Engine bolt tightening torque measuring and monitoring method

Abstract

The invention relates to the technical field of bolt tightening torque measurement, and discloses an engine bolt tightening torque measurement monitoring method, which comprises the following steps: step S101, collecting bolt parameters and engine connecting piece parameters, and performing preprocessing to generate an initial vector; step S102, constructing a training data set for training the tightening torque prediction model through an analog simulation platform; s103, inputting the initial vector into the trained tightening torque prediction model, wherein the output value represents the target tightening torque of the bolt; according to the method, the influence of temperature change and vibration change on the tightening torque of the bolt during operation of the engine is comprehensively considered, and the nonlinear mapping relation between the bolt parameters and the target tightening torque of the bolt and between the engine connecting piece parameters and the target tightening torque of the bolt is established through the tightening torque prediction model, so that the bolt assembly quality of the engine connecting piece is improved.

Description

Technical Field

[0001] The invention relates to the technical field of bolt tightening torque measurement, and more specifically, to a method for measuring and monitoring the tightening torque of engine bolts. Background Art

[0002] In engine manufacturing, the tightening torque of bolts is directly related to the reliability and service life of the engine. The engine contains a large number of bolt connections, such as cylinder head bolts, crankcase bolts, etc. These connections need to withstand high temperature, high pressure and high vibration working conditions. Therefore, it is crucial to ensure that the bolt connections have sufficient clamping force.

[0003] Traditional engine bolt assembly mainly relies on the operator's work experience. However, this method is difficult to ensure that the tightening torque is consistent for each operation. The tightening torque between different operators may vary greatly, making it difficult to ensure the quality of engine bolt assembly. Existing engine bolt assembly determines the tightening torque range of the bolt according to national or industry standards, and the operator uses an electronic torque tool to ensure that the tightening torque is within the tightening torque range. However, although this method can ensure that the tightening torque is consistent for each operation, it is difficult to establish a connection with the engine's operating parameters. For example, temperature changes during engine operation affect the expansion coefficient of the bolt material, thereby affecting the tightening torque of the bolt. Vibration changes during engine operation will also change the stress condition of the bolt, thereby affecting the tightening torque of the bolt, resulting in the inability to ensure the optimal operating state of the engine based solely on national or industry standards. Summary of the invention

[0004] The present invention provides a method for measuring and monitoring the tightening torque of engine bolts, which solves the technical problems in the above-mentioned background technology.

[0005] The present invention provides a method for measuring and monitoring the tightening torque of engine bolts, comprising the following steps:

[0006] Step S101, collecting bolt parameters and engine connection part parameters, and performing preprocessing to generate an initial vector;

[0007] The initial vector is obtained by concatenating the preprocessed bolt parameters and engine connection parameters;

[0008] Bolt parameters include: diameter, length, torque coefficient, thermal expansion coefficient, elastic modulus, pre-tightening torque and Poisson's ratio;

[0009] Engine connector parameters include: material type, thickness, hole diameter, hardness, compressibility, thermal expansion coefficient and elastic modulus;

[0010] Step S102, constructing a training data set for training a tightening torque prediction model through a simulation platform;

[0011] The input of the tightening torque prediction model is the initial vector;

[0012] The output of the tightening torque prediction model is the target tightening torque of the bolt;

[0013] The training data set includes U training samples, each of which includes a training data and a sample label, where U is a custom parameter;

[0014] The training data corresponds to the initial vector, and the sample label corresponds to the target tightening torque of the bolt;

[0015] Step S103, inputting the initial vector into the trained tightening torque prediction model, and the output value represents the target tightening torque of the bolt.

[0016] Furthermore, the pre-tightening torque F p The calculation formula is as follows:

[0017]

[0018] Where M represents the tightening torque of the bolt, f t Indicates the thread friction coefficient, f h It represents the friction coefficient between the contact surface of the bolt and the connecting part, and d represents the bolt diameter.

[0019] Further, the bolt parameters and the engine connection part parameters are preprocessed to generate an initial vector, including the following steps:

[0020] Step S201, directly filling the missing values ​​of bolt parameters and engine connection component parameters with zero values;

[0021] Step S202, normalizing the bolt parameters and the engine connection component parameters respectively by using standard scores;

[0022] The calculation formula for normalizing bolt parameters by standard fraction is as follows:

[0023]

[0024] Where 1≤i≤7, z i Represents the value of the i-th dimension of the normalized bolt parameter, x i represents the value of the i-th dimension of the bolt parameter before normalization, μ and σ represent the mean and standard deviation of the bolt parameter before normalization, respectively;

[0025] Step S203, concatenating the normalized bolt parameters and the normalized engine connection component parameters to obtain an initial vector.

[0026] Further, the tightening torque prediction model includes: a first hidden layer, a second hidden layer, a first unfolding layer, a second unfolding layer, a splicing layer and a classifier;

[0027] The first hidden layer inputs the initial vector and outputs the first feature matrix;

[0028] The second hidden layer inputs the initial vector and outputs the second feature matrix;

[0029] The first expansion layer is used to expand the first feature matrix into a vector representation;

[0030] The second expansion layer is used to expand the second feature matrix into a vector representation;

[0031] The concatenation layer is used to concatenate the vector representation of the first feature matrix and the vector representation of the second feature matrix into a combined vector;

[0032] The combined vector is input into the classifier, and the classification space of the classifier represents the target tightening torque of the bolt.

[0033] Furthermore, the calculation formula of the first hidden layer includes:

[0034] Matrix1=sigmoid(W2×(Vec T ×W1+UpMatrix)+b1);

[0035]

[0036] Where 1≤u≤14, 1≤v≤14, Matrix1 represents the first feature matrix of the first hidden layer output, Vec represents the initial vector of the first hidden layer input, UpMatrix represents the upper triangular matrix transformed by the initial vector, and the number of rows and columns of the upper triangular matrix is ​​the same as the number of dimensions of the initial vector. u，v Represents the element value of the uth row and vth column of the upper triangular matrix, Ele u represents the value of the u-th dimension of the initial vector, W1 and W2 represent the first weight parameter and the second weight parameter respectively, b1 represents the first bias parameter, T represents the transpose operation, and sigmoid represents the sigmoid activation function.

[0037] Furthermore, the calculation formula of the second hidden layer includes:

[0038] Matrix2=sigmoid(W4×(Vec T ×W3+DownMatrix)+b2);

[0039]

[0040] Where 1≤u≤14, 1≤v≤14, Matrix2 represents the second feature matrix of the second hidden layer output, Vec represents the initial vector of the second hidden layer input, DownMatrix represents the lower triangular matrix transformed by the initial vector, and the number of rows and columns of the lower triangular matrix is ​​the same as the number of dimensions of the initial vector, DownMatrix u，v Represents the element value of the u-th row and v-th column of the lower triangular matrix, Ele u represents the value of the u-th dimension of the initial vector, W3 and W4 represent the third weight parameter and the fourth weight parameter respectively, b2 represents the second bias parameter, T represents the transpose operation, and sigmoid represents the sigmoid activation function.

[0041] Furthermore, a training data set for training a tightening torque prediction model is constructed through a simulation platform, including the following steps:

[0042] Step S301, constructing a finite element analysis model of the bolt and the engine connection part through a simulation platform, and generating an initial vector according to step S101 as training data of a training sample;

[0043] Step S302, randomly generating K tightening torques between a lower limit value of the tightening torque and an upper limit value of the tightening torque;

[0044] Among them, K, lower limit of tightening torque and upper limit of tightening torque are all custom parameters;

[0045] Step S303, respectively calculating the sum of the environmental loads of the bolts at different ambient temperatures under each tightening torque;

[0046] The different ambient temperatures are all custom parameters;

[0047] Step S304, respectively calculating the sum of the dynamic loads of the bolts at different engine speeds under each tightening torque;

[0048] Step S305, respectively summing up the sum of the environmental loads of the bolts at different ambient temperatures under each tightening torque and the sum of the dynamic loads of the bolts at different engine speeds under the corresponding tightening torque to obtain a comprehensive score;

[0049] Step S306, taking the tightening torque with the smallest comprehensive score as a sample label of a training sample;

[0050] Step S307, repeat steps S302 to S306 until U training samples are obtained as the training data set.

[0051] Furthermore, the environmental load Load Env The calculation formula is as follows:

[0052] Load Env =F p -(E×Area×α×T);

[0053] Among them, F p , E, Area and α represent the pre-tightening torque, stiffness, cross-sectional area and thermal expansion coefficient of the bolt, respectively, and T represents the ambient temperature.

[0054] Furthermore, dynamic load dyn The calculation formula is as follows:

[0055]

[0056] Among them, F p , m and MaxSwing represent the pre-tightening torque, weight and maximum amplitude of the bolt respectively, n represents the engine speed, and β represents the proportional coefficient ranging from 0 to 1.

[0057] The present invention provides an engine bolt tightening torque measurement and monitoring system, comprising:

[0058] A data acquisition module, which is used to collect bolt parameters and engine connection parameters;

[0059] An initial vector generation module, which is used to pre-process bolt parameters and engine connection part parameters to generate an initial vector;

[0060] A training data set construction module, which is used to construct a training data set for training a tightening torque prediction model through a simulation platform;

[0061] The tightening torque prediction module is used to input the initial vector into the trained tightening torque prediction model, and the output value represents the target tightening torque of the bolt.

[0062] The beneficial effects of the present invention are as follows: the present invention comprehensively considers the influence of temperature changes and vibration changes during engine operation on the tightening torque of the bolts, and establishes a nonlinear mapping relationship between bolt parameters and engine connection parameters and the target tightening torque of the bolts through a tightening torque prediction model, thereby improving the bolt assembly quality of the engine connection. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a flow chart of a method for measuring and monitoring the tightening torque of engine bolts of the present invention;

[0064] Figure 2 It is a flow chart of the present invention for preprocessing bolt parameters and engine connecting part parameters to generate initial vectors;

[0065] Figure 3It is a flow chart of constructing a training data set for training a tightening torque prediction model through a simulation platform of the present invention;

[0066] Figure 4 It is a schematic diagram of an engine bolt tightening torque measurement and monitoring system of the present invention.

[0067] In the figure: data acquisition module 401, initial vector generation module 402, training data set construction module 403, tightening torque prediction module 404. DETAILED DESCRIPTION

[0068] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0069] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0070] like Figure 1 to Figure 4 As shown, a method for measuring and monitoring the tightening torque of engine bolts comprises the following steps:

[0071] Step S101, collecting bolt parameters and engine connection part parameters, and performing preprocessing to generate an initial vector;

[0072] The initial vector is obtained by concatenating the preprocessed bolt parameters and engine connection parameters;

[0073] Bolt parameters include: diameter, length, torque coefficient, thermal expansion coefficient, elastic modulus, pre-tightening torque and Poisson's ratio;

[0074] Engine connector parameters include: material type, thickness, hole diameter, hardness, compressibility, thermal expansion coefficient and elastic modulus;

[0075] Step S102, constructing a training data set for training a tightening torque prediction model through a simulation platform;

[0076] The input of the tightening torque prediction model is the initial vector;

[0077] The output of the tightening torque prediction model is the target tightening torque of the bolt;

[0078] The training data set includes U training samples, each training sample includes a training data and a sample label, where U is a custom parameter, preferably, U is set to 2000;

[0079] The training data corresponds to the initial vector, and the sample label corresponds to the target tightening torque of the bolt;

[0080] Step S103, inputting the initial vector into the trained tightening torque prediction model, and the output value represents the target tightening torque of the bolt.

[0081] It should be noted that the initial vector is expressed as: A = {a1...a7, a8...a 14};

[0082] Where a1…a7 represent the bolt parameters after pretreatment, namely, the bolt diameter, length, torque coefficient, thermal expansion coefficient, elastic modulus, pre-tightening torque and Poisson's ratio, a8…a 14 They respectively represent the parameters of the engine connector after preprocessing, namely, the material type, thickness, pore size, hardness, compression rate, thermal expansion coefficient and elastic modulus of the engine connector.

[0083] It should be noted that the diameter, length, torque coefficient, thermal expansion coefficient, elastic modulus and Poisson's ratio of the bolt are all provided by the bolt manufacturer, and the material type, thickness, aperture, hardness, compression rate, thermal expansion coefficient and elastic modulus of the engine connector are all provided by the engine manufacturer. The torque coefficient indicates the friction coefficient between the bolt and the engine connector, the thermal expansion coefficient indicates the degree of expansion or contraction of the material with temperature changes, the elastic modulus indicates the ability to resist stretching or compression during the elastic deformation stage, the Poisson's ratio indicates the proportion of contraction in the vertical direction when the material is stretched in the direction of force, and the compression rate indicates the proportion that can be compressed under pressure.

[0084] In one embodiment of the present invention, the pre-tightening torque F p The calculation formula is as follows:

[0085]

[0086] Where M represents the tightening torque of the bolt, f t Indicates the thread friction coefficient, f h It represents the friction coefficient between the contact surface of the bolt and the connecting part, and d represents the bolt diameter.

[0087] It should be noted that the tightening torque of the bolt is obtained through an electronic torque tool, and the thread friction coefficient and the friction coefficient between the bolt and the contact surface of the connecting part are provided by the bolt manufacturer and will not be elaborated here.

[0088] In one embodiment of the present invention, Figure 2 As shown, the bolt parameters and engine connection part parameters are preprocessed to generate an initial vector, including the following steps:

[0089] Step S201, directly filling the missing values ​​of bolt parameters and engine connection component parameters with zero values;

[0090] Step S202, normalizing the bolt parameters and the engine connection component parameters respectively by using standard scores;

[0091] The calculation formula for normalizing bolt parameters by standard fraction is as follows:

[0092]

[0093] Where 1≤i≤7, z i Represents the value of the i-th dimension of the normalized bolt parameter, x i represents the value of the i-th dimension of the bolt parameter before normalization, μ and σ represent the mean and standard deviation of the bolt parameter before normalization, respectively;

[0094] Step S203, concatenating the normalized bolt parameters and the normalized engine connection component parameters to obtain an initial vector.

[0095] In one embodiment of the present invention, the tightening torque prediction model includes: a first hidden layer, a second hidden layer, a first expansion layer, a second expansion layer, a splicing layer and a classifier;

[0096] The first hidden layer inputs the initial vector and outputs the first feature matrix;

[0097] The second hidden layer inputs the initial vector and outputs the second feature matrix;

[0098] The first expansion layer is used to expand the first feature matrix into a vector representation;

[0099] The second expansion layer is used to expand the second feature matrix into a vector representation;

[0100] The concatenation layer is used to concatenate the vector representation of the first feature matrix and the vector representation of the second feature matrix into a combined vector;

[0101] The combined vector is input into the classifier, and the classification space of the classifier represents the target tightening torque of the bolt.

[0102] In one embodiment of the present invention, the calculation formula of the first hidden layer includes:

[0103] Matrix1=sigmoid(W2×(Vec T ×W1+UpMatrix)+b1);

[0104]

[0105] Where 1≤u≤14, 1≤v≤14, Matrix1 represents the first feature matrix of the first hidden layer output, Vec represents the initial vector of the first hidden layer input, UpMatrix represents the upper triangular matrix transformed by the initial vector, and the number of rows and columns of the upper triangular matrix is ​​the same as the number of dimensions of the initial vector. u，v Represents the element value of the uth row and vth column of the upper triangular matrix, Ele u represents the value of the u-th dimension of the initial vector, W1 and W2 represent the first weight parameter and the second weight parameter respectively, b1 represents the first bias parameter, T represents the transpose operation, and sigmoid represents the sigmoid activation function.

[0106] It should be noted that the size of the initial vector is 1×14, and the size of the transposed initial vector is 14×1. The first weight parameter can be designed as a vector of size 1×14. The transposed initial vector is multiplied by the first weight parameter to obtain a matrix of size 14×14, and the matrix of size 14×14 is added to the upper triangular matrix to obtain a matrix of size 14×14. The second weight parameter can be designed as a matrix of size 16×14. Then, the first feature matrix obtained by multiplying the second weight parameter with the matrix of size 14×14 is a 16×14 matrix, where the number of matrix rows corresponding to the second weight parameter is a custom parameter.

[0107] In one embodiment of the present invention, the calculation formula of the second hidden layer includes:

[0108] Matrix2=sigmoid(W4×(Vec T ×W3+DownMatrix)+b2);

[0109]

[0110] Where 1≤u≤14, 1≤v≤14, Matrix2 represents the second feature matrix of the second hidden layer output, Vec represents the initial vector of the second hidden layer input, DownMatrix represents the lower triangular matrix transformed by the initial vector, and the number of rows and columns of the lower triangular matrix is ​​the same as the number of dimensions of the initial vector, DownMatrix u，v Represents the element value of the u-th row and v-th column of the lower triangular matrix, Ele u represents the value of the u-th dimension of the initial vector, W3 and W4 represent the third weight parameter and the fourth weight parameter respectively, b2 represents the second bias parameter, T represents the transpose operation, and sigmoid represents the sigmoid activation function.

[0111] It should be noted that the size of the initial vector is 1×14, and the size of the transposed initial vector is 14×1. The third weight parameter can be designed as a vector of size 1×14. The transposed initial vector is multiplied by the third weight parameter to obtain a matrix of size 14×14, and the matrix of size 14×14 is added to the lower triangular matrix to obtain a matrix of size 14×14. The fourth weight parameter can be designed as a matrix of size 16×14. Then, the second characteristic matrix obtained by multiplying the fourth weight parameter with the matrix of size 14×14 is a matrix of size 16×14, where the number of matrix rows corresponding to the fourth weight parameter is a custom parameter.

[0112] In one embodiment of the present invention, Figure 3 As shown, a training data set for training a tightening torque prediction model is constructed through a simulation platform, including the following steps:

[0113] Step S301, constructing a finite element analysis model of the bolt and the engine connection part through a simulation platform, and generating an initial vector according to step S101 as training data of a training sample;

[0114] Step S302, randomly generating K tightening torques between a lower limit value of the tightening torque and an upper limit value of the tightening torque;

[0115] Wherein K, the lower limit value of the tightening torque and the upper limit value of the tightening torque are all custom parameters. Preferably, K is set to 5, and the lower limit value of the tightening torque and the upper limit value of the tightening torque can be set according to the standards formulated by the country or the industry;

[0116] Step S303, respectively calculating the sum of the environmental loads of the bolts at different ambient temperatures under each tightening torque;

[0117] Different ambient temperatures are custom parameters;

[0118] For example, the ambient temperature can be set to 6 groups, that is, the upper and lower temperature limits that the engine can bear are divided into equal temperature intervals. For example, the upper and lower temperature limits that the engine can bear are 100°C and 0°C respectively, then the 6 groups of ambient temperatures are 0°C, 20°C, 40°C, 60°C, 80°C and 100°C respectively;

[0119] Step S304, respectively calculating the sum of the dynamic loads of the bolts at different engine speeds under each tightening torque;

[0120] The different engine speeds are all custom parameters;

[0121] For example, the engine speed can be set to 6 groups, that is, the maximum speed and the minimum speed of the engine are divided into equal speed intervals. For example, the maximum speed and the minimum speed of the engine are 3000RPM and 0RPM respectively, then the 6 groups of engine speeds are 0RPM, 600RPM, 1200RPM, 1800RPM, 2400RPM and 3000RPM respectively;

[0122] Step S305, respectively summing up the sum of the environmental loads of the bolts at different ambient temperatures under each tightening torque and the sum of the dynamic loads of the bolts at different engine speeds under the corresponding tightening torque to obtain a comprehensive score;

[0123] Step S306, taking the tightening torque with the smallest comprehensive score as a sample label of a training sample;

[0124] Step S307, repeat steps S302 to S306 until U training samples are obtained as the training data set.

[0125] In one embodiment of the present invention, the environmental load Load Env The calculation formula is as follows:

[0126] Load Env =F p -(E×Area×α×T);

[0127] where F p , E, Area and α represent the pre-tightening torque, stiffness, cross-sectional area and thermal expansion coefficient of the bolt, respectively, and T represents the ambient temperature.

[0128] In one embodiment of the present invention, the dynamic load Load dyn The calculation formula is as follows:

[0129]

[0130] where F p, m and MaxSwing represent the pre-tightening torque, weight and maximum amplitude of the bolt respectively, n represents the engine speed, and β represents the proportional coefficient ranging from 0 to 1.

[0131] In one embodiment of the present invention, Figure 4 As shown, the present invention provides an engine bolt tightening torque measurement and monitoring system, comprising:

[0132] A data acquisition module 401 is used to acquire bolt parameters and engine connection component parameters;

[0133] An initial vector generation module 402, which is used to pre-process bolt parameters and engine connection component parameters to generate an initial vector;

[0134] A training data set construction module 403, which is used to construct a training data set for training a tightening torque prediction model through a simulation platform;

[0135] The tightening torque prediction module 404 is used to input the initial vector into the trained tightening torque prediction model, and the output value represents the target tightening torque of the bolt.

[0136] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A method for measuring and monitoring the tightening torque of engine bolts, characterized in that: The following steps are involved: Step S101, collecting bolt parameters and engine connection part parameters, and performing preprocessing to generate an initial vector; The initial vector is obtained by concatenating the preprocessed bolt parameters and engine connection parameters; Bolt parameters include: diameter, length, torque coefficient, thermal expansion coefficient, elastic modulus, pre-tightening torque and Poisson's ratio; Engine connector parameters include: material type, thickness, hole diameter, hardness, compressibility, thermal expansion coefficient and elastic modulus; Step S102, constructing a training data set for training a tightening torque prediction model through a simulation platform; The input of the tightening torque prediction model is the initial vector; The output of the tightening torque prediction model is the target tightening torque of the bolt; The training data set includes U training samples, each of which includes a training data and a sample label, where U is a custom parameter; The training data corresponds to the initial vector, and the sample label corresponds to the target tightening torque of the bolt; Step S103, inputting the initial vector into the trained tightening torque prediction model, and the output value represents the target tightening torque of the bolt.

2. The engine bolt tightening torque measurement and monitoring method according to claim 1, characterized in that: Pre-tightening torque F p The calculation formula is as follows: Where M represents the tightening torque of the bolt, f t Indicates the thread friction coefficient, f h It represents the friction coefficient between the contact surface of the bolt and the connecting part, and d represents the bolt diameter.

3. The engine bolt tightening torque measurement and monitoring method according to claim 1, characterized in that: Preprocessing the bolt parameters and engine connection part parameters to generate an initial vector includes the following steps: Step S201, directly filling the missing values ​​of bolt parameters and engine connection component parameters with zero values; Step S202, normalizing the bolt parameters and the engine connection component parameters respectively by using standard scores; The calculation formula for normalizing bolt parameters by standard fraction is as follows: Where 1≤i≤7, z i Represents the value of the i-th dimension of the normalized bolt parameter, x i represents the value of the i-th dimension of the bolt parameter before normalization, μ and σ represent the mean and standard deviation of the bolt parameter before normalization, respectively; Step S203, concatenating the normalized bolt parameters and the normalized engine connection component parameters to obtain an initial vector.

4. The engine bolt tightening torque measurement and monitoring method according to claim 1, characterized in that: The tightening torque prediction model includes: a first hidden layer, a second hidden layer, a first expansion layer, a second expansion layer, a splicing layer and a classifier; The first hidden layer inputs the initial vector and outputs the first feature matrix; The second hidden layer inputs the initial vector and outputs the second feature matrix; The first expansion layer is used to expand the first feature matrix into a vector representation; The second expansion layer is used to expand the second feature matrix into a vector representation; The concatenation layer is used to concatenate the vector representation of the first feature matrix and the vector representation of the second feature matrix into a combined vector; The combined vector is input into the classifier, and the classification space of the classifier represents the target tightening torque of the bolt.

5. The engine bolt tightening torque measurement and monitoring method according to claim 4, characterized in that: The calculation formula for the first hidden layer includes: Matrix1=sigmoid(W2×(Vec T ×W1+UpMatrix)+b1); Where 1≤u≤14, 1≤v≤14, Matrix1 represents the first feature matrix of the first hidden layer output, Vec represents the initial vector of the first hidden layer input, UpMatrix represents the upper triangular matrix transformed by the initial vector, and the number of rows and columns of the upper triangular matrix is ​​the same as the number of dimensions of the initial vector. u，v Represents the element value of the uth row and vth column of the upper triangular matrix, Ele u represents the value of the u-th dimension of the initial vector, W1 and W2 represent the first weight parameter and the second weight parameter respectively, b1 represents the first bias parameter, T represents the transpose operation, and sigmoid represents the sigmoid activation function.

6. The engine bolt tightening torque measurement and monitoring method according to claim 4, characterized in that: The calculation formula for the second hidden layer includes: Matrix2=sigmoid(W4×(Vec T ×W3+DownMatrix)+b2); Where 1≤u≤14, 1≤v≤14, Matrix2 represents the second feature matrix of the second hidden layer output, Vec represents the initial vector of the second hidden layer input, DownMatrix represents the lower triangular matrix transformed by the initial vector, and the number of rows and columns of the lower triangular matrix is ​​the same as the number of dimensions of the initial vector, DownMatrix u，v Represents the element value of the u-th row and v-th column of the lower triangular matrix, Ele u represents the value of the u-th dimension of the initial vector, W3 and W4 represent the third weight parameter and the fourth weight parameter respectively, b2 represents the second bias parameter, T represents the transpose operation, and sigmoid represents the sigmoid activation function.

7. The engine bolt tightening torque measurement and monitoring method according to claim 1, characterized in that: The training data set for training the tightening torque prediction model is constructed through the simulation platform, including the following steps: Step S301, constructing a finite element analysis model of the bolt and the engine connection part through a simulation platform, and generating an initial vector according to step S101 as training data of a training sample; Step S302, randomly generating K tightening torques between a lower limit value of the tightening torque and an upper limit value of the tightening torque; Among them, K, lower limit of tightening torque and upper limit of tightening torque are all custom parameters; Step S303, respectively calculating the sum of the environmental loads of the bolts at different ambient temperatures under each tightening torque; The different ambient temperatures are all custom parameters; Step S304, respectively calculating the sum of the dynamic loads of the bolts at different engine speeds under each tightening torque; Step S305, respectively summing up the sum of the environmental loads of the bolts at different ambient temperatures under each tightening torque and the sum of the dynamic loads of the bolts at different engine speeds under the corresponding tightening torque to obtain a comprehensive score; Step S306, taking the tightening torque with the smallest comprehensive score as a sample label of a training sample; Step S307, repeat steps S302 to S306 until U training samples are obtained as the training data set.

8. The engine bolt tightening torque measurement and monitoring method according to claim 7, characterized in that: Environmental Load Env The calculation formula is as follows: Load Env =F p -(E×Area×α×T); Among them, F p , E, Area and α represent the pre-tightening torque, stiffness, cross-sectional area and thermal expansion coefficient of the bolt, respectively, and T represents the ambient temperature.

9. The engine bolt tightening torque measurement and monitoring method according to claim 7, characterized in that: Dynamic Load dyn The calculation formula is as follows: Among them, F p , m and MaxSwing represent the pre-tightening torque, weight and maximum amplitude of the bolt respectively, n represents the engine speed, and β represents the proportional coefficient ranging from 0 to 1.

10. An engine bolt tightening torque measurement and monitoring system, characterized in that: The method for measuring and monitoring the tightening torque of an engine bolt according to any one of claims 1 to 9 comprises: A data acquisition module, which is used to collect bolt parameters and engine connection parameters; An initial vector generation module, which is used to pre-process bolt parameters and engine connection part parameters to generate an initial vector; A training data set construction module, which is used to construct a training data set for training a tightening torque prediction model through a simulation platform; The tightening torque prediction module is used to input the initial vector into the trained tightening torque prediction model, and the output value represents the target tightening torque of the bolt.

Images