An Internet of Things-based online monitoring system for the operating status of solid waste recycling furnaces

Abstract

This invention discloses an online monitoring system for the operating status of a solid waste recycling furnace based on the Internet of Things (IoT), relating to the field of furnace operating status monitoring technology. The system includes: acquiring acoustic signals from inside the furnace collected by an acoustic sensor array deployed on the outer side of the furnace wall; simultaneously acquiring vibration signals from the furnace wall collected by a vibration sensor array deployed on the outer side of the furnace wall; extracting a first set of acoustic feature parameters based on the acoustic signals inside the furnace; extracting a first set of vibration feature parameters based on the furnace wall vibration signals; performing an acoustic-vibration coupling correlation operation based on the first acoustic feature parameter set and the first vibration feature parameter set to determine the acoustic-vibration coupling feature parameter set; and performing a status determination operation based on the acoustic-vibration coupling feature parameter set to determine the current operating status identifier of the furnace. The acoustic-vibration resonance frequency parameter is highly sensitive to changes in the furnace body structural characteristics and can directly reflect changes in the furnace lining thickness and furnace wall integrity.

Description

Technical Field

[0001] This invention relates to the field of furnace operation status monitoring technology, specifically to an online monitoring system for the operation status of a solid waste recycling furnace based on the Internet of Things. Background Technology

[0002] Solid waste recycling furnaces are key thermal equipment for processing municipal solid waste, industrial waste, and biomass fuels. Due to the complex composition, fluctuating calorific value, and corrosive substances in solid waste, the furnace interior is subjected to a harsh environment of high temperature, corrosion, and severe erosion for extended periods. Accurate monitoring of the furnace's operating status and timely identification of abnormal conditions such as furnace lining erosion and thinning, slag bridging, and disturbances during material feeding and discharging are crucial for ensuring safe furnace operation and improving the efficiency of solid waste resource utilization.

[0003] Existing furnace operation status monitoring technologies mainly rely on deploying thermocouple temperature sensor arrays on the furnace wall or inside the furnace chamber, installing in-furnace industrial cameras, and extracting combustion state parameters through flue gas analysis systems. Thermocouple temperature sensor arrays infer the distribution of the material layer and temperature field changes in the furnace through multi-point temperature measurements. However, thermocouples have a short lifespan in high-temperature and corrosive environments, and their installation positions are usually limited to pre-set openings on the furnace wall, resulting in sparse measurement points and difficulty in comprehensively reflecting the differences in operating conditions in different areas of the furnace space. In-furnace industrial cameras capture the height of the material surface and the flame pattern in the furnace through optical images, but the lenses are prone to coking and blurring in high-temperature and dusty environments, requiring short cleaning and maintenance cycles, and cannot penetrate dense smoke to monitor slagging and bridging in deep areas of the furnace. Flue gas analysis systems indirectly determine the combustion state by extracting flue gas from the furnace and measuring the concentration of its components, but there is a significant time lag in the flue gas transmission and sampling process, resulting in a slow response speed, and the flue gas component information is difficult to directly correlate with the integrity of the furnace wall structure. Summary of the Invention

[0004] Existing methods lack an inherent physical correlation between various data such as temperature, images, and flue gas composition, and these data are collected independently, making it difficult to comprehensively judge the furnace operating conditions from a data fusion perspective. To address the shortcomings of existing technologies, this invention provides an online monitoring system for the operating status of solid waste recycling furnaces based on the Internet of Things.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an online monitoring system for the operating status of a solid waste recycling furnace based on the Internet of Things, specifically comprising: Signal acquisition module: acquires the acoustic signals inside the furnace collected by the acoustic sensor array deployed on the outside of the furnace wall, and simultaneously acquires the furnace wall vibration signals collected by the vibration sensor array deployed on the outside of the furnace wall. Acoustic feature extraction module: Based on the acoustic signals inside the furnace, extracts a first set of acoustic feature parameters reflecting the working conditions inside the furnace; Vibration feature extraction module: Based on the furnace wall vibration signal, extracts a first set of vibration feature parameters reflecting the structural response characteristics of the furnace wall; Feature association module: Based on the first acoustic feature parameter set and the first vibration feature parameter set, perform acoustic-vibration coupling association operation to determine the acoustic-vibration coupling feature parameter set; Status determination module: Based on the set of acoustic-vibration coupling characteristic parameters, it performs a status determination operation to determine the current operating status identifier of the furnace.

[0006] Preferably, the signal acquisition module receives analog acoustic signals output from each channel of an acoustic sensing array composed of several acoustic sensing units, and receives analog vibration signals output from each channel of a vibration sensing array composed of several vibration sensing units. The module performs signal conditioning operations on the analog acoustic signals and analog vibration signals of each channel, including pre-amplification and anti-aliasing filtering. The conditioned signals from each channel are sent to a multi-channel synchronous analog-to-digital converter and synchronously sampled at a preset sampling frequency to obtain a multi-channel digital acoustic signal sequence and a multi-channel digital vibration signal sequence. The multi-channel digital acoustic signal sequence is used as the furnace acoustic signal, and the multi-channel digital vibration signal sequence is used as the furnace wall vibration signal.

[0007] Preferably, the acoustic feature extraction module extracts a first time-domain acoustic feature from the acoustic signal inside the furnace, the first time-domain acoustic feature including the short-time energy mean of the acoustic signal and the zero-crossing rate of the acoustic signal; The first frequency domain acoustic features are extracted from the acoustic signals inside the furnace. The first frequency domain acoustic features include the energy proportion of the low frequency band, the energy proportion of the mid frequency band, and the energy proportion of the high frequency band. The sound arrival time difference of the acoustic signal received by the acoustic sensing unit at different spatial positions in the acoustic sensing array is obtained. Based on the sound arrival time difference and the spatial distance between each acoustic sensing unit, the sound source localization area in the furnace space is determined. The specific steps for determining the sound source localization area are as follows: Identify the same transient acoustic event from the signal sequences of each acoustic sensing unit. A transient acoustic event is a waveform segment in which the signal amplitude shows a significant pulse-like increase in a short period of time. Record the reception time value of the same transient sound event received by each acoustic sensing unit. Using the reception time value of one acoustic sensing unit as a reference, calculate the difference between the reception time value of the other acoustic sensing units and the reference reception time value to obtain the sound arrival time difference between each acoustic sensing unit. Read the installation position coordinates of each acoustic sensor unit on the outside of the furnace wall, calculate the spatial distance between each acoustic sensor unit, and based on the spatial distance between each acoustic sensor unit and the sound arrival time difference, use the spatial intersection positioning method to determine the position coordinates of the sound source in the furnace space, and take the position coordinates and the surrounding neighborhood area as the sound source positioning area. The first time-domain acoustic features, the first frequency-domain acoustic features, and the sound source localization region are combined into a first acoustic feature parameter set.

[0008] Preferably, the vibration feature extraction module extracts the main vibration frequency and the vibration amplitude value corresponding to the main vibration frequency from the furnace wall vibration signal; The vibration envelope attenuation slope of the vibration signal during the first observation period is extracted from the furnace wall vibration signal. The vibration envelope attenuation slope represents the rate of change of the vibration signal amplitude over time. The vibration phase difference of vibration sensing units at different spatial positions in the vibration sensing array under the same excitation conditions is obtained, and the vibration mode shape of the furnace wall structure is determined based on the vibration phase difference. The principal vibration frequency, vibration amplitude, vibration envelope attenuation slope, and vibration mode shape are combined to form the first set of vibration characteristic parameters.

[0009] Preferably, the feature association module performs a time-domain synchronous comparison between the short-time average energy of the acoustic signal in the first acoustic feature parameter set and the vibration amplitude value in the first vibration feature parameter set to determine the delay time between the change in acoustic signal energy and the change in vibration amplitude, and uses the delay time as the acoustic-vibration delay parameter. The proportion of low-frequency energy in the first acoustic characteristic parameter set is compared with the main vibration frequency in the first vibration characteristic parameter set. When the frequency value corresponding to the maximum value of the low-frequency energy proportion is consistent with the main vibration frequency value, it is determined that acoustic resonance occurs between the sound field inside the furnace and the vibration of the furnace wall structure. The main vibration frequency value is used as the acoustic resonance frequency parameter. The spatial position of the sound source location area in the first acoustic feature parameter set is compared with the vibration mode shape in the first vibration feature parameter set to determine the spatial overlap between the sound source position and the position of the maximum amplitude of the vibration mode. The spatial overlap is used as the acoustic-vibration spatial coupling degree parameter. The acoustic vibration delay parameter, acoustic vibration resonance frequency parameter, and acoustic vibration spatial coupling degree parameter are combined into an acoustic vibration coupling characteristic parameter set.

[0010] Preferably, the state determination module compares the acoustic vibration delay parameter with a first delay threshold and a second delay threshold successively, wherein the first delay threshold is less than the second delay threshold; When the acoustic vibration delay parameter is less than or equal to the first delay threshold, the acoustic vibration response is determined to be in a fast coupling state; when the acoustic vibration delay parameter is greater than the first delay threshold and less than or equal to the second delay threshold, the acoustic vibration response is determined to be in a medium-speed coupling state; when the acoustic vibration delay parameter is greater than the second delay threshold, the acoustic vibration response is determined to be in a slow coupling state. The acoustic and vibration resonance frequency parameters are compared with the reference resonance frequency range recorded under the normal and stable operation of the furnace. When the acoustic and vibration resonance frequency parameters deviate from the reference resonance frequency range, it is determined that there is an abnormality in the furnace structure. The acoustic-vibration spatial coupling parameter is compared with the first coupling threshold. When the acoustic-vibration spatial coupling parameter is lower than the first coupling threshold, it is determined that there is local slagging or bridging phenomenon in the furnace. Based on the comprehensive judgment results of the acoustic and vibration response speed, whether there are abnormalities in the furnace structure, and whether there is local slagging or bridging, the current operating status of the furnace is determined. The current operating status is one of the following: stable operating status, furnace lining erosion status, furnace slagging status, or feeding and discharging disturbance status. Based on the comprehensive judgment results of the acoustic and vibration response speed, the presence of abnormal furnace structure, and the presence of local slagging or bridging phenomena, the current operating status of the furnace is determined, specifically including the following steps: When the acoustic and vibration response is in a rapid coupling state, there are no abnormalities in the furnace structure, and there is no local slagging or bridging, the current operating state is identified as a stable operating state. When the acoustic and vibration response is in a medium-speed coupling state and there is an abnormality in the furnace structure, but there is no local slagging or bridging phenomenon, the current operating status is identified as the furnace lining erosion status. When the acoustic and vibration response is in a slow coupling state and there is local slagging or bridging, the current operating status is identified as the furnace slagging status. When the acoustic vibration response is in a rapid coupling state, but the fluctuation amplitude of the short-time average energy of the acoustic signal exceeds the preset fluctuation threshold within the short-time window, the current operating state is identified as the feeding and discharging disturbance state.

[0011] This invention provides an online monitoring system for the operating status of a solid waste recycling furnace based on the Internet of Things, which has the following beneficial effects: This invention deploys both acoustic and vibration sensor arrays on the outside of the furnace wall. The acoustic sensor unit collects acoustic signals inside the furnace by contacting the furnace wall surface through a coupling medium, while the vibration sensor unit is directly installed on the outside of the furnace wall to collect vibration signals. At the same time, the sensor units are in a relatively low-temperature environment outside the furnace wall, which extends the service life of the sensor units and reduces the maintenance frequency.

[0012] This invention compares the acoustic resonance frequency parameters with the reference resonance frequency range recorded under normal and stable furnace operation. When the furnace lining is eroded and thinned, the overall stiffness of the furnace wall decreases, and the acoustic resonance frequency parameters shift to higher frequencies. When the furnace lining becomes loose or cracked, the change in the damping of the furnace wall structure causes a significant shift in the acoustic resonance frequency parameters. The acoustic resonance frequency parameters are highly sensitive to changes in the furnace body structural characteristics and can directly reflect changes in the furnace lining thickness and furnace wall integrity. Attached Figure Description

[0013] Figure 1 This is a system block diagram of the present invention; Figure 2 This is a diagram showing the acoustic-vibration coupling relationship of the present invention. Detailed Implementation

[0014] 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 skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Please see Figure 1 This invention provides an online monitoring system for the operating status of a solid waste recycling furnace based on the Internet of Things, comprising: Signal acquisition module: acquires the acoustic signals inside the furnace collected by the acoustic sensor array deployed on the outside of the furnace wall, and simultaneously acquires the furnace wall vibration signals collected by the vibration sensor array deployed on the outside of the furnace wall. In this embodiment of the invention, the signal acquisition module needs to be specifically described. The signal acquisition module receives the analog sound signals output from each channel of the acoustic sensing array composed of several acoustic sensing units. The acoustic sensing units are installed on the outside of the furnace wall. The vibration sensing unit receives the analog vibration signals output from each channel of the vibration sensing array composed of several vibration sensing units. The vibration sensing unit is installed on the outside of the furnace wall and is arranged alternately with the acoustic sensing unit in space. The module performs signal conditioning operations on the analog sound signals and analog vibration signals of each channel. The signal conditioning operations include pre-amplification and anti-aliasing filtering. The conditioned signals from each channel are sent to a multi-channel synchronous analog-to-digital converter and synchronously sampled at a preset sampling frequency to obtain a multi-channel digital acoustic signal sequence and a multi-channel digital vibration signal sequence. The multi-channel digital acoustic signal sequence is used as the furnace acoustic signal, and the multi-channel digital vibration signal sequence is used as the furnace wall vibration signal.

[0016] It should be noted that an acoustic sensor array refers to a group of acoustic signal acquisition devices formed by installing several acoustic sensor units on the outside of the furnace wall. Each acoustic sensor unit contains an acoustic sensing element and a preamplifier circuit. The acoustic sensing element is used to convert the sound pressure fluctuations inside the furnace received on the furnace wall surface into corresponding analog electrical signals, and the preamplifier circuit is used to perform preliminary amplitude amplification of the analog electrical signals.

[0017] A vibration sensor array is a set of vibration signal acquisition devices formed by installing several vibration sensor units on the outside of the furnace wall. Each vibration sensor unit contains a vibration sensing element and a preamplifier circuit. The vibration sensing element is used to convert the mechanical vibration acceleration or velocity received on the furnace wall surface into a corresponding analog electrical signal.

[0018] Signal conditioning operations include at least two sub-operations: preamplification and anti-aliasing filtering. Preamplification is used to amplify the weak electrical signal output by the sensing unit to an amplitude range that matches the input range of the analog-to-digital converter. Anti-aliasing filtering is used to filter out frequency components in the signal that are higher than half of the sampling frequency.

[0019] A multichannel synchronous analog-to-digital converter (ADC) is an integrated circuit device with multiple independent analog input channels, all of which perform sample-and-hold and analog-to-digital conversion on the same clock edge. The sampling times of each channel of a multichannel synchronous ADC are aligned with each other.

[0020] The specific working steps of the signal acquisition module are as follows: The signal acquisition module receives the analog sound signals output from each channel of the acoustic sensing array, which consists of several acoustic sensing units. Each acoustic sensing unit in the acoustic sensing array works independently. The sound-sensitive element of each acoustic sensing unit continuously senses the sound pressure fluctuations transmitted from the furnace wall surface and converts the sound pressure fluctuations into analog voltage signals whose amplitude changes with time. After the analog voltage signal is amplified by the preamplifier circuit inside the acoustic sensing unit, it is output to the analog input interface of the signal acquisition module through the shielded signal cable. Each channel of the acoustic sensing array is assigned an independent analog input port. The analog acoustic signal of each channel first enters the signal conditioning circuit after entering the signal acquisition module. It receives analog vibration signals output from each channel of a vibration sensing array composed of several vibration sensing units. Each vibration sensing unit in the vibration sensing array works independently. The vibration sensing element of each vibration sensing unit continuously senses the mechanical vibration of the furnace wall surface, converts the vibration acceleration or velocity into an analog voltage signal, and outputs it to the corresponding analog input port of the signal acquisition module through a shielded signal cable after pre-amplification. Signal conditioning operations are performed on the analog sound signals and analog vibration signals of each channel. The first sub-operation of the signal conditioning operation is pre-amplification. The signal acquisition module is equipped with a programmable gain amplifier array, which contains amplification channels equal to the total number of sensing channels. The signal acquisition module independently sets the amplification gain factor for each channel according to the signal amplitude range of each sensing channel, amplifying the amplitude of the input signal to a range that matches the full-scale input voltage of the subsequent analog-to-digital converter, so as to improve the signal-to-noise ratio and the resolution utilization of the analog-to-digital conversion. The second sub-operation of the signal conditioning operation is anti-aliasing filtering. The signal acquisition module is equipped with a low-pass filter array, which contains a number of filter channels equal to the total number of sensing channels. Each filter channel is an analog low-pass filter. The cutoff frequency of the low-pass filter is determined according to the preset sampling frequency. The anti-aliasing filtering operation effectively filters out high-frequency noise and interference components in the signal that are higher than the cutoff frequency, and only retains signal components whose frequency range is within the effective bandwidth, ensuring that no spectral aliasing occurs during the subsequent analog-to-digital conversion process. The conditioned signals from each channel are sent to a multi-channel synchronous analog-to-digital converter (ADC). The ADC contains an analog input channel equal to the total number of sensing channels. Each analog input channel receives a conditioned analog sound signal or analog vibration signal. The ADC uses a synchronous sample-and-hold circuit structure. The sample-and-hold switches of all channels are driven by the same sampling clock signal. At each valid edge of the sampling clock, the instantaneous voltage values ​​of the input signals of all channels are simultaneously captured and held on their respective holding capacitors. The analog-to-digital conversion core inside the multi-channel synchronous analog-to-digital converter performs analog-to-digital conversion operations on the voltage values ​​held by each channel sequentially or in parallel at a preset sampling frequency, quantizing the analog voltage values ​​into digital codes. The preset sampling frequency is determined during the system initialization phase based on the highest effective frequency components of the furnace acoustic signal and the furnace wall vibration signal. After the analog-to-digital conversion is completed, the signal acquisition module obtains the digital signal sequence of each channel, which is a set of digital coded values ​​arranged according to the sampling time. The digital signal sequences of each channel of the acoustic sensor array together constitute a multi-channel digital acoustic signal sequence, and the digital signal sequences of each channel of the vibration sensor array together constitute a multi-channel digital vibration signal sequence. The multi-channel digital acoustic signal sequence is used as the acoustic signal inside the furnace, and the multi-channel digital vibration signal sequence is used as the vibration signal of the furnace wall. The two sets of signal sequences correspond one-to-one at the sampling time. The signal acquisition module stores the acoustic signal inside the furnace and the vibration signal of the furnace wall in the form of data frames in the data buffer. Each data frame contains the values ​​of all acoustic and vibration sensing channels at the same sampling time. The signal acquisition module is connected to the acoustic and vibration sensing arrays through shielded signal cables. The shielded signal cables are used to prevent external electromagnetic interference from contaminating the weak sensing signals and to ensure the integrity and anti-interference of the signal transmission path.

[0021] Acoustic feature extraction module: Based on the acoustic signals inside the furnace, extracts a first set of acoustic feature parameters reflecting the working conditions inside the furnace; In this embodiment of the invention, the acoustic feature extraction module needs to be specifically described. The acoustic feature extraction module extracts a first time-domain acoustic feature from the acoustic signal inside the furnace. The first time-domain acoustic feature includes the short-time energy mean of the acoustic signal and the zero-crossing rate of the acoustic signal. The first frequency domain acoustic features are extracted from the acoustic signals inside the furnace. The first frequency domain acoustic features include the energy proportion of the low frequency band, the energy proportion of the mid frequency band, and the energy proportion of the high frequency band. The frequency range of the low frequency band is lower than that of the mid frequency band, and the frequency range of the mid frequency band is lower than that of the high frequency band. The sound arrival time difference of the acoustic signal received by the acoustic sensing unit at different spatial positions in the acoustic sensing array is obtained. Based on the sound arrival time difference and the spatial distance between each acoustic sensing unit, the sound source localization area in the furnace space is determined. The specific steps for determining the sound source localization area are as follows: Identify the same transient acoustic event from the signal sequences of each acoustic sensing unit. A transient acoustic event is a waveform segment in which the signal amplitude shows a significant pulse-like increase in a short period of time. Record the reception time value of the same transient sound event received by each acoustic sensing unit. Using the reception time value of one acoustic sensing unit as a reference, calculate the difference between the reception time value of the other acoustic sensing units and the reference reception time value to obtain the sound arrival time difference between each acoustic sensing unit. Read the installation position coordinates of each acoustic sensor unit on the outside of the furnace wall, calculate the spatial distance between each acoustic sensor unit, and based on the spatial distance between each acoustic sensor unit and the sound arrival time difference, use the spatial intersection positioning method to determine the position coordinates of the sound source in the furnace space, and take the position coordinates and the surrounding neighborhood area as the sound source positioning area. The first time-domain acoustic features, the first frequency-domain acoustic features, and the sound source localization region are combined into a first acoustic feature parameter set.

[0022] It should be noted that the short-time energy mean of the acoustic signal refers to the average value of the sum of the squares of the amplitudes of all sampling points in each frame of the digital signal sequence of the acoustic signal in the furnace, which is divided into several consecutive short-time frames according to a preset short-time window length. The average value of the short-time energy of the acoustic signal reflects the overall intensity level of the sound field in the furnace. When the material in the furnace is violently agitated, slag collapses, or feeding or discharging operations occur, the short-time energy mean of the acoustic signal will increase accordingly.

[0023] The zero-crossing rate of an acoustic signal refers to the ratio of the number of times the sign of the signal amplitude changes between two adjacent sampling points in a frame of acoustic signal sequence to the total number of sampling points in that frame. The zero-crossing rate of an acoustic signal reflects the richness of high-frequency components in the acoustic signal. When events such as sharp airflow whistling, metal impact, or material rupture occur in the furnace, which generate rich high-frequency components, the zero-crossing rate of the acoustic signal will increase accordingly.

[0024] The low-frequency energy ratio refers to the ratio obtained by summing the squared values ​​of the spectral amplitudes within the low-frequency range of the sound signal spectrum and dividing it by the sum of the squared values ​​of the spectral amplitudes within the entire analysis frequency range. The lower limit of the low-frequency range is taken as the starting frequency of the analysis frequency band, and the upper limit is taken as the first sub-frequency value. The low-frequency energy ratio reflects the contribution of the low-frequency sound components in the sound field inside the furnace, which are coupled back to the sound field by the vibration of the furnace structure.

[0025] The mid-frequency energy ratio refers to the ratio obtained by summing the squared values ​​of the spectral amplitudes within the mid-frequency range of the acoustic signal spectrum and dividing it by the sum of the squared values ​​of the spectral amplitudes within the entire analysis frequency range. The lower limit of the mid-frequency range is the first sub-frequency value, and the upper limit is the second sub-frequency value. The mid-frequency energy ratio reflects the proportion of acoustic signal energy generated by conventional operating conditions such as material friction and airflow turbulence inside the furnace.

[0026] The high-frequency energy ratio refers to the ratio obtained by summing the squared values ​​of the spectral amplitudes within the high-frequency range of the acoustic signal spectrum and dividing it by the sum of the squared values ​​of the spectral amplitudes within the entire analysis frequency range. The lower limit of the high-frequency range is the second sub-frequency value, and the upper limit is the termination frequency of the analysis band. The high-frequency energy ratio reflects the contribution of sudden high-frequency acoustic events occurring in the furnace, such as the sharp acoustic emission generated by the bursting of glass or metal in solid waste at high temperatures.

[0027] Transient acoustic events refer to a type of non-continuous acoustic signal segment in an acoustic signal sequence in which the signal amplitude rapidly jumps from the background noise level to a pulse peak significantly higher than the background noise level within a short period of time, and then falls back to near the background noise level within a short period of time. Transient acoustic events usually correspond to sudden processes such as impacts, explosions, or local collapses that occur inside the furnace.

[0028] The time difference of arrival (TDOA) refers to the difference between the times when the sound wave emitted by the same transient sound event reaches the acoustic sensing units at different spatial locations in the acoustic sensing array and receives the sound wave signal.

[0029] Spatial intersection localization is a localization method that uses the time difference of arrival of signals measured by multiple receivers at known spatial locations, calculates the distance difference between the sound source and each receiver, and solves for the hyperboloid intersection point corresponding to each distance difference, thereby determining the spatial location of the sound source.

[0030] The specific working steps of the acoustic feature extraction module are as follows: The first time-domain acoustic features are extracted from the acoustic signals inside the furnace. The first time-domain acoustic features include two parameters: the short-time energy mean of the acoustic signal and the zero-crossing rate of the acoustic signal. When extracting the short-time energy mean of the acoustic signal, the multi-channel digital acoustic signal sequence of the acoustic signal inside the furnace is read first. For the digital acoustic signal sequence of each acoustic sensing channel, the continuous digital acoustic signal sequence is divided into several short-time frames according to the preset short-time window length. The preset overlap ratio is set between adjacent short-time frames. For each frame of short-time signal, the amplitude of all sampling points in the frame is squared, and all squared values ​​are summed. The sum is then divided by the total number of sampling points in the frame to obtain the short-time energy value of the frame. The acoustic feature extraction module calculates the arithmetic mean of the short-time energy values ​​of all short-time frames in a channel to obtain the average short-time energy of the acoustic signal in that channel. Finally, the average of the average short-time energy values ​​of the acoustic signals in all channels is taken as the final average short-time energy of the acoustic signal. When extracting the zero-crossing rate of the acoustic signal, for each acoustic sensor channel's digital acoustic signal sequence, the amplitude sign of two adjacent sampling points is read frame by frame. When the amplitude sign changes, the zero-crossing count is incremented by one. The zero-crossing count of each frame is divided by the total number of sampling points in that frame to obtain the zero-crossing rate of that frame. Then, the arithmetic mean of the zero-crossing rates of all short-time frames in a channel is calculated to obtain the acoustic signal zero-crossing rate of that channel. Finally, the average of the acoustic signal zero-crossing rates of all channels is taken as the final acoustic signal zero-crossing rate. The first frequency domain acoustic features are extracted from the acoustic signals inside the furnace. The first frequency domain acoustic features include three parameters: the energy proportion of the low frequency band, the energy proportion of the mid frequency band, and the energy proportion of the high frequency band. For the digital acoustic signal sequence of each acoustic sensing channel, a representative steady-state signal segment is selected. After applying time-domain windowing to the steady-state signal segment, Fourier transform operation is performed to convert the time-domain signal into a frequency-domain spectral sequence. Each frequency point in the spectral sequence corresponds to a frequency value and an amplitude value at that frequency. The entire analysis frequency band is divided into three sub-bands: low frequency band, mid frequency band, and high frequency band. The frequency range of the low frequency band is from the starting frequency of the analysis frequency band to the first sub-frequency value, the frequency range of the mid frequency band is from the first sub-frequency value to the second sub-frequency value, and the frequency range of the high frequency band is from the second sub-frequency value to the ending frequency of the analysis frequency band. The first and second sub-frequency values ​​are determined during the system initialization stage based on the spectral distribution characteristics of the acoustic signal under normal furnace operating conditions. The low-frequency energy is obtained by summing the squared amplitude values ​​of all frequency points in the low-frequency band, the mid-frequency energy is obtained by summing the squared amplitude values ​​of all frequency points in the mid-frequency band, and the high-frequency energy is obtained by summing the squared amplitude values ​​of all frequency points in the high-frequency band. The total energy is obtained by summing the three energy values. The low-frequency energy is divided by the total energy to obtain the low-frequency energy ratio, the mid-frequency energy is divided by the total energy to obtain the mid-frequency energy ratio, and the high-frequency energy is divided by the total energy to obtain the high-frequency energy ratio. The low-frequency energy ratio, mid-frequency energy ratio, and high-frequency energy ratio are temporarily stored in the acoustic feature buffer.

[0031] To identify the same transient acoustic event from the signal sequences of each acoustic sensing unit, the acoustic feature extraction module sets an amplitude detection threshold. The amplitude detection threshold is determined in real time based on the current background noise amplitude statistics, for example, using a multiple of the background noise amplitude as the amplitude detection threshold. The digital acoustic signal sequence of each acoustic sensing channel is scanned point by point. When the amplitude of a certain sampling point jumps from below the amplitude detection threshold to above the amplitude detection threshold, and the duration of the rise is less than the preset pulse width threshold, it is determined that the starting edge of a transient acoustic event has been detected. The time of the occurrence of the starting edge is recorded as the receiving time value of the transient acoustic event received by the acoustic sensing channel. When the same acoustic event is detected in each acoustic sensing channel and the maximum difference between the receiving time values ​​is less than the preset event time difference threshold, it is determined that the same transient acoustic event is detected by each acoustic sensing channel. Using the reception time of one acoustic sensing unit as the reference reception time, the difference between the reception time values ​​of the remaining acoustic sensing units and the reference reception time value is calculated to obtain the sound arrival time difference between each acoustic sensing unit. The installation position coordinates of each acoustic sensing unit on the outside of the furnace wall are read. The installation position coordinates are determined by measurement during the installation of the acoustic sensing array and stored in the system parameter storage area. The spatial distance between each acoustic sensing unit is calculated. The spatial distance is the Euclidean distance between the installation position coordinates of two acoustic sensing units. Based on the spatial distance between each acoustic sensing unit and the sound arrival time difference, the spatial intersection positioning method is used to determine the position coordinates of the sound source in the furnace space. The specific operation of the spatial intersection positioning method is as follows: the sound propagation speed in the furnace is taken as a preset nominal value, and the sound arrival time difference is multiplied by the sound propagation speed in the furnace to obtain the distance difference between the sound source and each acoustic sensing unit. Each pair of acoustic sensing units is taken as a group. The distance difference between the sound source and these two acoustic sensing units determines a set of hyperboloids. The intersection point of the hyperboloids corresponding to multiple groups of acoustic sensing units in space is the spatial position of the sound source. The coordinates of the intersection point are taken as the sound source position coordinates, and the neighborhood area within the preset radius of the sound source position coordinates is taken as the sound source positioning area. The first time-domain acoustic features, the first frequency-domain acoustic features, and the sound source localization region are combined into a first acoustic feature parameter set. The specific method of this combination operation is as follows: the acoustic feature extraction module creates a parameter set data structure in memory. This parameter set data structure contains three members: the first member contains the first time-domain acoustic features, including the short-time average energy of the acoustic signal and the zero-crossing rate of the acoustic signal; the second member contains the first frequency-domain acoustic features, including the energy proportions of the low-frequency band, mid-frequency band, and high-frequency band; and the third member contains the sound source localization region, including the center coordinates and radius of the sound source localization region. The three members are arranged in the order of time domain features first, frequency domain features in the middle, and spatial features last. After the combination is completed, the parameter set data structure is the first acoustic feature parameter set.

[0032] Vibration feature extraction module: Based on the furnace wall vibration signal, extracts a first set of vibration feature parameters reflecting the structural response characteristics of the furnace wall; In this embodiment of the invention, the vibration feature extraction module needs to be specifically described. The vibration feature extraction module extracts the main vibration frequency and the vibration amplitude value corresponding to the main vibration frequency from the furnace wall vibration signal. The vibration envelope attenuation slope of the vibration signal during the first observation period is extracted from the furnace wall vibration signal. The vibration envelope attenuation slope represents the rate of change of the vibration signal amplitude over time. The vibration phase difference of vibration sensing units at different spatial positions in the vibration sensing array under the same excitation conditions is obtained, and the vibration mode shape of the furnace wall structure is determined based on the vibration phase difference. The principal vibration frequency, vibration amplitude, vibration envelope attenuation slope, and vibration mode shape are combined to form the first set of vibration characteristic parameters.

[0033] It should be noted that the principal vibration frequency refers to the frequency value corresponding to the frequency component with the largest amplitude in the spectrum of the furnace wall vibration signal. The principal vibration frequency reflects the main structural resonance frequency excited when the furnace wall structure is subjected to excitation effects such as the sound field and material impact in the furnace. When the furnace is operating stably, the principal vibration frequency is usually maintained near a relatively fixed reference frequency. When the furnace lining is eroded and thinned, the slag on the furnace wall thickens, or the material level in the furnace changes, the overall mass and stiffness distribution of the furnace wall structure changes, and the principal vibration frequency will shift accordingly.

[0034] Vibration amplitude value refers to the magnitude of the spectral amplitude corresponding to the main vibration frequency. The vibration amplitude value reflects the intensity of the excitation of the furnace wall at the main vibration frequency. An increase in vibration amplitude value usually means that the intensity of the excitation source in the furnace is enhanced or the damping of the furnace wall structure is reduced.

[0035] The vibration envelope attenuation slope refers to the rate at which the vibration amplitude decays over time after a vibration signal is subjected to a transient excitation. The extraction of the vibration envelope attenuation slope needs to be carried out within the first observation period. The first observation period refers to the time interval from the peak value of the vibration signal to the background noise level after a transient excitation event is identified from the vibration signal. The vibration envelope attenuation slope reflects the damping characteristics of the furnace wall structure: when the furnace wall structure is intact and the lining is dense, the vibration energy dissipates quickly and the vibration envelope attenuation slope is steep. When the furnace wall lining is eroded and cracks or loosening occur in the furnace wall structure, the structural damping decreases and the vibration envelope attenuation slope tends to be gentle.

[0036] Vibration phase difference refers to the difference between the phases of the same frequency components in the vibration signal waveforms of vibration sensing units at different spatial locations in a vibration sensing array under the same excitation condition. The same excitation condition means that each vibration sensing unit receives the furnace wall vibration response excited by the same transient event in the furnace.

[0037] Vibration mode shape refers to the relative distribution of vibration amplitude at various points on the furnace wall surface when the furnace wall structure resonates at a specific frequency. The vibration mode shape is determined by the vibration phase difference and vibration amplitude ratio between each vibration sensing unit.

[0038] The specific working steps of the vibration feature extraction module are as follows: The main vibration frequency and the vibration amplitude value corresponding to the main vibration frequency are extracted from the furnace wall vibration signal. The furnace wall vibration signal has been converted into a multi-channel digital vibration signal sequence in the signal acquisition module and stored in the data buffer. The vibration feature extraction module selects a representative steady-state vibration signal segment for the digital vibration signal sequence of each vibration sensing channel, applies time-domain windowing processing to the steady-state vibration signal segment, and performs Fourier transform operation to convert the time-domain vibration signal into a vibration spectrum sequence represented in the frequency domain. Each frequency point in the vibration spectrum sequence corresponds to a frequency value and an amplitude value at that frequency. By traversing the amplitude values ​​of all frequency points in the vibration spectrum sequence, the frequency value corresponding to the frequency point with the largest amplitude value is determined as the main vibration frequency, and the amplitude value corresponding to the frequency point with the largest amplitude value is determined as the vibration amplitude value. After extracting the main vibration frequency and vibration amplitude value of each vibration sensing channel, the arithmetic mean of the main vibration frequencies of all channels is taken to obtain the comprehensive main vibration frequency of the furnace wall structure, and the arithmetic mean of the vibration amplitude values ​​of all channels is taken to obtain the comprehensive vibration amplitude value of the furnace wall structure. The vibration envelope attenuation slope of the vibration signal within the first observation period is extracted from the furnace wall vibration signal. The vibration feature extraction module first identifies transient excitation events in the furnace wall vibration signal. The identification method is as follows: the vibration feature extraction module scans the digital vibration signal sequence of each vibration sensing channel in real time. When the signal amplitude of a certain channel rapidly jumps from the background noise level and exceeds the preset transient detection threshold in a short period of time, a transient excitation event is determined to have occurred. The peak occurrence time of the transient excitation event is taken as the time zero point, and a vibration signal segment with a duration of the first observation period is extracted along the time axis. The duration of the first observation period is preset according to the vibration attenuation time constant of the furnace wall structure after transient excitation. Envelope extraction is performed on the vibration signal segments within the first observation period. The specific method of envelope extraction is as follows: Hilbert transform is performed on the vibration signal segments to obtain the analytic signal of the vibration signal. The magnitude of the analytic signal is the instantaneous envelope of the vibration signal. In the instantaneous envelope sequence of the vibration signal, from the moment corresponding to the peak of the envelope to the moment when the envelope amplitude decays to the level corresponding to the background noise, the natural logarithm of the envelope amplitude is taken. The curve of the natural logarithm of the envelope amplitude changing with time is fitted with a linear fitting method to obtain a straight line. The slope of the straight line is the vibration envelope decay slope. The larger the absolute value of the vibration envelope decay slope, the faster the vibration decay and the greater the structural damping. The vibration envelope decay slope is temporarily stored in the vibration feature buffer. The vibration phase difference of vibration sensing units at different spatial positions in the vibration sensing array under the same excitation condition is obtained. The vibration mode shape of the furnace wall structure is determined based on the vibration phase difference. The same transient excitation event identified in the second step is selected as the same excitation condition. The vibration signal segments of each vibration sensing channel in the first observation period are read. Fourier transform operation is performed on the vibration signal segments of each vibration sensing channel. The phase value at the main vibration frequency is extracted from the obtained spectrum. For each vibration sensing channel, the real and imaginary parts of the complex spectrum value at the corresponding frequency point of the main vibration frequency are arctangented to obtain the phase value at that frequency point. One vibration sensing unit is selected as the reference vibration sensing unit, and its phase value is used as the reference phase value. The difference between the phase values ​​of the remaining vibration sensing units and the reference phase value is calculated to obtain the vibration phase difference of each vibration sensing unit relative to the reference vibration sensing unit. The vibration phase difference of each vibration sensing unit is correlated with its installation position coordinates on the outside of the furnace wall. The vibration phase difference represents the difference in the direction of motion of the furnace wall position where each vibration sensing unit is located during vibration: when the vibration phase difference between two vibration sensing units is close to zero, it means that the furnace wall at these two positions moves in the same direction at the same time; when the vibration phase difference is close to half a cycle, it means that the furnace wall at these two positions moves in opposite directions at the same time. Combining the vibration phase difference of each vibration sensing unit and the vibration amplitude value of each vibration sensing unit at the main vibration frequency, the vibration mode shape of the furnace wall structure at the main vibration frequency is constructed. The vibration mode shape describes the relative vibration amplitude and vibration direction of each position on the furnace wall surface at resonance. The primary vibration frequency, vibration amplitude, vibration envelope attenuation slope, and vibration mode shape are combined into the first vibration characteristic parameter set. The specific combination operation is as follows: the vibration feature extraction module creates a parameter set data structure in memory. The parameter set data structure contains four members. The first member is filled with the value of the primary vibration frequency, the second member is filled with the value of the vibration amplitude, the third member is filled with the value of the vibration envelope attenuation slope, and the fourth member is filled with the data of the vibration mode shape. After the combination is completed, the parameter set data structure is the first vibration characteristic parameter set.

[0039] Feature association module: Based on the first acoustic feature parameter set and the first vibration feature parameter set, perform acoustic-vibration coupling association operation to determine the acoustic-vibration coupling feature parameter set; In this embodiment of the invention, the feature association module needs to be specifically described. The feature association module performs a time-domain synchronous comparison between the short-time average energy of the acoustic signal in the first acoustic feature parameter set and the vibration amplitude value in the first vibration feature parameter set to determine the delay time between the change in acoustic signal energy and the change in vibration amplitude, and uses the delay time as the acoustic-vibration delay parameter. The proportion of low-frequency energy in the first acoustic characteristic parameter set is compared with the main vibration frequency in the first vibration characteristic parameter set. When the frequency value corresponding to the maximum value of the low-frequency energy proportion is consistent with the main vibration frequency value, it is determined that acoustic resonance occurs between the sound field inside the furnace and the vibration of the furnace wall structure. The main vibration frequency value is used as the acoustic resonance frequency parameter. The spatial position of the sound source location area in the first acoustic feature parameter set is compared with the vibration mode shape in the first vibration feature parameter set to determine the spatial overlap between the sound source position and the position of the maximum amplitude of the vibration mode. The spatial overlap is used as the acoustic-vibration spatial coupling degree parameter. The acoustic vibration delay parameter, acoustic vibration resonance frequency parameter, and acoustic vibration spatial coupling degree parameter are combined into an acoustic vibration coupling characteristic parameter set.

[0040] It should be noted that the acoustic-vibration delay parameter refers to the time difference between the moment when the acoustic sensor array detects the change in acoustic signal energy and the moment when the vibration sensor array detects the change in the amplitude of furnace wall vibration when the same transient excitation event occurs in the furnace. The acoustic-vibration delay parameter reflects the response time delay experienced by the sound wave from the sound source in the furnace to the furnace wall and excites the vibration of the furnace wall structure. When the temperature and density distribution of the medium in the furnace is uniform and the furnace wall structure is intact, the acoustic-vibration delay parameter remains within a relatively short and stable range. When a local high-temperature gas mass or material accumulation occurs in the furnace, causing a change in the sound propagation path or loosening of the furnace wall lining, the acoustic-vibration delay parameter will increase accordingly.

[0041] The acoustic resonance frequency parameter refers to the frequency value corresponding to the acoustic resonance phenomenon that occurs between the sound field inside the furnace and the vibration of the furnace wall structure. Acoustic resonance means that the energy of a certain frequency component of the sound field inside the furnace is transmitted to the furnace wall through sound waves and matches the natural vibration frequency of the furnace wall structure, resulting in a significant increase in the vibration amplitude of the furnace wall at that frequency. The acoustic resonance frequency parameter is determined as follows: when the frequency value corresponding to the maximum value of the low-frequency energy proportion in the first acoustic characteristic parameter set is consistent with the main vibration frequency value in the first vibration characteristic parameter set, acoustic resonance is determined to have occurred, and the main vibration frequency value is taken as the acoustic resonance frequency parameter.

[0042] The acoustic-vibration spatial coupling parameter refers to the degree of spatial overlap between the location of the sound source in the furnace space and the location of the maximum amplitude in the vibration mode of the furnace wall structure. The acoustic-vibration spatial coupling parameter reflects the degree of spatial matching between the excitation location of the sound source in the furnace and the vibration-sensitive area of ​​the furnace wall structure. When the sound source is located exactly in the maximum amplitude area of ​​a certain vibration mode of the furnace wall structure, the transmission efficiency of the sound source energy to the vibration of the furnace wall is the highest, and the acoustic-vibration spatial coupling parameter has the largest value. When the sound source is far away from the vibration-sensitive area of ​​the furnace wall structure, the acoustic-vibration spatial coupling parameter has a lower value.

[0043] The specific working steps of the feature association module are as follows: The short-time average energy of the acoustic signal in the first acoustic feature parameter set is compared with the vibration amplitude value in the first vibration feature parameter set in the time domain to determine the delay time between the change in acoustic signal energy and the change in vibration amplitude. The delay time is used as the acoustic-vibration delay parameter. The first acoustic feature parameter set is output by the acoustic feature extraction module and stored in the feature parameter storage area. The first vibration feature parameter set is output by the vibration feature extraction module and stored in the same feature parameter storage area. The time series of the short-time energy mean of the acoustic signal were read from the first acoustic feature parameter set, and the time series of the vibration amplitude value were read from the first vibration feature parameter set. The time series of the short-time energy mean of the acoustic signal recorded the change history of the short-time energy mean of the acoustic signal of each channel of the acoustic sensor array over time, and the time series of the vibration amplitude value recorded the change history of the vibration amplitude value of each channel of the vibration sensor array over time. Identify energy surge events in the time series of short-time energy mean of acoustic signals, that is, the moment when the short-time energy mean of acoustic signals jumps from the baseline level to the peak level in a short period of time, and record the occurrence time of the energy surge event as the acoustic event trigger time. In the time series of vibration amplitude values, starting from the moment the sound event is triggered, the moment when the vibration amplitude value begins to rise significantly from the baseline level is searched backward. The moment when the vibration amplitude value begins to rise significantly is recorded as the vibration response start time. The criteria for determining a significant rise in vibration amplitude value are: the vibration amplitude value at the current moment exceeds the baseline vibration amplitude value by a multiple or exceeds the preset response judgment multiple. The vibration response start time is subtracted from the sound event trigger time, and the resulting time difference is the delay time between the change in sound signal energy and the change in vibration amplitude. The arithmetic mean of the delay times obtained from multiple transient events within a certain period is taken, and the average value is determined as the sound vibration delay parameter. The larger the value of the sound vibration delay parameter, the longer the time required for the sound disturbance in the furnace to be transmitted to the furnace wall and excite significant vibration, and the more delayed the sound vibration response. The low-frequency energy ratio in the first acoustic feature parameter set is compared with the main vibration frequency in the first vibration feature parameter set to determine whether acoustic resonance occurs between the sound field inside the furnace and the vibration of the furnace wall structure, and to determine the acoustic resonance frequency parameter. The distribution data of the low-frequency energy ratio on the frequency axis is read from the first acoustic feature parameter set. The frequency distribution of the low-frequency energy ratio represents the change of the energy ratio of the sound signal at each frequency in the low-frequency band. In the frequency distribution of the low-frequency energy ratio, the frequency point with the largest energy ratio is found, and the frequency value corresponding to the frequency point is taken as the frequency value corresponding to the maximum value of the low-frequency energy ratio. The system reads the value of the main vibration frequency from the first set of vibration characteristic parameters. It then compares the frequency value corresponding to the maximum energy proportion of the low-frequency band with the main vibration frequency value to determine if they are consistent. The consistency is determined by calculating the absolute value of the difference between the frequency value corresponding to the maximum energy proportion of the low-frequency band and the main vibration frequency value. This absolute value is compared with a preset frequency consistency tolerance threshold. If the absolute value is less than or equal to the threshold, the frequency value corresponding to the maximum energy proportion of the low-frequency band is considered consistent with the main vibration frequency value. In this case, the dominant low-frequency frequency of the furnace sound field coincides with the main vibration frequency of the furnace wall structure, and acoustic resonance occurs between the furnace sound field and the furnace wall structure vibration. The feature association module uses the main vibration frequency value as the acoustic resonance frequency parameter. If the absolute value is greater than the frequency consistency tolerance threshold, the two frequency values ​​are considered inconsistent, and no significant acoustic resonance occurs between the furnace sound field and the furnace wall structure vibration. The acoustic resonance frequency parameter is then set as an invalid flag value. The spatial position of the sound source location area in the first acoustic feature parameter set is compared with the vibration mode shape in the first vibration feature parameter set to determine the spatial overlap between the sound source position and the position of the maximum amplitude of the vibration mode. The spatial overlap is used as the acoustic-vibration spatial coupling degree parameter. The sound source location area is read from the first acoustic feature parameter set. The sound source location area includes the center coordinates and radius of the sound source location. The vibration mode shape is read from the first vibration feature parameter set. The vibration mode shape describes the relative vibration amplitude distribution of each position on the furnace wall surface at the main vibration frequency. The position area with the largest vibration amplitude is identified in the vibration mode shape. The position area with the largest vibration amplitude is taken as the position of the maximum amplitude of the vibration mode. In the three-dimensional coordinate space of the furnace wall, the spatial distance between the center coordinates of the sound source location area and the center coordinates of the maximum amplitude position of the vibration mode is calculated. The area radius of the sound source location area and the area radius of the maximum amplitude position of the vibration mode are read. The spatial distance between the centers of the two areas is compared with the sum of the two area radii. When the spatial distance is less than or equal to the sum of the two area radii, it is determined that there is a spatial overlap between the sound source location area and the maximum amplitude position of the vibration mode. The area or volume of the overlapping area is calculated. The area or volume of the overlapping area is divided by the area or volume of the sound source location area, and the ratio is used as the sound-vibration spatial coupling degree parameter. When the spatial distance is greater than the sum of the two area radii, it is determined that the two areas are completely separated in space, and the sound-vibration spatial coupling degree parameter is set to zero. The closer the value of the sound-vibration spatial coupling degree parameter is to one, the higher the spatial overlap between the sound source position and the maximum amplitude position of the vibration mode, and the tighter the spatial coupling of the sound source energy to the furnace wall vibration. The acoustic vibration delay parameter, acoustic vibration resonance frequency parameter, and acoustic vibration spatial coupling degree parameter are combined into an acoustic vibration coupling characteristic parameter set. The specific method of the combination operation is as follows: a parameter set data structure is created in memory. The parameter set data structure contains three members. The first member is filled with the value of the acoustic vibration delay parameter, the second member is filled with the value of the acoustic vibration resonance frequency parameter, and the third member is filled with the value of the acoustic vibration spatial coupling degree parameter. After the combination is completed, the parameter set data structure is the acoustic vibration coupling characteristic parameter set.

[0044] Status determination module: Based on the acoustic-vibration coupling characteristic parameter set, it performs a status determination operation to determine the current operating status identifier of the furnace; In this embodiment of the invention, the state determination module needs to be specifically described. The state determination module compares the acoustic vibration delay parameter with the first delay threshold and the second delay threshold successively, wherein the first delay threshold is less than the second delay threshold. When the acoustic vibration delay parameter is less than or equal to the first delay threshold, the acoustic vibration response is determined to be in a fast coupling state; when the acoustic vibration delay parameter is greater than the first delay threshold and less than or equal to the second delay threshold, the acoustic vibration response is determined to be in a medium-speed coupling state; when the acoustic vibration delay parameter is greater than the second delay threshold, the acoustic vibration response is determined to be in a slow coupling state. The acoustic and vibration resonance frequency parameters are compared with the reference resonance frequency range recorded under the normal and stable operation of the furnace. When the acoustic and vibration resonance frequency parameters deviate from the reference resonance frequency range, it is determined that there is an abnormality in the furnace structure. The acoustic-vibration spatial coupling parameter is compared with the first coupling threshold. When the acoustic-vibration spatial coupling parameter is lower than the first coupling threshold, it is determined that there is local slagging or bridging phenomenon in the furnace. Based on the comprehensive judgment results of the acoustic and vibration response speed, whether there are abnormalities in the furnace structure, and whether there is local slagging or bridging, the current operating status of the furnace is determined. The current operating status is one of the following: stable operating status, furnace lining erosion status, furnace slagging status, or feeding and discharging disturbance status. Based on the comprehensive judgment results of the acoustic and vibration response speed, the presence of abnormal furnace structure, and the presence of local slagging or bridging phenomena, the current operating status of the furnace is determined, specifically including the following steps: When the acoustic and vibration response is in a rapid coupling state, there are no abnormalities in the furnace structure, and there is no local slagging or bridging, the current operating state is identified as a stable operating state. When the acoustic and vibration response is in a medium-speed coupling state and there is an abnormality in the furnace structure, but there is no local slagging or bridging phenomenon, the current operating status is identified as the furnace lining erosion status. When the acoustic and vibration response is in a slow coupling state and there is local slagging or bridging, the current operating status is identified as the furnace slagging status. When the acoustic vibration response is in a rapid coupling state, but the fluctuation amplitude of the short-time average energy of the acoustic signal exceeds the preset fluctuation threshold within the short-time window, the current operating state is identified as the feeding and discharging disturbance state.

[0045] It should be noted that the first delay threshold is the first time boundary value used to define the coupling speed level of the acoustic-vibration response. The value of the first delay threshold is less than the second delay threshold. The function of the first delay threshold is to distinguish between fast coupling and medium-speed coupling. When the acoustic-vibration delay parameter is less than or equal to the first delay threshold, it indicates that the time it takes for the sound wave to propagate from the sound source in the furnace to the furnace wall and excite significant vibration is extremely short, and the acoustic-vibration response is rapid.

[0046] The second delay threshold is the second time boundary value used to define the coupling speed level of the acoustic-vibration response. The value of the second delay threshold is greater than that of the first delay threshold. The function of the second delay threshold is to distinguish between medium-speed coupling and slow-speed coupling: when the acoustic-vibration delay parameter is greater than the second delay threshold, it indicates that the acoustic-vibration response is significantly lagging, and there may be an obstruction in the transmission channel between the sound field inside the furnace and the vibration of the furnace wall.

[0047] The rapid coupling state refers to the acoustic and vibration response state in which the acoustic and vibration delay parameters are at a low level and the changes in the acoustic field and the vibration response are almost synchronous. The rapid coupling state usually occurs under the conditions of stable furnace operation, uniform medium in the furnace and intact furnace wall structure.

[0048] The medium-speed coupling state refers to the acoustic vibration response state where the acoustic vibration delay parameter is in the middle range of the normal range, indicating that there is a certain degree of delay factor in the acoustic vibration transmission channel.

[0049] Slow coupling state refers to an acoustic-vibration response state in which the acoustic-vibration delay parameter is significantly high and there is a significant time delay between the change in the sound field and the vibration response. Slow coupling state usually indicates that the medium distribution in the furnace is uneven, the sound propagation path is blocked due to material accumulation, or the furnace wall lining is loose.

[0050] The reference resonance frequency range refers to the normal fluctuation range of the acoustic and vibration resonance frequency parameters obtained from long-term operational data statistics under normal and stable operating conditions of the furnace. The reference resonance frequency range has an upper limit frequency value and a lower limit frequency value. When the acoustic and vibration resonance frequency parameters fall within the reference resonance frequency range, it indicates that the resonance mode between the sound field inside the furnace and the vibration of the furnace wall structure is in a normal state. When the acoustic and vibration resonance frequency parameters exceed the reference resonance frequency range, it indicates that the structural characteristics inside the furnace have changed. For example, the furnace lining thickness is reduced, resulting in a decrease in the overall stiffness of the furnace wall, or slagging on the furnace wall increases the mass of the furnace wall, thereby causing a shift in the resonance frequency.

[0051] Abnormal furnace structure refers to an abnormal state that affects the integrity of the furnace structure, such as erosion and thinning of the furnace wall lining, cracks or loosening of the furnace wall structure. The basis for judging abnormal furnace structure is whether the acoustic resonance frequency parameters deviate from the reference resonance frequency range.

[0052] The first coupling threshold refers to the critical value of the acoustic-vibration spatial coupling parameter used to determine whether there is local slagging or bridging in the furnace. When the acoustic-vibration spatial coupling parameter is lower than the first coupling threshold, it indicates that the spatial overlap between the sound source location and the vibration-sensitive area of ​​the furnace wall is reduced. The sound waves emitted by the sound source in the furnace are locally blocked or scattered during their propagation to the furnace wall. This reduction in spatial coupling is usually caused by the change in the sound propagation path due to slagging accumulation or material bridging in local areas of the furnace.

[0053] The fluctuation threshold refers to the critical value of the fluctuation amplitude of the short-term average energy of the acoustic signal within a short time window. When the fluctuation amplitude of the short-term average energy of the acoustic signal exceeds the fluctuation threshold within the short time window, it indicates that the acoustic field energy in the furnace fluctuates violently in a short period of time. Violent fluctuations are usually caused by a large amount of room temperature material being suddenly put into the high-temperature furnace during the feeding and discharging operation, resulting in local temperature fluctuations and airflow disturbances.

[0054] The stable operation status indicator refers to the identifier that the furnace is currently in a normal and stable operating state. The furnace lining erosion status indicator refers to the identifier that the furnace wall lining has erosion, thinning, or structural loosening. The furnace slagging status indicator refers to the identifier that there is local slagging accumulation or material bridging inside the furnace. The feeding and discharging disturbance status indicator refers to the identifier that the furnace is in the process of feeding and discharging, and the furnace operating conditions are temporarily fluctuating due to the input or discharge of materials.

[0055] The specific working steps of the status determination module are as follows: The acoustic vibration delay parameter is compared successively with the first delay threshold and the second delay threshold to determine the coupling speed level of the acoustic vibration response. The value of the acoustic vibration delay parameter is read from the acoustic vibration coupling feature parameter set, which is output by the feature association module and stored in the feature parameter storage area. First, the value of the acoustic vibration delay parameter is compared with the first delay threshold: when the acoustic vibration delay parameter is less than or equal to the first delay threshold, the acoustic vibration response is determined to be in a fast coupling state. When the acoustic vibration delay parameter is greater than the first delay threshold, the acoustic vibration delay parameter is compared with the second delay threshold. When the acoustic vibration delay parameter is greater than the first delay threshold and less than or equal to the second delay threshold, the acoustic vibration response is determined to be in a medium-speed coupling state. When the acoustic vibration delay parameter is greater than the second delay threshold, the acoustic vibration response is determined to be in a slow coupling state. The acoustic and vibration resonance frequency parameters are compared with the reference resonance frequency range recorded under the normal and stable operation of the furnace to determine whether there is any structural abnormality in the furnace. The values ​​of the acoustic and vibration resonance frequency parameters are read from the acoustic and vibration coupling characteristic parameter set. The upper limit and lower limit frequency values ​​of the reference resonance frequency range are read. The acoustic and vibration resonance frequency parameters are compared with the lower limit frequency value and the upper limit frequency value one by one. When the acoustic and vibration resonance frequency parameters are greater than or equal to the lower limit frequency value and less than or equal to the upper limit frequency value, it is determined that the acoustic and vibration resonance frequency parameters are within the reference resonance frequency range and there is no structural abnormality in the furnace. When the acoustic resonance frequency parameter is less than the lower limit or greater than the upper limit, it is determined that the acoustic resonance frequency parameter deviates from the reference resonance frequency range, indicating an abnormality in the furnace structure. The direction and magnitude of the acoustic resonance frequency parameter deviating from the reference resonance frequency range contain further information about the type of abnormality in the furnace structure: a shift of the acoustic resonance frequency parameter below the lower limit usually corresponds to an increase in furnace wall mass, which may be caused by thickening of slag on the furnace wall; a shift of the acoustic resonance frequency parameter above the upper limit usually corresponds to a decrease in furnace wall stiffness, which may be caused by thinning of the furnace lining due to erosion or loosening of the furnace wall structure. The acoustic-vibration spatial coupling degree parameter is compared with the first coupling degree threshold to determine whether there is local slagging or bridging in the furnace. The value of the acoustic-vibration spatial coupling degree parameter is read from the acoustic-vibration coupling characteristic parameter set, and the acoustic-vibration spatial coupling degree parameter is compared with the first coupling degree threshold. When the acoustic-vibration spatial coupling degree parameter is greater than or equal to the first coupling degree threshold, it is determined that the spatial overlap between the sound source position and the position of the maximum amplitude of the vibration mode is at a normal level, and there is no obvious local slagging or bridging in the furnace. When the acoustic-vibration spatial coupling degree parameter is lower than the first coupling degree threshold, it is determined that the spatial overlap between the sound source position and the position of the maximum amplitude of the vibration mode is significantly reduced, and there is local slagging or bridging in the furnace. The first coupling degree threshold is determined by statistically analyzing the historical records of the acoustic-vibration spatial coupling degree parameter of the furnace under normal slagging-free operation. Based on the comprehensive judgment results of acoustic and vibration response speed, the presence of abnormal furnace structure, and the presence of local slagging or bridging phenomena, the current operating status indicator of the furnace is determined. The judgment results from the three dimensions are combined, and the corresponding operating status indicator is matched according to the combination result. The specific matching rules are as follows: When the acoustic and vibration response is in a rapid coupling state, there are no abnormalities in the furnace structure, and there is no local slag formation or bridging, the state determination module determines the current operating state as a stable operating state. The stable operating state indicates that the acoustic and vibration coupling relationship between the sound field inside the furnace and the furnace wall vibration is in a normal state, the furnace structure is intact, there is no obvious slag formation or material accumulation inside the furnace, and the furnace is operating smoothly as a whole.

[0056] When the acoustic-vibration response is in a medium-speed coupling state and there is an abnormality in the furnace structure, but there is no local slagging or bridging phenomenon, the state determination module determines the current operating state as the furnace lining erosion state. The furnace lining erosion state indicates that the furnace wall lining has undergone a certain degree of erosion and thinning or structural loosening, resulting in a shift in the natural vibration frequency of the furnace wall. However, since there is no obvious slagging, the acoustic-vibration spatial coupling degree remains normal. The medium-speed coupling state indicates that the acoustic-vibration transmission channel has been affected to some extent by the changes in the furnace lining structure.

[0057] When the acoustic-vibration response is in a slow coupling state and there is local slagging or bridging, the state determination module identifies the current operating state as the furnace slagging state. The furnace slagging state indicates that there is significant slagging or material bridging inside the furnace. The slagging area obstructs the normal propagation path of sound waves inside the furnace, leading to a significant increase in acoustic-vibration delay. Simultaneously, the spatial coupling degree decreases significantly due to the change in the sound propagation path. The simultaneous presence of slow coupling and slagging indicates that the impact of slagging on the furnace operating conditions is quite severe.

[0058] When the acoustic vibration response is in a rapid coupling state but the fluctuation amplitude of the short-time average energy of the acoustic signal exceeds the fluctuation threshold within the short-time window, the current operating state is identified as the feeding / discharging disturbance state. The feeding / discharging disturbance state indicates that the furnace is in the process of feeding / discharging. Although the acoustic vibration response speed remains fast, the acoustic field energy fluctuates violently due to the input of cold material or the discharge of hot material. The specific value of the fluctuation threshold is set during the system initialization stage based on the normal fluctuation range of the short-time average energy of the acoustic signal during the stable operation of the furnace.

[0059] The current operating status identifier is stored in the system status record area. If the current operating status identifier is any one of the following: furnace lining erosion status identifier, furnace slagging status identifier, or material feeding / discharging disturbance status identifier, the current operating status is determined to be an abnormal state.

[0060] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0061] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0062] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0063] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0064] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the described technical solution.

Claims

1. An online monitoring system for the running state of a solid waste regeneration furnace based on the Internet of Things, characterized in that, include: Signal acquisition module: acquires the acoustic signals inside the furnace collected by the acoustic sensor array deployed on the outside of the furnace wall, and simultaneously acquires the furnace wall vibration signals collected by the vibration sensor array deployed on the outside of the furnace wall. Acoustic feature extraction module: Based on the acoustic signals inside the furnace, extracts a first set of acoustic feature parameters reflecting the working conditions inside the furnace; Vibration feature extraction module: Based on the furnace wall vibration signal, extracts a first set of vibration feature parameters reflecting the structural response characteristics of the furnace wall; Feature association module: Based on the first acoustic feature parameter set and the first vibration feature parameter set, perform acoustic-vibration coupling association operation to determine the acoustic-vibration coupling feature parameter set; Specifically, the short-time average energy of the acoustic signal in the first acoustic feature parameter set is compared with the vibration amplitude value in the first vibration feature parameter set in the time domain to determine the delay time between the change in acoustic signal energy and the change in vibration amplitude, and the delay time is used as the acoustic-vibration delay parameter. The proportion of low-frequency energy in the first acoustic characteristic parameter set is compared with the main vibration frequency in the first vibration characteristic parameter set. When the frequency value corresponding to the maximum value of the low-frequency energy proportion is consistent with the main vibration frequency value, it is determined that acoustic resonance occurs between the sound field inside the furnace and the vibration of the furnace wall structure. The main vibration frequency value is used as the acoustic resonance frequency parameter. The spatial position of the sound source location area in the first acoustic feature parameter set is compared with the vibration mode shape in the first vibration feature parameter set to determine the spatial overlap between the sound source position and the position of the maximum amplitude of the vibration mode. The spatial overlap is used as the acoustic-vibration spatial coupling degree parameter. The acoustic vibration delay parameter, acoustic vibration resonance frequency parameter, and acoustic vibration spatial coupling degree parameter are combined into an acoustic vibration coupling characteristic parameter set; Status determination module: Based on the acoustic-vibration coupling characteristic parameter set, it performs a status determination operation to determine the current operating status identifier of the furnace; In this process, the acoustic vibration delay parameter is compared with a first delay threshold and a second delay threshold successively, wherein the first delay threshold is less than the second delay threshold; When the acoustic vibration delay parameter is less than or equal to the first delay threshold, the acoustic vibration response is determined to be in a fast coupling state; when the acoustic vibration delay parameter is greater than the first delay threshold and less than or equal to the second delay threshold, the acoustic vibration response is determined to be in a medium-speed coupling state; when the acoustic vibration delay parameter is greater than the second delay threshold, the acoustic vibration response is determined to be in a slow coupling state. The acoustic and vibration resonance frequency parameters are compared with the reference resonance frequency range recorded under the normal and stable operation of the furnace. When the acoustic and vibration resonance frequency parameters deviate from the reference resonance frequency range, it is determined that there is an abnormality in the furnace structure. The acoustic-vibration spatial coupling parameter is compared with the first coupling threshold. When the acoustic-vibration spatial coupling parameter is lower than the first coupling threshold, it is determined that there is local slagging or bridging phenomenon in the furnace. Based on the comprehensive judgment results of the acoustic and vibration response speed, the presence of abnormal internal furnace structure, and the presence of local slagging or bridging phenomena, the current operating status indicator of the furnace is determined. The current operating status indicator is one of the following: stable operating status indicator, furnace lining erosion status indicator, internal furnace slagging status indicator, or material feeding and discharging disturbance status indicator.

2. The online monitoring system for the running state of the solid waste regeneration smelting furnace based on the Internet of Things according to claim 1, characterized in that, The signal acquisition module receives analog acoustic signals output from each channel of an acoustic sensing array composed of several acoustic sensing units, and receives analog vibration signals output from each channel of a vibration sensing array composed of several vibration sensing units. It performs signal conditioning operations on the analog acoustic signals and analog vibration signals of each channel, including pre-amplification and anti-aliasing filtering. The conditioned signals from each channel are sent to a multi-channel synchronous analog-to-digital converter and synchronously sampled at a preset sampling frequency to obtain a multi-channel digital acoustic signal sequence and a multi-channel digital vibration signal sequence. The multi-channel digital acoustic signal sequence is used as the furnace acoustic signal, and the multi-channel digital vibration signal sequence is used as the furnace wall vibration signal.

3. The online monitoring system for the running state of a solid waste regeneration furnace based on the Internet of Things according to claim 1, characterized in that, The acoustic feature extraction module extracts a first time-domain acoustic feature from the acoustic signal inside the furnace. The first time-domain acoustic feature includes the short-time energy mean of the acoustic signal and the zero-crossing rate of the acoustic signal. The first frequency domain acoustic features are extracted from the acoustic signals inside the furnace. The first frequency domain acoustic features include the energy proportion of the low frequency band, the energy proportion of the mid frequency band, and the energy proportion of the high frequency band. The time difference of sound arrival is obtained from the acoustic signal received by the acoustic sensing unit at different spatial locations in the acoustic sensing array. Based on the time difference of sound arrival and the spatial distance between each acoustic sensing unit, the sound source localization area in the furnace space is determined.

4. The online monitoring system for the operating status of a solid waste recycling furnace based on the Internet of Things as described in claim 3, characterized in that, The specific steps for determining the sound source localization area are as follows: Identify the same transient acoustic event from the signal sequences of each acoustic sensing unit. A transient acoustic event is a waveform segment in which the signal amplitude shows a significant pulse-like increase in a short period of time. Record the reception time value of the same transient sound event received by each acoustic sensing unit. Using the reception time value of one acoustic sensing unit as a reference, calculate the difference between the reception time value of the other acoustic sensing units and the reference reception time value to obtain the sound arrival time difference between each acoustic sensing unit. Read the installation position coordinates of each acoustic sensor unit on the outside of the furnace wall, calculate the spatial distance between each acoustic sensor unit, and based on the spatial distance between each acoustic sensor unit and the sound arrival time difference, use the spatial intersection positioning method to determine the position coordinates of the sound source in the furnace space, and take the position coordinates and the surrounding neighborhood area as the sound source positioning area. The first time-domain acoustic features, the first frequency-domain acoustic features, and the sound source localization region are combined into a first acoustic feature parameter set.

5. The online monitoring system for the operating status of a solid waste recycling furnace based on the Internet of Things as described in claim 1, characterized in that, The vibration feature extraction module extracts the main vibration frequency and the vibration amplitude value corresponding to the main vibration frequency from the furnace wall vibration signal. The vibration envelope attenuation slope of the vibration signal during the first observation period is extracted from the furnace wall vibration signal. The vibration envelope attenuation slope represents the rate of change of the vibration signal amplitude over time. The vibration phase difference of vibration sensing units at different spatial positions in the vibration sensing array under the same excitation conditions is obtained, and the vibration mode shape of the furnace wall structure is determined based on the vibration phase difference. The principal vibration frequency, vibration amplitude, vibration envelope attenuation slope, and vibration mode shape are combined to form the first set of vibration characteristic parameters.

6. The online monitoring system for the operating status of a solid waste recycling furnace based on the Internet of Things as described in claim 1, characterized in that, Based on the comprehensive judgment results of the acoustic and vibration response speed, the presence of abnormal furnace structure, and the presence of local slagging or bridging phenomena, the current operating status of the furnace is determined, specifically including the following steps: When the acoustic and vibration response is in a rapid coupling state, there are no abnormalities in the furnace structure, and there is no local slagging or bridging, the current operating state is identified as a stable operating state. When the acoustic and vibration response is in a medium-speed coupling state and there is an abnormality in the furnace structure, but there is no local slagging or bridging phenomenon, the current operating status is identified as the furnace lining erosion status. When the acoustic and vibration response is in a slow coupling state and there is local slagging or bridging, the current operating status is identified as the furnace slagging status. When the acoustic vibration response is in a rapid coupling state, but the fluctuation amplitude of the short-time average energy of the acoustic signal exceeds the preset fluctuation threshold within the short-time window, the current operating state is identified as the feeding and discharging disturbance state.

Images