Gearbox abnormal state monitoring method and system based on infrared imaging change rate

Abstract

The invention belongs to the technical field of gearboxes, and particularly discloses a gearbox abnormal state monitoring method and system based on an infrared imaging change rate, and the method comprises the steps: collecting the surface infrared thermal imaging of a gearbox in real time, visualizing the gradient distribution condition of an infrared temperature field, and determining the position information of a calibration point on the gearbox; a temperature sensor is arranged at a calibration point on the gear box to obtain a temperature signal of the gear box; calculating a difference value matrix of the gearbox temperature signal and the infrared thermal imaging temperature, judging whether the maximum value of the difference value matrix exceeds a preset first alarm threshold value or not, and preliminarily judging whether the state of the tested piece is abnormal or not; and reconstructing the temperature field gradient image, comparing the maximum temperature value in the reconstructed temperature field gradient image with a preset second alarm threshold value, and re-determining whether the state of the measured piece is abnormal or not. By adopting the technical scheme, digital reconstruction and visual modeling of the temperature field are carried out, gradient zone imaging of the temperature field of the gearbox is monitored and analyzed, and the abnormal state of the gearbox is detected.

Description

Technical Field

[0001] The invention belongs to the technical field of gear boxes, and relates to a method and system for monitoring abnormal conditions of a gear box based on infrared imaging change rate. Background Art

[0002] The gearbox is one of the basic key components in mechanical equipment, and its working state directly affects the performance and life of the equipment. The transmission parts in the gearbox have power losses such as meshing loss, oil stirring loss, and windage loss during the movement and power transmission process, and the parts in the box will release a lot of heat during the working process.

[0003] If the lubrication system of the gearbox cannot absorb the heat released by the parts in the working process in time, the temperature of the parts and oil in the gearbox will be too high, affecting the normal operation of the gearbox. Temperature detection of the gearbox can help discover and predict faults and abnormalities inside the gearbox, so as to take measures to avoid faults and damage caused by high temperature.

[0004] Infrared thermal imaging technology is widely used in the field of temperature detection. Compared with traditional temperature sensors, infrared imaging has the advantages of non-contact, large detection area, intuitive imaging, and real-time monitoring. However, due to factors such as ambient light and object material, the temperature measurement accuracy of infrared thermal imaging is not high, and the judgment of abnormal temperature rise components is not real-time. Therefore, it is of great significance in practical engineering to calibrate and reconstruct the infrared imaging change rate to detect the abnormal state of the gearbox. Summary of the invention

[0005] The object of the present invention is to provide a method and system for monitoring abnormal state of a gearbox based on infrared imaging change rate, to calibrate and reconstruct the infrared imaging change rate, and to detect abnormal state of the gearbox.

[0006] In order to achieve the above object, the basic scheme of the present invention is: a gearbox abnormal state monitoring method based on infrared imaging change rate, comprising the following steps:

[0007] Real-time acquisition of infrared thermal imaging of the gearbox surface;

[0008] Based on the image processing algorithm, the infrared thermal imaging change rate matrix is ​​calculated to visualize the gradient distribution of the infrared temperature field;

[0009] Based on the gradient distribution of the infrared temperature field, determine the position information of the calibration points on the gearbox;

[0010] A temperature sensor is set at a calibration point on the gearbox to obtain the temperature signal of the gearbox in real time;

[0011] Calculate the difference matrix between the gearbox temperature signal and the infrared thermal imaging temperature, determine whether the maximum value of the difference matrix exceeds the preset first alarm threshold, and preliminarily determine whether the state of the tested part is abnormal;

[0012] Based on the iterative least squares method, the calibration function is fitted to the temperature signal of the gearbox to minimize the sum of square errors between the fitting function and the calibration value, and the calibration matrix is ​​established.

[0013] The calibration matrix and the infrared thermal imaging change rate matrix are combined to reconstruct the temperature field gradient image. The maximum temperature in the reconstructed temperature field gradient image is compared with the preset second alarm threshold to determine again whether the state of the tested object is abnormal.

[0014] The working principle and beneficial effects of this basic solution are as follows: This technical solution monitors the temperature data of the gearbox during operation in real time, visualizes the gradient distribution of the infrared temperature field based on the image processing algorithm, and determines the position information of the calibration point based on the temperature gradient.

[0015] The temperature data of the selected points of the box are measured by the temperature sensor, and the calibration data matrix is ​​established. The temperature image is segmented, fitted and reconstructed based on the infrared change rate. The gearbox state is comprehensively judged by setting the temperature abnormality threshold and the infrared imaging change rate threshold, and then an early warning or alarm is issued to realize the identification and processing of the abnormal state of the gearbox.

[0016] Furthermore, based on the image processing algorithm, the infrared thermal imaging change rate matrix is ​​calculated to visualize the gradient distribution of the infrared temperature field. The specific steps are as follows:

[0017] Obtain the infrared thermal imaging image file of the gearbox surface and read the image attributes;

[0018] Read the original temperature data and construct the coordinates and temperature matrix of the pixel points;

[0019] Preprocess the read original temperature data to make the image temperature data consistent with the actual data;

[0020] Calculate the temperature change rate matrix and determine the isotherm interval;

[0021] The temperature gradient distribution diagram is drawn through the function algorithm.

[0022] By real-time monitoring of the temperature data of the gearbox during operation, the infrared temperature field gradient distribution is visualized based on the image processing algorithm.

[0023] Furthermore, the method of obtaining the image file of the surface infrared thermal imaging of the gearbox and reading the image attributes is as follows:

[0024] After obtaining the temperature image of infrared thermal imaging, open the file in binary read-write mode and locate the 36 bytes from the end of the file;

[0025] Read the width W and height H of the image from the file and calculate the number of pixels in the image:

[0026] pixels = W * H;

[0027] Calculate the image data offset offset:

[0028] offset=-(36+pixels*2+128);

[0029] The actual infrared temperature value dfd corresponding to the pixel position in the i-th row and j-th column ij for:

[0030] dfd ij =dfd ij / 1000+offset.

[0031] Simple operation and easy to use.

[0032] Furthermore, the temperature change rate matrix is ​​calculated and the isotherm interval is determined as follows:

[0033] Resize the globally processed temperature matrix into a matrix of width w and height h:

[0034]

[0035] Among them, dfd ij Indicates the actual infrared temperature value corresponding to the pixel position in the i-th row and j-th column;

[0036] All image temperature data are stored in the infrared temperature raw data matrix D original Find the global minimum value dfd of the matrix min And the corresponding coordinate position (a km ,b km ), define the temperature change rate ΔT = as:

[0037]

[0038] Among them, a ij , b ij ) represents the coordinates of the i-th row and j-th column of the coordinate matrix; a ij is the horizontal coordinate of the pixel point coordinate matrix in the i-th row and j-th column, b ij is the vertical coordinate of the pixel point coordinate matrix in the i-th row and j-th column; a km is the horizontal coordinate of the kth row and mth column of the pixel coordinate matrix; b km The horizontal coordinate of the kth row and mth column of the pixel coordinate matrix;

[0039] Calculate the temperature change rate of each point relative to the lowest point in turn, and finally take the minimum point as the reference value 1 to obtain the temperature change rate matrix D rate , find the global minimum value ΔT of the matrix min and maximum value ΔT max , considering the different local temperature change rates, in order to avoid drawing local isotherms too densely, the interval n of the isothermal gradient is determined as:

[0040]

[0041] Search for temperature equal value points, use the function algorithm to visualize the isotherm diagram with an interval of n, and determine the number k of points to be calibrated and their position coordinates (x i ,y i ), i represents the i-th calibration point.

[0042] Taking into account the different local temperature change rates, the interval of the isothermal gradient is determined to avoid drawing local isotherms too densely.

[0043] Furthermore, based on the iterative least squares method, a calibration matrix is ​​established. The specific steps are as follows:

[0044] Define the loss function S(x) as:

[0045]

[0046] Among them, r(x) is the residual function; x is the substitution parameter; A is the sampling value of the input independent variable, that is, the infrared temperature matrix to be calibrated; F is the observed output value, that is, the calibration matrix measured by the infinite temperature sensor;

[0047] Assuming that the actual temperature changes continuously and the function can be linearly approximated in a certain range of x, the Taylor expansion is:

[0048] r(x0+Δ)=r(x0)+J r Δ

[0049] Among them, X0 represents the value that can be linearly approximated, J r Jordan standard form matrix transformed from the residual function matrix;

[0050] Solution:

[0051]

[0052] The solution to this problem is:

[0053] Δ=-(J r T J r ) -1 J r T r(x0)

[0054] By continuously iterating x to approximate it, the optimal solution is reached, and the maximum number of iterations k is defined as ≤ 10:

[0055] x (k+1) =x (k) +αΔ

[0056] Among them, x (k+1) is the value of the k+1th iteration, x (k) is the value of the kth iteration, α is the iteration correction coefficient;

[0057] The fitting correction error based on iterative least squares method meets the calibration requirements within the allowable range, and the temperature calibration matrix D is obtained. standard :

[0058]

[0059] Where w is the image width, h is the image length, and d ij Represents the fitted temperature value of the i-th row and j-th column.

[0060] Based on the iterative least squares fitting algorithm, the temperature numerical calibration is performed by continuously iteratively updating the parameters so that the sum of the square errors between the fitting function and the calibration value is minimized.

[0061] Furthermore, based on the calibration matrix D standard , perform unit conversion and bias correction, and finally restore the reconstructed temperature data matrix D final :

[0062] D final =1000×D standard -offset×J

[0063] Among them, offset is the image data offset, and J represents a matrix of all ones.

[0064] Based on the reconstructed temperature data matrix, the temperature field is reconstructed and the isotherm diagram is drawn to detect whether the maximum temperature exceeds the set threshold, determine whether the gearbox is in an abnormal state, and issue early warning and timely alarm to help employees maintain equipment safety and reduce potential accidents.

[0065] The present invention also provides a gearbox abnormal state monitoring system based on the method of the present invention, comprising an infrared thermal imager, a temperature sensor, a communication module and a host computer;

[0066] The infrared thermal imager is used to thermally image the surface of the gearbox and measure the overall temperature;

[0067] The temperature sensor is installed at the calibration point of the gear box and is used to collect the temperature signal on the gear box. The temperature sensor is connected to the host computer through the communication module.

[0068] The system has a simple structure and can visualize the temperature field of the collected infrared temperature images, realize the imaging monitoring, analysis and display of the temperature field gradient of the gearbox, and calibrate and digitally reconstruct the temperature field data of the gearbox through temperature correction technology to realize the abnormal status monitoring of the gearbox.

[0069] Furthermore, it also includes a magnetic base, and the temperature sensor is detachably connected to the outer wall of the gear box via the magnetic base.

[0070] The temperature sensor is installed by magnetic base and can be easily disassembled.

[0071] Furthermore, it also includes a control switch, which is installed on the gear box, and the output end of the control switch is connected to the control end of the temperature sensor.

[0072] The control switch can control the temperature sensor to start and end acquisition, making it more flexible to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 It is a flow chart of a method for monitoring abnormal state of a gearbox based on infrared imaging change rate of the present invention;

[0074] Figure 2 It is a flow chart of an infrared temperature field gradient imaging algorithm of a gearbox abnormal state monitoring method based on infrared imaging change rate of the present invention;

[0075] Figure 3 It is a structural schematic diagram of the gear box abnormal state monitoring system of the present invention.

[0076] The reference numerals in the drawings of the specification include: gear box 1, infrared thermal imager 2, temperature sensor 3, antenna base 4, magnetic base 5, control switch 6, temperature receiver 7, host computer 8. DETAILED DESCRIPTION

[0077] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0078] In the description of the present invention, it is necessary to understand that the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0079] In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0080] The present invention discloses a gearbox abnormal state monitoring method based on infrared imaging change rate, such as Figure 1 As shown, the following steps are included:

[0081] Real-time acquisition of infrared thermal imaging of the gearbox surface;

[0082] Based on the image processing algorithm, the infrared thermal imaging change rate matrix is ​​calculated to visualize the gradient distribution of the infrared temperature field;

[0083] Based on the gradient distribution of the infrared temperature field, determine the position information of the calibration points on the gearbox;

[0084] A temperature sensor is set at the calibration point on the gearbox to obtain the temperature signal ΔM of the gearbox in real time. i ;

[0085] Calculate the difference matrix between the gearbox temperature signal and the infrared thermal imaging temperature, determine whether the maximum value of the difference matrix exceeds the preset first alarm threshold, and preliminarily determine whether the state of the tested part is abnormal;

[0086] Based on the iterative least squares method, the calibration function is fitted to the temperature signal of the gearbox to minimize the sum of square errors between the fitting function and the calibration value, and the calibration matrix is ​​established.

[0087] Combine the calibration matrix with the infrared thermal imaging change rate matrix to reconstruct the temperature field gradient image, compare the maximum temperature in the reconstructed temperature field gradient image with the preset second alarm threshold, and determine again whether the state of the test piece is abnormal (the first judgment is a preliminary judgment based on the original infrared imaging data. Since the data of the infrared imaging original data matrix needs to be reconstructed, the second comparison is based on the reconstructed temperature matrix. The objects of the two judgments are different, but both use whether the maximum value exceeds the threshold to determine whether the state is abnormal).

[0088] In a preferred embodiment of the present invention, Figure 2 As shown, based on the image processing algorithm, the infrared thermal imaging change rate matrix is ​​calculated to visualize the infrared temperature field gradient distribution. The specific steps are:

[0089] Obtain the infrared thermal imaging image file of the gearbox surface and read the image attributes;

[0090] Read the original temperature data, construct the coordinates of the pixel points and the temperature matrix (import the temperature image obtained by the infrared imager into MATLAB, open the jpg format file in binary reading and writing, and use the image processing algorithm to extract the temperature data matrix; set the three reference position points in the infrared field of view that are easy to measure the actual distance as l, m, and n. The three points are not on a straight line in the infrared image at the same time. For the convenience of calculation, one of the points is selected to be always perpendicular to the line formed by the other two points. Define this point as the origin of the coordinate matrix (0,0). Measure the actual distance between the three points, read the pixel distance of the three points in the infrared image, calculate the scale, and convert the coordinates of each pixel point in turn (a ij ,b ij ), construct pixel coordinate matrix);

[0091] Preprocess the read raw temperature data (such as unit conversion, m℃ to ℃, dividing the whole by 1000; calculating the image offset, subtracting the offset from the temperature matrix, etc.) to make the image temperature data consistent with the actual data;

[0092] Calculate the temperature change rate matrix and determine the isotherm interval;

[0093] The temperature gradient distribution diagram is drawn through the function algorithm.

[0094] By real-time monitoring of the temperature data of the gearbox during operation, the infrared temperature field gradient distribution is visualized based on the image processing algorithm.

[0095] In a preferred embodiment of the present invention, the method for obtaining the image file of the surface infrared thermal imaging of the gearbox and reading the image attributes is:

[0096] After obtaining the temperature image of infrared thermal imaging, open the file in binary read-write mode and locate the 36 bytes from the end of the file;

[0097] Read the width W and height H of the image from the file (read as int16 type) and calculate the number of pixels in the image:

[0098] pixels = W * H;

[0099] Calculate the image data offset offset:

[0100] offset=-(36+pixels*2+128);

[0101] The original data unit is m℃, which is converted to ℃ after global processing. The actual infrared temperature value dfd corresponding to the pixel position in the i-th row and j-th column is ij for:

[0102] dfd ij =dfd ij / 1000+offset;

[0104] First, calculate the image data offset. The original data unit of the infrared temperature image is millidegrees Celsius. To unify the units, divide the temperature value extracted from the infrared image by 1000 to convert it to Celsius. After the unit conversion, add the offset to get the actual infrared temperature value dfd ij .

[0105] In a preferred embodiment of the present invention, the method for calculating the temperature change rate matrix and determining the isotherm interval is as follows:

[0106] Resize the globally processed temperature matrix into a matrix of width w and height h:

[0107]

[0108] Among them, dfd ij Indicates the actual infrared temperature value corresponding to the pixel position in the i-th row and j-th column;

[0109] All image temperature data are stored in the infrared temperature raw data matrix D original Find the global minimum value dfd of the matrix min And the corresponding coordinate position (a km ,b km ), define the temperature change rate ΔT = as:

[0110]

[0111] Among them, (a ij , b ij ) represents the coordinates of the i-th row and j-th column of the coordinate matrix; a ij is the horizontal coordinate of the pixel point coordinate matrix in the i-th row and j-th column, bij is the vertical coordinate of the pixel point coordinate matrix in the i-th row and j-th column; a km is the horizontal coordinate of the kth row and mth column of the pixel coordinate matrix; b km The horizontal coordinate of the kth row and mth column of the pixel coordinate matrix;

[0112] Calculate the temperature change rate of each point relative to the lowest point in turn, and finally take the minimum point as the reference value 1 to obtain the temperature change rate matrix D rate , find the global minimum value ΔT of the matrix min and maximum value ΔT max , considering the different local temperature change rates, in order to avoid drawing local isotherms too densely, the interval n of the isothermal gradient is determined as:

[0113]

[0114] Search for temperature equal value points, use the function algorithm to visualize the isotherm diagram with an interval of n, and determine the number k of points to be calibrated and their position coordinates (x i ,y i ), i represents the i-th calibration point.

[0115] In a preferred embodiment of the present invention, a calibration matrix is ​​established based on iterative least squares method, and the specific steps are as follows:

[0116] Define the loss function S(x) as:

[0117]

[0118] Among them, r(x) is the residual function; x is the substitution parameter; A is the sampling value of the input independent variable, that is, the infrared temperature matrix to be calibrated; F is the observed output value, that is, the calibration matrix measured by the infinite temperature sensor;

[0119] Assuming that the actual temperature changes continuously and the function can be linearly approximated in a certain range of x, the Taylor expansion is:

[0120] r(x0+Δ)=r(x0)+J r Δ

[0121] Among them, X0 represents the value that can be linearly approximated, J r Jordan standard form matrix transformed from the residual function matrix;

[0122] Solution:

[0123]

[0124] The solution to this problem is:

[0125] Δ=-(J r TJ r ) -1 J r T r(x0)

[0126] By continuously iterating x to approximate it, the optimal solution is reached, and the maximum number of iterations k is defined as ≤ 10:

[0127] x (k+1) =x (k) +αΔ

[0128] Among them, x (k+1) is the value of the k+1th iteration, x (k) is the value of the kth iteration, α is the iteration correction coefficient;

[0129] The fitting correction error based on iterative least squares method meets the calibration requirements within the allowable range, and the temperature calibration matrix D is obtained. standard :

[0130]

[0131] Where w is the image width, h is the image length, and d ij Represents the fitted temperature value of the i-th row and j-th column.

[0132] Preferably, based on the calibration matrix D standard , perform unit conversion and bias correction, and finally restore the reconstructed temperature data matrix D final (Regenerate temperature image):

[0133] D final =1000×D standard -offset×J

[0134] Where offset is the image data offset, and J is a matrix of all ones. The coefficient is 1000, and the unit is converted to millidegrees Celsius. This is the inverse operation of the initial processing to regenerate the temperature image.

[0135] Finally, based on the reconstructed temperature matrix, the temperature field is reconstructed and the isotherm diagram is drawn to detect whether the maximum temperature exceeds the set threshold, determine whether the gearbox is in an abnormal state, and issue early warning and timely alarm to help employees maintain equipment safety and reduce potential accidents.

[0136] The present invention also provides a gearbox abnormal state monitoring system based on the method of the present invention, such as Figure 3 As shown, it includes an infrared thermal imager 2, a temperature sensor 3, a communication module and a host computer 8. The infrared thermal imager 2 is used to thermally image the surface of the gearbox 1 and measure the overall temperature. The infrared thermal imager 2 is provided with a tripod for easy installation and positioning.

[0137] The temperature sensor 3 is installed at the calibration point of the gearbox 1 to collect the temperature signal on the gearbox 1. The temperature sensor 3 is electrically connected to the host computer 8 through the communication module. The communication module can use an antenna base 4 and a temperature receiver 7. The antenna base 4 transmits the temperature sensor 3 data, and the temperature receiver 7 (such as Zigbee, etc.) receives the temperature data sent by the antenna base 4 and transmits it to the host computer 8. The host computer 8 can use a computer or other equipment to receive, store, analyze, process and display data.

[0138] This system has the characteristics of infrared temperature gradient display, high acquisition efficiency, and precise temperature calibration. It can digitally reconstruct and visualize the temperature field of the acquired infrared images, and realize imaging monitoring, analysis, display and compensation correction of the temperature field gradient of the gearbox 1, which well meets the needs of temperature monitoring of the gearbox 1 in industrial applications.

[0139] In a preferred embodiment of the present invention, the abnormal state monitoring system of the gear box 1 further comprises a magnetic base 5 , and the temperature sensor 3 is detachably connected to the outer wall of the gear box 1 via the magnetic base 5 .

[0140] The temperature sensor 3 is mounted on the gear box 1 by a wireless magnetic attraction method of the magnetic base 5, and is easy to disassemble.

[0141] In a preferred embodiment of the present invention, the gearbox 1 abnormal state monitoring system also includes a control switch 6, which is fixedly installed (such as welded, bonded, etc.) on the gearbox 1, and the output end of the control switch 6 is electrically connected to the control end of the temperature sensor 3.

[0142] The control switch 6 can control the temperature sensor 3 to start and end collection, which is more flexible to use.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0144] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A gearbox abnormal state monitoring method based on infrared imaging change rate, characterized in that: The steps include: Real-time acquisition of infrared thermal imaging of the gearbox surface; Based on the image processing algorithm, the infrared thermal imaging change rate matrix is ​​calculated to visualize the gradient distribution of the infrared temperature field; Based on the gradient distribution of the infrared temperature field, determine the position information of the calibration points on the gearbox; A temperature sensor is set at a calibration point on the gearbox to obtain the temperature signal of the gearbox in real time; Calculate the difference matrix between the gearbox temperature signal and the infrared thermal imaging temperature, determine whether the maximum value of the difference matrix exceeds the preset first alarm threshold, and preliminarily determine whether the state of the tested part is abnormal; Based on the iterative least squares method, the calibration function is fitted to the temperature signal of the gearbox to minimize the sum of square errors between the fitting function and the calibration value, and the calibration matrix is ​​established. The calibration matrix and the infrared thermal imaging change rate matrix are combined to reconstruct the temperature field gradient image. The maximum temperature in the reconstructed temperature field gradient image is compared with the preset second alarm threshold to determine again whether the state of the tested object is abnormal.

2. The method for monitoring abnormal condition of a gearbox based on infrared imaging change rate according to claim 1, characterized in that: Based on the image processing algorithm, the infrared thermal imaging change rate matrix is ​​calculated to visualize the gradient distribution of the infrared temperature field. The specific steps are as follows: Obtain the infrared thermal imaging image file of the gearbox surface and read the image attributes; Read the original temperature data and construct the coordinates and temperature matrix of the pixel points; Preprocess the read original temperature data to make the image temperature data consistent with the actual data; Calculate the temperature change rate matrix and determine the isotherm interval; The temperature gradient distribution diagram is drawn through the function algorithm.

3. The method for monitoring abnormal state of a gearbox based on infrared imaging change rate according to claim 2, characterized in that: The method of obtaining the infrared thermal imaging image file of the gearbox surface and reading the image attributes is: After obtaining the temperature image of infrared thermal imaging, open the file in binary read-write mode and locate the 36 bytes from the end of the file; Read the width W and height H of the image from the file and calculate the number of pixels in the image: pixels = W * H; Calculate the image data offset offset: offset=-(36+pixels*2+128); The actual infrared temperature value dfd corresponding to the pixel position in the i-th row and j-th column ij for: dfd ij =dfd ij / 1000+offset。 4. The method for monitoring abnormal state of a gearbox based on infrared imaging change rate according to claim 3, characterized in that: The method to calculate the temperature change rate matrix and determine the isotherm interval is as follows: Resize the globally processed temperature matrix into a matrix of width w and height h: Among them, dfd ij Indicates the actual infrared temperature value corresponding to the pixel position in the i-th row and j-th column; All image temperature data are stored in the infrared temperature raw data matrix D original Find the global minimum value of the matrix dfd min And the corresponding coordinate position (a km ,b km ), define the temperature change rate ΔT as: Among them, (a ij , b ij ) represents the coordinates of the i-th row and j-th column of the coordinate matrix; a ij is the horizontal coordinate of the pixel point coordinate matrix in the i-th row and j-th column, b ij is the vertical coordinate of the i-th row and j-th column of the pixel coordinate matrix; a km is the horizontal coordinate of the kth row and mth column of the pixel coordinate matrix; b km The horizontal coordinate of the kth row and mth column of the pixel coordinate matrix; Calculate the temperature change rate of each point relative to the lowest point in turn, and finally take the minimum point as the reference value 1 to obtain the temperature change rate matrix D rate , find the global minimum value ΔT of the matrix min and maximum value ΔT max , considering the different local temperature change rates, in order to avoid drawing local isotherms too densely, the interval n of the isothermal gradient is determined as: Search for temperature equal value points, use the function algorithm to visualize the isotherm diagram with an interval of n, and determine the number k of points to be calibrated and the position coordinates (x i ,y i ), i represents the i-th calibration point.

5. The method for monitoring abnormal state of a gearbox based on infrared imaging change rate according to claim 1, characterized in that: Based on the iterative least squares method, the calibration matrix is ​​established. The specific steps are: Define the loss function S(x) as: Among them, r(x) is the residual function; x is the substitution parameter; A is the sampling value of the input independent variable, that is, the infrared temperature matrix to be calibrated; F is the observed output value, that is, the calibration matrix measured by the infinite temperature sensor; Assuming that the actual temperature changes continuously and the function can be linearly approximated in a certain range of x, the Taylor expansion is: r(x0+Δ)=r(x0)+J r Δ Among them, X0 represents the value that can be linearly approximated, J r Jordan standard form matrix transformed from the residual function matrix; Solution: The solution to this problem is: Δ=-(J r T J r ) -1 J r T r(x0) By continuously iterating x to approximate it, the optimal solution is reached, and the maximum number of iterations k is defined as ≤ 10: x (k+1) =x (k) +aD Among them, x (k+1) is the value of the k+1th iteration, x (k) is the value of the kth iteration, α is the iteration correction coefficient; The fitting correction error based on iterative least squares method meets the calibration requirements within the allowable range, and the temperature calibration matrix D is obtained. standard : Where w is the image width, h is the image length, and d ij Represents the fitted temperature value of the i-th row and j-th column.

6. The method for monitoring abnormal condition of a gearbox based on infrared imaging change rate according to claim 5, characterized in that: Based on the calibration matrix D standard , perform unit conversion and bias correction, and finally restore the reconstructed temperature data matrix D final : D final =1000×D standard -offset×J Among them, offset is the image data shift, and J represents a matrix of all ones.

7. A gearbox abnormal state monitoring system based on the method according to any one of claims 1 to 6, characterized in that: Including infrared thermal imager, temperature sensor, communication module and host computer; The infrared thermal imager is used to thermally image the surface of the gearbox and measure the overall temperature; The temperature sensor is installed at the calibration point of the gear box and is used to collect the temperature signal on the gear box. The temperature sensor is connected to the host computer through the communication module.

8. The gearbox abnormal state monitoring system according to claim 7, characterized in that: It also includes a magnetic base, and the temperature sensor is detachably connected to the outer wall of the gear box through the magnetic base.

9. The gearbox abnormal state monitoring system according to claim 7, characterized in that: It also includes a control switch, which is installed on the gear box, and the output end of the control switch is connected to the control end of the temperature sensor.

Images