Thermal deformation prediction method and thermal deformation real-time monitoring system

Abstract

The invention relates to a thermal deformation prediction method and a thermal deformation real-time monitoring system. The method comprises the steps of obtaining deformation data transmitted by a sensing device, preprocessing the deformation data to obtain preprocessed target data, determining a target prediction model in preset prediction models according to data features of the target data, inputting the target data into the target prediction model for thermal deformation prediction processing, and obtaining a thermal deformation prediction result. Obtaining a first prediction result; according to the method, the target prediction model can be determined according to the data features of the target data to carry out thermal deformation prediction processing, and compared with a traditional method that a single prediction model is adopted to predict the thermal deformation of the equipment structure, prediction is carried out by combining the data features, so that the prediction accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of industrial safety management, and in particular to a thermal deformation prediction method and a thermal deformation real-time monitoring system. Background Art

[0002] During the welding repair process of industrial equipment, thermal deformation is an important factor affecting the processing quality and service life of industrial equipment. In traditional technologies, contact dial indicators or photoelectric displacement measuring devices are usually used to monitor the deformation or displacement of objects in real time, and the obtained deformation or displacement is input into the prediction model to predict the development trend of thermal deformation and ensure the safety and reliability of welding repair.

[0003] However, different equipment structures produce different thermal deformations under the same environment. Using a single prediction model to predict the thermal deformation of each equipment structure has the problem of low prediction accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide a thermal deformation prediction method and a thermal deformation real-time monitoring system that can improve prediction accuracy in response to the above technical problems.

[0005] In a first aspect, the present application provides a thermal deformation prediction method, which is applied to a thermal deformation real-time monitoring system. The thermal deformation real-time monitoring system includes a plurality of sensing devices, wherein the sensing devices are used to obtain deformation data of a target object in a non-contact manner. The method includes:

[0006] Acquire deformation data transmitted by the sensing device, pre-process the deformation data, and obtain pre-processed target data;

[0007] Determine data features corresponding to the target data, and determine a target prediction model in a preset prediction model based on the data features, wherein the data features include mathematical features for characterizing changes in the target data over time;

[0008] The target data is input into the target prediction model for thermal deformation prediction processing to obtain the first prediction result.

[0009] In one embodiment, the method further comprises:

[0010] When the deformation data is greater than the deformation threshold, an alarm signal is output, and the target data and the device number of the sensing device corresponding to the target data are recorded;

[0011] When the first prediction result is greater than the deformation threshold, a first warning signal is output, and the device number of the sensing device corresponding to the first prediction result is recorded.

[0012] In one embodiment, the method further comprises:

[0013] Adjust the model parameters of the target prediction model based on the data characteristics to obtain a thermal deformation prediction model;

[0014] The target data is input into the thermal deformation prediction model for thermal deformation prediction processing to obtain a second prediction result.

[0015] In one embodiment, the method further comprises:

[0016] When the second prediction result is greater than the deformation threshold, a second warning signal is output, and the device number of the sensing device corresponding to the second prediction result is recorded.

[0017] In one of the embodiments, the preset prediction model includes a linear regression model, a time series model, and a machine learning model;

[0018] Preprocessing includes data outlier processing and data missing value filling.

[0019] In a second aspect, the present application further provides a thermal deformation prediction device, which is applied to a thermal deformation real-time monitoring system. The thermal deformation real-time monitoring system includes a plurality of sensing devices, wherein the sensing devices are used to obtain deformation data of a target object in a non-contact manner. The device includes:

[0020] An acquisition module is used to acquire deformation data transmitted by the sensing device, pre-process the deformation data, and obtain pre-processed target data;

[0021] A determination module, used to determine data features corresponding to target data, and determine a target prediction model in a preset prediction model based on the data features, wherein the data features include mathematical features for characterizing changes in the target data over time;

[0022] The prediction module is used to input the target data into the target prediction model to perform thermal deformation prediction processing to obtain a first prediction result.

[0023] In a third aspect, the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0024] In a fourth aspect, the present application further provides a real-time monitoring system for thermal deformation, the real-time monitoring system for thermal deformation comprising the above-mentioned computer device and a plurality of sensing devices, the computer device being connected to each sensing device respectively;

[0025] Among them, the sensing device is used to obtain the deformation data of the target object in a non-contact manner.

[0026] In one embodiment, the sensing device includes a photoelectric sensor.

[0027] In one embodiment, the computer device is connected to each sensing device via wireless communication; wherein the wireless communication connection includes at least one of a Bluetooth communication connection, a Zigbee communication connection and a WiFi communication connection.

[0028] The above-mentioned thermal deformation prediction method and thermal deformation real-time monitoring system obtain deformation data transmitted by the sensing device, pre-process the deformation data, obtain pre-processed target data, and determine the target prediction model in the preset prediction model according to the data characteristics of the target data, and input the target data into the target prediction model for thermal deformation prediction processing to obtain a first prediction result; the present application determines the target prediction model according to the data characteristics of the target data to perform thermal deformation prediction processing. Compared with the traditional method of using a single prediction model to predict the thermal deformation of the equipment structure, the prediction is performed by combining data characteristics to improve the accuracy of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 A connection diagram of a real-time monitoring system for thermal deformation in one embodiment;

[0031] Figure 2 A schematic diagram of a process of thermal deformation prediction method in one embodiment;

[0032] Figure 3 is a structural block diagram of a thermal deformation prediction device in one embodiment;

[0033] Figure 4 A schematic diagram of a non-contact measurement principle of a photoelectric sensor in one embodiment;

[0034] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0035] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0037] It can be understood that the terms "first", "second", etc. used in the present application can be used in this article to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element.

[0038] It can be understood that the “connection” in the following embodiments should be understood as “electrical connection”, “communication connection”, etc. if the connected circuits, modules, units, etc. have electrical signals or data transmission between each other.

[0039] It can be understood that “at least one” means one or more, “plurality” means two or more, and “at least part of an element” means part or all of an element.

[0040] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" and the like specify the presence of stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0041] At present, in the welding and repair process of large equipment such as turbines, thermal deformation is an important factor affecting the processing quality and service life of the equipment. In traditional technologies, contact dial gauges or photoelectric displacement measuring devices are usually used to monitor the deformation or displacement of objects in real time. Among them, the contact dial gauge contacts the surface of the object to be measured through mechanical contacts to measure its displacement or deformation. It usually needs to be used with a clamp and a fixing device, and the installation is relatively complicated. The photoelectric displacement measuring device uses a laser or photoelectric sensor to measure the displacement of the object to be measured without direct contact with the object. However, whether it is a contact dial gauge or a photoelectric displacement measuring device, it measures the displacement of a single point. If multi-point measurement is required, the data must be read manually one by one. In addition, after the deformation or displacement is obtained, it is impossible to perform real-time data analysis and does not have the ability to automatically alarm. There are problems of low real-time monitoring efficiency and high cost.

[0042] In traditional technology, the development trend of thermal deformation is predicted by inputting the acquired deformation or displacement into the prediction model. However, different equipment structures produce different thermal deformations under the same environment. If only a single prediction model is used to predict the thermal deformation of each equipment structure, there is a problem of low prediction accuracy.

[0043] The thermal deformation prediction method provided in the embodiment of the present application can be applied to Figure 1 In the real-time monitoring system for thermal deformation shown in the figure, the real-time monitoring system for thermal deformation includes a plurality of sensing devices 110 and a computer device 120 respectively connected to each sensing device. The sensing device 110 is used to obtain deformation data of the target object in a non-contact manner and output the deformation data to the computer device 120. The computer device 120 pre-processes the deformation data to obtain pre-processed target data, and determines a target prediction model in a preset prediction model according to the data characteristics of the target data, inputs the target data into the target prediction model for thermal deformation prediction processing, and obtains a first prediction result. Compared with the traditional method of using a single prediction model to predict the thermal deformation of the equipment structure, the prediction is performed by combining data characteristics, thereby improving the accuracy of the prediction.

[0044] In an exemplary embodiment, Figure 2 As shown in the figure, a thermal deformation prediction method is provided, which can be applied to Figure 1 Taking the computer device in the example as an example, the method includes:

[0045] S202, acquiring deformation data transmitted by the sensing device, preprocessing the deformation data, and obtaining preprocessed target data.

[0046] The device type of the sensing device can be set according to actual conditions, as long as the device has the function of acquiring deformation data of the target object in a non-contact manner.

[0047] Specifically, the sensing device is set close to the target object, and the sensing device obtains the deformation data of the target object in real time without contact, and transmits the deformation data to the computer device, wherein there are multiple sensing devices, each sensing device works independently, and synchronously transmits the obtained deformation data to the computer device, forming a centralized monitoring platform, realizing multi-point real-time monitoring, and analyzing and processing abnormal situations; the computer device receives and pre-processes each deformation data, obtains the target data that has completed the pre-processing, and the pre-processing steps can be set according to actual conditions, and the pre-processing is used to ensure the accuracy and continuity of the data.

[0048] Exemplarily, the computer device can record deformation data to facilitate subsequent data analysis; the computer device is configured with a display unit, which can intuitively display the deformation data to the user through the display unit, that is, intuitively display the thermal deformation of each target object, and the thermal deformation can dynamically display its own changing trend through charts, curves, etc.

[0049] It should be noted that the target object can be set according to the actual situation. Different target objects correspond to different installation positions of the sensing equipment. Generally, the sensing equipment is set in the heat-affected zone and surrounding areas of the target object during the welding repair process. For example, taking the welding repair of turbine blades as an example, the deformation that may occur during the welding process is mainly concentrated in the following positions: ① Blade root area, location characteristics: The blade root is the key part connected to the main shaft, with large force and complex shape, and more heat input during welding repair; Connection surface flatness: Measure the flatness change of the root connection surface to ensure that it fits accurately when connected to the main shaft; Edge warping deformation: Monitor whether the edge of the blade root is warped to avoid assembly stress. ② Blade middle area, location characteristics: The middle of the blade is usually a curved surface, and the welding heat input is prone to cause local expansion and uneven contraction; Blade panel deformation: Monitor the flatness of the middle blade curved surface and measure the concave and convex deformation of the panel; Welding heat affected zone: Arrange measurement points near the weld to monitor the shrinkage and bending deformation of the heat affected zone. ③ Blade leading edge and trailing edge area, location characteristics: the leading edge and trailing edge are the key parts of fluid dynamics, and are prone to longitudinal contraction and bending deformation during welding; leading edge linearity: monitor whether there is bending or twisting on the leading edge of the blade after welding repair; trailing edge warping: measure the overall warping deformation of the trailing edge area to ensure that the aerodynamic performance is not affected.

[0050] For turbine blades, the main locations where welding deformation needs to be measured, that is, the locations where the sensing device is set include: the root area, which is used to measure flatness and edge warping; the middle area, which is used to measure panel flatness and welding heat-affected zone deformation; the leading and trailing edge areas, which are used to measure linearity and warping; the blade tip area, which is used to measure displacement and overall height change. By arranging sensing equipment at the corresponding positions, it is possible to monitor welding deformation (deformation data) in real time, analyze deformation trends in a timely manner, and take effective thermal deformation control measures to ensure the structural accuracy and performance of turbine blades after welding repair.

[0051] S204, determining data features corresponding to the target data, and determining a target prediction model in a preset prediction model based on the data features, wherein the data features include mathematical features for characterizing changes in the target data over time.

[0052] Specifically, the computer equipment adopts multi-threaded processing technology, which can efficiently process the target data corresponding to each target object, determine the corresponding data features according to the acquired target data, and select the appropriate target prediction model based on the data features. The mathematical features include the trend of target data changing over time.

[0053] Exemplarily, data features may also include distribution features, and the target data is a discrete value (such as "yes / no"). Suitable models include logistic regression, decision tree, random forest, support vector machine, etc. The target data is a continuous value (such as price, temperature), and optional models include linear regression, ridge regression, regression tree, neural network, etc.; the target data obtained in the embodiment of the present application is a continuous value, and the preset prediction model may include a linear regression model, a time series model, and a machine learning model. By dividing the target data into a training set and a validation set, the training set is input into each preset prediction model respectively, and the obtained result is compared with the validation set, and the target prediction model is determined according to the comparison result.

[0054] S206, inputting the target data into the target prediction model to perform thermal deformation prediction processing to obtain a first prediction result.

[0055] Specifically, the computer device inputs the target data into the selected target prediction model, performs thermal deformation prediction processing, and obtains a first prediction result. The first prediction result is used to prompt the user to adjust the welding parameters in time, such as optimizing the welding sequence, controlling the temperature and cooling rate, to prevent further deformation of the target object.

[0056] Exemplarily, the display unit of the computer device may also be used to display the first prediction result, prompting the user to make adjustments.

[0057] In the above-mentioned thermal deformation prediction method, the deformation data transmitted by the sensing device is obtained, the deformation data is preprocessed to obtain the preprocessed target data, and the target prediction model is determined in the preset prediction model according to the data characteristics of the target data. The target data is input into the target prediction model for thermal deformation prediction processing to obtain the first prediction result. Compared with the traditional method of using a single prediction model to predict the thermal deformation of the equipment structure, the prediction is made by combining data characteristics, which improves the accuracy of the prediction.

[0058] In one embodiment, the method further comprises:

[0059] When the deformation data is greater than the deformation threshold, an alarm signal is output, and the target data and the device number of the sensing device corresponding to the target data are recorded;

[0060] When the first prediction result is greater than the deformation threshold, a first warning signal is output, and the device number of the sensing device corresponding to the first prediction result is recorded.

[0061] Among them, the deformation threshold can be set according to actual conditions and is not limited in the embodiments of the present application.

[0062] Specifically, the computer device obtains the deformation data output by each sensing device, and performs dynamic display and analysis. When it is detected that the deformation data exceeds the set deformation threshold, an alarm is automatically triggered and an alarm signal is output. The alarm signal can be used to remind the user to intervene in time through sound, visual prompts or text message notifications. The user can quickly locate the target object that needs to be adjusted through the recorded device number; when it is detected that the first prediction result exceeds the set deformation threshold, an early warning is automatically triggered and a first early warning signal is output. The first early warning signal can be used to remind the user to intervene in time through sound, visual prompts or text message notifications. The user can quickly locate the target object that needs to be adjusted through the recorded device number; wherein, both the alarm signal and the first early warning signal are used to prompt the user to intervene in time, and the prompting methods are different, such as: different sound volumes, different text message contents, etc.

[0063] In an embodiment of the present application, by comparing the deformation data and the deformation threshold, and comparing the first prediction result and the deformation threshold, when the deformation data and the first prediction result of any target object exceed the deformation threshold, an alarm is automatically triggered to avoid equipment damage due to excessive thermal deformation, thereby providing safety protection for the welding repair process.

[0064] In one embodiment, the method further comprises:

[0065] Adjust the model parameters of the target prediction model based on the data characteristics to obtain a thermal deformation prediction model;

[0066] The target data is input into the thermal deformation prediction model for thermal deformation prediction processing to obtain a second prediction result.

[0067] Specifically, according to the mathematical characteristics of the target data changing with time, the target prediction model is fitted and modeled, and then the model parameters of the target prediction model are adjusted, so that the acquired thermal deformation prediction model is closer to the actual situation and the prediction accuracy is improved; the target data is input into the thermal deformation prediction model for thermal deformation prediction processing to obtain a second prediction result, and the second prediction result is used to prompt the user to adjust the welding parameters in time, such as optimizing the welding sequence, controlling the temperature and cooling rate, to prevent further aggravation of the deformation of the target object.

[0068] For example, during the welding repair process, the monitoring data of a certain structural area showed that the deformation was 0.5mm when the welding lasted for 10 minutes, increased to 1.2mm when the welding lasted for 20 minutes, and reached 1.9mm at 30 minutes. The linear regression model was fitted to obtain the deformation trend equation (thermal deformation prediction model), based on which it was predicted that the deformation would reach 2.6mm at 40 minutes (the second prediction result). This result prompts the user to adjust the welding parameters in time, such as optimizing the welding sequence, controlling the temperature and cooling rate, to prevent further aggravation of the deformation. In addition, by combining the machine learning model to analyze complex nonlinear data, more detailed deformation laws can be captured in actual monitoring, and the welding scheme can be further optimized. Through the above method, the prediction results are visualized, providing key inflection points and warning values, providing a scientific basis for process decision-making and quality control in the welding repair process, and ensuring the safety and reliability of welding repair.

[0069] In an embodiment of the present application, a thermal deformation prediction model is obtained by adjusting the model parameters of the target prediction model based on data characteristics, and the thermal deformation prediction model is used to perform thermal deformation prediction processing to obtain a second prediction result, thereby improving the accuracy of the prediction while ensuring the safety and reliability of welding repair.

[0070] In one embodiment, the method further comprises:

[0071] When the second prediction result is greater than the deformation threshold, a second warning signal is output, and the device number of the sensing device corresponding to the second prediction result is recorded.

[0072] Specifically, when the computer device detects that the deformation data exceeds the set deformation threshold, it automatically triggers an early warning and outputs a second early warning signal to prompt the user to intervene in time. The user can quickly locate the target object that needs to be adjusted through the recorded device number; wherein, the alarm signal, the first early warning signal and the second early warning signal are all used to prompt the user to intervene in time, and there are different ways of prompting, such as: different sound volumes, different text message contents, etc., which are not elaborated in the embodiments of the present application.

[0073] In an embodiment of the present application, the second prediction result and the deformation threshold are compared. When the second prediction result of any target object exceeds the deformation threshold, an alarm is automatically triggered to avoid equipment damage due to excessive thermal deformation, thereby providing safety protection for the welding repair process.

[0074] In one of the embodiments, the preset prediction model includes a linear regression model, a time series model, and a machine learning model;

[0075] Preprocessing includes data outlier processing and data missing value filling.

[0076] Specifically, the computer device obtains the deformation data transmitted by the sensing device and pre-processes the deformation data, including data outlier processing and data missing value filling. The outliers in the deformation data are eliminated by setting a threshold. The data missing value filling includes mean filling, median filling, mode filling and interpolation filling, etc. The computer device fills the blank data in the deformation data through at least one of the above filling methods.

[0077] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0078] Based on the same inventive concept, the embodiment of the present application also provides a thermal deformation prediction device for implementing the thermal deformation prediction method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more thermal deformation prediction device embodiments provided below can refer to the limitations of the thermal deformation prediction method above, and will not be repeated here.

[0079] In an exemplary embodiment, Figure 3 As shown, a thermal deformation prediction device 300 is provided, which is applied to a thermal deformation real-time monitoring system. The thermal deformation real-time monitoring system includes a plurality of sensing devices, wherein the sensing devices are used to obtain deformation data of a target object in a non-contact manner. The device 300 includes:

[0080] An acquisition module 301 is used to acquire deformation data transmitted by a sensing device, pre-process the deformation data, and obtain pre-processed target data;

[0081] A determination module 302 is used to determine data features corresponding to the target data, and determine a target prediction model in a preset prediction model based on the data features, wherein the data features include mathematical features for characterizing changes in the target data over time;

[0082] The prediction module 303 is used to input the target data into the target prediction model to perform thermal deformation prediction processing to obtain a first prediction result.

[0083] In one embodiment, the device 300 further includes a warning module, which is used to output a warning signal when the deformation data is greater than the deformation threshold, and record the target data and the device number of the sensing device corresponding to the target data;

[0084] When the first prediction result is greater than the deformation threshold, a first warning signal is output, and the device number of the sensing device corresponding to the first prediction result is recorded.

[0085] In one embodiment, the apparatus 300 further includes an adjustment module for adjusting model parameters of the target prediction model based on data features to obtain a thermal deformation prediction model;

[0086] The target data is input into the thermal deformation prediction model for thermal deformation prediction processing to obtain a second prediction result.

[0087] In one of the embodiments, the warning module is further configured to output a second warning signal when the second prediction result is greater than the deformation threshold, and record a device number of the sensing device corresponding to the second prediction result.

[0088] In one of the embodiments, the preset prediction model includes a linear regression model, a time series model, and a machine learning model;

[0089] Preprocessing includes data outlier processing and data missing value filling.

[0090] Each module in the above-mentioned thermal deformation prediction device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0091] In an exemplary embodiment, a real-time monitoring system for thermal deformation is provided, the real-time monitoring system for thermal deformation comprises the above-mentioned computer device and a plurality of sensing devices, the computer device being connected to each sensing device respectively;

[0092] Among them, the sensing device is used to obtain the deformation data of the target object in a non-contact manner.

[0093] Specifically, by using multiple sensing devices to build a distributed monitoring network, real-time and synchronous measurements can be performed on multiple monitoring points (target objects) in the welding repair process, solving the problem of multi-point monitoring difficulties in traditional methods and realizing global real-time monitoring of thermal deformation.

[0094] It should be noted that the real-time thermal deformation monitoring system is not only suitable for thermal deformation monitoring of turbine welding repairs, but can also be extended to other scenarios that require multi-point high-precision displacement monitoring, such as the assembly, repair and quality inspection of large-scale mechanical equipment, and can adapt to a variety of industrial scenarios.

[0095] In an embodiment of the present application, the real-time monitoring system for thermal deformation includes a plurality of sensing devices respectively arranged at corresponding target objects. The sensing devices obtain deformation data of the target objects in a non-contact manner and output them to a computer device. The computer device can display the deformation data in real time and perform thermal deformation prediction processing based on the deformation data, thereby solving the problem of difficulty in multi-point monitoring in traditional methods and realizing global real-time monitoring of thermal deformation.

[0096] In one embodiment, the sensing device includes a photoelectric sensor.

[0097] Specifically, photoelectric sensors can use laser triangulation to achieve non-contact acquisition of deformation data of target objects, greatly improving measurement accuracy and environmental adaptability, avoiding the installation difficulties of traditional contact dial indicators in welding scenarios such as high temperature and complex surfaces, and improving measurement stability and dynamic response capabilities.

[0098] Figure 4 An example of a non-contact measurement principle is shown. Figure 4 As shown, the photoelectric sensor includes a wireless communicator, a signal processor, a linear CCD array, a semiconductor laser and a lens, wherein the semiconductor laser irradiates the surface of the object to be measured (target object) with a beam of laser at a certain incident angle, and the reference distance can be set according to the actual situation. After the laser is reflected and scattered on the surface of the object, it is converged by a lens to form an image on the CCD (photosensitive coupling component) position sensor. When the object to be measured moves along the laser direction, the light spot on the position sensor (linear CCD array) will move, and the size of the displacement corresponds to the moving distance of the object to be measured. Through algorithm design, the distance value between the object to be measured and the baseline can be calculated from the light spot displacement distance. The signal processor converts the signal output by the position sensor into a processable digital signal, that is, deformation data, and transmits the deformation data to the computer device through the wireless communicator. It can be understood that by adopting a modular design, the photoelectric sensor has a light structure and is easy to be quickly deployed on complex surfaces and narrow spaces, which significantly improves the efficiency and flexibility of welding repair operations.

[0099] For example, during the installation of a photoelectric sensor, also known as a photoelectric deformation sensor, the direction of the optical path is adjusted by a special fixture or bracket to ensure that the light beam can stably irradiate the surface of the measured point, and an initial calibration is performed to eliminate environmental interference. The initial calibration may include the following steps:

[0100] Step 1, equipment installation and fixation: Use a special clamp or bracket to firmly fix the photoelectric deformation sensor near the welding repair area, adjust the direction of the optical path, and ensure that the laser beam stably irradiates the surface of the measured point.

[0101] Step 2, surface treatment of the measured point: clean the dust, oil stains, welding slag, etc. on the surface of the measured point, polish the rough surface if necessary, or paste high reflectivity materials to improve the reflection effect of the laser signal.

[0102] Step 3, initial zero point calibration: Set the zero point position of the device, record the initial measurement value, let the device stand still, continuously monitor the data, eliminate device deviation and system error, and ensure that the initial measurement is stable and accurate.

[0103] Step 4, temperature and environment compensation: record the current ambient temperature, enable the temperature compensation function, and correct the system error caused by temperature changes. At the same time, take measures to reduce the impact of vibration, such as adding damping and shockproof brackets or averaging the measurement data to eliminate the impact of vibration.

[0104] Step 5, optical path and signal inspection: Check the reflection stability of the laser signal to ensure the correct direction of the optical path, and reduce external light interference through optical filtering or shading devices to improve measurement accuracy.

[0105] Step 6, data verification and recording: Use different photoelectric deformation sensors to measure the same measured point multiple times to verify the consistency and stability of the data. After confirming the calibration effect, record the calibration parameters such as zero point position, optical path angle, temperature compensation value, etc. as the basis for subsequent measurements.

[0106] From the above, it can be concluded that after the initial calibration, the photoelectric sensor stores calibration parameters such as zero point position, optical path angle, temperature compensation value, etc., which serve as the basis for subsequent measurements, thereby improving the measurement accuracy and the accuracy of subsequent predictions.

[0107] In the embodiment of the present application, a photoelectric sensor is used to obtain the deformation data of the target object in a non-contact manner, thereby solving the problem of the complex installation of the traditional contact dial indicator. Non-contact measurement is achieved through an optical system and a high-precision sensor, thereby avoiding the wear, error and environmental adaptability problems caused by mechanical contact. The measurement accuracy can reach the micron level, which is suitable for real-time monitoring under complex working conditions such as high temperature and high pressure.

[0108] In one embodiment, the computer device is connected to each sensing device via wireless communication; wherein the wireless communication connection includes at least one of a Bluetooth communication connection, a Zigbee communication connection and a WiFi communication connection.

[0109] Specifically, the computer device is wirelessly connected to the wireless communicator in the photoelectric sensor. The wireless communicator connects multiple photoelectric sensors to a unified network through at least one of Bluetooth communication connection, Zigbee communication connection and WiFi communication connection, supports synchronous data transmission of up to dozens of photoelectric sensors, and ensures the breadth and real-time nature of the real-time monitoring range.

[0110] In the embodiment of the present application, the sensing device is connected to the computer device via wireless communication, and the computer device dynamically displays the deformation data to ensure the timeliness of monitoring.

[0111] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a thermal deformation prediction method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0112] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0113] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned thermal deformation prediction method when executing the computer program.

[0114] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned thermal deformation prediction method is implemented.

[0115] In one embodiment, a computer program product is provided, comprising a computer program, which implements the above thermal deformation prediction method when executed by a processor.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0117] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0118] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0119] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A thermal deformation prediction method, characterized in that: Applied to a real-time monitoring system for thermal deformation, the real-time monitoring system for thermal deformation includes a plurality of sensing devices, wherein the sensing devices are used to obtain deformation data of a target object in a non-contact manner, and the method includes: Acquiring the deformation data transmitted by the sensing device, and preprocessing the deformation data to obtain preprocessed target data; Determine data features corresponding to the target data, and determine a target prediction model in a preset prediction model based on the data features, wherein the data features include mathematical features for characterizing changes of the target data over time; The target data is input into the target prediction model to perform thermal deformation prediction processing to obtain a first prediction result.

2. The method according to claim 1, characterized in that The method further comprises: When the deformation data is greater than the deformation threshold, an alarm signal is output, and the target data and the device number of the sensing device corresponding to the target data are recorded; When the first prediction result is greater than the deformation threshold, a first warning signal is output, and the device number of the sensing device corresponding to the first prediction result is recorded.

3. The method according to claim 1, characterized in that The method further comprises: Adjusting the model parameters of the target prediction model based on the data features to obtain a thermal deformation prediction model; The target data is input into the thermal deformation prediction model for thermal deformation prediction processing to obtain a second prediction result.

4. The method according to claim 3, characterized in that The method further comprises: When the second prediction result is greater than the deformation threshold, a second warning signal is output, and the device number of the sensing device corresponding to the second prediction result is recorded.

5. The method according to claim 1, characterized in that The preset prediction models include linear regression models, time series models and machine learning models; The preprocessing includes data outlier processing and data missing value filling.

6. A thermal deformation prediction device, characterized in that: Applied to a real-time monitoring system for thermal deformation, the real-time monitoring system for thermal deformation includes a plurality of sensing devices, wherein the sensing devices are used to obtain deformation data of a target object in a non-contact manner, and the device includes: An acquisition module, used for acquiring the deformation data transmitted by the sensing device, preprocessing the deformation data, and obtaining preprocessed target data; A determination module, used to determine data features corresponding to the target data, and determine a target prediction model in a preset prediction model based on the data features, wherein the data features include mathematical features for characterizing changes of the target data over time; The prediction module is used to input the target data into the target prediction model to perform thermal deformation prediction processing to obtain a first prediction result.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A real-time monitoring system for thermal deformation, characterized in that: The real-time monitoring system for thermal deformation comprises the computer device as claimed in claim 7 and a plurality of sensing devices, wherein the computer device is respectively connected to each of the sensing devices; Wherein, the sensing device is used to obtain deformation data of the target object in a non-contact manner.

9. The real-time thermal deformation monitoring system according to claim 8, characterized in that: The sensing device includes a photoelectric sensor.

10. The real-time thermal deformation monitoring system according to claim 8, characterized in that: The computer device is connected to each of the sensing devices via wireless communication; wherein the wireless communication connection includes at least one of a Bluetooth communication connection, a Zigbee communication connection and a WiFi communication connection.

Images