Calculation: Introduce the cumulative distribution function and reliability function of Weibull distribution to quantify the statistical distribution characteristics of population life; the cumulative distribution function formula is , which represents the sample proportion of life ≤t in the population; the reliability function is: , which represents the sample proportion of life >t in the population; where β is the shape parameter and η is the scale parameter; arrange the life data set {t a , t b , t c ,..., t n} from small to large to obtain the ordered life data set {t1, t2, t3,..., t max}; and calculate the specific values of parameters γ, β, and η according to the data; S5, model verification and eligibility judgment: extract the specific quantile life and substitute it into the weibull model to calculate the group theoretical life, and compare the individual theoretical life t0, if the difference is within a reasonable range, the model is judged to be qualified; The life prediction and health assessment module uses the information in the data set to build a prediction model and predicts the time for the target heat transfer component to reach the deformation threshold; The deformation feature sensing module collects data from the target heat transfer component to obtain the first deformation value of the heat transfer component; The intelligent maintenance strategy screening module calls the preset maintenance strategy library to screen out the maintenance scheme suitable for the process flow, and records this scheme in the training set; The maintenance effect verification module calculates the second deformation value of the heat transfer component after maintenance at intervals, and compares the second deformation value with the deformation threshold; The self-learning strategy optimization module: if the second deformation value is less than the deformation threshold, the maintenance scheme is included in the optimal scheme set; if the second deformation value is greater than the deformation threshold, the maintenance is included in the screening set for manual judgment.

2. The deep learning-based heat transfer component fault diagnosis system of claim 1, wherein, The R(t) represents the percentage of samples that can work normally to the time point, and has no fixed value. The value of R(t) is specified according to actual requirements, and the weibull model is used to calculate the time t0 of the target heat transfer component to reach the failure period.

3. The deep learning-based heat transfer component fault diagnosis system of claim 1, wherein, The deformation of the target heat transfer component is based on digital image method, which needs to pretreat the surface of the unused heat transfer component; first, a discrete feature point system with stable recognition is designed, laser direct marking technology is used on the surface of the heat transfer component with matte treatment, and a dot matrix structure is constructed on the surface of the heat transfer component as a reference mark for subsequent displacement measurement; the camera is used to collect dot matrix images at different time periods, and for a certain mark point, the three-dimensional coordinate displacement of the mark point before and after the time period is calculated through image matching algorithm.

4. The deep learning-based heat transfer component fault diagnosis system of claim 3, wherein, The displacement of the mark point three-dimensional coordinates is denoted as Δx, Δy, Δz, and the total deformation of the heat transfer component is denoted as , with the unit of m.

5. The deep learning-based heat transfer component fault diagnosis system of claim 1, wherein, Different deformation thresholds are designed for different heat transfer components, and the calculation formula is, Deformation threshold wherein ΔT is the difference between the highest temperature reached during the production of the heat transfer component and the temperature at the end of the process, in °C; α is the coefficient of expansion of the material, which is the elongation per unit length of the material for each 1 K of temperature rise, in °C / m -1 ; L is the diameter of the voids of the material of the heat transfer component, in m; E cff is the effective modulus of elasticity, which is the actual stiffness of the material at the operating temperature, in Pa, measured by high-temperature tensile tests or taken from material handbooks; σ is the allowable stress of the material, which is the maximum allowable stress for the safe operation of the material over time at the operating temperature, which reflects the ability of the material to resist deformation and the thermal deformation sensitivity of the material, in Pa; S is the safety factor, which reflects the safety redundancy of the engineering design; and r is the structural correction factor.

6. The deep learning-based heat transfer component fault diagnosis system of claim 1, wherein, The total deformation of the heat transfer component is compared with the deformation threshold, and the total deformation is less than the deformation threshold, and the heat transfer component is judged to be in normal operation period, and the total deformation is greater than the deformation threshold, and is judged to be in functional failure period.

7. The deep learning-based heat transfer component fault diagnosis system of claim 1, wherein, Different maintenance schemes are set according to the process route, and the total deformation of the target heat transfer component is calculated again using image matching algorithm after reaching the target time, if it is lower than the deformation threshold, the maintenance scheme is effective, if it is higher than the deformation threshold, the maintenance scheme is invalid.

Images