Real-time monitoring system and method for flame state of cutting machine

Abstract

The invention discloses a real-time monitoring system and method for the flame state of a cutting machine, and belongs to the technical field of flame cutting. The real-time monitoring system for the flame state of the cutting machine comprises a data acquisition module, an ADC module, a data processing module and a display module; the data acquisition module is used for acquiring sound wave signal data when the flame cutting machine works through a microphone; the ADC module performs analog-to-digital conversion on the sound wave signal output by each microphone to obtain a digital signal, and the digital signal is converted into a frequency amplitude signal through Fourier transform; the data processing module compares the current frequency amplitude signal data with preset standard frequency amplitude signal data when the flame state is normal through a frequency amplitude comparison algorithm so as to monitor the flame state; the display module displays the current flame state of the cutting machine in real time and provides fault reminding when abnormity is detected, and the problems that in the prior art, the flame state monitoring precision is not high, and abnormity feedback is not timely are solved.

Description

Technical Field

[0001] The invention relates to the technical field of flame cutting, and in particular to a system and method for real-time monitoring of flame status of a cutting machine. Background Art

[0002] With the development of industrial automation, flame cutting machines are widely used in metal processing, shipbuilding, automobile manufacturing and construction as an efficient and precise cutting tool. Flame cutting machines efficiently cut steel billets by spraying oxygen and combustible gas in a certain proportion. However, during the flame cutting process, the state of the flame directly affects the cutting quality and efficiency. Abnormal flame state leads to uneven cutting, rough cutting surface, and even damage to the flame cutting machine equipment. Therefore, real-time monitoring of the flame state is of great significance to ensure the normal operation of the flame cutting machine and improve the cutting quality.

[0003] Currently, the commonly used flame monitoring methods include manual observation, camera monitoring and temperature monitoring. The manual observation method is to judge the flame state by the operator observing the color, shape and stability of the flame. This method relies on the experience of the operator and has great subjectivity and errors. The camera detection method uses a high-temperature camera or an infrared camera to capture the flame image and analyze the flame state through image processing technology. Although this method is more accurate, it is costly and affected by ambient light. The temperature detection method uses thermocouples or infrared temperature sensors to measure the flame temperature to judge the flame state. This method is sensitive to temperature changes, but can only provide flame temperature information and cannot directly reflect the stability and uniformity of the flame. In addition, thermocouples and infrared temperature sensors are easily damaged in high temperature environments and have high maintenance costs. Summary of the invention

[0004] The object of the present invention is to provide a system and method for real-time monitoring of flame status of a cutting machine to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a real-time monitoring system for the flame state of a cutting machine, the system comprising: a data acquisition module, an ADC module, a data processing module and a display module; the data acquisition module realizes the collection of data when the flame cutting machine is working through a microphone, and the microphone is used to collect sound wave signal data and output analog sound wave signal data, and record the acoustic characteristics of the flame combustion process; the ADC module is used to convert the analog sound wave signal output by each microphone into a digital signal through an analog-to-digital converter, and the digital signal is converted into frequency-amplitude signal data through Fourier transform; the data processing module compares the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data when the flame state is normal through a frequency-amplitude comparison algorithm, so as to monitor whether the flame state is normal; the display module is used to display the current flame state of the cutting machine in real time, and provide a fault reminder when an abnormality is detected.

[0006] Furthermore, the data acquisition module includes M microphones, which are placed according to the layout of the Fibonacci wheel array, and continuously receive the sound wave signal data of the flame cutting machine when it is working at a collection frequency of f Hz and output analog sound wave signal data, wherein M represents the number of microphones used to collect sound wave signals.

[0007] Furthermore, the ADC module converts the analog sound wave signal output by the microphone into a digital signal, and performs Fourier transform on the digital signal to convert it into frequency-amplitude signal data.

[0008] Furthermore, the data processing module compares the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data when the flame state is normal through a frequency-amplitude comparison algorithm. The preset standard frequency-amplitude signal data when the flame state is normal is based on the sound wave data collected by M microphones in the data acquisition module when the flame cutting machine is in normal working condition, and is converted into a digital signal through an analog-to-digital converter. The digital signal is converted into frequency-amplitude signal data through Fourier transform.

[0009] A method for real-time monitoring of flame status of a cutting machine comprises the following steps:

[0010] S1: Collect the acoustic wave data of the flame cutting machine during operation;

[0011] S2: converting the acquired sound wave data of the flame cutting machine during operation into a continuous digital signal, and converting it into frequency-amplitude signal data through Fourier transform;

[0012] S3: By using a frequency-amplitude comparison algorithm, the current frequency-amplitude signal data is compared with the preset standard frequency-amplitude signal data when the flame state is normal, so as to monitor the flame state of the cutting machine in real time.

[0013] Furthermore, in step S1: the microphone is directed toward the cutting nozzle of the flame cutting machine to collect the acoustic wave data when the flame cutting machine is running, and outputs an analog acoustic wave signal to accurately locate the sound source, thereby ensuring that the collected acoustic wave data comes from the key parts of the flame cutting process, improving the data collection accuracy, and being able to monitor in real time whether the flame state of the cutting machine is abnormal, promptly discover and feedback abnormal situations, reduce the impact of environmental noise and other interference signals, and enhance the robustness and adaptability in complex environments.

[0014] Furthermore, in step S2: the collected acoustic wave data of the flame cutting machine during operation is converted into continuous digital signals, and these signals are subjected to Fourier transform to obtain an amplitude value sequence in the frequency domain, which is represented as an array X = {X1, X2, X3, ..., X n-1 , X n}, where array X represents the amplitude value sequence in the frequency domain, n represents the number of frequency domain components, and X n Represents the amplitude value of the nth frequency domain component.

[0015] Further, in step S3: the current frequency-amplitude signal data is compared with the preset standard frequency-amplitude signal data when the flame state is normal through the frequency-amplitude comparison algorithm, and the specific steps include:

[0016] S3-1: Calculate the standard deviation of each frequency signal data. The formula is as follows:

[0017]

[0018] Where n is the number of frequency sampling points, x i is the sampling value of a specific sampling point, represents the mean of the sampling points;

[0019] S3-2: Normalize each measured waveform array according to the standard deviation and mean, and the current frequency amplitude signal data X′ j The normalized calculation formula is as follows:

[0020]

[0021] The preset standard frequency signal data Y′ when the flame state is normal j The normalized calculation formula is as follows:

[0022]

[0023] Calculate the current frequency amplitude signal data X′ j The standard frequency signal data Y′ when the flame state is normal j The absolute distance D j , the formula is as follows:

[0024]

[0025] Where: j = 1, 2, 3, ..., m, μX j and μY j They are the frequency and amplitude signal data X j and Y j The mean of and They are the frequency and amplitude signal data X j and Y j The standard deviation of

[0026] S3-3: Introducing correction parameter k and absolute distance threshold r th , when the signal changes slightly, the absolute distance D at the current moment j Less than or equal to the absolute distance D at the previous moment j-1 ; Calculate the absolute distance D at the current moment j The absolute distance D from the previous moment j-1 The rate of change between them is calculated as follows:

[0027]

[0028] Calculate the threshold r th The formula is as follows:

[0029]

[0030] where j = k, k-1, ... 1, r th represents the threshold of absolute distance, k represents the correction parameter, D j Indicates the distance between the current amplitude signal data and the preset standard amplitude signal data, D j-1 Indicates the distance between the amplitude signal data at the previous moment and the preset standard amplitude signal data;

[0031] When the signal changes greatly, the absolute distance D at the current moment j Greater than the absolute distance D at the previous moment j-1 , it is necessary to introduce a dynamic adjustment correction parameter k, dynamically adjust the frequency and amplitude signal data in the calculation process, dynamically adjust the correction parameters and the absolute distance threshold, which can adapt to different signal changes and improve the robustness and adaptability in complex environments.

[0032] S3-4: Calculate the current frequency and amplitude signal data X′ j The standard frequency signal data Y′ when the flame state is normal j The similarity coefficient P xy , the formula is as follows:

[0033]

[0034] Among them, C ov (X′ j ,Y′ j ) are the frequency and amplitude signal data X′ j and Y′ j covariance; D(X′ j ) and D(Y′ j ) are the frequency and amplitude signal data X′ j and Y′ j The variance of xy Analyze the correlation between two sets of frequency signal data: When |P xy |=0, indicating that the two are unrelated; when |P xy When |=1, it means that the two signals are completely identical, P xy The closer to 1, the stronger the correlation; when 0≤|P xy |<0.8, the cutting machine flame is judged to be in an abnormal state. xy |≤1, the flame of the cutting machine is judged to be normal. By comparing the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data through the frequency-amplitude comparison algorithm, the flame state can be monitored in real time and accurately to ensure that the abnormality of the flame state can be detected at the first time. By calculating the standard deviation and mean, the frequency-amplitude signal data is normalized to eliminate the deviation between different signal data. By introducing the dynamic adjustment correction parameter k and the absolute distance threshold r th ,The system can adaptively adjust parameters according to the changes of real-time signals,,improving the adaptability under different signal change conditions.

[0035] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention arranges multiple microphones according to the layout of the Fibonacci wheel array, converts the collected analog sound wave signal data into digital signals, and then converts the digital signals into frequency-amplitude signal data through Fourier transform, and uses a frequency-amplitude comparison algorithm to compare the frequency-amplitude signal data with the preset standard frequency-amplitude signal data when the flame state is normal, thereby monitoring the flame state of the cutting machine in real time. In addition, a real-time monitoring system for the flame state of a cutting machine reduces dependence on manual observation and enhances the efficiency and reliability of monitoring. The system has strong adaptability to ambient light and temperature changes, can operate stably in various working environments, ensures that the flame state of the flame cutting machine is normal, and thus improves cutting quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0037] Figure 1 It is a schematic diagram of microphone layout in a method for real-time monitoring of flame status of a cutting machine according to the present invention;

[0038] Figure 2 It is a structural diagram of a real-time monitoring system for flame status of a cutting machine according to the present invention;

[0039] Figure 3 The present invention is a flow chart of a method for real-time monitoring of flame status of a cutting machine. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1-Figure 3 The present invention provides a technical solution: a real-time monitoring system for the flame state of a cutting machine, the system comprising: a data acquisition module, an ADC module, a data processing module and a display module; the data acquisition module realizes the acquisition of data when the flame cutting machine is working through a microphone, the microphone is used to collect sound wave signal data and output analog sound wave signal data, and record the acoustic characteristics of the flame combustion process; the ADC module is used to convert the analog sound wave signal output by each microphone into a digital signal through an analog-to-digital converter, and the digital signal is converted into frequency-amplitude signal data through Fourier transform; the data processing module compares the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data when the flame state is normal through a frequency-amplitude comparison algorithm, so as to monitor whether the flame state is normal; the display module is used to display the current flame state of the cutting machine in real time, and provide a fault reminder when an abnormality is detected.

[0042] The data acquisition module includes M microphones, which are placed according to the layout of the Fibonacci wheel array, continuously receive the sound wave signal data of the flame cutting machine when it is working at a collection frequency of fHz and output analog sound wave signal data, where M represents the number of microphones used to collect sound wave signals.

[0043] The ADC module converts the analog sound wave signal output by the microphone into a digital signal, and performs Fourier transform on the digital signal to convert it into frequency-amplitude signal data.

[0044] The data processing module compares the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data when the flame state is normal through a frequency-amplitude comparison algorithm. The preset standard frequency-amplitude signal data when the flame state is normal is based on the sound wave data collected by M microphones in the data acquisition module when the flame cutting machine is in normal working condition, and is converted into a digital signal through an analog-to-digital converter. The digital signal is converted into frequency-amplitude signal data through Fourier transform.

[0045] A method for real-time monitoring of flame status of a cutting machine comprises the following steps:

[0046] S1: Collect the acoustic wave data of the flame cutting machine during operation;

[0047] S2: converting the acquired sound wave data of the flame cutting machine during operation into a continuous digital signal, and converting it into frequency-amplitude signal data through Fourier transform;

[0048] S3: By using the frequency-amplitude comparison algorithm, the current frequency-amplitude signal data is compared with the preset standard frequency-amplitude signal data when the flame state is normal, so as to monitor the flame state of the cutting machine in real time;

[0049] In step S1: the microphone is directed toward the cutting nozzle of the flame cutting machine to collect the acoustic wave data when the flame cutting machine is running, and outputs the simulated acoustic wave signal to accurately locate the sound source, thereby ensuring that the collected acoustic wave data comes from the key parts of the flame cutting process, improving the data collection accuracy, and being able to monitor in real time whether the flame state of the cutting machine is abnormal, and promptly discover and feedback the abnormal situation; reducing the influence of environmental noise and other interference signals, and enhancing the robustness and adaptability in complex environments.

[0050] In step S2: the collected acoustic wave data of the flame cutting machine during operation is converted into continuous digital signals, and these signals are subjected to Fourier transform to obtain an amplitude value sequence in the frequency domain, which is represented as an array X = {X1, X2, X3, ..., X n-1 , X n}, where array X represents the amplitude value sequence in the frequency domain, n represents the number of frequency domain components, and X n Represents the amplitude value of the nth frequency domain component.

[0051] In step S3: the current frequency-amplitude signal data is compared with the preset standard frequency-amplitude signal data when the flame state is normal through the frequency-amplitude comparison algorithm. The specific steps include:

[0052] S3-1: Calculate the standard deviation of each frequency signal data. The formula is as follows:

[0053]

[0054] Where n is the number of frequency sampling points, xi is the sampling value of a specific sampling point, represents the mean of the sampling points;

[0055] S3-2: Normalize each measured waveform array according to the standard deviation and mean, and the current frequency amplitude signal data X′ j The normalized calculation formula is as follows:

[0056]

[0057] The preset standard frequency signal data Y′ when the flame state is normal j The normalized calculation formula is as follows:

[0058]

[0059] Calculate the current frequency amplitude signal data X′ j The standard frequency signal data Y′ when the flame state is normal j The absolute distance D j , the formula is as follows:

[0060]

[0061] Where: j = 1, 2, 3, ..., m, μX j and μY j They are the frequency and amplitude signal data X j and Y j The mean of and They are the frequency and amplitude signal data X j and Y j The standard deviation of

[0062] S3-3: Introducing correction parameter k and absolute distance threshold r th , when the signal changes slightly, the absolute distance D at the current moment j Less than or equal to the absolute distance D at the previous moment j-1 ; Calculate the absolute distance D at the current moment j The absolute distance D from the previous moment j-1 The rate of change between them is calculated as follows:

[0063]

[0064] Calculate the threshold r th The formula is as follows:

[0065]

[0066] where j = k, k-1, ... 1, r threpresents the threshold of absolute distance, k represents the correction parameter, D j Indicates the distance between the current amplitude signal data and the preset standard amplitude signal data, D j-1 Indicates the distance between the amplitude signal data at the previous moment and the preset standard amplitude signal data;

[0067] When the signal changes greatly, the absolute distance D at the current moment j Greater than the absolute distance D at the previous moment j-1 , it is necessary to introduce a dynamic adjustment correction parameter k, dynamically adjust the frequency and amplitude signal data in the calculation process, dynamically adjust the correction parameters and the absolute distance threshold, which can adapt to different signal changes and improve the robustness and adaptability in complex environments.

[0068] S3-4: Calculate the current frequency and amplitude signal data X′ j The standard frequency signal data Y′ when the flame state is normal j The similarity coefficient P xy , the formula is as follows:

[0069]

[0070] Among them, C ov (X′ j ,Y′ j ) are the frequency and amplitude signal data X′ j and Y′ j covariance; D(X′ j ) and D(Y′ j ) are the frequency and amplitude signal data X′ j and Y′ j The variance of xy Analyze the correlation between two sets of frequency signal data: When |P xy |=0, indicating that the two are unrelated; when |P xy When |=1, it means that the two signals are completely identical, P xy The closer to 1, the stronger the correlation; when 0≤|P xy |<0.8, the cutting machine flame is judged to be in an abnormal state. xy |≤1, the flame of the cutting machine is judged to be normal. By comparing the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data through the frequency-amplitude comparison algorithm, the flame state can be monitored in real time and accurately to ensure that the abnormality of the flame state can be detected at the first time. By calculating the standard deviation and mean, the frequency-amplitude signal data is normalized to eliminate the deviation between different signal data. By introducing the dynamic adjustment correction parameter k and the absolute distance threshold r th,The system can adaptively adjust parameters according to the changes of real-time signals,,improving the adaptability under different signal change conditions.

[0071] In the embodiment, five MEMS microphones are placed in a Fibonacci array, and the sound wave signal data of the flame cutting machine is continuously received at a collection frequency of 10kHz when the flame cutting machine is working, and the simulated sound wave signal data is output. The standard frequency signal data Y=[0.5, 0.52, 0.51, 0.52, 0.5] when the flame state is normal is preset, and the flame state frequency signal data X at the current moment is collected. j =[0.45, 0.48, 0.47, 0.49, 0.46], the flame state frequency signal data X collected at the last moment j-1 =[0.48,0.52,0.51,0.53,0.50], data X at time j-2 j-2 =[0.48,0.52,0.50,0.52,0.50], data X at time j-3 j-3 =[0.48,0.51,0.49,0.52,0.49], data X at time j-4 j-4 =[0.47,0.50,0.48,0.51,0.48]; calculate the mean x of the standard frequency signal data = 0.51, standard deviation Calculate the currently collected frequency amplitude signal data X j The mean Standard deviation S = 0.016, calculate the frequency amplitude signal data X at the previous moment j-1 The mean Standard deviation S = 0.019, data X at time j-2 j-2 The mean Standard deviation S = 0.017, data X at time j-3 j-3 The mean Standard deviation S = 0.016, data X at time j-4 j-4 The mean Standard deviation S = 0.016; normalize the standard frequency signal data to obtain For the currently collected frequency amplitude signal data X j Normalization processing, using Get x′ j =[-1.25,0.63,0.00,1.25,-0.63], for the frequency amplitude signal data X at the previous moment j-1 Normalization processing, using Get x′ j-1 =[-1.65,0.71,0.18,1.29,-0.47],X j-2 Normalization

[0072] x′ j-2 =[-1.87,0.80,-0.53,0.80,-0.53],X j-3 Normalization x′ j-3 =[-1.29,0.86,-0.57,1.57,-0.57],X j-4 Normalize x′ j-4 =[-1.29,0.86,-0.57,1.57,-0.57];Use Calculate the absolute distance D at the current moment j =1.24, calculate the absolute distance D at the previous moment j-1 =1.94, absolute distance D at time j-2 j-2 =2.27, absolute distance D at time j-3 j-3 =2.00, absolute distance D at time j-4 j-4 =2.00; calculate the rate of change of the absolute distance between the current moment and the previous moment The absolute distance change rate between j-1 and j-2 is -0.145, the absolute distance change rate between j-2 and j-3 is 0.135, and the absolute distance change rate between j-3 and j-4 is 0.00; calculate the absolute distance threshold Compare the rate of change ΔD with the threshold r th , the signal changes little, and there is no need to introduce dynamic adjustment correction parameters to calculate X′ j and Y′ j The variance D(X′ j ) and D(Y′ j ), we get D(X′ j )=1.04,D(X′ j )=0.8, calculate the similarity coefficient According to the calculation results of similarity coefficient P xy ≈0.822, 0.8≤|P xy |≤1, it can be determined that the current cutting machine flame state is normal.

[0073] In another embodiment, five MEMS microphones are placed in a Fibonacci array to continuously receive the acoustic signal data of the flame cutting machine at work at a collection frequency of 10 kHz and output analog acoustic signal data. The standard frequency signal data Y = [0.5, 0.52, 0.51, 0.52, 0.5] when the flame state is normal is preset, and the flame state frequency signal data X at the current moment is collected. j =[0.60, 0.59, 0.62, 0.61, 0.60], the flame state frequency signal data X collected at the last moment j-1=[0.58,0.57,0.59,0.58,0.57], data X at time j-2 j-2 =[0.55,0.54,0.56,0.55,0.54], data X at time j-3 j-3 =[0.53,0.52,0.54,0.53,0.52], data X at time j-4 j-4 =[0.50,0.51,0.52,0.53,0.54]; calculate the mean x=0.51 of the standard frequency signal data, and the standard deviation Calculate the currently collected frequency amplitude signal data X j The mean Standard deviation S = 0.011, calculate the frequency amplitude signal data X at the previous moment j-1 The mean Standard deviation S = 0.0084, data X at time j-2 j-2 The mean Standard deviation S = 0.0084, data X at time j-3 j-3 The mean Standard deviation S = 0.0084, data X at time j-4 j-4 The mean Standard deviation S = 0.016; normalize the standard frequency signal data to obtain For the currently collected frequency amplitude signal data X j Normalization processing, using Get x′ j =[-0.36,-1.27,1.45,0.55,-0.36], for the frequency amplitude signal data X at the previous moment j-1 Normalization processing, using Get x′ j-1 =[0.24,-0.95,1.43,0.24,-0.95],X j-2 Normalization x′ j-2 =[0.24,-0.95,1.43,0.24,-0.95],X j-3 Normalization x′ j-3 =[0.24,-0.95,1.43,0.24,-0.95],X j-4 Normalize x′ j-4 =[-1.25,-0.625,0,0.625,1.25];Use Calculate the absolute distance D at the current moment j =5.45, calculate the absolute distance D at the previous moment j-1 =4.50, absolute distance D at time j-2 j-2 =5.27, absolute distance D at time j-3j-3 =4.17, absolute distance D at time j-4 j-4 =4.50; calculate the rate of change of the absolute distance between the current moment and the previous moment The absolute distance change rate between j-1 and j-2 is -0.146, the absolute distance change rate between j-2 and j-3 is 0.263, and the absolute distance change rate between j-3 and j-4 is -0.073; calculate the absolute distance threshold Compare the rate of change ΔD with the threshold r th , the signal changes greatly, and it is necessary to introduce a dynamic adjustment correction parameter k to calculate X′ j and Y′ j The variance D(X′ j ) and D(Y′ j ), we get D(X′ j )=0.85702,D(X′ j )=0.8, calculate the similarity coefficient According to the calculation results of similarity coefficient P xy ≈-0.0783, at 0≤|P xy |<0.8, so it can be determined that the current cutting machine flame state is abnormal. When the cutting machine flame state is detected to be abnormal.

[0074] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0075] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A real-time monitoring system for flame status of a cutting machine, characterized in that: The system comprises: a data acquisition module, an ADC module, a data processing module and a display module; the data acquisition module realizes the acquisition of data when the flame cutting machine is working through a microphone, and the microphone is used to acquire sound wave signal data and output analog sound wave signal data, and record the acoustic characteristics of the flame combustion process; the ADC module is used to convert the analog sound wave signal output by each microphone into a digital signal through an analog-to-digital converter, and the digital signal is converted into frequency-amplitude signal data through Fourier transform; the data processing module compares the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data when the flame state is normal through a frequency-amplitude comparison algorithm, so as to monitor whether the flame state is normal; the display module is used to display the current flame state of the cutting machine in real time, and provide a fault reminder when an abnormality is detected.

2. A cutting machine flame status real-time monitoring system according to claim 1, characterized in that: The data acquisition module includes M microphones, which are placed according to the layout of the Fibonacci wheel array, continuously receive the sound wave signal data of the flame cutting machine when it is working at a collection frequency of f Hz and output simulated sound wave signal data, wherein M represents the number of microphones used to collect sound wave signals.

3. A cutting machine flame status real-time monitoring system according to claim 1, characterized in that: The ADC module converts the analog sound wave signal output by the microphone into a digital signal, and performs Fourier transform on the digital signal to convert it into frequency-amplitude signal data.

4. A cutting machine flame status real-time monitoring system according to claim 1, characterized in that: The data processing module compares the current frequency-amplitude signal data with the preset standard frequency-amplitude signal data when the flame state is normal through a frequency-amplitude comparison algorithm. The preset standard frequency-amplitude signal data when the flame state is normal is based on the sound wave data collected by M microphones in the data acquisition module when the flame cutting machine is in normal working condition, and is converted into a digital signal through an analog-to-digital converter. The digital signal is converted into frequency-amplitude signal data through Fourier transform.

5. A method for real-time monitoring of flame status of a cutting machine, comprising the following steps: S1: Collect the acoustic wave data of the flame cutting machine during operation; S2: converting the acquired sound wave data of the flame cutting machine during operation into a continuous digital signal, and converting it into frequency-amplitude signal data through Fourier transform; S3: By using a frequency-amplitude comparison algorithm, the current frequency-amplitude signal data is compared with the preset standard frequency-amplitude signal data when the flame state is normal, so as to monitor the flame state of the cutting machine in real time.

6. A method for real-time monitoring of flame status of a cutting machine according to claim 5, characterized in that: In step S1: the microphone is directed toward the cutting nozzle of the flame cutting machine, collects the sound wave data when the flame cutting machine is running, and outputs a simulated sound wave signal.

7. A method for real-time monitoring of flame status of a cutting machine according to claim 5, characterized in that: In step S2: the collected acoustic wave data of the flame cutting machine during operation is converted into continuous digital signals, and these signals are subjected to Fourier transform to obtain an amplitude value sequence in the frequency domain, which is represented as an array X = {X1, X2, X3, ..., X n-1 , X n }, where array X represents the amplitude value sequence in the frequency domain, n represents the number of frequency domain components, and X n Represents the amplitude value of the nth frequency domain component.

8. A method for real-time monitoring of flame status of a cutting machine according to claim 5, characterized in that: In step S3: the current frequency-amplitude signal data is compared with the preset standard frequency-amplitude signal data when the flame state is normal through the frequency-amplitude comparison algorithm. The specific steps include: S3-1: Calculate the standard deviation of each frequency signal data. The formula is as follows: Where n is the number of frequency sampling points, x i is the sampling value of a specific sampling point, represents the mean of the sampling points; S3-2: Normalize each measured waveform array according to the standard deviation and mean. The current frequency and amplitude signal data X j The normalized calculation formula is as follows: The preset standard frequency signal data Y when the flame state is normal j The normalized calculation formula is as follows: Calculate the current frequency signal data X j ′ and the preset standard frequency signal data Y when the flame state is normal j The absolute distance D j , the formula is as follows: Where j = 1, 2, 3, ..., m, μX j and μY j They are the frequency and amplitude signal data X j and Y j The mean of and They are the frequency and amplitude signal data X j and Y j The standard deviation of S3-3: Introducing correction parameter k and absolute distance threshold r th , when the signal changes slightly, the absolute distance D at the current moment j Less than or equal to the absolute distance D at the previous moment j-1 , calculate the absolute distance D at the current moment j The absolute distance D from the previous moment j-1 The rate of change between them is calculated as follows: Calculate the threshold r th The formula is as follows: where j = k, k-1, ... 1, r th represents the threshold of absolute distance, k represents the correction parameter, D j Indicates the distance between the current amplitude signal data and the preset standard amplitude signal data, D j-1 Indicates the distance between the amplitude signal data at the previous moment and the preset standard amplitude signal data; When the signal changes greatly, the absolute distance D at the current moment j Greater than the absolute distance D at the previous moment j-1 , it is necessary to introduce a dynamic adjustment correction parameter k to dynamically adjust the frequency and amplitude signal data during the calculation process. S3-4: Calculate the current frequency and amplitude signal data X′ j The standard frequency signal data Y′ when the flame state is normal j The similarity coefficient P xy , the formula is as follows: Among them, C ov (X′ j ,Y′ j ) are the frequency and amplitude signal data X′ j and Y′ j covariance; D(X′ j ) and D(Y′ j ) are the frequency and amplitude signal data X′ j and Y′ j The variance of xy Analyze the correlation between two sets of frequency signal data: When |P xy |=0, indicating that the two are unrelated; when |P xy When |=1, it means that the two signals are completely identical, P xy The closer to 1, the stronger the correlation; when 0≤|P xy |<0.8, the cutting machine flame is judged to be in an abnormal state. xy When |≤1, the cutting machine flame is judged to be normal.

Images