Rotary kiln gear residual stress monitoring method and system based on ultrasonic waves

Abstract

The application relates to the technical field of gear monitoring, and discloses a rotary kiln gear residual stress monitoring method and system based on ultrasonic waves, which comprises the following steps: carrying out finite element analysis on gear structure data to obtain a gear basic model, carrying out attenuation analysis on ultrasonic wave data to obtain reflection characteristics, determining an initial residual distribution map based on the reflection characteristics and the gear basic model, acquiring temperature data of the rotary kiln gear, carrying out gradient analysis on the temperature data to obtain a temperature region distribution map, inputting the temperature region distribution map and the initial residual distribution map into a pre-trained stress correction model to obtain an accurate residual distribution map, and realizing residual stress monitoring of the gear in a working state, which can effectively reflect the dynamic residual stress state of the gear in an actual working condition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gear monitoring, more particularly, the present application relates to a rotary kiln gear residual stress monitoring method and system based on ultrasonic waves. BACKGROUND

[0002] The rotary kiln gear is a crucial mechanical transmission component in rotary kiln equipment, widely used in rotary kilns in the fields of cement, metallurgy, chemical industry, etc. It bears high-strength load and is responsible for transmitting the rotary power of the kiln body to ensure the stable operation of the equipment. The rotary kiln gear is usually made of high-strength alloy steel or other wear-resistant materials and is precisely machined to ensure sufficient load-bearing capacity and durability. However, during the machining process, residual stress often occurs due to uneven cooling, machining deformation, and material non-uniformity. These residual stresses not only affect the geometric shape of the gear but also negatively impact the fatigue life, wear behavior, and load-bearing capacity of the gear. Therefore, accurately monitoring and evaluating the residual stress state of the rotary kiln gear is crucial for ensuring the reliability of the equipment.

[0003] Currently, the residual stress analysis of the rotary kiln gear mainly relies on static monitoring methods and empirical models. These methods usually evaluate the stress distribution based on static conditions after the gear is machined. However, in actual use, the rotary kiln gear is under dynamic working conditions with high temperature and high load. The residual stress inside the gear changes due to the influence of the high-temperature environment, making it difficult for static monitoring methods to accurately reflect the true stress distribution of the rotary kiln gear under working conditions.

[0004] In view of the above problems, the present application proposes a rotary kiln gear residual stress monitoring method and system based on ultrasonic waves. SUMMARY

[0005] To overcome the above-mentioned defects of the prior art, the present application provides a rotary kiln gear residual stress monitoring method and system based on ultrasonic waves.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] In a first aspect, a rotary kiln gear residual stress monitoring method based on ultrasonic waves is provided, comprising:

[0008] Obtaining ultrasonic wave data and gear structure data, performing finite element analysis on the gear structure data to obtain a gear base model, performing attenuation analysis on the ultrasonic wave data to obtain reflection characteristics, and determining an initial residual distribution map based on the reflection characteristics and the gear base model. The initial residual distribution map refers to the residual stress distribution map of the rotary kiln gear under static conditions.

[0009] The temperature data of the rotary kiln gear is acquired, and gradient analysis is performed on the temperature data to obtain a temperature region distribution diagram, which is a temperature region distribution gradient diagram of the rotary kiln gear in a working state.

[0010] The temperature region distribution diagram and the initial residual distribution diagram are input into a pre-trained stress correction model to obtain an accurate residual distribution diagram, which is a residual stress distribution diagram of the rotary kiln gear in the working state, and the stress monitoring result is obtained by analyzing the accurate residual distribution diagram.

[0011] Further, the ultrasonic data includes emission intensity values, reception intensity values, propagation time and phase difference values, and the method for obtaining the reflection characteristics by performing attenuation analysis on the ultrasonic data includes:

[0012] The propagation time is corrected according to the phase difference value, the signal propagation distance is calculated according to the corrected propagation time and a preset propagation speed, the attenuation coefficient is calculated according to the signal propagation distance, the emission intensity value and the reception intensity value, the intensity ratio between the reception intensity value and the emission intensity value is calculated, and the attenuation coefficient and the intensity ratio are taken as the reflection characteristics.

[0013] Further, the method for determining the initial residual distribution diagram based on the reflection characteristics and the gear basic model includes:

[0014] The stress distribution of the gear basic model is simulated by finite element analysis to obtain a basic stress distribution diagram, each distribution sub-region in the basic stress distribution diagram is acquired, a regression coefficient is established between each distribution sub-region and the corresponding reflection characteristics by polynomial regression, and the initial residual distribution diagram is obtained based on the regression coefficient and the basic stress distribution diagram.

[0015] Further, the method for acquiring each distribution sub-region in the basic stress distribution diagram and establishing a regression coefficient between each distribution sub-region and the corresponding reflection characteristics by polynomial regression includes:

[0016] The stress gradient of the basic stress distribution diagram is determined by finite difference method, the basic stress distribution diagram is divided into G distribution sub-regions by the stress gradient, and the regression coefficient is obtained by fitting the G distribution sub-regions and the corresponding reflection characteristics based on polynomial regression.

[0017] Further, the method for obtaining the initial residual distribution diagram based on the regression coefficient and the basic stress distribution diagram includes:

[0018] The initial residual stress value of each distribution sub-region is calculated by the regression coefficient, and the initial residual distribution diagram is determined based on the initial residual stress value of each distribution sub-region.

[0019] Further, the temperature data comprises a real-time temperature value and a temperature change rate value, the method for gradient analysis on the temperature data to obtain a temperature region distribution map comprises:

[0020] The real-time temperature value is filtered according to the temperature change rate value to obtain a target temperature value, a derivative operation is performed on the target temperature value along a radial direction of the rotary kiln gear to obtain a temperature gradient, and the temperature region distribution map is generated according to the temperature gradient.

[0021] Further, the method for filtering the real-time temperature value according to the temperature change rate value comprises:

[0022] When the temperature change rate value is greater than a preset change rate threshold, the real-time temperature value is subjected to median filtering to obtain the target temperature value.

[0023] Further, the method for analyzing the accurate residual distribution map to obtain a stress monitoring result comprises:

[0024] Stress analysis information of the accurate residual distribution map is obtained, a target stress region in the accurate residual distribution map is marked according to the stress analysis information, and a real-time stress value of the target stress region is taken as the stress monitoring result.

[0025] In a second aspect, a rotary kiln gear residual stress monitoring system based on ultrasonic waves is provided, which is used to implement the above-mentioned rotary kiln gear residual stress monitoring method based on ultrasonic waves, and comprises:

[0026] A first processing module is configured to obtain ultrasonic wave data and gear structure data, perform finite element analysis on the gear structure data to obtain a gear basic model, perform attenuation analysis on the ultrasonic wave data to obtain reflection characteristics, and determine an initial residual distribution map based on the reflection characteristics and the gear basic model, wherein the initial residual distribution map refers to a residual stress distribution map of the rotary kiln gear in a static state.

[0027] A second processing module is configured to obtain temperature data of the rotary kiln gear, perform gradient analysis on the temperature data to obtain a temperature region distribution map, wherein the temperature region distribution map refers to a temperature region distribution gradient map of the rotary kiln gear in a working state.

[0028] An analysis module is configured to input the temperature region distribution map and the initial residual distribution map into a pre-trained stress correction model to obtain an accurate residual distribution map, analyze the accurate residual distribution map to obtain a stress monitoring result, and wherein the accurate residual distribution map refers to a residual stress distribution map of the rotary kiln gear in the working state.

[0029] Compared with the prior art, the present application has the following beneficial effects:

[0030] The application firstly carries out finite element analysis on gear structure data to obtain a gear basic model, carries out attenuation analysis on ultrasonic data to obtain reflection characteristics, determines an initial residual distribution map based on the reflection characteristics and the gear basic model, obtains temperature data of the rotary kiln gear, carries out gradient analysis on the temperature data to obtain a temperature region distribution map, inputs the temperature region distribution map and the initial residual distribution map into a stress correction model pre-trained to obtain an accurate residual distribution map, so that the residual stress monitoring of the gear in the working state is realized, and the dynamic residual stress state of the gear in the actual working condition can be effectively reflected. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 It is a flowchart of the rotary kiln gear residual stress monitoring method based on ultrasonic waves in the application.

[0032] Figure 2 It is a structural schematic diagram of the rotary kiln gear residual stress monitoring system based on ultrasonic waves in the application.

[0033] Figure 3 It is a flowchart of the method for carrying out attenuation analysis on ultrasonic data to obtain reflection characteristics in the application.

[0034] Figure 4 It is a flowchart of the method for determining an initial residual distribution map based on reflection characteristics and a gear basic model in the application. DETAILED DESCRIPTION

[0035] To make the objectives, technical solutions and advantages of the embodiments of the application clearer, the technical solutions of the embodiments of the application will be described below in detail with reference to the drawings of the embodiments of the application. Obviously, the described embodiments are some but not all of the embodiments of the application. Based on the described embodiments of the application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the scope of protection of the application.

[0036] Unless otherwise defined, the technical terms or scientific terms used in the application should be understood as the usual meanings understood by those of ordinary skill in the art to which the application belongs. The terms "first", "second" and similar terms used in the application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0037] Embodiment 1

[0038] Please see Figure 1 As shown, this embodiment discloses a method for monitoring residual stress in rotary kiln gears based on ultrasound, including:

[0039] S10: Acquire ultrasonic data and gear structure data, perform finite element analysis on the gear structure data to obtain the gear basic model, perform attenuation analysis on the ultrasonic data to obtain reflection characteristics, and determine the initial residual distribution map based on the reflection characteristics and the gear basic model. The initial residual distribution map refers to the residual stress distribution map of the rotary kiln gear under static conditions.

[0040] In this embodiment, the gear structure data includes at least geometric dimension data and material property data. The geometric dimension data includes gear diameter, number of teeth, tooth pitch, tooth height, gear wall thickness, tooth root thickness, and tooth tip thickness, etc. The material property data includes material type, elastic modulus, and Poisson's ratio, etc. In the above, material type refers to the type of material used in the gear (e.g., steel, aluminum alloy, composite material, etc.). The differences in mechanical properties of different materials will directly affect the residual stress of the gear.

[0041] The method to obtain the basic gear model by performing finite element analysis on the gear structure data can be to pre-build it using existing modeling software, such as ANSYS or ABAQUS. Taking ANSYS as an example, firstly, a geometric model of the rotary kiln gear is created or imported into ANSYS. Then, material properties are defined for the gear in ANSYS, and relevant data on the material type used in the gear (such as steel, aluminum alloy, composite material, etc.) are input. Building the basic gear model is an existing technology, and this embodiment will not elaborate on it further.

[0042] In this embodiment, the ultrasonic data includes the emission intensity value, the received intensity value, the propagation time, and the phase difference value. The emission intensity value refers to the intensity of the sound wave generated by the ultrasonic transmitter when it emits a signal. The received intensity value refers to the intensity of the ultrasonic signal returned after passing through the object being tested (such as a rotary kiln gear) during propagation. The phase difference value refers to the phase difference between the reflected signal and the incident signal.

[0043] like Figure 3 As shown, methods for obtaining reflection characteristics by performing attenuation analysis on ultrasonic data include:

[0044] The propagation time is corrected based on the phase difference. The signal propagation distance is calculated based on the corrected propagation time and the preset propagation speed. Then, the attenuation coefficient is calculated based on the signal propagation distance, the transmitted intensity value, and the received intensity value. The intensity ratio between the received intensity value and the transmitted intensity value is calculated. The attenuation coefficient and the intensity ratio are used as reflection characteristics.

[0045] It should be noted that the method of correcting the propagation time according to the phase difference value can be realized by converting the phase difference value into a time deviation, and then summing the time deviation and the propagation time to obtain the corrected propagation time.

[0046] The method of converting the phase difference value into a time deviation includes:

[0047]

[0048] wherein, is the time deviation caused by the phase difference value, is the phase difference value, is the frequency of the ultrasonic wave.

[0049] wherein, the propagation velocity refers to the velocity of the ultrasonic wave propagating in a specific material, which is related to the elastic modulus and density of the material, and is usually a constant value.

[0050] The method of calculating the attenuation coefficient according to the signal propagation distance, the transmission intensity value and the reception intensity value includes:

[0051]

[0052] wherein, is the attenuation coefficient, is the signal propagation distance, is the transmission intensity value, is the reception intensity value, is the logarithmic function with base 10.

[0053] As shown in Figure 4 , the method of determining the initial residual distribution map based on the reflection feature and the gear base model includes:

[0054] The stress distribution of the gear base model is simulated by finite element analysis to obtain a base stress distribution map, each distribution sub-region in the base stress distribution map is obtained, the regression coefficients of each distribution sub-region and the corresponding reflection feature are established by polynomial regression, and the initial residual distribution map is obtained based on the regression coefficients and the base stress distribution map.

[0055] It should be noted that the method of simulating the stress distribution of the gear base model by finite element analysis can be to select a static analysis solver in ANSYS software, calculate the stress distribution of the gear under given load conditions, and the given load can be torque load and axial load, etc. Taking the torque load as an example, the torque load is usually applied to the tooth surface of the gear, simulating the torque transmitted by the gear in actual work. The torque load will cause the distortion and stress of the gear. The torque load can be applied to the tooth surface of the gear, or the axial torque can be applied through the shaft center point of the gear.

[0056] ​​The method for obtaining each distribution sub-region in the basic stress distribution map and establishing regression coefficients between each distribution sub-region and the corresponding reflection feature through polynomial regression includes:

[0057] The stress gradient of the basic stress distribution map is determined through the finite difference method, the basic stress distribution map is divided into G distribution sub-regions through the stress gradient, and the G distribution sub-regions are fitted with the corresponding reflection feature based on polynomial regression to obtain the regression coefficients.

[0058] It can be understood that the finite difference method is a mathematical method commonly used in numerical calculation, and is particularly suitable for solving partial differential equations (PDEs) or difference equations. The basic idea is to discretize the continuous problem and convert the differential operation into a difference operation to obtain an approximate solution. In the calculation of the stress gradient, the main role of the finite difference method is to calculate the stress change rate of each node or grid element in the basic stress distribution map, and then obtain the stress gradient.

[0059] Therefore, in the present embodiment, the method for dividing the basic stress distribution map into G distribution sub-regions through the stress gradient can be to set a threshold according to the change rate of the stress gradient. The regions with larger stress gradients generally represent stress concentration regions, and these regions need to be divided into distribution sub-regions separately, for example:

[0060] The value of the stress gradient is used to divide the basic stress distribution map. The following criteria can be set:

[0061] Regions with larger stress gradients (i.e., higher change rates) are divided into separate sub-regions (usually stress concentration regions);

[0062] Regions with smaller stress gradients (i.e., slower change rates) are considered as a whole region or divided into multiple sub-regions.

[0063] The division criteria can be based on the specific numerical value of the stress gradient, or divided according to the change of the relative gradient, for example:

[0064] High stress gradient region: a region with large stress change, which can be divided into a high gradient sub-region;

[0065] Low stress gradient region: a region with small stress change, which is a low gradient sub-region.

[0066] In this process, G represents the total number of distribution sub-regions divided.

[0067] It should be noted that the relationship between the reflection characteristics and the stress gradient is generally based on the interaction of the physical properties of the material and the stress state. Specifically, there is a certain nonlinear relationship between the reflection characteristics (such as the attenuation coefficient and the intensity ratio) and the stress gradient, which is mainly reflected in the influence of stress on the internal structure and surface characteristics of the material (such as density, elastic modulus, micro-defects, etc.), thereby affecting the propagation of acoustic waves. For example, when a material (such as a rotary kiln gear) is under stress, especially when the stress gradient is large in different regions, the internal structure of the material will change, which affects the propagation characteristics of acoustic waves. When the stress gradient is large, the microstructure changes in the material (such as micro-cracks, phase changes, density changes, etc.) cause greater obstacles to the propagation of acoustic waves, thereby increasing the attenuation of acoustic waves. The attenuation coefficient of the target stress region is usually higher. The intensity ratio refers to the ratio of the reflected signal intensity to the incident signal intensity, which is usually related to the surface state of the material, the interface characteristics, and the change of the acoustic wave propagation path. When the stress gradient is large, the surface characteristics of the material will change (such as cracks or small deformations), thereby affecting the reflection characteristics of acoustic waves. The area with a large stress gradient usually results in a large change in reflected intensity, thereby affecting the intensity ratio.

[0068] The method for obtaining the initial residual distribution map based on the regression coefficients and the basic stress distribution map includes:

[0069] The initial residual stress value of each distribution sub-region is calculated by the regression coefficient, and the initial residual distribution map is determined based on the initial residual stress value of each distribution sub-region.

[0070] The specific method for calculating the initial residual stress value of each distribution sub-region by the regression coefficient is as follows:

[0071] A regression model is established between the stress value of each distribution sub-region in the basic stress distribution map and the corresponding reflection characteristics (such as the attenuation coefficient and the intensity ratio) by polynomial regression. The form of the regression model is as follows:

[0072]

[0073] wherein, is the initial residual stress value, is the attenuation coefficient, is the intensity ratio, , , , , , … are regression coefficients, representing the influence degree of the reflection characteristics on the initial residual stress.

[0074] For each distribution sub-region, the attenuation coefficient and the intensity ratio The attenuation coefficient And the intensity ratio The initial residual stress value is substituted into the regression model to calculate the initial residual stress value The initial residual stress distribution map is determined based on the initial residual stress value of each distribution sub-region, which means that the initial residual stress value is assigned to each distribution sub-region of the basic stress distribution map. In this way, the calculated initial residual stress value can be distributed in the basic stress distribution map to form the initial residual stress distribution map.

[0075] In the above steps, the following technical effects can be achieved:

[0076] First, the structure data is obtained and the gear basic model is constructed, then the reflection characteristics are calculated using ultrasonic data, and finally the initial residual distribution map is established based on the two, which ensures the accuracy of the residual stress distribution calculation and can more truly reflect the static residual stress state of the rotary kiln gear. The finite element analysis provides the overall stress distribution trend of the gear, and the ultrasonic data provides the local attenuation information. The initial residual distribution map obtained by combining the two can reflect the overall stress state of the gear and also reflect the local stress characteristics, ensuring the integrity and accuracy of the distribution map.

[0077] S20: Obtain the temperature data of the rotary kiln gear, and perform gradient analysis on the temperature data to obtain a temperature region distribution map, wherein the temperature region distribution map refers to a temperature region distribution gradient map of the rotary kiln gear under working conditions.

[0078] In this embodiment, the temperature data refers to the temperature-related data of each region of the rotary kiln gear under working conditions. These data are usually provided by temperature sensors or infrared imaging devices and are used to reflect the temperature distribution of the gear under high-temperature working conditions. The above working conditions refer to the comprehensive influence of load, temperature and other factors on the gear during the actual operation of the rotary kiln, so as to ensure the smooth rotation of the kiln body and the completion of the material processing process.

[0079] It should be noted that the temperature data includes real-time temperature values and temperature change rate values.

[0080] The method for performing gradient analysis on the temperature data to obtain the temperature region distribution map includes:

[0081] The real-time temperature values are filtered according to the temperature change rate values to obtain target temperature values, and the target temperature values are subjected to derivative operation along the radial direction of the rotary kiln gear to obtain temperature gradients, and the temperature region distribution map is generated according to the temperature gradients.

[0082] The method for filtering the real-time temperature values according to the temperature change rate values includes:

[0083] When the temperature change rate value is greater than the preset change rate threshold value, the real-time temperature value is subjected to median filtering processing to obtain a target temperature value.

[0084] It can be understood that the purpose of the median filtering processing of the real-time temperature value is to remove noise and outliers, thereby improving the smoothness and accuracy of the temperature data. Specifically, median filtering is a nonlinear filtering method suitable for removing burst noise or extreme values in a signal. Median filtering can remove outliers without significantly changing the true trend of the data. Through the median filtering processing of the temperature data, the actual change of the temperature can be more accurately reflected, and in further gradient analysis, a more accurate temperature gradient can be effectively calculated.

[0085] The purpose of the derivative operation of the target temperature value along the radial direction of the kiln gear is that the radial gradient of the temperature reflects the rate of change of the temperature from the center to the edge of the gear. By performing the derivative operation on the temperature data, the change of the temperature with the spatial position can be quantified, helping to identify areas with large temperature differences.

[0086] The method of generating a temperature region distribution map according to the temperature gradient can include: combining the temperature gradient with a gear base model, for example, dividing the gear base model into sub-regions along the radial direction of the kiln gear, and each sub-region corresponds to a temperature gradient.

[0087] In this embodiment, the combination of step S10 and step S20 in sequence can produce the following effects:

[0088] Step S10 constructs a gear base model through finite element analysis and performs attenuation analysis combined with ultrasonic data to extract reflection characteristics, thereby obtaining an initial residual distribution map. Step S20 further introduces temperature data of the kiln gear and performs gradient analysis to obtain a temperature region distribution map. On the basis of static initial residual stress analysis, the influence of temperature on stress is combined to correct the residual stress distribution and improve the accuracy of measurement.

[0089] S30: inputting the temperature region distribution map and the initial residual distribution map into the pre-trained stress correction model to obtain an accurate residual distribution map, and analyzing the accurate residual distribution map to obtain a stress monitoring result, wherein the accurate residual distribution map refers to a residual stress distribution map of the kiln gear in a working state;

[0090] The training method of the stress correction model includes:

[0091] The preset fully connected neural network is used as a base model. The input layer of the fully connected neural network receives historical temperature region distribution maps and historical initial residual distribution maps. The output layer of the fully connected neural network outputs historical accurate residual distribution maps.

[0092] The cross-entropy loss function is selected as the loss function when training the fully connected neural network, and the loss function is minimized by gradient descent method.

[0093] The weight parameters of the fully connected neural network are updated, and the stress correction model is obtained through iterative training.

[0094] It should be noted that the principle of correcting the initial residual distribution map by the temperature region distribution map is as follows:

[0095] In the working process of the rotary kiln gear, temperature change and stress distribution are closely related. The change of temperature will directly affect the thermal expansion, deformation, elastic modulus and other characteristics of the material, and further affect the stress state of the gear. Especially in the high temperature region, higher residual stress may be induced. Therefore, the temperature region distribution map provides information about the change of temperature, which can be used to adjust and optimize the initial residual stress distribution map. Through finite element analysis and other methods, the initial residual distribution map of the gear under static state is obtained. These stress values are usually calculated based on the load conditions without considering the temperature factor. The change of temperature will cause the material to expand or shrink, and further affect the stress state. Especially in the high temperature region, the elastic modulus and yield strength of the material may change. The temperature region distribution map provides temperature change information for each region, which helps to predict the thermal stress impact that these regions may receive. Through the temperature region distribution map, each region in the initial residual stress distribution map can be corrected to consider the stress change caused by temperature. Specifically, the regions with higher temperature usually need to increase the stress value, and the regions with lower temperature do not need to increase the stress value.

[0096] The method for obtaining the stress monitoring result by analyzing the accurate residual distribution map includes:

[0097] Obtain stress analysis information of the accurate residual distribution map, and mark the target stress region in the accurate residual distribution map according to the stress analysis information. The real-time stress value of the target stress region is taken as the stress monitoring result.

[0098] The stress analysis information can be the maximum stress value. Then a relative proportion (such as a certain percentage of the maximum stress value) is selected as the threshold value. For example, if the maximum stress value is The threshold value can be set as 0.8x , which means that the region with stress greater than 80% of the maximum stress value is considered as the target stress region.

[0099] The embodiment first carries out finite element analysis on the gear structure data to obtain a gear basic model, carries out attenuation analysis on the ultrasonic data to obtain reflection characteristics, determines an initial residual distribution map based on the reflection characteristics and the gear basic model, then obtains temperature data of the rotary kiln gear, carries out gradient analysis on the temperature data to obtain a temperature region distribution map, inputs the temperature region distribution map and the initial residual distribution map into a stress correction model which has been pre-trained to obtain an accurate residual distribution map, so that the residual stress monitoring of the gear in the working state is realized, and the dynamic residual stress state of the gear in the actual working condition can be effectively reflected.

[0100] Embodiment 2

[0101] Please refer to Figure 2 Based on the same inventive concept, the embodiment discloses a rotary kiln gear residual stress monitoring system based on ultrasonic waves, and the details of the embodiment can be referred to the description of the related part in Embodiment 1. The system comprises:

[0102] The first processing module is configured to obtain ultrasonic data and gear structure data, carry out finite element analysis on the gear structure data to obtain a gear basic model, carry out attenuation analysis on the ultrasonic data to obtain reflection characteristics, and determine an initial residual distribution map based on the reflection characteristics and the gear basic model. The initial residual distribution map refers to a residual stress distribution map of the rotary kiln gear in a static state.

[0103] In the embodiment, the ultrasonic data includes a transmission intensity value, a receiving intensity value, a propagation time, and a phase difference value. The transmission intensity value refers to the sound wave intensity generated by the ultrasonic transmitter when transmitting signals. The receiving intensity value refers to the signal intensity returned after the ultrasonic signal propagates through the detected object (such as the rotary kiln gear). The phase difference value refers to the phase difference between the reflected signal and the incident signal.

[0104] The method for carrying out attenuation analysis on the ultrasonic data to obtain the reflection characteristics comprises:

[0105] According to the phase difference value, the propagation time is corrected. According to the corrected propagation time and a preset propagation speed, the signal propagation distance is calculated. Then, according to the signal propagation distance, the transmission intensity value, and the receiving intensity value, the attenuation coefficient is calculated. The intensity ratio between the receiving intensity value and the transmission intensity value is calculated. The attenuation coefficient and the intensity ratio are taken as the reflection characteristics.

[0106] The method for obtaining the regression coefficients by establishing a regression relationship between each distribution sub-region in the basic stress distribution map and the corresponding reflection characteristics comprises:

[0107] The stress gradient of the foundation stress distribution map is determined by the finite difference method, the foundation stress distribution map is divided into G distribution sub-regions by the stress gradient, the G distribution sub-regions are fitted with the corresponding reflection characteristics based on polynomial regression, and the regression coefficients are obtained.

[0108] The method for obtaining the initial residual distribution map based on the regression coefficients and the foundation stress distribution map comprises:

[0109] The initial residual stress value of each distribution sub-region is calculated by the regression coefficient, and the initial residual distribution map is determined based on the initial residual stress value of each distribution sub-region.

[0110] The second processing module is used for obtaining temperature data of the rotary kiln gear, performing gradient analysis on the temperature data, and obtaining a temperature region distribution map, which is a temperature region distribution gradient map of the rotary kiln gear in a working state.

[0111] In this embodiment, the temperature data refers to temperature-related data of each region of the rotary kiln gear in a working state, which is usually provided by a temperature sensor or an infrared imaging device and is used to reflect the temperature distribution of the gear under high-temperature working conditions. The above working state refers to the comprehensive influence of load, temperature and other factors on the gear during the actual operation of the rotary kiln, so as to ensure that the kiln body can rotate smoothly and complete the material processing process.

[0112] It should be noted that the temperature data includes real-time temperature values and temperature change rate values.

[0113] The method for performing gradient analysis on the temperature data to obtain the temperature region distribution map comprises:

[0114] The real-time temperature values are filtered according to the temperature change rate values to obtain target temperature values, the target temperature values are subjected to derivative operation along the radial direction of the rotary kiln gear to obtain temperature gradients, and the temperature region distribution map is generated according to the temperature gradients.

[0115] The method for filtering the real-time temperature values according to the temperature change rate values comprises:

[0116] When the temperature change rate value is greater than a preset change rate threshold, the real-time temperature values are subjected to median filtering to obtain the target temperature values.

[0117] The analysis module is used for inputting the temperature region distribution map and the initial residual distribution map into a pre-trained stress correction model to obtain an accurate residual distribution map, analyzing the accurate residual distribution map, and obtaining a stress monitoring result, wherein the accurate residual distribution map refers to a residual stress distribution map of the rotary kiln gear in a working state.

[0118] In the drawings of the embodiments of the present application, only the structures related to the embodiments of the present application are involved, and other structures can be referred to the general design, and in the case of no conflict, the features in the same embodiment and different embodiments of the present application can be combined with each other, and the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited to this, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application, therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of monitoring residual stresses in a rotary kiln gear based on ultrasonic waves, characterized in that, The application relates to a method for monitoring stress of a rotary kiln gear. The method comprises the following steps: transmitting ultrasonic waves to a detected object through an ultrasonic transmitter, acquiring ultrasonic data and gear structure data; the ultrasonic data at least comprises a transmission intensity value, a receiving intensity value, a propagation time and a phase difference value; carrying out finite element analysis on the gear structure data to obtain a gear basic model, carrying out attenuation analysis on the ultrasonic data to obtain reflection characteristics, and determining an initial residual distribution map based on the reflection characteristics and the gear basic model; the initial residual distribution map refers to a residual stress distribution map of the rotary kiln gear in a static state; acquiring temperature data of the rotary kiln gear, carrying out gradient analysis on the temperature data to obtain a temperature region distribution map; the temperature region distribution map refers to a temperature region distribution gradient map of the rotary kiln gear in a working state; inputting the temperature region distribution map and the initial residual distribution map into a pre-trained stress correction model to obtain an accurate residual distribution map, and carrying out analysis on the accurate residual distribution map to obtain a stress monitoring result; the accurate residual distribution map refers to a residual stress distribution map of the rotary kiln gear in the working state. The method for carrying out attenuation analysis on the ultrasonic data to obtain the reflection characteristics comprises the following steps:

2. The ultrasonic-based rotary kiln gear residual stress monitoring method of claim 1, wherein, correcting the propagation time according to the phase difference value, calculating a signal propagation distance according to the corrected propagation time and a preset propagation speed, calculating an attenuation coefficient according to the signal propagation distance, the transmission intensity value and the receiving intensity value, calculating an intensity ratio between the receiving intensity value and the transmission intensity value, and taking the attenuation coefficient and the intensity ratio as the reflection characteristics. The method for determining the initial residual distribution map based on the reflection characteristics and the gear basic model comprises the following steps:

3. The ultrasonic-based rotary kiln gear residual stress monitoring method of claim 2, wherein, carrying out stress distribution simulation on the gear basic model through finite element analysis to obtain a basic stress distribution map, acquiring each distribution sub-region in the basic stress distribution map, establishing a regression coefficient between each distribution sub-region and the corresponding reflection characteristics through polynomial regression, and obtaining the initial residual distribution map based on the regression coefficient and the basic stress distribution map. The method for acquiring each distribution sub-region in the basic stress distribution map and establishing the regression coefficient between each distribution sub-region and the corresponding reflection characteristics through polynomial regression comprises the following steps:

4. The ultrasonic-based rotary kiln gear residual stress monitoring method of claim 3, wherein, determining a stress gradient of the basic stress distribution map through finite difference method, dividing the basic stress distribution map into G distribution sub-regions through the stress gradient, fitting the G distribution sub-regions and the corresponding reflection characteristics based on polynomial regression to obtain the regression coefficient. The method for obtaining the initial residual distribution map based on the regression coefficient and the basic stress distribution map comprises the following steps:

5. The ultrasonic-based rotary kiln gear residual stress monitoring method of claim 3, wherein, calculating an initial residual stress value of each distribution sub-region through the regression coefficient, and determining the initial residual distribution map based on the initial residual stress value of each distribution sub-region. The temperature data comprises real-time temperature values and temperature change rate values, and the method for carrying out gradient analysis on the temperature data to obtain the temperature region distribution map comprises the following steps:

6. The ultrasonic-based rotary kiln gear residual stress monitoring method of claim 1, wherein, filtering the real-time temperature values according to the temperature change rate values to obtain target temperature values, carrying out derivative operation on the target temperature values along a radial direction of the rotary kiln gear to obtain a temperature gradient, and generating the temperature region distribution map according to the temperature gradient. The method for filtering the real-time temperature values according to the temperature change rate values comprises the following steps:

7. The ultrasonic-based rotary kiln gear residual stress monitoring method of claim 6, wherein, ​ When the temperature change rate value is greater than the preset change rate threshold value, then the real-time temperature value is subjected to median filtering processing to obtain a target temperature value.

8. The ultrasonic-based rotary kiln gear residual stress monitoring method of claim 1, wherein, The method for analyzing the accurate residual distribution map to obtain the stress monitoring result comprises: Obtaining stress analysis information of the accurate residual distribution map, marking a target stress region in the accurate residual distribution map according to the stress analysis information, and taking a real-time stress value of the target stress region as the stress monitoring result.

9. An ultrasonic-based rotary kiln gear residual stress monitoring system for implementing the ultrasonic-based rotary kiln gear residual stress monitoring method of any one of claims 1-8, characterized by, Comprise: The first processing module is used for emitting ultrasonic waves to the detected object through the ultrasonic wave emitter, acquiring ultrasonic wave data and gear structure data; The ultrasonic wave data at least comprises a transmission intensity value, a receiving intensity value, a propagation time and a phase difference value; the gear structure data is subjected to finite element analysis to obtain a gear basic model, and the ultrasonic wave data is subjected to attenuation analysis to obtain a reflection characteristic, and the initial residual distribution map is determined based on the reflection characteristic and the gear basic model, wherein the initial residual distribution map refers to a residual stress distribution map of the rotary kiln gear in a static state; The second processing module is used for acquiring temperature data of the rotary kiln gear, and performing gradient analysis on the temperature data to obtain a temperature region distribution map, wherein the temperature region distribution map refers to a temperature region distribution gradient map of the rotary kiln gear in a working state; The analysis module is used for inputting the temperature region distribution map and the initial residual distribution map into a pre-trained stress correction model to obtain an accurate residual distribution map, and analyzing the accurate residual distribution map to obtain a stress monitoring result, wherein the accurate residual distribution map refers to a residual stress distribution map of the rotary kiln gear in the working state.

Images