Real-time signal processing early warning method

Abstract

The invention discloses a real-time signal processing early warning method, and relates to the technical field of adaptive signal processing, and the early warning method specifically comprises the following steps: installing a vibration sensor at a bearing pedestal and a housing of a motor, and ensuring that the x direction of the sensor is aligned with the operation direction of equipment; then the driver is calibrated to ensure the accuracy of subsequent data acquisition; the method comprises the following steps: setting acquisition interval time in data acquisition as 5-10S, and performing normalization preprocessing on data acquired by a vibration sensor, and has the advantages that time domain and frequency domain analysis is performed on a vibration signal, a time domain signal is converted into a frequency domain signal by using fast Fourier transform (FFT), and the amplitude of each frequency point is calculated, so that the accuracy of the data acquisition is improved, and the accuracy of the data acquisition is improved. The fusion processing mode can provide deeper understanding of motor vibration characteristics, effectively reveals energy distribution of signals on different frequency components, and is helpful for identifying potential faults or abnormal conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive signal processing, and in particular to a real-time signal processing early warning method. Background Art

[0002] With the continuous development of technologies such as artificial intelligence, big data and the Internet of Things, signal processing technology is also continuously improving. Traditional signal processing methods can no longer meet the real-time, accuracy and efficiency requirements of modern applications. Therefore, real-time signal processing and early warning methods have emerged. They combine the latest algorithms and hardware technologies to achieve fast and accurate signal processing and timely warning. Real-time signal processing and early warning methods are widely used in various fields, such as industrial monitoring, security monitoring, traffic management, climate change monitoring, etc. These fields have extremely high requirements for the real-time and accuracy of signals, which has promoted the development of real-time signal processing and early warning methods.

[0003] However, the existing early warning processing methods mostly use high-performance processors and optimized algorithms to quickly process and analyze the real-time collected signals, extract key features from the signals, and compare them with preset thresholds or models to achieve early warning of potential risks. However, this early warning method does not have adaptive capabilities when faced with characteristics that may have dynamic changes, such as real-time changes in parameters such as frequency, amplitude, and phase, and cannot adjust processing parameters in real time to adapt to signal changes. For this reason, we propose a real-time signal processing early warning method. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time signal processing early warning method.

[0005] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: a real-time signal processing early warning method, the early warning method specifically comprises the following steps:

[0006] Step 1: Install the vibration sensor on the bearing seat and housing of the motor, and ensure that the x-direction of the sensor is aligned with the direction of operation of the equipment, and then calibrate the actuator to ensure the accuracy of subsequent data collection;

[0007] Step 2: Set the data collection interval to 5-10 seconds, and normalize the data collected by the vibration sensor to make signals of different magnitudes comparable, thereby improving the accuracy and stability of subsequent processing;

[0008] Step 3: Under normal operation of the motor, collect vibration signals for a period of time, then convert the collected vibration signals, convert the time domain signals into frequency domain signals, and calculate the amplitude of each frequency point and display it in the form of a line graph. The calculation formula is: Where x(K) is the frequency domain signal, x(n) is the time domain signal, N is the signal length, and k represents the frequency index;

[0009] Step 4: Calculate the mean deviation and variance of the vibration signal amplitude. The mean is the average value of the signal and can reflect the overall level of the signal, while the variance measures the degree of deviation between the sample value and the mean. That is, the larger the variance, the higher the degree of dispersion and the greater the difference between the signal value and its mean.

[0010] Step 5: Extract the amplitude of each frequency point calculated in step 3 and name the feature |b|, and pass Formula to calculate the Poisson kernel Pb(e it ), and further through the formula Calculate the normalized Poisson kernel Pb(e it );

[0011] Step 6: Further analyze the characteristics of the normalized Poisson kernel, such as its changes over time and its values ​​at different frequencies. These frequencies can reflect the characteristics of the motor vibration signal. When the Poisson kernel changes significantly at a certain frequency, it means that the motor has abnormal vibration at this frequency.

[0012] Step 7: Calculate the value range of the normalized Poisson kernel in the normal state and take the mean plus or minus a certain multiple of the standard deviation as the threshold range, and set an abnormal threshold The normalized Poisson kernel value calculated in real time is compared with the set abnormal threshold. When the Poisson kernel value exceeds the abnormal threshold range, the early warning mechanism is triggered;

[0013] Step eight, the early warning mechanism can communicate with the outside through the wireless communication module. When the early warning mechanism is triggered, the controller will start the buzzer alarm to sound a buzzer alarm and the warning light will flash alternately to remind the on-site staff. At the same time, the abnormal information will be transmitted to the email address of the relevant personnel through network communication.

[0014] As a further solution of the present invention: the normalization processing mentioned in step 2 includes but is not limited to deep cleaning of the data to ensure the accuracy and consistency of the data, and we fine-tune the collection interval to between 5 and 10 seconds to improve the accuracy of data measurement and reserve sufficient calculation time for subsequent calculation processes.

[0015] As a further solution of the present invention: the conversion process mentioned in the step three is the process of converting the initially collected vibration signal and its conversion from time domain to frequency domain. The vibration signal initially collected by the vibration sensor exists in the time domain form, that is, these signals describe the change law of vibration over time, and in order to more deeply analyze the vibration characteristics of the motor, these time domain signals are converted into frequency domain signals to reveal the energy distribution of the signal in different frequency components. In this conversion process, we adopted the fast Fourier transform (FFT) algorithm, and through FFT conversion, we obtained the amplitude information of each frequency point. These amplitudes directly reflect the vibration intensity of the motor at this frequency, and provide an important data basis for subsequent detailed analysis and processing.

[0016] As a further solution of the present invention: the mean and variance calculation formulas mentioned in step 4 are respectively and The mean value U indicates the average level of the motor vibration signal over a period of time. It is obtained by summing the vibration signal values ​​x(n) of the sampling points and then dividing it by the total number of sampling points N. This value can reflect the overall trend of the motor vibration, while the variance a 2 It is obtained by calculating the square of the difference between the vibration signal value x(n) of each sampling point and U, then summing these square differences and finally dividing by the total number of sampling points N.

[0017] As a further solution of the present invention: in the step five, it is necessary to extract the amplitude characteristics of each frequency point calculated in the step three, and calculate it using the Poisson kernel calculation formula.

[0018] As a further solution of the present invention: in step six, by drawing a curve chart showing the change of the Poisson kernel over time, we can intuitively observe the stability or volatility of the vibration signal in different time periods, and its values ​​at different frequencies also reflect the intensity distribution of the motor vibration signal at different frequencies.

[0019] As a further solution of the present invention: the abnormal threshold K designed in step 7 is obtained by , and k is 1.5, that is, the value range of the normalized Poisson kernel under normal conditions is calculated, and the standard deviation of its mean plus or minus 1.5 times is taken as the upper and lower limits of the threshold range.

[0020] As a further solution of the present invention: the early warning mechanism mentioned in step 8 also communicates with the outside through a wireless communication module. It can transmit the abnormal information to the email box of the relevant personnel through network communication, so that they can obtain the abnormal information and process it in the first time. This remote communication method not only improves the response speed, but also expands the scope of information transmission, so that more people can participate in the abnormal processing.

[0021] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0022] 1. The present invention performs time domain and frequency domain analysis on the vibration signal, converts the time domain signal into a frequency domain signal using the fast Fourier transform (FFT), and calculates the amplitude of each frequency point. This fusion processing method can provide a deeper understanding of the vibration characteristics of the motor, effectively reveal the energy distribution of the signal at different frequency components, and help identify potential faults or abnormal conditions. In addition, the Poisson kernel is used to analyze the vibration signal of the motor. By calculating the Poisson kernel and analyzing its normalized characteristics, such as changes over time and values ​​at different frequencies, the abnormal vibration of the motor at a specific frequency can be captured more keenly, providing a new method and idea for motor fault monitoring, thereby increasing a certain degree of adaptive capability;

[0023] 2. The present invention fully considers the distribution of data by calculating the value range of the normalized Poisson kernel under normal conditions and taking the mean plus or minus 1.5 times the standard deviation as the threshold range. It can more reliably determine whether the motor has abnormal vibration. The method of adding or subtracting the standard deviation of the mean can effectively filter out some normal fluctuations and only issues warnings for situations that exceed a reasonable range, thereby greatly increasing the reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the method steps in an embodiment of the present invention;

[0025] Figure 2 Schematic diagram of the conversion process in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0027] Example 1, please refer to the attached Figure 1 -Attached Figure 2 The present invention provides a technical solution: the early warning method specifically comprises the following steps:

[0028] Step 1: Install the vibration sensor on the bearing seat and housing of the motor, and ensure that the x-direction of the sensor is aligned with the direction of operation of the equipment, and then calibrate the actuator to ensure the accuracy of subsequent data collection;

[0029] Step 2: Set the data collection interval to 5-10 seconds, and perform normalization preprocessing on the data collected by the vibration sensor to make signals of different magnitudes comparable, thereby improving the accuracy and stability of subsequent processing;

[0030] Step 3: Under normal operation of the motor, collect vibration signals for a period of time, then convert the collected vibration signals, convert the time domain signals into frequency domain signals, and calculate the amplitude of each frequency point and display it in the form of a line graph. The calculation formula is: Where x(K) is the frequency domain signal, x(n) is the time domain signal, N is the signal length, and k represents the frequency index;

[0031] Step 4: Calculate the mean deviation and variance of the vibration signal amplitude. The mean is the average value of the signal and can reflect the overall level of the signal, while the variance measures the degree of deviation between the sample value and the mean. That is, the larger the variance, the higher the degree of dispersion and the greater the difference between the signal value and its mean.

[0032] Step 5: Extract the amplitude of each frequency point calculated in step 3 and name the feature |b|, and pass Formula to calculate the Poisson kernel Pb(e it ), and further through the formula Calculate the normalized Poisson kernel Pb(e it );

[0033] Step 6: Further analyze the characteristics of the normalized Poisson kernel, such as its changes over time and its values ​​at different frequencies. These frequencies can reflect the characteristics of the motor vibration signal. When the Poisson kernel changes significantly at a certain frequency, it means that the motor has abnormal vibration at this frequency.

[0034] Step 7: Calculate the value range of the normalized Poisson kernel in the normal state and take the mean plus or minus a certain multiple of the standard deviation as the threshold range, and set an abnormal threshold The normalized Poisson kernel value calculated in real time is compared with the set abnormal threshold. When the Poisson kernel value exceeds the abnormal threshold range, the early warning mechanism is triggered;

[0035] Step eight, the early warning mechanism can communicate with the outside through the wireless communication module. When the early warning mechanism is triggered, the controller will start the buzzer alarm to sound a buzzer alarm and the warning light will flash alternately to remind the on-site staff. At the same time, the abnormal information will be transmitted to the email address of the relevant personnel through network communication.

[0036] Please see attached Figure 1 -Attached Figure 2 ,The normalization processing mentioned in step 2 includes but is not limited to deep cleaning of the data to ensure the accuracy and consistency of the data, and we fine-tune the collection interval to between 5-10S, aiming to improve the accuracy of data measurement and reserve sufficient calculation time for the subsequent calculation process. The conversion process mentioned in step 3 is the conversion process of the initially collected vibration signal and its conversion from time domain to frequency domain. The vibration signal initially collected by the vibration sensor exists in the form of time domain, that is, these signals describe the law of vibration change over time, and in order to more deeply analyze the vibration characteristics of the motor, these time domain signals are converted into frequency domain signals to reveal the energy distribution of the signal at different frequency components. In this conversion process, we use the fast Fourier transform (FFT) algorithm, and through FFT conversion, we obtain the amplitude information of each frequency point, which directly reflects the vibration intensity of the motor at this frequency, and provides an important data basis for subsequent detailed analysis and processing. The mean and variance calculation formulas mentioned in step 4 are respectively and The mean value U indicates the average level of the motor vibration signal over a period of time. It is obtained by summing the vibration signal values ​​x(n) of the sampling points and then dividing it by the total number of sampling points N. This value can reflect the overall trend of the motor vibration, while the variance a 2 It is obtained by calculating the square of the difference between the vibration signal value x(n) of each sampling point and U, then summing these square differences and finally dividing by the total number of sampling points N;

[0037] In this embodiment, the calculation of the mean value U can be used to compare the vibration levels of different time periods or different motors to understand the changes in the motor operating state, while the variance a 2It reflects the stability of motor vibration. The larger the variance, the higher the instability of motor vibration, which may mean that there is a potential fault or abnormality in the motor. That is, a larger variance indicates that the fluctuation of the motor vibration signal is large, that is, the difference between the value of each sampling point and the mean is large; if the variance is small, it means that the motor vibration signal is relatively stable, and the value of each sampling point is close to the mean. In step three, the time domain vibration signal collected under normal operation of the motor is converted, and the frequency domain signal is obtained by using the FFT algorithm. Specifically, these amplitude data are substituted into the Poisson kernel calculation formula as input parameters, and the Poisson kernel is calculated using these amplitude data. The calculated Poisson kernel value is further used for subsequent normalization processing, which provides more representative and comparable data for analyzing the characteristics of the motor vibration signal and judging whether there is abnormal vibration. In general, the frequency point amplitude data calculated in step three is an important basis and foundation for calculating the Poisson kernel in step five. They play a key role in connecting the upper and lower parts of the entire early warning method process. Through precise mathematical calculations and data transmission, the process of motor vibration signal from simple amplitude measurement to more in-depth feature analysis and abnormal judgment is realized.

[0038] When in use, the vibration signal is analyzed in the time domain and frequency domain, the time domain signal is converted into a frequency domain signal using the fast Fourier transform (FFT), and the amplitude of each frequency point is calculated. This fusion processing method can provide a deeper understanding of the vibration characteristics of the motor, effectively reveal the energy distribution of the signal in different frequency components, and help identify potential faults or abnormal conditions. In addition, the Poisson kernel is used to analyze the motor vibration signal. By calculating the Poisson kernel and analyzing its normalized characteristics, such as changes over time and values ​​at different frequencies, the abnormal vibration of the motor at a specific frequency can be captured more sensitively, providing a new method and idea for motor fault monitoring, thereby increasing a certain degree of adaptive capability.

[0039] Example 2, please refer to the attached Figure 1 -Attached Figure 2 The present invention provides a technical solution: the early warning method specifically comprises the following steps:

[0040] Step 1: Install the vibration sensor on the bearing seat and housing of the motor, and ensure that the x-direction of the sensor is aligned with the direction of operation of the equipment, and then calibrate the actuator to ensure the accuracy of subsequent data collection;

[0041] Step 2: Set the data collection interval to 5-10 seconds, and perform normalization preprocessing on the data collected by the vibration sensor to make signals of different magnitudes comparable, thereby improving the accuracy and stability of subsequent processing;

[0042] Step 3: Under normal operation of the motor, collect vibration signals for a period of time, then convert the collected vibration signals, convert the time domain signals into frequency domain signals, and calculate the amplitude of each frequency point and display it in the form of a line graph. The calculation formula is: Where x(K) is the frequency domain signal, x(n) is the time domain signal, N is the signal length, and k represents the frequency index;

[0043] Step 4: Calculate the mean deviation and variance of the vibration signal amplitude. The mean is the average value of the signal and can reflect the overall level of the signal, while the variance measures the degree of deviation between the sample value and the mean. That is, the larger the variance, the higher the degree of dispersion and the greater the difference between the signal value and its mean.

[0044] Step 5: Extract the amplitude of each frequency point calculated in step 3 and name the feature |b|, and pass Formula to calculate the Poisson kernel Pb(e it ), and further through the formula Calculate the normalized Poisson kernel Pb(e it );

[0045] Step 6: Further analyze the characteristics of the normalized Poisson kernel, such as its changes over time and its values ​​at different frequencies. These frequencies can reflect the characteristics of the motor vibration signal. When the Poisson kernel changes significantly at a certain frequency, it means that the motor has abnormal vibration at this frequency.

[0046] Step 7: Calculate the value range of the normalized Poisson kernel in the normal state and take the mean plus or minus a certain multiple of the standard deviation as the threshold range, and set an abnormal threshold The normalized Poisson kernel value calculated in real time is compared with the set abnormal threshold. When the Poisson kernel value exceeds the abnormal threshold range, the early warning mechanism is triggered;

[0047] Step eight, the early warning mechanism can communicate with the outside through the wireless communication module. When the early warning mechanism is triggered, the controller will start the buzzer alarm to sound a buzzer alarm and the warning light will flash alternately to remind the on-site staff. At the same time, the abnormal information will be transmitted to the email address of the relevant personnel through network communication.

[0048] Please see attached Figure 1 -Attached Figure 2In step 5, the amplitude characteristics of each frequency point calculated in step 3 need to be extracted and calculated using the Poisson kernel calculation formula. In step 6, a curve chart of the Poisson kernel changing with time needs to be drawn. We can intuitively observe the stability or volatility of the vibration signal in different time periods, and its values ​​at different frequencies also reflect the intensity distribution of the motor vibration signal at different frequencies. The abnormal threshold K designed in step 7 is obtained by the mean , and k is 1.5, that is, the value range of the normalized Poisson kernel under normal conditions is calculated, and the standard deviation of the mean plus or minus 1.5 times is taken as the upper and lower limits of the threshold range. The early warning mechanism mentioned in step eight also communicates with the outside through the wireless communication module. It can transmit abnormal information to the email addresses of relevant personnel through network communication, so that they can obtain the abnormal information and process it in the first time. This remote communication method not only improves the response speed, but also expands the scope of information transmission, allowing more people to participate in abnormal processing;

[0049] In this embodiment, the abnormal threshold is K, and the Poisson kernel Pb(e it ) and K are compared by comparing the normalized Poisson kernel value calculated in real time with the preset abnormal threshold range. If the normalized Poisson kernel value is greater than the upper threshold limit or less than the lower threshold limit, that is, it exceeds the abnormal threshold range, this indicates that the motor may have an abnormal situation under the current vibration state. For example, when the value of the Poisson kernel at a certain frequency exceeds the normal range, according to the analysis of step six, it means that the motor may have abnormal vibration at this frequency. If the normalized Poisson kernel value is within the abnormal threshold range, it means that the current vibration state of the motor is within the normal range. Real-time monitoring and data processing continue. When it is found that the Poisson kernel value exceeds the abnormal threshold range, When the warning mechanism is triggered, according to step eight, the wireless communication module communicates with the outside, the controller starts the buzzer alarm to sound a buzzer alarm, and the warning light emits an alternating flashing light source to remind the on-site staff. At the same time, the abnormal information is transmitted to the email address of the relevant personnel through network communication in a timely manner, so that the relevant personnel can quickly take measures to troubleshoot and deal with the fault. Even after the warning is triggered, it is still necessary to continue to monitor the vibration of the motor and record the data, so as to conduct a more in-depth analysis and diagnosis of the fault later. At the same time, the early warning mechanism and the setting of the abnormal threshold can be optimized and adjusted according to the actual situation to improve the accuracy and reliability of the early warning.

[0050] When in use, the value range of the normalized Poisson kernel under normal conditions is calculated, and the mean plus or minus 1.5 times the standard deviation is taken as the threshold range to fully consider the distribution of the data. It can more reliably determine whether the motor has abnormal vibration, and the method of adding or subtracting the standard deviation of the mean can effectively filter out some normal fluctuations and only issue warnings for situations that exceed a reasonable range, thereby greatly increasing the reliability of the system.

[0051] Working principle:

[0052] First, install the vibration sensor on the bearing seat and casing of the motor. Make sure that the x direction of the sensor is strictly aligned with the direction of the equipment operation. Only when the sensor is correctly installed can the vibration of the motor be accurately captured. After the installation is completed, calibrate the sensor to eliminate possible errors and ensure the accuracy of subsequent data collection. Set the interval time of data collection to 5-10S. This time interval can ensure that enough data points are collected to reflect the vibration characteristics of the motor, and will not generate too much data to cause processing difficulties. At the same time, the data collected by the vibration sensor is normalized and preprocessed, including but not limited to deep cleaning data, to ensure the accuracy and consistency of the data. Then, under the normal operation of the motor, collect the vibration signal for a period of time. Then, use the fast Fourier transform (FFT) algorithm to convert the collected time domain vibration signal into a frequency domain signal to reveal the energy distribution of the signal at different frequency components. The amplitude of each frequency point is calculated and displayed in the form of a line graph. These amplitudes directly reflect the vibration intensity of the motor at different frequencies, providing an important data basis for subsequent analysis. According to the mean and variance calculation formulas, the mean U and variance a of the vibration signal amplitude are calculated respectively. 2 The mean reflects the average level of the motor vibration signal over a period of time. It is obtained by summing the vibration signal values ​​x(n) of the sampling points and dividing them by the total number of sampling points N. The variance measures the degree of deviation between the sample value and the mean. It is obtained by calculating the square of the difference between the vibration signal value x(n) of each sampling point and the mean U, then summing these square differences and finally dividing them by the total number of sampling points N. The amplitude characteristics of each frequency point calculated in step 3 are extracted and the Poisson kernel Pb(e it ), and further calculate the normalized Poisson kernel Pb(e it), draw a curve chart of the change of Poisson kernel over time, observe the stability or volatility of the vibration signal in different time periods, and analyze the values ​​of Poisson kernel at different frequencies to understand the intensity distribution of the motor vibration signal at different frequencies. When the Poisson kernel changes greatly at a certain frequency, it means that the motor may have abnormal vibration at this frequency. Calculate the value range of the normalized Poisson kernel under normal conditions, take the standard deviation of its mean plus or minus 1.5 times as the upper and lower limits of the threshold range, set the abnormal threshold K, and compare the normalized Poisson kernel value calculated in real time with the set abnormal threshold. Once it exceeds the abnormal threshold range, the early warning mechanism will be triggered. When the early warning mechanism is triggered, it communicates with the outside through the wireless communication module, the controller starts the buzzer alarm to sound a buzzer alarm, and the warning light emits an alternating flashing light source to remind the on-site staff. At the same time, the abnormal information is transmitted to the email address of the relevant personnel through network communication so that they can obtain the abnormal information and process it in the first time.

[0053] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0054] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0055] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A real-time signal processing early warning method, characterized in that: The early warning method specifically comprises the following steps: Step 1: Install the vibration sensor on the bearing seat and housing of the motor, and ensure that the x-direction of the sensor is aligned with the direction of operation of the equipment, and then calibrate the actuator to ensure the accuracy of subsequent data collection; Step 2: Set the data collection interval to 5-10 seconds, and normalize the data collected by the vibration sensor to make signals of different magnitudes comparable, thereby improving the accuracy and stability of subsequent processing; Step 3: Under normal operation of the motor, collect vibration signals for a period of time, then convert the collected vibration signals, convert the time domain signals into frequency domain signals, and calculate the amplitude of each frequency point and display it in the form of a line graph. The calculation formula is: Where x(K) is the frequency domain signal, x(n) is the time domain signal, N is the signal length, and k represents the frequency index; Step 4: Calculate the mean deviation and variance of the vibration signal amplitude. The mean is the average value of the signal and can reflect the overall level of the signal, while the variance measures the degree of deviation between the sample value and the mean. That is, the larger the variance, the higher the degree of dispersion and the greater the difference between the signal value and its mean. Step 5: Extract the amplitude of each frequency point calculated in step 3 and name the feature |b|, and use Pb Formula to calculate the Poisson kernel Pb(e it ), and further through the formula Calculate the normalized Poisson kernel Pb(e it ); Step 6: Further analyze the characteristics of the normalized Poisson kernel, such as its changes over time and its values ​​at different frequencies. These frequencies can reflect the characteristics of the motor vibration signal. When the Poisson kernel changes significantly at a certain frequency, it means that the motor has abnormal vibration at this frequency. Step 7: Calculate the value range of the normalized Poisson kernel in the normal state and take the mean plus or minus a certain multiple of the standard deviation as the threshold range, and set an abnormal threshold The normalized Poisson kernel value calculated in real time is compared with the set abnormal threshold. When the Poisson kernel value exceeds the abnormal threshold range, the early warning mechanism is triggered; Step eight, the early warning mechanism can communicate with the outside through the wireless communication module. When the early warning mechanism is triggered, the controller will start the buzzer alarm to sound a buzzer alarm and the warning light will flash alternately to remind the on-site staff. At the same time, the abnormal information will be transmitted to the email address of the relevant personnel through network communication.

2. A real-time signal processing early warning method according to claim 1, characterized in that: The normalization process mentioned in step 2 includes but is not limited to deep cleaning of the data to ensure the accuracy and consistency of the data, and we fine-tune the collection interval to between 5 and 10 seconds to improve the accuracy of data measurement and reserve sufficient computing time for subsequent calculation processes.

3. A real-time signal processing early warning method according to claim 1, characterized in that: The conversion process mentioned in the step three is the process of converting the initially collected vibration signal and its conversion from time domain to frequency domain. The vibration signal initially collected by the vibration sensor exists in the time domain, that is, these signals describe the change law of vibration over time. In order to more deeply analyze the vibration characteristics of the motor, these time domain signals are converted into frequency domain signals to reveal the energy distribution of the signal in different frequency components. In this conversion process, we use the fast Fourier transform (FFT) algorithm, and through FFT conversion, we obtain the amplitude information of each frequency point. These amplitudes directly reflect the vibration intensity of the motor at this frequency and provide an important data basis for subsequent detailed analysis and processing.

4. A real-time signal processing early warning method according to claim 1, characterized in that: The mean and variance calculation formulas mentioned in step 4 are: and The mean value U indicates the average level of the motor vibration signal over a period of time. It is obtained by summing the vibration signal values ​​x(n) of the sampling points and then dividing it by the total number of sampling points N. This value can reflect the overall trend of the motor vibration, while the variance a 2 It is obtained by calculating the square of the difference between the vibration signal value x(n) of each sampling point and U, then summing these square differences and finally dividing by the total number of sampling points N.

5. A real-time signal processing early warning method according to claim 1, characterized in that: In the step five, the amplitude characteristics of each frequency point calculated in the step three need to be extracted and calculated using the Poisson kernel calculation formula.

6. A real-time signal processing early warning method according to claim 1, characterized in that: In step six, a curve graph of the Poisson kernel changing with time is drawn. We can intuitively observe the stability or volatility of the vibration signal in different time periods, and its values ​​at different frequencies also reflect the intensity distribution of the motor vibration signal at different frequencies.

7. A real-time signal processing early warning method according to claim 1, characterized in that: The abnormal threshold K designed in step 7 is calculated by the mean U-standard deviation Mean U + standard deviation , and k is 1.5, that is, the value range of the normalized Poisson kernel under normal conditions is calculated, and the standard deviation of its mean plus or minus 1.5 times is taken as the upper and lower limits of the threshold range.

8. A real-time signal processing early warning method according to claim 1, characterized in that: The early warning mechanism mentioned in the step eight also communicates with the outside through a wireless communication module, which can transmit the abnormal information to the email box of relevant personnel through network communication so that they can obtain the abnormal information and process it in the first time. This remote communication method not only improves the response speed, but also expands the scope of information transmission, allowing more people to participate in abnormal processing.

Images