High-temperature environment water mist penetrating three-wavelength temperature measuring device and method

Abstract

The invention discloses a high-temperature environment water mist penetrating three-wavelength temperature measuring device and method. The device comprises a high-temperature measuring equipment assembly and a shell. The high-temperature measurement equipment assembly comprises a three-waveband light splitting detection module, a data storage and processing analysis module, a data display and system setting module, a video monitoring and laser indication module, a front mirror protection sleeve and an electrical interface; the three-waveband light splitting detection module comprises a three-color prism and a three-radiation detection assembly, each emitting surface of the three-color prism is plated with a radiation filtering film only allowing light of a specific waveband to penetrate through, and the three-radiation detection assembly comprises a focusing lens, a radiation detector, a circuit board and a stray light shielding sleeve. The method comprises the steps of temperature measurement data acquisition, temperature measurement data fusion, temperature measurement parameter setting and temperature measurement model application. According to the invention, the interference of water mist, dust and the like can be effectively dealt with through a multi-band precise light splitting technology and dynamic model optimization, so that the measurement error of the device in a dynamic high-temperature and multi-working-condition environment is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of high-temperature industrial production, and in particular to a device and method for measuring temperature in a high-temperature environment through three-wavelength water mist penetration. Background Art

[0002] In high-temperature industrial production environments (such as steel rolling, non-ferrous metal smelting, etc.), temperature is an important parameter that determines product quality and production efficiency, which directly affects the workpiece's organizational uniformity, mechanical properties, and subsequent processing characteristics. Therefore, it is particularly important to accurately measure the temperature of the material during high-temperature processes. On the one hand, this helps to optimize the process and reduce energy consumption; on the other hand, it also provides reliable data support for improving product quality. However, such high-temperature environments are often accompanied by extreme conditions, such as high-temperature radiation, strong water mist interference, dust coverage, and oxide scale peeling, which pose severe challenges to the accuracy and stability of traditional temperature measurement technologies. This makes the development of new high-precision temperature measurement technologies that can adapt to complex on-site environments an important direction for industrial development.

[0003] Single-wavelength infrared temperature measurement technology is one of the earliest temperature measurement methods used in industrial sites. Although this technology has a simple structure, it relies on a fixed emissivity and is difficult to adapt to emissivity fluctuations caused by changes in the oxide film or uneven coverage of the measured surface. In contrast, although the dual-wavelength ratio temperature measurement technology partially solves the emissivity dependence problem, it is still subject to the unevenness of signal attenuation in complex environments in practical applications. Especially in dynamic working conditions, this error intensifies with environmental changes, which limits the effectiveness of dual-wavelength technology. Therefore, how to design a temperature measurement technology that can take into account both high precision and strong environmental adaptability has become an important technical problem that needs to be solved urgently.

[0004] In this context, three-wavelength temperature measurement technology is gradually applied to industrial sites as an improved solution. By introducing the radiation signal of the third wavelength, the three-wavelength technology can realize multi-parameter coupling and solution, effectively improving the anti-interference ability in complex environments. For example, patent CN202111016320.2 provides a three-wavelength colorimetric infrared temperature measurement system, method and device based on emissivity iteration. The radiation signals of three bands with large wavelength differences are measured by a spectrometer and a reflector, and the different penetration and detection characteristics of different wavelengths are used. Combined with the emissivity iteration algorithm, the real temperature is fitted to improve the measurement accuracy. Patent CN202110168504.4 provides a three-wavelength radiation temperature measurement device and method for turbine blades. By collecting the radiation energy and ambient energy of three bands, and using the LM algorithm with step-length search, the radiation temperature inversion under unknown emissivity is realized.

[0005] Although the three-wavelength temperature measurement technology has improved the temperature measurement accuracy and environmental adaptability to a certain extent, the existing technology still has many shortcomings. On the one hand, most solutions assume that the emissivity of different bands is consistent, ignoring the uneven attenuation of water mist and dust in complex environments on signals in different bands, which leads to deviations in temperature measurement results under dynamic conditions. On the other hand, in order to achieve higher measurement accuracy, some solutions often require additional collection of environmental parameters or the introduction of complex calculation algorithms, which not only increases the complexity of the system, but also limits the efficiency of real-time temperature measurement. In addition, most of the current research and technical applications are mainly aimed at temperature measurement needs under static conditions, and are not adaptable enough when directly extended to dynamic, large-area, and high-temperature scenes such as hot rolling of steel. Summary of the invention

[0006] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is the problem of low temperature measurement accuracy due to serious interference from water mist and dust.

[0007] To achieve the above-mentioned object, the present invention provides a high-temperature environment water mist penetration three-wavelength temperature measurement device, including a high-temperature measurement device component and a housing;

[0008] The high temperature measurement equipment assembly includes a three-band spectroscopic detection module, a data storage and processing analysis module, a data display and system setting module, a video monitoring and laser indication module, a front mirror protection sleeve, and an electrical interface;

[0009] The three-band spectroscopic detection module includes a three-color prism and three radiation detection components, each emitting surface of the three-color prism is coated with a different radiation filter film, and the three radiation detection components include a focusing lens, a radiation detector, a circuit board and a stray light shielding sleeve;

[0010] The light beam separated from the trichromatic prism is concentrated on the radiation detector through a focusing lens, which converts it into an electrical signal. The circuit board then transmits the electrical signal to the data storage and processing analysis module.

[0011] The present invention utilizes the precise spectroscopic capabilities of trichromatic prisms and radiation filters to achieve independent separation of optical signals in specific bands, eliminate measurement interference caused by wavelength overlap, and improve temperature measurement accuracy. Multi-band precise spectroscopic technology and dynamic model optimization effectively deal with interference such as water mist and dust, greatly reducing the measurement error of the device in a dynamic high-temperature environment.

[0012] Furthermore, each emitting surface of the trichromatic prism is coated with a radiation filtering film that only allows light of a specific wavelength band to pass through.

[0013] Further, the data storage and processing analysis module includes a processor, which is responsible for receiving raw data from the radiation detection component, performing calculations and analyses to determine the temperature value, and storing the data for subsequent reading;

[0014] The data display and system setting module includes a monitor and buttons;

[0015] The video surveillance and laser designation module includes a camera and laser lighting.

[0016] The data storage and processing analysis module in the present invention is based on real-time algorithms to analyze multi-wavelength data fusion, and can dynamically adjust model parameters to adapt to different working conditions, ensuring measurement accuracy in complex environments. The multi-module collaborative design in the present invention significantly improves the device's adaptability to temperature and humidity fluctuations and interference factors, and is suitable for a variety of complex industrial application scenarios.

[0017] Furthermore, the front mirror protection sleeve includes a protection sleeve, a quartz window and an air blowing hole; the protection sleeve is connected to the temperature measuring device body by threads; the quartz window protects the three-band spectroscopic detection module; the air blowing hole is externally connected to an air blowing device; the electrical interface includes a connection port and an external power supply.

[0018] The front mirror protection sleeve equipped with a blowing device and the quartz window design in the present invention effectively prevent dust and water mist from contaminating the optical components, while ensuring that the optical path is clean and transparent, thereby ensuring the temperature measurement stability in high temperature scenes. The efficient blowing and water cooling protection design of the protection sleeve reduces the frequency of contamination and damage of the optical system, and reduces the maintenance difficulty and use cost of the equipment.

[0019] Furthermore, the high temperature measurement device assembly is contained in a housing, and a water cooling jacket is provided outside the housing to isolate the high temperature measurement device assembly from the high temperature environment.

[0020] In another aspect, the present invention provides a method for using the high-temperature environment water mist to penetrate the three-wavelength temperature measuring device according to the first aspect, the temperature measuring method comprising:

[0021] Step 1, temperature measurement data collection: After locating the area to be measured, the three radiation detection components receive the corresponding band light signal and convert it into an electrical signal. After the air purge device is purged, the real temperature of the target to be measured is obtained by the ratio temperature measurement method;

[0022] Step 2, temperature measurement data fusion: establish a temperature measurement model according to the on-site working conditions, fuse the radiation energy ratios under three different wavelength combinations, and obtain the final temperature measurement value;

[0023] Step 3, temperature measurement parameter setting: based on the temperature measurement data set constructed after data collection, the temperature measurement model parameters are optimally set;

[0024] Step 4: Application of temperature measurement model: Combined with the judgment of abnormal fluctuation temperature measurement data, the temperature measurement model is fully applied, and the temperature measurement model parameters are updated regularly.

[0025] The present invention uses radiation signals of three different band combinations to establish ratio temperature measurement models, respectively, to achieve effective penetration and compensation of water mist and steam interference on signals in complex environments. The temperature measurement model is established with the help of a neural network, and the model parameters are dynamically optimized based on the data set and updated regularly to adapt to different industrial production modes and field conditions. The model parameters are shared based on similar environmental conditions, which improves the applicability of the method in high-temperature water mist interference scenarios.

[0026] Furthermore, in step 1, water mist in a high temperature environment penetrates the three-wavelength temperature measuring device to collect data in an area with water mist interference and an air purge device, and the position of the target to be measured is accurately located by laser illumination, and the radiation energy of the three optical paths at the i-th measurement is obtained by converting the light signal received by the three radiation detection components into an electrical signal. i (λ1,T i ), M i (λ2,T i ) and M i (λ3,T i ), where λ1, λ2, and λ3 are the central wavelengths allowed to pass through the three-sided radiation filter films of the trichromatic prism; T i is the real temperature of the target to be measured at the i-th measurement. The real temperature of the target to be measured is purged by the air purge device arranged in the area based on the two selected wavelengths λ m ,λ n ,m,n∈{1,2,3}, the radiation energy ratio is approximately:

[0027]

[0028] Where C2 is the second radiation constant.

[0029] Furthermore, in step 2, based on the ratio temperature measurement principle, the radiation energy ratios under three different wavelength combinations are established in the same measurement:

[0030]

[0031] Considering the influence of interference such as water mist and steam on the radiation at each wavelength, and the different emissivity of the high-temperature target to be measured at different wavelengths, and the temperature measurement accuracy under different wavelength combinations is different under various working conditions (such as production mode, ambient temperature and humidity, etc.), the temperature measurement model f is established to obtain the final temperature measurement value

[0032]

[0033] Where α∈{1,2,…,N} represents different production conditions and θ is the model parameter.

[0034] Furthermore, the data storage and processing analysis module in step 3 stores the relevant temperature measurement data, and the data set obtained after L data collections is The optimal temperature measurement model parameter θ* is obtained as:

[0035]

[0036] In the formula, a multi-layer feedforward network is used to establish the temperature measurement model f, and the gradient descent method is used to iteratively update the parameters θ of the neural network temperature measurement model.

[0037] Furthermore, in step 4, the correlation of the environment in the adjacent areas is taken into consideration, and the parameters of the temperature measurement model can be applied to other links in the high temperature environment where there is water mist and steam interference and it is difficult to completely achieve purging, so as to more accurately test and obtain the actual temperature of the target to be measured;

[0038] In step 4, when the temperature measurement model outputs abnormal fluctuations, based on the camera acquisition image, combined with machine vision and expert experience, it is determined whether the target to be measured is in an abnormal state, and whether there is serious water vapor and water fog interference in the measurement optical path; if there is an abnormal state or interference, the fluctuation data is discarded; if there is no abnormal state or interference, the obtained temperature measurement data is accepted;

[0039] In addition, step 4 also includes regularly updating the temperature measurement model parameters based on historical accumulated temperature measurement data.

[0040] The temperature measurement method provided by the present invention has the following technical effects:

[0041] 1. Significantly improve temperature measurement accuracy: Through the multi-parameter fusion of three-wavelength signals, the influence of emissivity uncertainty, water mist and steam interference on temperature measurement accuracy is greatly reduced, so that the temperature measurement error under dynamic conditions is significantly reduced;

[0042] 2. Enhanced environmental adaptability: Through data correction and model optimization, this method can adapt to a variety of complex production conditions and meet the needs of real-time and high-precision temperature measurement in dynamic and high-humidity environments;

[0043] 3. Expand application scenarios: The innovative method can be transferred to other high-temperature water mist interference environments, greatly improving the universality and market potential of temperature measurement devices.

[0044] Compared with the prior art, the practicability of the present invention is as follows:

[0045] The present invention combines three-wavelength temperature measurement technology and learning algorithms to achieve full adaptation to complex working conditions such as high temperature, water mist, and dust in the production environment. In particular, the adaptive correction of the three-wavelength energy ratio fusion coefficient and the model online update mechanism significantly reduce the temperature measurement error caused by environmental changes and interference, and the measurement accuracy is better than that of traditional dual-wavelength and single-wavelength technologies.

[0046] The present invention replaces the traditional design of multiple splitters / reflectors with a three-color prism and integrates video monitoring and laser indication modules, thereby realizing hardware integration of multi-source information collection, reducing dependence on external measurement equipment and multiple debugging, and improving system stability and work efficiency.

[0047] The concept, specific structure and technical effects of the present invention will be further described below in conjunction with the accompanying drawings to fully understand the purpose, characteristics and effects of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of a three-wavelength infrared temperature measuring device for high-temperature environment water mist penetration according to a preferred embodiment of the present invention;

[0049] Figure 2 It is a schematic diagram of the temperature measurement deployment in a high temperature environment of hot rolling of steel according to a preferred embodiment of the present invention;

[0050] Figure 3 The present invention is a flowchart of a method for measuring temperature in a high-temperature environment by water mist penetrating three-wavelength infrared light according to a preferred embodiment of the present invention.

[0051] Wherein: 1—three-wavelength temperature measuring device; 2—housing; 3—blowing hole; 4—protective sleeve; 5—quartz window; 6—semi-transparent and semi-reflective mirror; 7—camera; 8—laser illumination; 9—trichromatic prism; 10—first radiation filter membrane; 11—first radiation detection assembly; 12—first focusing lens; 13—first radiation detector; 14—first circuit board; 15—first stray light shielding sleeve; 16—second radiation filter membrane; 17—second radiation detection assembly; 18—second focusing lens; 19—second radiation detector; 20—second circuit board; 21—second stray light shielding sleeve; 22—third radiation filter membrane; 23—third radiation detection component; 24—third focusing lens; 25—third radiation detector; 26—third circuit board; 27—third stray light shielding sleeve; 28—processor; 29—tail housing; 30—electrical interface; 31—monitor; 32—finishing mill frame; 33—air purge device; 34—laminar cooling nozzle; 35—curling machine; 36—first temperature measurement area; 37—second temperature measurement area. DETAILED DESCRIPTION

[0052] The following describes several preferred embodiments of the present invention with reference to the drawings in the specification, so that the technical content is clearer and easier to understand. The present invention can be embodied in many different forms of embodiments, and the protection scope of the present invention is not limited to the embodiments mentioned in the text.

[0053] In the drawings, components with the same structure are indicated by the same numerical reference numerals, and components with similar structures or functions are indicated by similar numerical reference numerals. The size and thickness of each component shown in the drawings are arbitrarily shown, and the present invention does not limit the size and thickness of each component. In order to make the illustration clearer, the thickness of the components is appropriately exaggerated in some places in the drawings.

[0054] like Figure 1 As shown, the present invention provides a high-temperature environment water mist penetration three-wavelength temperature measurement device 1, comprising: a high-temperature measurement device assembly and a housing 2. The high-temperature measurement device assembly comprises a three-band spectroscopic detection module, a data storage and processing analysis module, a data display and system setting module, a video monitoring and laser indication module, a front mirror protection sleeve, and an electrical interface 30;

[0055] The three-band spectroscopic detection module includes: a trichromatic prism 9, each emitting surface of the trichromatic prism 9 is coated with a first radiation filter film 10, a second radiation filter film 16, and a third radiation filter film 22, respectively, to ensure that only light of a specific wavelength band can pass through; three radiation detection components, the first radiation detection component 11 includes a first focusing lens 12, a first radiation detector 13, a first circuit board 14, and a first stray light shielding sleeve 15; the second radiation detection component 17 includes a second focusing lens 18, a second radiation detector 19, a second circuit board 20, and a second stray light shielding sleeve 21; the third radiation detection component 23 includes a third focusing lens 24, a third radiation detector 25, a third circuit board 26, and a third stray light shielding sleeve 27, to receive radiation signals of a specific wavelength band and convert them into electrical signals;

[0056] The data storage and processing analysis module includes: a processor 28, which is responsible for receiving raw data from the first radiation detection component 11, the second radiation detection component 17, and the third radiation detection component 23, performing calculations and analyses to determine the temperature value, and storing the data for subsequent reading;

[0057] The data display and system setting module includes: a monitor 31, which provides a user interface so that the operator can view the measurement results, set parameters, adjust the system configuration, etc. in real time through the display screen; a group of buttons for adjusting the temperature measurement model parameters under various working conditions.

[0058] The video monitoring and laser indication module includes: a camera 7, a semi-transparent and semi-reflective mirror 6 adjusts the optical path of a specific light so that the light can be received by the camera 7 and an image is formed, thereby realizing the operator's real-time remote monitoring of the temperature measurement point; a laser lighting 8, a semi-transparent and semi-reflective mirror 6 accurately locates the measurement area by changing the optical path of the laser lighting 8;

[0059] The front mirror protection sleeve includes: a protection sleeve 4, which is tightly matched with the temperature measuring device body through threads to protect the optical system from the influence of adverse environmental factors such as fog and dust; a quartz window 5, which is used but not limited to being embedded between the protection sleeve and the temperature measuring device body with screws to maintain the cleanliness and transparency of the optical path and protect the three-band spectroscopic detection module; an air hole 3, which is connected to an external air blowing device to prevent dust or water vapor from approaching and ensure that the measurement accuracy is not disturbed by external conditions;

[0060] The electrical interface 30 includes: a standardized connection port connected to external devices such as power supply, data acquisition, and remote control.

[0061] Furthermore, each emitting surface of the trichromatic prism 9 is coated with a specific first radiation filter film 10, a second radiation filter film 16, and a third radiation filter film 22. These filter films only allow light of a specific wavelength band to pass through, thereby ensuring that the first radiation detection component 11, the second radiation detection component 17, and the third radiation detection component 23 receive light signals of a single wavelength band.

[0062] Furthermore, the light beam separated from the trichromatic prism 9 is concentrated on the first radiation detector 13, the second radiation detector 19, and the third radiation detector 25 through the first focusing lens 12, the second focusing lens 18, and the third focusing lens 24. The first radiation detector 13, the second radiation detector 19, and the third radiation detector 25 convert the optical signal into an electrical signal, and the first circuit board 14, the second circuit board 20, and the third circuit board 26 then transmit the electrical signal to the data storage and processing analysis module.

[0063] Furthermore, the data storage and processing analysis module is responsible for receiving the raw data of the first radiation detection component 11, the second radiation detection component 17, and the third radiation detection component 23, and performing relevant algorithm processing;

[0064] Further, the high temperature measurement device assembly is contained in a housing 2, which may provide a water cooling jacket to insulate the device from the high temperature environment.

[0065] like Figure 2As shown, the present invention provides a deployment schematic diagram of a three-wavelength temperature measuring device 1 suitable for high-temperature environment of hot rolling of steel. The device can be flexibly moved in the area between the final stand 32 of the finishing rolling mill and the coiler 35. At the entrance of this area, an air purge device 33 is provided, thereby forming a first temperature measuring area 36 with water mist interference and air purge. In the laminar cooling area, multiple groups of laminar cooling nozzles 34 are arranged to form a second temperature measuring area 37 with water mist interference but without air purge.

[0066] On the other hand, the present invention provides a method for measuring temperature in a high-temperature environment by water mist penetrating a three-wavelength infrared device, the method comprising the following steps:

[0067] Step 1, temperature measurement data collection: the laser lighting 8 accurately locates the area to be measured, the first radiation detection component 11, the second radiation detection component 17, and the third radiation detection component 23 receive the corresponding band light signal and convert it into an electrical signal, and the air purge device 33 obtains the real temperature of the target to be measured through the ratio temperature measurement method after purging;

[0068] Step 2, temperature measurement data fusion: Considering different on-site working conditions, a temperature measurement model is established to fuse the radiation energy ratios under three different wavelength combinations to obtain the final temperature measurement value;

[0069] Step 3, temperature measurement parameter setting: based on the temperature measurement data set constructed after multiple data collections, the temperature measurement model parameters are optimally set;

[0070] Step 4: Application of temperature measurement model: Combined with the determination of abnormal fluctuation temperature measurement data based on camera images, the temperature measurement model is fully applied, and the temperature measurement model parameters are regularly updated online.

[0071] Furthermore, in step 1, the temperature measuring device 1 is used to collect data in the first temperature measuring area 36 with water mist interference and arranged with the air purge device 33, and the position of the target to be measured is accurately located by the laser illumination 8. The radiation energy M of the three optical paths at the i-th measurement is obtained by converting the optical signals received by the first radiation detection component 11, the second radiation detection component 17, and the third radiation detection component 23 into electrical signals. i (λ1,T i ), M i (λ2,T i ), M i (λ3,T i ), where λ1, λ2, and λ3 are the central wavelengths allowed to pass through by the first radiation filter film 10, the second radiation filter film 16, and the third radiation filter film 22 of the trichromatic prism 9, respectively; T i is the real temperature of the target to be measured during the i-th measurement. After being purged by the air purge device 33 arranged in the area, based on the two selected wavelengths λ m ,λn , the radiation energy ratio under m,n∈{1,2,3} is approximately obtained:

[0072]

[0073] Where C2 is the second radiation constant.

[0074] Furthermore, in step 2, based on the ratio temperature measurement principle, the radiation energy ratios under three different wavelength combinations are established in the same measurement:

[0075]

[0076] Considering the influence of water mist and steam on the radiation at each wavelength, and the different emissivity of the high-temperature target to be measured at different wavelengths, the temperature measurement accuracy under different wavelength combinations varies under various working conditions (such as production mode, environment, etc.).

[0077] The temperature measurement model is established to obtain the final temperature measurement value.

[0078]

[0079] Where α∈{1,2,…,N} represents different production conditions and θ is the model parameter.

[0080] Furthermore, the data storage and processing analysis module in step 3 stores the relevant temperature measurement data, based on the data set obtained after L data collections. Get the best temperature measurement model parameter θ*:

[0081]

[0082] In the formula, a multi-layer feedforward network is used to establish the temperature measurement model f, and the gradient descent method is used to iteratively update the parameters θ of the neural network temperature measurement model.

[0083] Furthermore, step 4 takes into account the correlation of the environment in similar areas, and the temperature measurement model parameters can be applied to other parts of the high-temperature environment where there is water mist and steam interference and it is difficult to completely achieve purging, so as to more accurately measure the temperature of the target to be measured. When the temperature measurement model output fluctuates abnormally, based on the image collected by camera 7, combined with machine vision and expert experience, it is determined whether the target to be measured is in an abnormal state and whether there is serious water vapor and water mist interference in the measurement optical path. If the above-mentioned abnormal state or interference exists, the fluctuation data is discarded; if the above-mentioned interference does not exist, the temperature measurement data is accepted. In addition, based on the historical accumulated temperature measurement data, the temperature measurement model parameters are updated regularly.

[0084] like Figure 3As shown in the figure, taking a typical high-temperature steel hot rolling production process as an example, the high-temperature environment water mist penetration three-wavelength infrared temperature measurement method flow chart, the specific steps are as follows:

[0085] Step 1: Considering that the temperature measurement range of the steel hot rolling process needs to cover 500℃ to 1200℃, based on the blackbody radiation spectrum curve, three temperature measurement wavelengths are selected in sequence as λ1=800nm, λ2=900nm, and λ3=1000nm. For the first temperature measurement area 36 between the final stand of the finishing rolling mill and the laminar cooling inlet, the three-wavelength temperature measurement device 1 of the present invention is used to collect data, and the radiation energy M of the three optical paths during the i-th measurement is obtained respectively. i (λ1,T i ), M i (λ2,T i ) and M i (λ3,T i ). Among them, T i is the real temperature of the strip at the i-th measurement, which is approximately obtained based on the ratio of the radiation energy at the two selected wavelengths λ1 and λ2 after being purged by the air purging device 33 arranged here in the rolling line:

[0086]

[0087] Where C2 is the second radiation constant.

[0088] Step 2: In the same measurement, based on the ratio temperature measurement principle, establish the radiation energy ratio under three different wavelength combinations:

[0089]

[0090] Radiation energy ratio For example, the expression is as follows, considering that the radiation effect κ1 at wavelength λ1 and the radiation effect κ2 at wavelength λ2 caused by interference such as water mist and steam are different, and the strip emissivity ε(λ1,T) and ε(λ2,T) at the two wavelengths are not exactly the same:

[0091]

[0092] At the same time, considering that the temperature measurement accuracy under different wavelength combinations is different under various working conditions (such as rolling mode, ambient temperature and humidity, etc.), a BP neural network temperature measurement model f with one hidden layer is established to fuse the energy ratios under the three wavelength combinations to obtain the final temperature measurement value.

[0093]

[0094] Where α∈{1,2,…,N} represents different hot rolling production conditions, and θ is the model parameter.

[0095] Step 3: The data storage and processing analysis module stores the relevant temperature measurement data based on the data set obtained after L data collections. Get the best temperature measurement model parameter θ*:

[0096]

[0097] In the formula, the specific method of finding the optimal parameters is to randomly select P (P≤L) indexes {i1,i2,…,i P} data combination, and iteratively update the temperature measurement model parameters θ in a gradient descent manner:

[0098]

[0099] In the formula, l θ is the learning rate for parameter update, ▽ θ is the gradient operator with respect to θ.

[0100] Step 4: Considering the correlation of the environment in the vicinity of the hot rolling line, the temperature measurement model parameters can be applied to laminar cooling and other links where there is water mist and steam interference and it is difficult to completely achieve purging, such as the second temperature measurement area 37 in the laminar cooling zone, so as to more accurately measure the strip temperature. When the temperature measurement model output shows abnormal fluctuations, the image obtained by the camera 7 is analyzed and abnormality detected to determine whether there are abnormal points such as iron oxide scale or serious water vapor and water mist interference in the measured area. If the above-mentioned abnormal points or interference exist, the abnormal data is discarded; if the above-mentioned interference does not exist, the temperature measurement data is accepted. In addition, based on the historical accumulated temperature measurement data, the temperature measurement model parameters are updated regularly.

[0101] The preferred specific embodiments of the present invention are described in detail above. It should be understood that ordinary technicians in the field can make many modifications and changes based on the concept of the present invention without creative work. Therefore, all technical solutions that can be obtained by technicians in the technical field based on the concept of the present invention through logical analysis, reasoning or limited experiments on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A three-wavelength temperature measuring device for water mist penetration in a high-temperature environment, characterized in that: Includes high temperature measurement equipment assemblies and enclosures; The high temperature measurement equipment assembly includes a three-band spectroscopic detection module, a data storage and processing analysis module, a data display and system setting module, a video monitoring and laser indication module, a front mirror protection sleeve, and an electrical interface; The three-band spectroscopic detection module includes a three-color prism and three radiation detection components, each emitting surface of the three-color prism is coated with a different radiation filter film, and the three radiation detection components include a focusing lens, a radiation detector, a circuit board and a stray light shielding sleeve; The light beam separated from the trichromatic prism is concentrated on the radiation detector through a focusing lens, which converts it into an electrical signal. The circuit board then transmits the electrical signal to the data storage and processing analysis module.

2. The high temperature environment water mist penetration three-wavelength temperature measuring device according to claim 1, characterized in that: Each emitting surface of the trichromatic prism is coated with a radiation filtering film that only allows light of a specific wavelength band to pass through.

3. The high temperature environment water mist penetration three-wavelength temperature measuring device according to claim 1, characterized in that: The data storage and processing analysis module includes a processor, which is responsible for receiving raw data from the radiation detection component, performing calculations and analyses to determine the temperature value, and storing the data for subsequent reading; The data display and system setting module includes a monitor and buttons; The video surveillance and laser designation module includes a camera and laser lighting.

4. The high temperature environment water mist penetration three-wavelength temperature measuring device according to claim 1, characterized in that: The front mirror protection sleeve comprises a protection sleeve, a quartz window and a blowing hole; The protective sleeve is connected to the temperature measuring device body via threads; The quartz window protects the three-band spectroscopic detection module; The blowing hole is externally connected to a blowing device; The electrical interface includes a connection port and an external power source.

5. The high temperature environment water mist penetration three-wavelength temperature measuring device according to claim 1, characterized in that: The high temperature measurement device assembly is contained in a housing, and a water cooling jacket is arranged outside the housing to isolate the high temperature measurement device assembly from a high temperature environment.

6. A method using the high temperature environment water mist penetration three-wavelength temperature measurement device according to claims 1-5, characterized in that: The temperature measurement method comprises: Step 1, temperature measurement data collection: After locating the area to be measured, the three radiation detection components receive the corresponding band light signal and convert it into an electrical signal. After the air purge device is purged, the real temperature of the target to be measured is obtained by the ratio temperature measurement method; Step 2, temperature measurement data fusion: establish a temperature measurement model according to the on-site working conditions, fuse the radiation energy ratios under three different wavelength combinations, and obtain the final temperature measurement value; Step 3, temperature measurement parameter setting: based on the temperature measurement data set constructed after data collection, the temperature measurement model parameters are optimally set; Step 4: Application of temperature measurement model: Combined with the judgment of abnormal fluctuation temperature measurement data, the temperature measurement model is fully applied, and the temperature measurement model parameters are updated regularly.

7. The method according to claim 6, characterized in that The step 1 uses the high temperature environment water mist to penetrate the three-wavelength temperature measuring device to collect data in an area with water mist interference and arranged with an air purge device, accurately locates the position of the target to be measured by laser illumination, and uses the electrical signal converted from the light signal received by the three radiation detection components to obtain the radiation energy of the three light paths at the i-th measurement, which are M i (λ1,T i ), M i (λ2,T i ) and M i (λ3,T i ), where λ1, λ2, and λ3 are the central wavelengths allowed to pass through the three-sided radiation filter films of the trichromatic prism respectively; T i is the real temperature of the target to be measured at the i-th measurement. The real temperature of the target to be measured is purged by the air purge device arranged in the area based on the two selected wavelengths λ m ,λ n ,m,n∈{1,2,3}, the radiation energy ratio is approximately: Where C2 is the second radiation constant.

8. The method according to claim 6, characterized in that Step 2: In the same measurement, based on the ratio temperature measurement principle, establish the radiation energy ratio under three different wavelength combinations: Considering the influence of interference such as water mist and steam on the radiation at each wavelength, and the different emissivity of the high-temperature target to be measured at different wavelengths, and the different temperature measurement accuracy under different wavelength combinations under various working conditions, the temperature measurement model f is established to obtain the final temperature measurement value In the formula, α∈{1,2, … , N} represents different production conditions, and θ is the model parameter.

9. The method according to claim 6, characterized in that In step 3, the data storage and processing analysis module stores the relevant temperature measurement data. The data set obtained after L data collections is The optimal temperature measurement model parameter θ* is obtained as: In the formula, a multi-layer feedforward network is used to establish the temperature measurement model f, and the gradient descent method is used to iteratively update the parameters θ of the neural network temperature measurement model.

10. The method according to claim 6, characterized in that Step 4: Taking into account the relevance of the environment in the adjacent areas, the parameters of the temperature measurement model are used to test and obtain the actual temperature of the target to be measured in other links where there is water mist and steam interference and it is difficult to completely achieve purging in a high temperature environment; In step 4, when the output of the temperature measurement model fluctuates abnormally, based on the camera acquisition image, combined with machine vision and expert experience, it is determined whether the target to be measured is in an abnormal state, and whether there is serious water vapor and water fog interference in the measurement optical path; If there is an abnormal state or interference, the fluctuation data is discarded; If there is no abnormal state or interference, the obtained temperature measurement data is accepted; Step 4 also includes: regularly updating the temperature measurement model parameters based on historical accumulated temperature measurement data.

Images