Hearth temperature field intelligent visualization system based on sound sensing technology

Abstract

The invention relates to the technical field of acoustic measurement, in particular to a hearth temperature field intelligent visualization system based on an acoustic sensing technology. Comprising an array type sound sensing data acquisition unit; a working condition adaptive inversion unit; a three-dimensional temperature field intelligent visualization unit; and a working condition early warning and interaction unit. The method comprises the following steps: receiving sound wave data, working condition parameters and a corrected temperature field, extracting sound wave frequency-amplitude features, working condition mean values and fluctuation features in a branched manner, and dynamically distributing attention weights according to feature credibility to obtain fusion features; fusion features are input into an inversion model to obtain a current temperature field, the actually measured temperature of the thermocouple is used as a reference to calculate errors, regularization coefficients which are negatively correlated with the errors and the number of iterations are adopted to optimize, the errors are disassembled to adjust related parameters, working condition changes can be adapted without manual intervention, and system automation and long-term operation reliability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of acoustic measurement, in particular to a furnace temperature field intelligent visualization system based on acoustic sensing technology. BACKGROUND

[0002] Accurate monitoring of the furnace temperature field is the core requirement for ensuring the safe operation and efficient temperature control of thermal equipment such as power plant boilers and industrial furnaces. Traditional contact-type temperature measurement methods (such as thermocouples) are susceptible to high-temperature corrosion and dust abrasion, and have the limitations of short service life and only single-point data acquisition. Non-contact infrared and optical temperature measurement technologies are difficult to accurately capture the global temperature due to interference from flue gas radiation and equipment visual angle obstruction in the furnace. Acoustic temperature measurement technology, relying on the core principle that the speed of sound propagation is strongly related to the temperature of the medium, has the advantages of non-invasiveness, fast response speed, and wide measurement range, and has become a key technology direction in the field of furnace temperature field monitoring. By measuring parameters such as sound wave flight time and combining inversion algorithms, the temperature field can be reconstructed and monitored.

[0003] In the prior art, research has been conducted on acoustic temperature measurement signal optimization and the construction of a power plant boiler temperature monitoring system. For example, in "Boiler Furnace Temperature Field Acoustic Temperature Measurement Signal Research Based on Multi-Dimensional Optimization Strategy", the focus is on the filtering and noise reduction optimization of acoustic signals, and the signal-to-noise ratio is improved through multi-parameter collaborative processing to reduce the interference of noise on temperature measurement data. In "Research on Power Plant Boiler Temperature Monitoring System Based on Acoustic Temperature Measurement Principle", a basic acoustic temperature measurement hardware framework is constructed, and real-time acquisition and output of temperature data during the operation of the power plant boiler are realized, providing data support for subsequent temperature analysis.

[0004] Although the above technical solutions have corresponding design advantages, the above technical solutions still have the following technical defects: firstly, the temperature measurement accuracy is insufficient under complex working conditions: although the signal quality under a single noise scene can be improved in the "Study on Acoustic Temperature Measurement Signal of Boiler Furnace Temperature Field Based on Multi-dimensional Optimization Strategy", the problem of sound ray refraction caused by the coupling of high temperature gradient and axial airflow in the furnace is not solved, and the noise reduction effect of multi-source superimposed noise such as combustion noise and soot blower working noise is limited. In the model construction of the "Research on Temperature Monitoring System of Power Station Boiler Based on Acoustic Temperature Measurement Principle", the "sound ray straight line propagation" assumption is adopted, which further ignores the influence of airflow disturbance on the sound ray propagation path, resulting in poor temperature reconstruction accuracy in the high temperature area, which cannot meet the strict requirements of industrial scenes on temperature measurement accuracy. Secondly, the reconstruction model is fixed and lacks the ability to adapt to working conditions: the technical solutions corresponding to the above two documents both adopt a fixed general reconstruction algorithm (such as Landweber iteration method), and the key parameters such as regularization parameter and iteration number in the algorithm depend on artificial experience preset. When the boiler faces load changes, coal replacement and other working condition changes, or internal changes such as coking and ash accumulation, the fixed model parameters cannot match the real-time working conditions, and the operator needs to frequently manually adjust the parameters, which not only increases the operation and maintenance cost, but also greatly limits the automation, intelligence level and long-term stable operation reliability of the system. Thirdly, it lacks temperature field visualization capability: the above technical solutions do not construct a visualization model of the temperature field, and can only output discrete temperature values, and cannot realize two-dimensional or three-dimensional image display of the global temperature distribution, making it difficult for the operation and maintenance personnel to intuitively perceive the key information such as the temperature gradient and local overheating in the furnace, and being out of touch with the industrial operation and maintenance demand of "intelligent visualization". In view of this, we propose an intelligent visualization system for furnace temperature field based on acoustic sensing technology. SUMMARY

[0005] The purpose of the present application is to provide an intelligent visualization system for furnace temperature field based on acoustic sensing technology to solve the problems of insufficient temperature measurement accuracy under complex working conditions, fixed reconstruction model and lack of working condition adaptation ability and lack of temperature field visualization capability in the background art.

[0006] To solve the above technical problems, the purpose of the present application is to provide an intelligent visualization system for furnace temperature field based on acoustic sensing technology, which comprises: An array acoustic sensing data acquisition unit, which is arranged with multiple groups of acoustic sensor arrays along the circumference of the furnace to collect acoustic wave signals in the furnace; the acoustic wave signals are filtered to suppress characteristic noise, and combined with airflow data of a differential pressure flow sensor to output basic data for sound ray propagation correction; The working condition self-adaptive inversion unit receives real-time working condition parameters of the boiler DCS system and basic data of the acoustic wave signal output by the array acoustic sensing data acquisition unit, obtains the minimum propagation time of each acoustic wave path by solving the Eikonal equation based on the current iterative temperature field distribution and the input airflow velocity field using the fast marching method, and reversely conducts the time residual to the temperature field update process through the automatic differentiation mechanism; meanwhile, an improved algorithm of double-branch attention fusion and residual feedback dynamic regularization is used to extract the time sequence features of the acoustic data and the steady-state and dynamic features of the working condition parameters, respectively, to realize nonlinear fusion of heterogeneous data through dynamic allocation of attention weights, reversely conduct the temperature distribution error to dynamically adjust the algorithm parameters in the iteration process, and output the global three-dimensional temperature distribution data of the furnace; The three-dimensional temperature field intelligent visualization unit receives the global three-dimensional temperature distribution data of the furnace output by the working condition self-adaptive inversion unit, converts the format, constructs the furnace geometric model through a general rendering tool and superimposes the temperature information to generate a real-time temperature field image, which has the functions of temperature value labeling, regional feature display and view switching; The working condition early warning and interaction unit compares the abnormal temperature information identified by the three-dimensional temperature field intelligent visualization unit based on the temperature safety range of the furnace equipment, outputs an acoustic and light alarm signal and pushes the abnormal region coordinates when triggering the early warning, and is equipped with a human-computer interaction interface that can display real-time temperature field images, historical data curves and early warning records and support adjustment of interface parameters.

[0007] As a further improvement of the technical solution, the array acoustic sensing data acquisition unit includes an array arrangement module, a signal acquisition module, a filtering processing module and a data fusion module, wherein: The array arrangement module is used to cooperatively arrange multiple groups of acoustic sensor arrays and differential pressure flow rate sensors along the circumference of the furnace, the installation height of the acoustic sensor array is adapted to the flame center area of the furnace, the differential pressure flow rate sensor corresponds to the furnace area one by one with the acoustic sensor array, the spacing between adjacent sampling points is ≤1.5 m, and the spatial matching of the acoustic wave and airflow data is ensured; The signal acquisition module is integrated in the acoustic sensor array of the array arrangement module and is used to synchronously acquire acoustic wave signals in different areas of the furnace, and the acquisition frequency is matched with the propagation period of the acoustic wave in the furnace; The filtering processing module is signal-connected with the signal acquisition module and is used to receive the original acoustic wave signal, retain the frequency band related to the furnace combustion by band-pass filtering, and filter out the signal of the interference frequency band; The data fusion module is signal-connected with the filtering processing module and the differential pressure flow rate sensor, respectively, and is used to time-synchronize the filtered acoustic wave signal and the airflow data, integrate them into acoustic ray propagation correction basic data, and output them to the working condition self-adaptive inversion unit.

[0008] As a further improvement of the technical solution, the working condition adaptive inversion unit comprises a data receiving module, a sound ray propagation correction module, a feature fusion module, an iterative optimization module and a result output module, wherein: The input end of the data receiving module is respectively connected with the boiler DCS system and the array acoustic sensing data acquisition unit signal, for receiving real-time working condition parameters and acoustic signal basic data, and synchronously distributing to the sound ray propagation correction module and the feature fusion module; The sound ray propagation correction module is connected with the data receiving module signal, for receiving the initial temperature field , airflow velocity field and measured sound wave propagation time , generating a corrected temperature field through sound ray propagation path error correction, and outputting to the feature fusion module; The feature fusion module is connected with the sound ray propagation correction module and the data receiving module signal respectively, for extracting sound wave features and working condition features , generating a fusion feature vector through double-branch attention fusion, and outputting to the iterative optimization module; The iterative optimization module is connected with the feature fusion module signal, based on inversion of the current temperature field , combined with the regularization coefficient to perform residual feedback dynamic regularization optimization, output and the corresponding mean absolute error to the result output module, while the non-converged is fed back to the sound ray propagation correction module; The result output module is connected with the iterative optimization module signal, for determining the iterative convergence, when the temperature field error and gradient stability conditions are met for 3 consecutive iterations, output to the three-dimensional temperature field intelligent visualization unit.

[0009] As a further improvement of the technical solution, the sound ray propagation correction module performs the sound ray propagation correction process, which comprises the following steps: S22.1, receiving the initial temperature field , real-time airflow velocity field transmitted by the data receiving module, and measured sound wave propagation time output by the array acoustic sensing data acquisition unit; wherein is the furnace design reference temperature field or the last round temperature field result fed back by the iterative optimization module; S22.2, for any three-dimensional space coordinates Calculate the sound wave propagation speed after temperature and airflow coupling according to general acoustic relationships. The angle between the airflow and the direction of sound propagation The data was obtained by calculating the airflow direction data from the DCS system and the coordinates of the acoustic sensor deployment. S22.3. Taking the sound sensor transmitter as the starting point and the receiver as the ending point, the Eikonal equation is solved using the fast travel method to obtain the shortest path of sound wave propagation and the corresponding theoretical propagation time. ; S22.4, Calculation and residual Through automatic differentiation mechanism Reverse conduction to Generate the corrected temperature field And transmit it to the feature fusion module.

[0010] As a further improvement to this technical solution, the sound wave propagation speed in S22.2 The calculation supports airflow humidity adaptation, and the specific adaptation process includes the following steps: S22.21 Receive the relative humidity of the airflow inside the furnace output by the DCS system. ; S22.22, Introduce a humidity correction factor , The value of varies Linear change, The value range is [0,1]; S22.23, based on and Adjustment The computational logic enables It is adapted to the sound speed propagation characteristics under corresponding humidity conditions.

[0011] As a further improvement to this technical solution, the feature fusion module performs the dual-branch attention fusion process, which includes the following steps: S23.1 Receive the raw acoustic wave data and operating parameters transmitted by the data receiving module, and synchronously receive the corrected temperature field output by the acoustic ray propagation correction module. ; S23.2 Perform dual-branch feature extraction. The first branch uses the sliding window method to extract the frequency-amplitude features of the acoustic wave data. The second branch extracts the mean and fluctuation characteristics of the operating condition parameters. ; S23.3 Calculating the reliability of acoustic wave features based on the statistical characteristics of feature data. The reliability of the operating condition characteristics is negatively correlated with the standard deviation and positively correlated with the mean. negative correlation with the standard deviation of the operating condition characteristics and positive correlation with the mean value; S23.4、According to negative correlation with the standard deviation of the operating condition characteristics and positive correlation with the mean value; Assigning attention weights , and obtaining the fusion feature vector through weighted calculation , the weights are updated in real time according to new feature data and output to the iterative optimization module.

[0012] As a further improvement of the technical solution, the process of the iterative optimization module performing residual feedback dynamic regularization optimization includes the following steps: S24.1, the feature fusion module outputs input temperature field inversion model, and calculate the current round furnace global temperature field ; S24.2, taking the actual measured temperature of the furnace wall thermocouple as the basis, calculating the mean absolute error of , is the actual measured temperature value at the coordinate ; S24.3, the value of is negatively correlated with , and the number of iterations is negatively correlated with , the smaller the error is, the smaller the error is in the early stage of iteration , and the smaller the error is, the larger the error is in the later stage of iteration ; S24.4, disassembling the source, adjusting the angle between the airflow and the sound ray propagation direction of the sound ray propagation correction module , if the sound ray residual error changes synchronously with , adjust the calculation weight of ; , if the feature stability and change synchronously, correct the correlation weight of the standard deviation and the mean value in , and to the result output module.

[0013] As a further improvement of the technical solution, the process of the result output module performing result determination and output includes the following steps: S25.1, receiving the current round temperature field and the corresponding mean absolute error transmitted by the iterative optimization module; S25.2 When the preset stability conditions of temperature field error and global temperature gradient are met for three consecutive iterations, the iteration is determined to be converged. S25.3 If the iteration converges, output This data serves as the final three-dimensional temperature distribution data for the entire furnace, transmitted to the three-dimensional temperature field intelligent visualization unit. If convergence is not achieved, Feedback is sent to the sound propagation correction module as the initial temperature field for the next iteration. .

[0014] As a further improvement to this technical solution, the three-dimensional temperature field intelligent visualization unit includes a data adaptation module, a model construction module, and a visualization interaction module, wherein: The data adaptation module is signal-connected to the working condition adaptive inversion unit and is used to receive three-dimensional temperature distribution data of the entire furnace, perform data format conversion, and match the spatial coordinate system and data accuracy standard of the furnace geometric model in the model construction module. The model building module and the data adaptation module are connected by a signal. The model building module is used to call a general rendering tool to build a geometric model that matches the actual furnace, and to overlay the converted temperature data onto the corresponding spatial region of the geometric model to generate a real-time temperature field image of the furnace. The visualization interaction module is signal-connected to the model building module and is used to perform temperature value annotation and furnace combustion area feature display operations on the real-time temperature field image, while also supporting multi-view switching function.

[0015] As a further improvement to this technical solution, the working condition early warning and interaction unit includes a working condition comparison module, an early warning triggering module, and a human-machine interaction module, wherein: The operating condition comparison module is connected to the three-dimensional temperature field intelligent visualization unit and is used to retrieve the preset safe temperature range of the furnace equipment, compare the temperature field data output by the three-dimensional temperature field intelligent visualization unit, and identify abnormal temperature information that exceeds the safe range. The early warning triggering module is signal-connected to the operating condition comparison module. When abnormal temperature information is detected, it outputs an audible and visual alarm signal and simultaneously pushes the coordinates of the furnace area corresponding to the abnormal temperature. The human-computer interaction module is connected to the early warning triggering module and the three-dimensional temperature field intelligent visualization unit, respectively, and is used to display real-time temperature field images, historical temperature data curves and early warning records. It also supports the adjustment of interface display parameters.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. The present application arranges acoustic sensors and differential pressure flow sensors circumferentially along the hearth, synchronously collects acoustic wave and airflow data, integrates the corrected basic data after filtering out interference through band-pass filtering, and then obtains the sound wave propagation path and theoretical time by solving the equation through the fast marching method, calculates the time residual and reversely conducts the temperature field correction, and also adjusts the sound speed calculation by introducing a correction coefficient combined with the relative humidity of the airflow, effectively correcting the sound wave propagation error and improving the accuracy of the hearth temperature field reconstruction under complex working conditions; 2. The present application receives acoustic wave data, working condition parameters and corrected temperature field, extracts acoustic wave frequency-amplitude characteristics and working condition mean value, fluctuation characteristics from each branch, dynamically allocates attention weight according to the characteristic reliability (negatively correlated with standard deviation, positively correlated with mean value) to obtain fusion characteristics; the fusion characteristics are input into the inversion model to obtain the current temperature field, the error is calculated based on the actual measured temperature of the thermocouple, the regularization coefficient negatively correlated with the error and the number of iterations is used for optimization, and the related parameters are adjusted by disassembling the error, without manual intervention to adapt to the working condition changes, improving the system automation and long-term operation reliability; 3. The present application receives global three-dimensional temperature data, converts the format, calls tools to build a geometric model matched with the actual hearth, superimposes temperature data to generate real-time temperature field images, supports temperature labeling, combustion area display and multi-view switching; at the same time, abnormality is identified by comparing with the preset temperature safety range, sound and light alarm is output when abnormality occurs, and abnormal area coordinates are pushed, real-time images, historical curves and warning records can also be displayed, parameter adjustment is supported, and the temperature gradient and local overheating in the furnace are intuitively perceived by the operation and maintenance personnel, which meets the intelligent operation and maintenance needs. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The system framework of the present application is shown in the figure; The meanings of the various labels in the figure are as follows: 1, array type acoustic sensing data acquisition unit; 11, array arrangement module; 12, signal acquisition module; 13, filter processing module; 14, data fusion module; 2, working condition adaptive inversion unit; 21, data receiving module; 22, acoustic line propagation correction module; 23, feature fusion module; 24, iterative optimization module; 25, result output module; 3, three-dimensional temperature field intelligent visualization unit; 31, data adaptation module; 32, model building module; 33, visualization interaction module; 4, working condition warning and interaction unit; 41, working condition comparison module; 42, warning triggering module; 43, man-machine interaction module. DETAILED DESCRIPTION

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, this embodiment provides an intelligent visualization system for furnace temperature field based on acoustic sensing technology, including: The array-type acoustic sensing data acquisition unit 1 has multiple sets of acoustic sensor arrays arranged around the furnace circumference to collect acoustic wave signals inside the furnace; the acoustic wave signals are filtered to suppress characteristic noise, and combined with the airflow data of the differential pressure flow velocity sensor, the basic data for sound ray propagation correction is output. In this embodiment, the array-type acoustic sensing data acquisition unit 1 includes an array deployment module 11, a signal acquisition module 12, a filtering processing module 13, and a data fusion module 14, wherein: The array deployment module 11 is used to coordinate the deployment of multiple acoustic sensor arrays and differential pressure flow sensors along the circumference of the furnace. The installation height of the acoustic sensor array is adapted to the center area of ​​the furnace flame, and the differential pressure flow sensors correspond one-to-one with the acoustic sensor arrays in the furnace area. The distance between adjacent sampling points is ≤1.5m to ensure the spatial matching of acoustic wave and airflow data. Specifically, the array deployment module 11 divides the furnace circumference into multiple monitoring sub-regions. Each sub-region corresponds to a set of high-temperature resistant and dust-resistant piezoelectric acoustic sensor arrays and a Pitot tube differential pressure sensor, which are deployed together at the height section of the furnace flame center area. The distance between adjacent sampling points is adjusted by a laser rangefinder to ≤1.5m, so as to realize the spatial matching acquisition of sound wave and airflow data.

[0020] The signal acquisition module 12 is integrated into the acoustic sensor array of the array deployment module 11 and is used to synchronously acquire acoustic wave signals in different areas of the furnace. The acquisition frequency is matched with the propagation period of the acoustic wave in the furnace. Specifically, the signal acquisition module 12 is integrated into the acoustic sensor array and adopts a multi-channel synchronous acquisition architecture. It synchronously acquires acoustic wave signals from each region at a frequency of 20kHz to 50kHz. The acquisition timing is ensured by the FPGA synchronous trigger circuit, and the analog signal is converted into a digital signal by a 16-bit analog-to-digital converter.

[0021] The filtering module 13 is connected to the signal acquisition module 12 and is used to receive the original acoustic signal. It uses bandpass filtering to retain the relevant characteristic frequency bands of furnace combustion and filter out interference frequency band signals. Specifically, the filter processing module 13 adopts a digital signal processor to realize band-pass filtering, the passband is set to 500Hz-5000Hz to retain the characteristics of the combustion-related sound waves, a 5th order Butterworth filtering algorithm is adopted to suppress power frequency, mechanical vibration and high frequency electromagnetic clutter interference.

[0022] The data fusion module 14 is respectively connected with the filter processing module 13 and the differential pressure type flow rate sensor signal, used to time synchronize the filtered sound wave signal and the airflow data, and integrate them into sound line propagation correction basis data output to the working condition adaptive inversion unit 2.

[0023] Specifically, the data fusion module 14 adds high-precision time stamps to the sound wave signal and airflow data through GPS time service or PTP protocol to realize time synchronization, integrates the synchronized data into a structured data packet containing sub-region number, sound wave segment, airflow speed and time stamp, and outputs it to the working condition adaptive inversion unit 2 through the Profinet industrial Ethernet interface.

[0024] It can be understood that the differential pressure type flow rate sensor adopts a cooling sleeve protection measure: the sensor probe is placed in the cooling sleeve, cooling medium (such as compressed air) is introduced into the sleeve to isolate the high temperature of the furnace, and ensure that the sensor works stably in an environment of ≤850℃, avoiding signal distortion or equipment damage caused by high temperature.

[0025] The working condition adaptive inversion unit 2 receives real-time working condition parameters of the boiler DCS system and sound wave signal basis data output by the array type sound perception data acquisition unit 1, based on the current iterative temperature field distribution and input airflow speed field, adopts the fast marching method to solve the Eikonal equation to obtain the minimum propagation time of each sound wave path, and through the automatic differentiation mechanism, the time residual is conducted reversely to the temperature field updating process; at the same time, an improved algorithm of double-branch attention fusion and residual feedback dynamic regularization is adopted to extract the sound wave data time sequence features and the working condition parameter steady-state and dynamic features respectively, realize nonlinear fusion of heterogeneous data through dynamic allocation of attention weight, and in the iteration process, the temperature distribution error is conducted reversely to dynamically adjust the algorithm parameters, and the full-domain three-dimensional temperature distribution data of the furnace is output; the working condition adaptive inversion unit 2 includes a data receiving module 21, a sound line propagation correction module 22, a feature fusion module 23, an iterative optimization module 24 and a result output module 25, wherein: In the embodiment, the input end of the data receiving module 21 is respectively connected with the boiler DCS system and the array type sound perception data acquisition unit 1, used to receive real-time working condition parameters and sound wave signal basis data, and synchronously distribute them to the sound line propagation correction module 22 and the feature fusion module 23; Specifically, the data receiving module 21 adopts a double-interface architecture to realize data synchronous receiving and distribution, ensuring the real-time and consistency of multi-source data. It establishes a communication link with the boiler DCS system through the ModbusTCP protocol, and the transmission rate is set to ≥100Mbps. The received real-time operating condition parameters include furnace load, airflow direction vector , airflow relative humidity ; At the same time, the data receiving module 21 is connected with the array acoustic sensing data acquisition unit 1 through the Profinet protocol, and receives the acoustic wave signal basic data output by the array acoustic sensing data acquisition unit 1, which specifically includes the measured acoustic wave propagation time , and the airflow velocity field collected by the differential pressure type flow sensor .

[0026] Further, in order to avoid the time sequence deviation of multi-source data, the data receiving module 21 is built-in with a timestamp synchronization engine, which adds a timestamp with a precision of ≤1μs to the two types of received data; after the data time sequence is aligned, the data receiving module 21 synchronously distributes it to the acoustic ray propagation correction module 22 and the feature fusion module 23, providing a unified time reference data source for subsequent processing.

[0027] In the present embodiment, the acoustic ray propagation correction module 22 is signal-connected with the data receiving module 21, for receiving the initial temperature field , airflow velocity field and measured acoustic wave propagation time , generating a corrected temperature field through acoustic ray propagation path error correction, and outputting to the feature fusion module 23; the process of acoustic ray propagation correction performed by the acoustic ray propagation correction module 22 includes the following steps: S22.1, receiving the initial temperature field , real-time airflow velocity field transmitted by the data receiving module 21, and the measured acoustic wave propagation time output by the array acoustic sensing data acquisition unit 1; wherein is the furnace design reference temperature field or the temperature field result of the last iteration fed back by the iterative optimization module 24; S22.2, for any three-dimensional space coordinate in the furnace, calculating the acoustic wave propagation speed coupled by temperature and airflow according to the general acoustic relationship, and the included angle between the airflow and the acoustic ray propagation direction, which is calculated through the DCS system airflow direction data and the acoustic sensor layout coordinates; the calculation of the acoustic wave propagation speed in S22.2 supports airflow humidity adaptation, and the specific adaptation process includes the following steps: S22.21 Receive the relative humidity of the airflow inside the furnace output by the DCS system. ; S22.22, Introduce a humidity correction factor , The value of varies Linear change, The value range is [0,1]; S22.23, based on and Adjustment The computational logic enables It is adapted to the sound speed propagation characteristics under corresponding humidity conditions.

[0028] S22.3. Taking the sound sensor transmitter as the starting point and the receiver as the ending point, the Eikonal equation is solved using the fast travel method to obtain the shortest path of sound wave propagation and the corresponding theoretical propagation time. ; S22.4, Calculation and residual Through automatic differentiation mechanism Reverse conduction to Generate the corrected temperature field And transmit it to the feature fusion module 23.

[0029] Specifically, the sound propagation correction module 22 is signal-connected to the data receiving module 21, and performs sound propagation path error correction according to the steps in the claims, ultimately generating a corrected temperature field. The specific process is as follows: First, the initial temperature field transmitted by the data receiving module 21 is received. Real-time airflow velocity field The measured sound wave propagation time output by the array-type acoustic sensing data acquisition unit 1. .in, The reference temperature field for furnace design (retrieved from the boiler design database) or the temperature field results from the previous round fed back by the iterative optimization module 24; It is vector data, in the format of , representing coordinates airflow at the location , , The directional velocity component is acquired using a differential pressure flow velocity sensor in the array-type acoustic sensing data acquisition unit 1, with a sensor accuracy class of 0.5. The sound sensor transmitter (denoted as) ) to the receiving end (denoted as The actual propagation time is calculated as follows: ; wherein, denotes the time when the acoustic sensor transmits the acoustic wave, denotes the time when the acoustic sensor receives the acoustic wave, the time measurement accuracy is ≤1ms; Subsequently, for any three-dimensional spatial coordinates in the furnace , the acoustic wave propagation speed after coupling of temperature and air flow is calculated according to the general acoustic relationship , and the calculation formula is: ; wherein, denotes the acoustic speed in dry air determined only by temperature, the unit is m / s, and the formula is: ; wherein, denotes the temperature value at the coordinates in the initial temperature field, the unit is ℃; denotes the air flow velocity vector at the coordinates (the format is ), is the module length (scalar, unit: m / s) of the air flow velocity vector, which is calculated from the air flow velocity field vector module length, and the formula is: ; wherein, respectively denote the component velocities of the air flow velocity vector in the direction, and the units are both m / s; denotes the included angle between the air flow and the acoustic line propagation direction, the unit is rad (radian), which is calculated by the vector dot product of the air flow direction vector output by the DCS system and the acoustic line direction vector ( ), and the formula is: ; wherein, denotes the air flow direction vector, denotes the acoustic line direction vector from the transmitting end to the receiving end , respectively denote the module lengths of the two vectors.

[0030] At the same time, in order to adapt to the influence of air flow humidity on acoustic speed, a humidity correction coefficient is introduced, and the specific adaptation process is as follows: The relative humidity of the air flow in the furnace output by the DCS system is received (Values ​​range [0,1], unitless, humidity sensor measurement accuracy ≤±3%RH); Humidity correction factor The calculation formula is: ; The derivation of the above formula is based on the conclusion regarding the relationship between air speed and humidity in the authoritative textbook in the field of acoustics, *Fundamentals of Acoustics* (by Du Gonghuan, Zhu Zhemin, and Gong Xiufen, 3rd edition): When air humidity increases, the average molecular weight of air decreases because the molecular weight of water vapor (18 g / mol) is smaller than that of dry air (approximately 29 g / mol). Since the speed of sound is inversely proportional to the square root of the molecular weight of the medium, at the same temperature, the speed of sound increases by approximately 0.2% for every 100% increase in relative humidity (RH). Based on this physical mechanism, a linear relationship is used to adapt the effect of humidity on the speed of sound.

[0031] based on and Adjusting the sound velocity calculation logic yields a sound wave propagation speed adapted to humidity levels. The formula is: ; In the formula, This represents the speed of sound propagation after temperature and airflow coupling. This indicates the final sound wave propagation speed after humidity adjustment, and the unit is m / s.

[0032] Next, using the acoustic sensor transmitter... For the starting point and the receiving end Using the fast travel method as the endpoint, the Eikonal equation is solved to obtain the shortest path for sound wave propagation and the corresponding theoretical propagation time. The Eikonal equation is in the form of: ; In the formula, Indicates theoretical propagation time The spatial gradient reflects the rate of change of time in three-dimensional space; This represents the sound wave propagation speed after humidity adjustment, in m / s. During the solution process, the three-dimensional space of the furnace is divided into a grid with a grid size of ≤0.5m. This value is based on the requirement in the "Power Plant Boiler Performance Test Procedure" (GB / T10184-2025) that "the density of temperature measurement points in the furnace must meet the requirement of a grid size ≤0.5m". The speed of sound is calculated iteratively for each grid node using the fast travel method. Finally, the receiving end is taken place As a voice The theoretical propagation time.

[0033] Finally, the residual between the theoretical propagation time and the measured time is calculated. The formula is: ; In the formula, Indicates vocal timbre The theoretical propagation time, measured in seconds (s); Indicates vocal timbre The measured propagation time, in seconds. Then, an automatic differentiation mechanism is used to... Reverse conduction to the initial temperature field Generate a corrected temperature field The formula is: ; In the formula, This represents the correction factor, with a value range of [0.1, 0.5]. Residual For the initial temperature field The partial derivatives are calculated using PyTorch's autograd automatic differentiation module; Represents the coordinates in the corrected temperature field The temperature value at the location, in °C, is finally output to the feature fusion module 23.

[0034] Furthermore, the process of solving the Eikonal equations using the fast travel method includes the following steps: Initialization rules: Set the acoustic sensor transmitter end Assuming it's a "determined point", its theoretical propagation time is... ;by Centered on the grid, the surrounding adjacent grid nodes are set as "active points" (included in narrowband management), and the remaining nodes are set as "undetermined points".

[0035] Narrowband management method: Uses a binary heap (priority queue) to store active points, and the queue is ordered by... Sort by size from smallest to largest to ensure that each retrieval is successful. Update the smallest active point.

[0036] The nearest neighbor update formula uses a first-order upwind scheme (adapted to the hyperbolic properties of the Eikonal equation) to calculate the nearest neighbor points. The formula is: ; In the formula, For the current neighboring points to be updated, For the already determined points, The spacing between grid nodes is ≤0.5m. for The sound velocity is adapted to the humidity level; after the update, if... of Converge, then turn it into "determined points", and add its undetermined adjacent points to the active point queue.

[0037] Difference format selection: first-order upwind format is adopted, because the solution of Eikonal equation is monotonically increasing along the sound ray propagation direction, and the upwind format can avoid numerical oscillation and ensure calculation stability.

[0038] Further, the automatic differentiation module of PyTorch is used to calculate the logic as follows: Input parameter format: the initial temperature field is stored in a three-dimensional grid data structure, and the temperature value of each grid node is a differentiable variable; Forward propagation path: taking as input, sequentially calculating , and finally outputting residual error ; Back propagation: through the automatic differentiation algorithm (based on the chain rule), the partial derivative of each grid node temperature value in to residual error is calculated in reverse, which directly reflects the influence of temperature change on residual error.

[0039] In the traditional sound ray propagation correction, the humidity influence is often ignored or the sound ray is simplified as a straight line, and the empirical temperature adjustment also relies on manual operation. The inaccurate calculation of sound speed under complex flow field will cause large deviation of theoretical propagation time , and the simplified sound ray path will lead to useless residual error in the wrong direction. Manual temperature adjustment is slow and inaccurate, and the correction accuracy of temperature field cannot keep up with the changes in working conditions. In this embodiment, the sound ray propagation correction module 22 adopts the method of "temperature-airflow-humidity three-factor coupled sound speed calculation + fast marching method to solve Eikonal equation (0.5m grid to track sound ray bending) + automatic differentiation residual error reverse correction of temperature field", which is like giving the sound ray a "precision navigator". Its core function is to make the sound ray more realistic under complex working conditions, directly feedback to adjust the initial temperature field , solve the deviation problem of traditional models ignoring humidity and simplifying sound rays, and make the corrected more accurate, laying a solid data foundation for subsequent inversion.

[0040] In this embodiment, the feature fusion module 23 is signal connected with the sound ray propagation correction module 22 and the data receiving module 21, respectively, for extracting sound wave features and working condition features , and generating a fusion feature vector through double-branch attention fusion ​​, output to the iterative optimization module 24; the feature fusion module 23 performs the process of double-branch attention fusion, including the following steps: S23.1, receiving the sound wave raw data and working condition parameters transmitted by the data receiving module 21, and synchronously receiving the corrected temperature field output by the sound line propagation correction module 22 ; S23.2, performing double-branch feature extraction, the first branch adopts the sliding window method to extract the frequency-amplitude feature of the sound wave data , and the second branch extracts the mean value and fluctuation feature of the working condition parameters ; S23.3, calculating the reliability based on the statistical characteristics of the feature data, the sound wave feature reliability is negatively correlated with the standard deviation of the sound wave feature and positively correlated with the mean value, and the working condition feature reliability is negatively correlated with the standard deviation of the working condition feature and positively correlated with the mean value; S23.4, according to and assigning attention weights , obtaining the fusion feature vector through weighted calculation , the weight is updated in real time with new feature data and output to the iterative optimization module 24.

[0041] Specifically, the feature fusion module 23 is signal connected with the sound line propagation correction module 22 and the data receiving module 21 respectively, extracts and integrates features through double-branch attention fusion, generates a fusion feature vector , and the specific process is as follows: First, receiving the sound wave raw data, working condition parameters transmitted by the data receiving module 21, and the corrected temperature field output by the sound line propagation correction module 22 ; pre-processing the three types of data, eliminating invalid values (such as temperature, flow rate outliers beyond the reasonable range) that occur during transmission, and classifying and associating the data according to the furnace space area (corresponding to the sampling area of the array type sound perception data acquisition unit 1), and the calculation period of the corrected temperature field is synchronized with the 10s statistical period of the working condition feature, ensuring the matching of the data in the time and space dimensions and the pertinence of feature extraction.

[0042] Then, the first branch extracts the sound wave feature (frequency-amplitude feature), which adopts the sliding window method to process the sound wave raw data, the window size W=2048 and the step size S=1024; Fourier transform is performed on the sound wave time domain signal ( is the time) in each window to extract the frequency-amplitude feature, and the formula is: ; In the formula, This indicates the peak frequency of the sound wave within the window, expressed in Hz. This represents the sound wave amplitude corresponding to the peak frequency, in Pa (amplitude range 0-100 Pa). This represents the average amplitude of all frequency components within the window, in Pa. The second branch extracts working condition features. (Mean and fluctuation characteristics), select three key operating parameters (load) output by the boiler DCS system. airflow speed ,humidity The statistical period is set to 10 seconds; the mean and fluctuation characteristics are extracted using the following formula: ; In the formula, This represents the average furnace load over 10 seconds. This represents the standard deviation of the furnace load over 10 seconds. This represents the average airflow velocity over 10 seconds. This represents the standard deviation of airflow velocity over 10 seconds. This represents the average relative humidity of the airflow over 10 seconds, and has no unit. It represents the standard deviation of relative humidity of airflow within 10 seconds.

[0043] Next, the confidence level is calculated based on the statistical properties of the feature data, specifically the confidence level of the acoustic wave features. The formula is: ; In the formula, This represents the mean value of the average amplitude in the characteristics of a sound wave. The standard deviation of the average amplitude in the characteristics of a sound wave is expressed in Pa. The value range is [0,1], and Negative correlation with They are positively correlated.

[0044] Reliability of operating condition characteristics The formula is: ; In the formula, These represent the coefficients of variation (dimensionless) for load, airflow velocity, and humidity, respectively; the denominator "3" represents the number of operating parameter types, ensuring... Normalize to the range [0,1]. It is negatively correlated with the coefficient of variation of each parameter, reflecting the stability of the operating condition.

[0045] Finally, according to and The attention weights are dynamically assigned using the following formula: ; ; In the formula, indicates the attention weight of the acoustic wave feature, indicates the attention weight of the working condition feature, and the sum of the two is 1.

[0046] and , The normalized features are obtained by using Min-Max standardization , (the value range is [0, 1]), and the weighted fusion feature vector is calculated , and the formula is: ; In the formula, indicates the normalized acoustic wave feature, indicates the normalized working condition feature, indicates the final fusion feature vector (dimension 9), which is output to the iterative optimization module 24.

[0047] In traditional multi-source feature fusion, fixed weight splicing features are often used regardless of the feature confidence level - the effective information of the acoustic wave feature will be covered by the fluctuating working condition parameters, and the working condition is stable. When the role is not prominent, the fusion feature does not reflect the actual working condition well, and the deviation of the inverted temperature field also becomes large. In the embodiment, the feature fusion module 23 adopts the means of “double-branch extraction of acoustic wave ‘frequency-amplitude’, working condition ‘mean value-fluctuation’ features + confidence quantification , combined with statistical characteristics) + dynamic attention weight allocation”, which is like giving the feature a “smart sorter”. The core function is that the feature with high confidence can obtain a higher weight, avoiding the fusion deviation of the fixed weight when the working condition fluctuates, so that the current working condition can be matched more accurately, solving the representation deficiency problem of simple splicing of heterogeneous data and improving the input quality of subsequent temperature field inversion.

[0048] In the embodiment, the iterative optimization module 24 is signal connected with the feature fusion module 23, based on inversion of the current temperature field , combined with the regularization coefficient to perform residual feedback dynamic regularization optimization, output and the corresponding mean absolute error to the result output module 25, while the non-converged is fed back to the acoustic ray propagation correction module 22; the process of the iterative optimization module 24 performing residual feedback dynamic regularization optimization includes the following steps: S24.1, The output of the feature fusion module 23 Input the temperature field inversion model to calculate the global temperature field of the furnace in the current cycle. ; S24.2, The actual temperature measured by thermocouples on the furnace wall. Based on the baseline, calculate Mean absolute error , coordinates The measured temperature value at the location; S24.3, The value of and It is negatively correlated with the number of iterations. They are negatively correlated; the larger the error, the better in the early stages of iteration. The smaller the value, the smaller the error, and the better in the later stages of iteration. The larger; S24.4 Disassembly The source of the sound is adjusted by changing the angle between the airflow and the direction of sound propagation in the sound propagation correction module 22. If the vocal timbre is imperfect and Synchronous change, i.e., adjustment Calculate the weights; adjust the feature fusion module 23 feature confidence. , Computational logic, if feature stability and Synchronization of changes, i.e., correction , The association weights between the median standard deviation and the mean are then output. and To the results output module 25.

[0049] Specifically, the iterative optimization module 24 is signal-connected to the feature fusion module 23. Based on the fused features, the temperature field is inverted and residual feedback dynamic regularization optimization is performed. The specific process is as follows: First, the feature fusion module 23 outputs... Input the temperature field inversion model, which is a fully connected neural network containing two hidden layers (64 neurons each) and using ReLU as the activation function; invert the global furnace temperature field for the current cycle. The formula is: ; In the formula, This represents a fully connected neural network. This represents the fused feature vector of the input. This represents the pre-training parameters (weights, biases) of the neural network. Indicates the number of iterations (initial). =1), Indicates the first Coordinates in the temperature field of the next iteration The temperature value at that location is expressed in °C.

[0050] Then, the temperature was measured by thermocouples on the furnace wall. As a benchmark ( For the first The coordinates of the thermocouples, , ≥8), calculate Mean absolute error The formula is: ; In the formula, Indicates the number of thermocouples on the furnace wall; Indicates the first Coordinates in the temperature field of the next iteration The temperature value at that location, in °C; Representing coordinates The measured temperature value of the thermocouple, in °C.

[0051] Next, the regularization coefficient and Negatively correlated with the number of iterations They are negatively correlated, and the calculation formula is: ; In the formula, This represents the initial regularization coefficient, with a value range of [0.01, 0.1], determined by model pre-training; This represents the error impact coefficient, with a value range of [1, 5], ensuring... The larger, The smaller; This represents the influence coefficient of the iteration number, with a value range of [0.05, 0.2], ensuring... The larger, The larger; Indicates the first The regularization coefficient of the next iteration, which is dimensionless.

[0052] Finally, disassemble The source and dynamically adjust the correlation parameters: if the acoustic residual and Synchronous changes (such as) When it increases (Also increase), then adjust the angle between the airflow and the direction of sound propagation in the sound propagation correction module 22. The weights are calculated and adjusted using the following formula: ; In the formula, Indicates the adjusted included angle; Indicates the included angle before adjustment; This represents the angle adjustment coefficient, with a value range of [0.05, 0.1]. Indicates the first The mean absolute error of the iterations. Indicates the first The mean absolute error of the iterations.

[0053] If the characteristic stability is Synchronous changes (e.g.) Decrease If the value is increased, the calculation logic for feature confidence in feature fusion module 23 is modified to adjust the confidence of acoustic features. For example, the corrected formula is: ; In the formula, Indicates the reliability of the corrected acoustic wave characteristics; This represents the correction factor, with a value range of [0.8, 1.2]. This represents the mean of the average amplitude in the characteristics of a sound wave. It represents the standard deviation of the average amplitude in the characteristics of a sound wave.

[0054] After the adjustment is completed, the iterative optimization module 24 outputs. and corresponding The results are output to module 25, and the non-converged results are also included. Feedback is sent to the sound propagation correction module 22 as the initial temperature field for the next iteration. .

[0055] Furthermore, the pre-training details of the temperature field inversion model are as follows: Network Dimension Matching: Input layer dimension is 9 (and fused feature vector) (Consistent with 9 dimensions), both hidden layers have 64 neurons each, and the output layer dimension is... (In this embodiment, the number of nodes is consistent with the number of nodes in the furnace grid) The mapping relationship between the output layer and the temperature field mesh is "output layer 1". The first neuron corresponds to the furnace. Temperature value of each grid node; The pre-training dataset is sourced from historical data of a 300MW power plant boiler over a continuous month, including: acoustic signals, operating parameters (load, airflow velocity, humidity), and measured temperatures of the furnace wall thermocouples (a total of 8 measuring points). Training process: The Adam optimizer was used to train for 50 epochs with the loss function being the "mean absolute error between the predicted temperature field and the measured temperature" and the learning rate being set to 0.001.

[0056] In addition, the quantification criterion of "synchronous change" is based on the change rate of the sound ray residual error and the mean absolute error of the last 5 iterations, which is calculated as follows: With the change rate of the sound ray residual error: With the change rate of the mean absolute error: The change rate of the sound ray residual error is calculated as follows: ; ; In the formula, the change rate of the sound ray residual error (dimensionless) of the i-th iteration relative to the (i-1)-th iteration is represented by ; The sound ray residual error of the i-th iteration is represented by ; The sound ray residual error of the (i-1)-th iteration is represented by ; The sound ray residual error of the i-th iteration is represented by ; The change rate of the mean absolute error is calculated as follows: ; ; In the formula, the change rate of the mean absolute error (dimensionless) of the i-th iteration relative to the (i-1)-th iteration is represented by ; The mean absolute error of the i-th iteration is represented by ; The mean absolute error of the (i-1)-th iteration is represented by ; The mean absolute error of the i-th iteration is represented by ; The synchronous change condition is determined as follows: first, the Pearson correlation coefficient ρ (dimensionless, value range ) between the sound ray residual error and the mean absolute error is calculated, and the formula is as follows: ; ; In the formula, the linear correlation degree between the sound ray residual error and the mean absolute error is represented by ; The iteration index is represented by i (take the last 5 iterations from the 1st to the 5th iteration); The sound ray residual error of the i-th iteration is represented by ;The average value of the 5 iterations is represented by ;The mean absolute error of the i-th iteration is represented by ;The average value of the 5 iterations is represented by . ​​​​​​

[0057] If the following two conditions are met, it is determined that Δτ and Ek "synchronously change", and the calculation weight of the sound ray included angle needs to be adjusted: (indicates and is a strong positive linear correlation); is consistent with the sign of (indicates and the change direction is the same, such as increasing or decreasing at the same time).

[0058] In the traditional temperature field iterative optimization, the regularization coefficient is fixed, and the error is large. It is not known how to adjust it. The large coefficient in the early stage of iteration will limit the precision improvement, and the small coefficient in the later stage will easily overfit, and the error can only be roughly adjusted to the model, and the inversion result is always floating in high-risk working conditions. In this embodiment, the iterative optimization module 24 adopts the means of "dynamic regularization coefficient adjusts , adaptively) + error decomposition and tracing (correlation , characteristic stability parameter adjustment) + thermocouple actual measurement error anchoring". Its core function is to maintain accuracy in the early stage of iteration and prevent overfitting in the later stage. When the error is large, the sound ray included angle and the characteristic credibility weight can be adjusted to make more consistent with the actual measurement value of the thermocouple, solving the problems of slow convergence and overfitting in traditional iteration, and improving the stability of the inversion result.

[0059] In this embodiment, the result output module 25 is signal connected with the iterative optimization module 24, for determining the iterative convergence. When the temperature field error and the gradient stability condition are met for 3 consecutive iterations, the result is output to the three-dimensional temperature field intelligent visualization unit 3. The process of result determination and output executed by the result output module 25 includes the following steps: S25.1, receiving the current round temperature field and the corresponding mean absolute error transmitted by the iterative optimization module 24; S25.2, when the temperature field error and the preset stability condition of the global temperature gradient are met for 3 consecutive iterations, it is determined that the iteration is converged; S25.3, if the iteration is converged, output as the final global three-dimensional temperature distribution data of the furnace to the three-dimensional temperature field intelligent visualization unit 3; if not converged, feedback to the sound ray propagation correction module 22 as the initial temperature field of the next iteration.

[0060] Specifically, the result output module 25 is signal connected with the iterative optimization module 24, responsible for determining the iteration convergence and outputting the final temperature field, and the detailed process is as follows: First, the current round temperature field transmitted by the iterative optimization module 24 is received And the corresponding mean absolute error , two types of data are stored in a structured manner (format: "iteration number ", and an association index of iteration number and result is established, which is convenient for tracing and calling.

[0061] Then, when the preset conditions of "temperature field error stability" and "global temperature gradient stability" are met for 3 consecutive iterations, the iteration is determined to be converged. Among them, the "error stability" condition is: ; In the formula, , , respectively represent the mean absolute error of the first , , iteration, unit: ℃; Error threshold, value range: [1, 3] ℃, according to the industrial boiler temperature measurement accuracy requirement (such as "furnace temperature measurement allowed error ≤3℃" in GB / T10184-2025).

[0062] The "global temperature gradient stability" condition is: ; In the formula, , respectively represent the spatial gradient of the first , iteration temperature field, unit: ℃ / m; Temperature gradient threshold, value range: [5, 10] ℃ / m.

[0063] Finally, if the iteration is determined to be converged, the result output module 25 outputs As the final global three-dimensional temperature distribution data of the furnace, it is transmitted to the three-dimensional temperature field intelligent visualization unit 3 through the industrial Ethernet interface; if it is not converged, it is fed back to the sound line propagation correction module 22 as the initial temperature field of the next iteration , and the maximum number of iterations is set to 20 (to avoid infinite loop, the value of 20 is based on the engineering practice of numerical iteration algorithm), if the number of iterations reaches 20 and still does not converge, trigger the equipment self-checking prompt.

[0064] The three-dimensional temperature field intelligent visualization unit 3 receives the global three-dimensional temperature distribution data of the furnace output by the working condition adaptive inversion unit 2, converts the format, constructs the geometric model of the furnace through a general rendering tool and superimposes the temperature information, generates a real-time temperature field image, and has the functions of temperature value marking, regional feature display and view switching; In the embodiment, the three-dimensional temperature field intelligent visualization unit 3 includes a data adaptation module 31, a model construction module 32 and a visualization interaction module 33, wherein: The data adaptation module 31 is signal connected with the working condition adaptive inversion unit 2, and is used to receive the global three-dimensional temperature distribution data of the furnace, perform data format conversion, and match the spatial coordinate system of the geometric model of the furnace in the model construction module 32 and the data precision standard; Specifically, the data adaptation module 31 receives the global three-dimensional temperature distribution data of the furnace output by the working condition adaptive inversion unit 2 through an industrial Ethernet interface (such as using Profinet protocol, transmission rate ≥ 100 Mbps). The data is a structured data set (such as a self-defined binary format or a JSON format) containing spatial coordinates (x, y, z) and corresponding temperature values.

[0065] Meanwhile, the data adaptation module 31 is built-in with a coordinate conversion engine to convert the calculation coordinate system (defined by the inversion unit) of the data into the Cartesian world coordinate system consistent with the model construction module 32. The conversion process is realized through a preset coordinate offset and a rotation matrix (which can be calibrated on site according to the actual installation position of the furnace). At the same time, the temperature data precision is normalized, and the last two decimal places are uniformly retained to ensure complete matching with the spatial coordinate system and data precision standard of the model construction module 32. The processed data is temporarily stored in an intermediate format (such as CSV or a rendering tool-specific data format) recognizable by the rendering tool, providing a basis for subsequent temperature superposition.

[0066] The model construction module 32 is signal connected with the data adaptation module 31, and is used to call a general rendering tool to construct a geometric model matched with the actual furnace, superimpose the converted temperature data to the corresponding spatial region of the geometric model, and generate a real-time temperature field image of the furnace; Specifically, the model construction module 32 calls a general rendering tool (such as using OpenGL graphics library to realize bottom rendering, or using Unity engine to improve interactivity), imports a CAD three-dimensional model file (such as STEP format, containing size parameters of key structures such as inner wall and burner of the furnace) of the furnace, or parameterizes the geometric model based on the actual size (diameter, height, combustion area position, etc.) of the furnace, to ensure that the shape and size of the model deviate from the actual furnace by ≤5%.

[0067] Meanwhile, the model construction module 32 superimposes the temperature data converted by the data adaptation module 31 to the corresponding spatial region of the geometric model through a color mapping algorithm (such as setting a temperature-color mapping table: ≤800℃ is green, 800-1000℃ is yellow, and ≥1000℃ is red), and each spatial coordinate point is associated with a model vertex in terms of temperature value; and real-time color rendering is achieved by using a vertex shader technology, and the image refresh rate is kept at 10-15 frames / second, thereby ensuring the real-time performance of temperature field visualization.

[0068] The visualization interaction module 33 is in signal connection with the model construction module 32, and is configured to perform temperature value labeling and hearth combustion region feature display operations on the real-time temperature field image, while supporting multi-view view switching function.

[0069] Specifically, the visualization interaction module 33 constructs a human-computer interaction interface based on the generated real-time temperature field image. The temperature value labeling function is realized by embedding a UI control in the rendering interface, and when the user clicks or selects a model region, the module triggers a coordinate query event, reads the temperature value of the corresponding spatial point, and displays it in the form of a floating window (the numerical accuracy is consistent with that of the data adaptation module 31); the hearth combustion region feature display function automatically identifies and marks the high-temperature concentration region by presetting a high-temperature threshold (such as ≥1100℃), and highlights the display in red or with a dynamic flashing effect; Meanwhile, the multi-view view switching function supports top view (hearth directly above view), side view (hearth side view), and three-dimensional free rotation view, and the user can realize view switching through interface buttons, shortcut keys, or mouse dragging (wheel zooming, left key rotating); the camera parameters (position, angle, field of view) of each preset view can be pre-set through a configuration file, thereby ensuring the stability and convenience of view switching.

[0070] The working condition warning and interaction unit 4 compares the abnormal temperature information identified by the three-dimensional temperature field intelligent visualization unit 3 based on the temperature safety range of the hearth equipment, triggers a warning when the temperature exceeds the safety range, outputs an audible and visual alarm signal and pushes the abnormal region coordinates, and is equipped with a human-computer interaction interface that can display real-time temperature field images, historical data curves, and warning records, and supports adjustment of interface parameters.

[0071] In the embodiment, the working condition warning and interaction unit 4 includes a working condition comparison module 41, a warning triggering module 42, and a human-computer interaction module 43, wherein: The working condition comparison module 41 is in signal connection with the three-dimensional temperature field intelligent visualization unit 3, and is configured to call the preset temperature safety range of the hearth equipment, compare the temperature field data output by the three-dimensional temperature field intelligent visualization unit 3, and identify abnormal temperature information that exceeds the safety range; Specifically, the working condition comparison module 41 receives the furnace global temperature field data (including real-time temperature values and corresponding coordinate information of each spatial coordinate point) output by the three-dimensional temperature field intelligent visualization unit 3 through an industrial Ethernet interface (adapted to the output interface of the three-dimensional temperature field intelligent visualization unit 3, using Ethernet / IP protocol, transmission rate ≥ 100 Mbps).

[0072] Meanwhile, the working condition comparison module 41 has a local configuration database built-in, which pre-stores the sub-regional temperature safety range based on the furnace equipment material characteristics and the running safety standard setting (for example, the safe temperature of the furnace water cooling wall region ≤ 600 ℃, the safe temperature of the burner outlet region ≤ 1200 ℃, which can be modified and updated through the subsequent man-machine interaction module 43).

[0073] Further, in the comparison process, the working condition comparison module 41 compares the real-time temperature value with the preset safety range of the corresponding region in a “spatial coordinate point by spatial coordinate point” logic: if the temperature of a coordinate point continuously exceeds the upper limit of the safety range of the region or is lower than the lower limit of the safety range (if there is a low-temperature safety requirement, such as pipe anti-freezing) for 10 seconds (which can be configured), the coordinate point is marked as an “abnormal temperature point”, and the coordinates and temperature values of all abnormal temperature points are integrated to form a structured abnormal temperature information package (including abnormal occurrence time, abnormal coordinate set, corresponding region safety range, actual temperature value), which is transmitted to the early warning triggering module 42.

[0074] The early warning triggering module 42 is signal connected with the working condition comparison module 41, and is used to output an audible and visual alarm signal when an abnormal temperature information is identified, and simultaneously push the furnace region coordinates corresponding to the abnormal temperature; Specifically, the early warning triggering module 42 establishes a signal connection with the working condition comparison module 41 through an RS485 bus, and after receiving the abnormal temperature information package transmitted by the working condition comparison module 41, first analyzes the abnormal level in the package (which can be pre-divided according to the temperature deviation: deviation ≤ 50 ℃ for “first-level early warning”, and deviation > 50 ℃ for “second-level early warning”).

[0075] Further, for different early warning levels, the early warning triggering module 42 drives the external industrial audible and visual alarm to output audible and visual alarm signals of corresponding intensity (which can be installed at a conspicuous position in the control room and at a duty room near the furnace equipment).

[0076] Meanwhile, the early warning triggering module 42 pushes the furnace region coordinates corresponding to the abnormal temperature (consistent with the Cartesian coordinate system of the three-dimensional temperature field intelligent visualization unit 3) through two ways: one is to send to the man-machine interaction module 43 in real time, and display the coordinates in a pop-up window; the other is to send to the boiler DCS system through the Modbus protocol (if linkage control is needed, such as triggering the burner load adjustment), to ensure that the operation and maintenance personnel and the control system synchronously obtain the abnormal position information.

[0077] In addition, the early warning triggering module 42 also automatically records the triggering time of each early warning, the early warning level, the abnormal coordinate, the processing state (initially "unprocessed"), and synchronizes the record to the early warning record database of the human-computer interaction module 43.

[0078] The human-computer interaction module 43 is respectively connected with the early warning triggering module 42 and the three-dimensional temperature field intelligent visualization unit 3, and is used for displaying the real-time temperature field image, the temperature history data curve and the early warning record, and supporting the adjustment operation of the interface display parameter.

[0079] It should be noted that the inversion period (1s) of the working condition self-adaptive inversion unit 2 is taken as the time synchronization reference, the acquisition period of the array acoustic sensing data acquisition unit 1 is 100ms, 10 groups of data are continuously acquired by the array acoustic sensing data acquisition unit 1 in the inversion period of each working condition self-adaptive inversion unit 2 and stored in a special data cache pool, for calling by the working condition self-adaptive inversion unit 2 during inversion; the control period of the working condition early warning and interaction unit 4 is 5s, and the feedback control operation needs to be performed after the mean fusion of the 5 inversion results continuously output by the working condition self-adaptive inversion unit 2, so as to realize the synchronous matching of the control period and the inversion period.

[0080] Those skilled in the art can understand that the processes of implementing all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by programs instructing related hardware.

[0081] The basic principles, main features and advantages of the present application are shown and described above. Those skilled in the art should understand that the present application is not limited by the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only preferred examples of the present application, and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A furnace temperature field intelligent visualization system based on acoustic sensing technology, characterized in that, include: An array-type acoustic sensing data acquisition unit (1) is provided with multiple sets of acoustic sensor arrays arranged along the circumference of the furnace to collect acoustic wave signals inside the furnace. The acoustic signal is filtered to suppress characteristic noise, and combined with the airflow data from the differential pressure flow velocity sensor, the basic data for sound ray propagation correction is output. The adaptive inversion unit (2) receives the real-time operating parameters of the boiler DCS system and the basic data of the acoustic signal output by the array-type acoustic sensing data acquisition unit (1). Based on the current iterative temperature field distribution and the input airflow velocity field, the Eikonal equation is solved by the fast travel method to obtain the minimum propagation time of each acoustic path. The time residual is transmitted back to the temperature field update process through the automatic differentiation mechanism. At the same time, the improved algorithm of dual-branch attention fusion and residual feedback dynamic regularization is adopted to extract the time series features of acoustic data and the steady-state and dynamic features of operating parameters respectively. The nonlinear fusion of heterogeneous data is realized by dynamically allocating attention weights. In the iterative process, the temperature distribution error is transmitted back to dynamically adjust the algorithm parameters by combining the sound ray propagation correction results, and the three-dimensional temperature distribution data of the entire furnace is output. The three-dimensional temperature field intelligent visualization unit (3) receives the furnace full-domain three-dimensional temperature distribution data output by the working condition adaptive inversion unit (2), and after format conversion, constructs the furnace geometric model and superimposes the temperature information through a general rendering tool to generate a real-time temperature field image, which has the functions of temperature value labeling, regional feature display and view switching. The working condition early warning and interaction unit (4) compares the abnormal temperature information identified by the three-dimensional temperature field intelligent visualization unit (3) based on the safe temperature range of the furnace equipment; when the early warning is triggered, it outputs an audible and visual alarm signal and pushes the coordinates of the abnormal area; it is equipped with a human-machine interaction interface, which can display real-time temperature field images, historical data curves and early warning records, and supports the adjustment of interface parameters.

2. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 1, characterized in that, The array-type acoustic sensing data acquisition unit (1) includes an array deployment module (11), a signal acquisition module (12), a filtering module (13), and a data fusion module (14), wherein: The array layout module (11) is used to coordinate the layout of multiple acoustic sensor arrays and differential pressure flow sensors along the circumference of the furnace. The installation height of the acoustic sensor array is adapted to the center area of ​​the furnace flame, and the differential pressure flow sensor and the acoustic sensor array correspond one-to-one to the furnace area. The signal acquisition module (12) is integrated into the acoustic sensor array of the array deployment module (11) and is used to synchronously acquire acoustic wave signals in different areas of the furnace. The acquisition frequency is matched with the propagation period of the acoustic wave in the furnace. The filtering module (13) is connected to the signal acquisition module (12) and is used to receive the original acoustic signal. It uses bandpass filtering to retain the relevant characteristic frequency bands of furnace combustion and filter out interference frequency band signals. The data fusion module (14) is connected to the filtering module (13) and the differential pressure flow velocity sensor signal respectively, and is used to synchronize the filtered sound wave signal with the airflow data in time and integrate it into the sound ray propagation correction basic data output to the working condition adaptive inversion unit (2).

3. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 2, characterized in that, The adaptive inversion unit (2) includes a data receiving module (21), a sound propagation correction module (22), a feature fusion module (23), an iterative optimization module (24), and a result output module (25), wherein: The input terminal of the data receiving module (21) is connected to the boiler DCS system and the array-type acoustic sensing data acquisition unit (1) respectively, and is used to receive real-time operating parameters and basic data of acoustic signals, and synchronously distribute them to the sound propagation correction module (22) and the feature fusion module (23). The acoustic propagation correction module (22) is signal-connected to the data receiving module (21) and is used to receive the initial temperature field. airflow velocity field and measured sound wave propagation time A corrected temperature field is generated by correcting the sound propagation path error. , and output to the feature fusion module (23); The feature fusion module (23) is connected to the sound propagation correction module (22) and the data receiving module (21) respectively, and is used to extract sound wave features. Operating characteristics A fused feature vector is generated through dual-branch attention fusion. , and output to the iterative optimization module (24); The iterative optimization module (24) and the feature fusion module (23) are connected by a signal, based on Invert the current temperature field Combined with regularization coefficient Perform residual feedback dynamic regularization optimization and output and the corresponding mean absolute error To the result output module (25), and simultaneously the unconverged Feedback is sent to the sound propagation correction module (22); The result output module (25) is signal-connected to the iterative optimization module (24) and is used to determine the convergence of the iteration. When the temperature field error and gradient stability conditions are met for three consecutive iterations, the output is... To the three-dimensional temperature field intelligent visualization unit (3).

4. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 3, characterized in that, The process of sound propagation correction by the sound propagation correction module (22) includes the following steps: S22.1, Initial temperature field transmitted by the data receiving module (21) Real-time airflow velocity field The measured sound wave propagation time output by the array-type acoustic sensing data acquisition unit (1) ;in The previous round temperature field results are fed back by the furnace design reference temperature field or iterative optimization module (24); S22.2, For any three-dimensional spatial coordinates within the furnace Calculate the sound wave propagation speed after temperature and airflow coupling according to general acoustic relationships. The angle between the airflow and the direction of sound propagation The data was obtained by calculating the airflow direction data from the DCS system and the coordinates of the acoustic sensor deployment. S22.

3. Taking the sound sensor transmitter as the starting point and the receiver as the ending point, the Eikonal equation is solved using the fast travel method to obtain the shortest path of sound wave propagation and the corresponding theoretical propagation time. ; S22.4, Calculation and residual Through automatic differentiation mechanism Reverse conduction to Generate the corrected temperature field And transmit it to the feature fusion module (23).

5. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 4, characterized in that, The speed of sound wave propagation in S22.2 The calculation supports airflow humidity adaptation, and the specific adaptation process includes the following steps: S22.21 Receive the relative humidity of the airflow inside the furnace output by the DCS system. ; S22.22, Introduce a humidity correction factor , The value of varies Linear change, The value range is [0,1]; S22.23, based on and Adjustment The computational logic enables It is adapted to the sound speed propagation characteristics under corresponding humidity conditions.

6. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 5, characterized in that, The process of performing dual-branch attention fusion by the feature fusion module (23) includes the following steps: S23.1 Receive the raw acoustic wave data and operating parameters transmitted by the data receiving module (21), and synchronously receive the corrected temperature field output by the acoustic ray propagation correction module (22). ; S23.2 Perform dual-branch feature extraction. The first branch uses the sliding window method to extract the frequency-amplitude features of the acoustic wave data. The second branch extracts the mean and fluctuation characteristics of the operating condition parameters. ; S23.3 Calculating the reliability of acoustic wave features based on the statistical characteristics of feature data. The reliability of the operating condition characteristics is negatively correlated with the standard deviation and positively correlated with the mean. It is negatively correlated with the standard deviation of the operating condition characteristics and positively correlated with the mean; S23.4, according to and Assign attention weights The fused feature vector is obtained through weighted calculation. The weights are updated in real time with the new feature data and output to the iterative optimization module (24).

7. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 6, characterized in that, The process of performing residual feedback dynamic regularization optimization by the iterative optimization module (24) includes the following steps: S24.1, The output of the feature fusion module (23) Input the temperature field inversion model to calculate the global temperature field of the furnace in the current cycle. ; S24.2, The actual temperature measured by thermocouples on the furnace wall. Based on the baseline, calculate Mean absolute error , coordinates The measured temperature value at the location; S24.3, The value of and It is negatively correlated with the number of iterations. They are negatively correlated; the larger the error, the better in the early stages of iteration. The smaller the value, the smaller the error, and the better in the later stages of iteration. The larger; S24.4 Disassembly The source of the sound is adjusted by setting the angle between the airflow and the direction of sound propagation in the sound propagation correction module (22). If the vocal timbre is imperfect and Synchronous change, i.e., adjustment Calculate the weights; adjust the feature fusion module (23) feature credibility. , Computational logic, if feature stability and Synchronization of changes, i.e., correction , The association weights between the median standard deviation and the mean are then output. and To the result output module (25).

8. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 7, characterized in that, The result output module (25) performs the result determination and output process, which includes the following steps: S25.1 Receive the current round temperature field transmitted by the iterative optimization module (24). and corresponding mean absolute error ; S25.2 When the preset stability conditions of temperature field error and global temperature gradient are met for three consecutive iterations, the iteration is determined to be converged. S25.3 If the iteration converges, output As the final three-dimensional temperature distribution data of the entire furnace, it is sent to the three-dimensional temperature field intelligent visualization unit (3); if it does not converge, Feedback is sent to the sound propagation correction module (22) as the initial temperature field for the next iteration. .

9. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 8, characterized in that, The three-dimensional temperature field intelligent visualization unit (3) includes a data adaptation module (31), a model building module (32), and a visualization interaction module (33), wherein: The data adaptation module (31) is connected to the working condition adaptive inversion unit (2) by signal, and is used to receive the three-dimensional temperature distribution data of the entire furnace, perform data format conversion, and match the spatial coordinate system and data accuracy standard of the furnace geometric model in the model construction module (32). The model building module (32) is connected to the data adaptation module (31) by signal, and is used to call the general rendering tool to build a geometric model that matches the actual furnace, and to superimpose the converted temperature data onto the corresponding spatial area of ​​the geometric model to generate a real-time temperature field image of the furnace. The visualization interaction module (33) is connected to the model building module (32) by signal, and is used to perform temperature value annotation and furnace combustion area feature display operations on the real-time temperature field image, while supporting multi-view switching function.

10. The intelligent visualization system for furnace temperature field based on acoustic sensing technology according to claim 9, characterized in that, The working condition early warning and interaction unit (4) includes a working condition comparison module (41), an early warning triggering module (42), and a human-computer interaction module (43), wherein: The working condition comparison module (41) is connected to the three-dimensional temperature field intelligent visualization unit (3) by signal, and is used to retrieve the preset safe temperature range of the furnace equipment, compare the temperature field data output by the three-dimensional temperature field intelligent visualization unit (3), and identify abnormal temperature information that exceeds the safe range. The early warning triggering module (42) is connected to the working condition comparison module (41) by signal, and is used to output an audible and visual alarm signal when abnormal temperature information is detected, and simultaneously push the coordinates of the furnace area corresponding to the abnormal temperature. The human-computer interaction module (43) is connected to the early warning trigger module (42) and the three-dimensional temperature field intelligent visualization unit (3) respectively, and is used to display real-time temperature field images, temperature historical data curves and early warning records, while supporting the adjustment of interface display parameters.

Images