On-line monitoring and analyzing system for magnetic variable measurement of unit

Abstract

The invention belongs to the technical field of unit electromagnetic monitoring, and particularly relates to a unit magnetic variable measurement on-line monitoring and analysis system, background noise is removed and weak electromagnetic signals are amplified through a filtering enhancement module, and the definition and identifiability of the signals are ensured; an environment interference elimination module is used for adjusting and eliminating influence of external mechanical electromagnetism according to known environment parameters, and interference of false signals is reduced; and the detection threshold is updated through the dynamic threshold setting module according to real-time data, so that the sensitivity to the change of the weak electromagnetic signal is improved, and the possibility of misjudgment is reduced. Through the improvement measures, the system can detect early fault signals more accurately, and real fault signals and false signals are effectively distinguished, so that the reliability and the maintenance efficiency of the system are improved, potential problems can be found in time, a maintenance plan is optimized, the service life of equipment is prolonged, and the shutdown risk is reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of electromagnetic monitoring of units, and in particular relates to an online monitoring and analysis system for measuring magnetic variables of units. Background Art

[0002] In the operation and management of modern industrial equipment, electromagnetic monitoring systems play a vital role. Traditional electromagnetic monitoring systems for units mainly use sensors to collect electromagnetic signals generated by electromechanical equipment during operation, and perform preliminary processing and analysis to evaluate the operating status of the equipment. However, the performance of these systems is often limited by the interference of background noise, the influence of external environmental factors, and the fixedness of detection thresholds.

[0003] Specifically, the existing technical solutions usually include the following aspects: Signal acquisition: Use electromagnetic sensors to capture the electromagnetic signals emitted by the equipment when it is running and convert them into electrical signals for preliminary processing.

[0004] Filtering: Basic filtering techniques are used to remove some noise, but it is difficult to effectively eliminate complex background noise, especially noise in weak signals.

[0005] Feature extraction: Extract key features from the processed signal for subsequent analysis.

[0006] Fault diagnosis: Compare the current signal with historical data based on a fixed threshold to determine whether a fault exists.

[0007] Although the above methods can meet the needs of daily monitoring to a certain extent, they face a significant technical problem in actual operation: how to accurately distinguish real fault signals from false signals. Since traditional systems lack dynamic adjustment mechanisms to adapt to changing working environments and conditions, they are less sensitive to changes in weak electromagnetic signals, which can easily lead to misjudgments or missed judgments, thus affecting the reliability and maintenance efficiency of the system. Summary of the invention

[0008] The purpose of the present invention is to provide an online monitoring and analysis system for measuring magnetic variables of a unit, which can not only detect early fault signals more accurately, but also effectively distinguish real fault signals from false signals, thereby improving the reliability and maintenance efficiency of the system. This helps to timely discover potential problems, optimize maintenance plans, extend the service life of equipment, and reduce the risk of downtime, so as to solve the problems raised in the above background technology.

[0009] To achieve the above object, the present invention adopts the following technical solution: a unit magnetic variable measurement online monitoring and analysis system, comprising: A signal acquisition module is used to collect electromagnetic signals of the unit; the signal acquisition module is connected to the filter enhancement module to remove background noise and amplify weak electromagnetic signals; The output of the filter enhancement module is connected to the feature extraction module for identifying and extracting key features in the electromagnetic signal; the feature extraction module is connected to the environmental interference elimination module for adjusting and eliminating the influence of external mechanical electromagnetics according to known environmental parameters; The environmental interference elimination module is connected to the dynamic threshold setting module to update the detection threshold according to real-time data; the dynamic threshold setting module is connected to the signal verification module to confirm the authenticity of the signal; The signal verification module is followed by the correlation analysis module, which determines the current signal status by comparing historical data; the correlation analysis module is connected to the early warning generation module, which immediately issues a warning once an abnormality is found.

[0010] Preferably, the signal acquisition module includes: The electromagnetic sensor submodule is used to sense the electromagnetic field of the unit and convert it into an electrical signal; The electromagnetic sensor submodule is connected to the signal preprocessing submodule for amplifying and preliminarily filtering the electrical signal; the signal preprocessing submodule is followed by the frequency selection submodule for screening useful frequency signals according to a preset frequency range; The frequency selection submodule is connected to the data standardization submodule to convert the frequency signal into a unified format for subsequent processing.

[0011] Preferably, the filtering enhancement module includes: The noise recognition submodule is used to detect and mark the background noise transmitted by the signal acquisition module; The noise identification submodule is connected to the dynamic filtering submodule and is used to adjust the filtering parameters according to the marking to remove the background noise; The dynamic filtering submodule is followed by a signal amplification submodule, which amplifies the filtered signal; the signal amplification submodule is connected to the signal optimization submodule, which optimizes the signal quality by adjusting the amplitude and frequency characteristics of the signal.

[0012] Preferably, the feature extraction module includes: The spectrum analysis submodule is used to convert the signal transmitted from the filtering enhancement module into a frequency domain representation; The spectrum analysis submodule is connected to the peak detection submodule, which is used to identify and mark significant peaks in the frequency domain signal; the peak detection submodule is followed by a feature selection submodule, which selects the parts related to the electromagnetic features from the peaks according to predefined rules; The feature selection submodule is connected to the feature quantization submodule to convert the selected features into numerical form for subsequent processing.

[0013] Preferably, the environmental interference elimination module includes: The environmental parameter input submodule is used to receive and process known environmental parameter data; the environmental parameter input submodule is connected to the interference identification submodule, and is used to analyze the characteristic signal transmitted by the characteristic extraction module and mark the part that can be affected by external mechanical electromagnetic influence; The interference identification submodule is followed by the interference compensation submodule, which adjusts the signal according to the marker to compensate for the external mechanical and electromagnetic effects; The interference compensation submodule is connected to the signal reconstruction submodule, which combines the compensated signal with the original signal to reconstruct a clean electromagnetic signal.

[0014] Preferably, the dynamic threshold setting module includes: A real-time data acquisition submodule, used to collect clean electromagnetic signals and current operating condition data from the environmental interference elimination module; The real-time data acquisition submodule is connected to the baseline calculation submodule and is used to calculate the baseline value under normal operating conditions based on the clean electromagnetic signal; The baseline calculation submodule is followed by the fluctuation analysis submodule, which analyzes the fluctuation range of the signal according to the baseline value and determines its upper and lower limits; the fluctuation analysis submodule is connected to the threshold update submodule, which compares the upper and lower limits with the existing detection threshold and updates them.

[0015] Preferably, the signal verification module includes: The threshold comparison submodule is used to compare the signal transmitted from the dynamic threshold setting module with the latest detection threshold; the threshold comparison submodule is connected to the abnormal marking submodule, and is used to mark the signal part exceeding the threshold range according to the comparison result; The abnormal marking submodule is followed by the pattern recognition submodule, which identifies possible real fault signals and false signals by analyzing the marked abnormal signal part; the pattern recognition submodule is connected to the signal confirmation submodule, which makes a final confirmation on the identified pattern to determine whether it is a real fault signal.

[0016] Preferably, the association analysis module includes: A historical data acquisition submodule, used to extract past data related to the signal confirmed by the signal verification module from the database; The historical data acquisition submodule is connected to the data alignment submodule, which is used to perform time alignment processing on the current signal and the historical data; the data alignment submodule is followed by the feature comparison submodule, which identifies abnormal patterns by comparing the feature differences between the current signal and the historical signal in the aligned data set; The feature comparison submodule is connected to the trend analysis submodule, and the changing trend of the signal is analyzed according to the feature difference to determine whether there is a potential fault.

[0017] Preferably, the warning generation module includes: The anomaly detection submodule is used to monitor the trend data output by the association analysis module and identify whether there are anomalies; The anomaly detection submodule is connected to the risk assessment submodule, which is used to calculate the risk level based on the identified anomalies; the risk assessment submodule is followed by the warning level setting submodule, which determines the corresponding warning level based on the risk level; The warning level setting submodule is connected to the notification sending submodule to send the warning information to the relevant users or systems according to the set level.

[0018] Preferably, it also includes: a comprehensive report module for summarizing information and providing users with detailed operating conditions and suggestions.

[0019] Technical effects and advantages of the present invention: Compared with the prior art, the online monitoring and analysis system for measuring magnetic variables of a unit proposed by the present invention has the following advantages: The present invention uses a filtering enhancement module to remove background noise and amplify weak electromagnetic signals to ensure signal clarity and recognizability; uses an environmental interference elimination module to adjust and eliminate the influence of external mechanical electromagnetics according to known environmental parameters to reduce the interference of false signals; and uses a dynamic threshold setting module to update the detection threshold according to real-time data to improve the sensitivity to changes in weak electromagnetic signals and reduce the possibility of misjudgment. These improvements enable the system to detect early fault signals more accurately and effectively distinguish between real fault signals and false signals, thereby improving the reliability and maintenance efficiency of the system, helping to promptly discover potential problems, optimize maintenance plans, extend the service life of equipment, and reduce the risk of downtime. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a block diagram of the electromagnetic online monitoring and analysis system of the unit of the present invention.

[0021] Figure 2 It is a block diagram of the electromagnetic online monitoring and analysis method of the unit of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the accompanying 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, rather than all the embodiments. The specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] The present invention provides Figure 1The online monitoring and analysis system for measuring magnetic variables of a unit shown in the figure includes: a signal acquisition module, a filtering enhancement module, a feature extraction module, an environmental interference elimination module, a dynamic threshold setting module, a signal verification module, a correlation analysis module and an early warning generation module. The interaction of each module enables the system to detect early fault signals more accurately and effectively distinguish between real fault signals and false signals, thereby improving the reliability and maintenance efficiency of the system, helping to timely discover potential problems, optimize maintenance plans, extend the service life of equipment, and reduce the risk of downtime, as follows:

[0024] Specifically, the signal acquisition module is used to collect electromagnetic signals of the unit; the signal acquisition module includes: The electromagnetic sensor submodule is used to sense the electromagnetics of the unit and convert them into electrical signals. This process converts physical electromagnetics into processable electrical signals, providing basic data for subsequent signal processing.

[0025] The electromagnetic sensor submodule is connected to the signal preprocessing submodule, which is used to amplify and preliminarily filter the electrical signal. The formula is Y=A*X+B, where X represents the input electrical signal, Y represents the output signal, A is the amplification factor, and B is the offset. By adjusting the amplification factor and offset, the useful signal can be enhanced and the noise interference can be reduced.

[0026] The signal preprocessing submodule is followed by the frequency selection submodule, which filters useful frequency signals according to the preset frequency range. The formula is F=(YC) / D, where F represents the filtered frequency signal, C is the noise parameter, and D is the adjustment parameter. It filters useful frequency signals according to the preset frequency range, removes unnecessary background noise and other interference signals, and further improves signal quality.

[0027] The frequency selection submodule is connected to the data standardization submodule to convert the frequency signal into a unified format for subsequent processing. The conversion formula is Z=(FE) / G, where Z is the standardized signal value, E is the standard parameter, and G is the quantitative parameter. Converting the frequency signal into a unified format for subsequent processing ensures that data from different sources can be compared and analyzed under the same standard, thereby improving the consistency and reliability of the data.

[0028] Through the design and collaboration of the electromagnetic sensor submodule, signal preprocessing submodule, frequency selection submodule and data standardization submodule, it is ensured that the signal acquisition module can efficiently and accurately collect and preliminarily process the electromagnetic signals of the unit, providing a high-quality data foundation for subsequent modules.

[0029] Assuming that there is a unit whose electromagnetic signal needs to be monitored, the specific steps are as follows: Electromagnetic sensor submodule: The electromagnetic sensor detects the electromagnetic of the unit and converts it into an electrical signal X. For example, assume that the detected initial electrical signal X is 0.5V.

[0030] Signal preprocessing submodule: The signal is amplified and preliminarily filtered. Assume that the amplification factor A is 2 and the offset B is -0.1V.

[0031] Use the formula Y=A*X+B to calculate: Y=2*0.5V-0.1V=1.0V-0.1V=0.9V; The output signal Y is 0.9V, which enhances the signal strength and eliminates the DC offset.

[0032] Frequency selection submodule: Filter useful frequency signals according to the preset frequency range. Assume that the noise parameter C is 0.2V and the adjustment parameter D is 1.5.

[0033] Use the formula F=(YC) / D to calculate: F=(0.9V-0.2V) / 1.5=0.7V / 1.5≈0.467V; The frequency signal F after screening is about 0.467V, and the background noise is removed.

[0034] Data normalization submodule: Convert the frequency signal to a uniform format. Assume that the standard parameter E is 0.1V and the quantization parameter G is 0.5.

[0035] Use the formula Z=(FE) / G to calculate: Z=(0.467V-0.1V) / 0.5=0.367V / 0.5=0.734; The signal value Z after standardization is 0.734, which enables the signal to be subsequently processed and analyzed under a unified standard.

[0036] Through the above steps, the signal acquisition module can efficiently and accurately collect and preliminarily process the electromagnetic signals of the unit, providing a high-quality data foundation for subsequent modules.

[0037] Specifically, the signal acquisition module is connected to the filtering enhancement module to remove background noise and amplify weak electromagnetic signals; the filtering enhancement module includes: The noise recognition submodule is used to detect and mark the background noise transmitted by the signal acquisition module; this process can identify the specific location and intensity of the background noise, providing a basis for subsequent filtering processing.

[0038] The noise identification submodule is connected to the dynamic filtering submodule, which is used to adjust the filtering parameters according to the mark to remove the background noise. The formula is N=H*(SP), where N represents the filtered signal, S is the input signal, P is the noise parameter, and H is the filtering coefficient; the filtering parameters are adjusted according to the mark to remove the background noise, ensuring that the signal does not contain unnecessary interference components, thereby improving the clarity and recognizability of the signal.

[0039] The dynamic filtering submodule is followed by the signal amplification submodule, which amplifies the filtered signal. The formula is Amp=K*N+L, where Amp represents the amplified signal, K is the amplification factor, and L is the offset. The filtered signal is amplified to enhance the strength of the useful signal, making it easier to be processed and analyzed by subsequent modules.

[0040] The signal amplification submodule is connected to the signal optimization submodule, which optimizes the signal quality by adjusting the amplitude and frequency characteristics of the signal. The formula is Opt=(Amp-M) / Q, where Opt represents the optimized signal, M is the optimization parameter, and Q is the weight. By adjusting the amplitude and frequency characteristics of the signal to optimize the signal quality, the reliability and consistency of the signal are further improved to ensure that it is suitable for subsequent feature extraction and fault diagnosis.

[0041] Through the design and collaboration of the noise identification submodule, dynamic filtering submodule, signal amplification submodule and signal optimization submodule, it is ensured that the filtering enhancement module can effectively remove background noise and amplify weak electromagnetic signals, thereby improving the accuracy and reliability of subsequent analysis.

[0042] Assume that there is an electromagnetic signal that has been preliminarily processed and needs to be further filtered and enhanced. The specific steps are as follows: Noise identification submodule: Detect and mark the background noise transmitted by the signal acquisition module. Assume that the input signal S is 1.2V and the noise parameter P is 0.3V.

[0043] Dynamic filter submodule: Adjust the filter parameters according to the markers to remove background noise. Assume the filter coefficient H is 0.8.

[0044] Use the formula N=H*(SP) to calculate: N=0.8*(1.2V-0.3V)=0.8*0.9V=0.72V; The signal N after filtering is 0.72V, and the influence of background noise is removed.

[0045] Signal amplification submodule: Amplify the filtered signal, assuming that the amplification factor K is 1.5 and the offset L is -0.1V.

[0046] Use the formula Amp=K*N+L to calculate: Amp=1.5*0.72V-0.1V=1.08V-0.1V=0.98V; The amplified signal Amp is 0.98V, which enhances the signal strength.

[0047] Signal optimization submodule: Adjust the amplitude and frequency characteristics of the signal to optimize the signal quality. Assume that the optimization parameter M is 0.2V and the weight Q is 0.6.

[0048] Use the formula Opt = (Amp-M) / Q to calculate: Opt=(0.98V-0.2V) / 0.6=0.78V / 0.6=1.3V; The optimized signal Opt is about 1.3V, which further improves the signal quality and reliability.

[0049] Through the above steps, the filtering enhancement module can effectively remove background noise and amplify weak electromagnetic signals to ensure signal clarity and reliability.

[0050] Specifically, the output of the filtering enhancement module is connected to the feature extraction module for identifying and extracting key features in the electromagnetic signal; the feature extraction module includes: The spectrum analysis submodule is used to convert the signal transmitted from the filter enhancement module into a frequency domain representation; through frequency domain analysis, the frequency components in the signal can be more clearly identified, which is convenient for subsequent feature extraction.

[0051] The spectrum analysis submodule is connected to the peak detection submodule to identify and mark significant peaks in the frequency domain signal. The formula is Peak=max(Freq), where Peak represents the peak value and Freq is the input frequency domain signal. These peaks are usually related to specific electromagnetic modes of the equipment and help to detect potential faults.

[0052] The peak detection submodule is followed by the feature selection submodule, which selects the parts related to the electromagnetic features from the peak according to predefined rules. The formula is Sel=select(Peak,Rule), where Sel represents the selected features and Rule is the selection rule. This step can screen out the most representative features and reduce the interference of irrelevant information.

[0053] The feature selection submodule is connected to the feature quantization submodule to convert the selected features into numerical form for subsequent processing. The formula is Quant=quantize(Sel,Param), where Quant represents the quantized feature value and Param is the quantization parameter. Through quantization processing, the data can be made more standardized and easier to compare, improving the accuracy and consistency of subsequent analysis.

[0054] Through the design and collaboration of spectrum analysis submodule, peak detection submodule, feature selection submodule and feature quantification submodule, it is ensured that the feature extraction module can effectively identify and extract important features in electromagnetic signals, providing reliable data support for subsequent fault diagnosis.

[0055] Assume that there is an electromagnetic signal that needs to be feature extracted after filtering and enhancement. The specific steps are as follows: Spectrum analysis submodule: The signal transmitted from the filter enhancement module is converted into a frequency domain representation. Assuming that the input signal is a time domain signal, after Fourier transform, the frequency domain signal Freq is obtained, and its value is [0.1, 0.5, 1.2, 0.8, 0.3].

[0056] Peak detection submodule: Identify and mark significant peaks in the frequency domain signal. Use the formula Peak=max(Freq) for calculation: Peak=max([0.1,0.5,1.2,0.8,0.3])=1.2; A significant peak is marked at 1.2, which is the highest point in the frequency domain signal.

[0057] Feature selection submodule: Select the part related to electromagnetic characteristics from the peak according to the predefined rules. Assume that the selection rule is to select all peaks greater than or equal to 1.0: Sel=select([0.1,0.5,1.2,0.8,0.3],Rule)=[1.2]; The feature picked out is 1.2, which is a significant peak that complies with the rule.

[0058] Feature quantization submodule: Convert the selected features into numerical form for subsequent processing. Assume that the quantization parameter Param is 0.1: Quant=quantize([1.2],0.1)=12; The quantized eigenvalue is 12, which standardizes the feature data and facilitates subsequent analysis and comparison.

[0059] Specifically, the feature extraction module is connected to the environmental interference elimination module, which is used to adjust and eliminate the influence of external mechanical and electromagnetic according to known environmental parameters; the environmental interference elimination module includes: The environmental parameter input submodule is used to receive and process known environmental parameter data; these environmental parameters include temperature, humidity, external electromagnetic, etc., providing a reference for subsequent interference identification.

[0060] The environmental parameter input submodule is connected to the interference identification submodule, which is used to analyze the characteristic signal transmitted by the feature extraction module and mark the parts that may be affected by external mechanical and electromagnetic influences. The formula is Int=detect(Feat,Env), where Int represents the marked interference part, Feat is the input characteristic signal, and Env is the environmental parameter; this step can identify which signal parts are affected by environmental interference for subsequent compensation.

[0061] The interference identification submodule is followed by the interference compensation submodule, which adjusts the signal according to the mark to compensate for the influence of external mechanical electromagnetic. The formula is Comp=adjust(Int,V), where Comp represents the compensated signal and V is the compensation coefficient. The signal is adjusted by the compensation coefficient to remove or weaken the interference component and restore the original state of the signal.

[0062] The interference compensation submodule is connected to the signal reconstruction submodule, which combines the compensated signal with the original signal to reconstruct a clean electromagnetic signal. The formula is Rec=combine(Feat,Comp,W), where Rec represents the reconstructed signal and W is the reconstruction weight. This step ensures that the final output signal is a high-quality signal after interference elimination and compensation processing, which is convenient for subsequent fault diagnosis.

[0063] Through the design and collaboration of the environmental parameter input submodule, interference identification submodule, interference compensation submodule and signal reconstruction submodule, it is ensured that the environmental interference elimination module can effectively adjust and eliminate the influence of external mechanical electromagnetics on electromagnetic signals according to known environmental parameters, thereby improving the accuracy and reliability of fault diagnosis.

[0064] Assume that there is an electromagnetic signal that needs to be processed after feature extraction and environmental interference elimination. The specific steps are as follows: Environmental parameter input submodule: Receive and process known environmental parameter data. Assume that the environmental parameters Env include temperature 25°C and humidity 60%, and the external mechanical electromagnetic frequency range is 50-100Hz.

[0065] Interference identification submodule: Analyze the characteristic signal transmitted by the feature extraction module and mark the part that may be affected by external mechanical electromagnetic. Assume that the input characteristic signal Feat is [0.8, 1.2, 1.5, 0.9, 1.1], and some of the signals are in the range of 50-100Hz.

[0066] Use the formula Int=detect(Feat,Env) to calculate: Assume that the detected interference part is [1.2,1.5], that is, the signal in the range of 50-100Hz.

[0067] The marked interference part Int is [1.2,1.5].

[0068] Interference compensation submodule: Adjust the signal according to the marker to compensate for the external mechanical and electromagnetic influence. Assume that the compensation coefficient V is 0.7.

[0069] Use the formula Comp=adjust(Int,V) to calculate: Comp=adjust([1.2,1.5],0.7)=[1.2*0.7,1.5*0.7]=[0.84,1.05] The compensated signal Comp is [0.84,1.05].

[0070] Signal reconstruction submodule: The compensated signal is combined with the original signal to reconstruct a clean electromagnetic signal. Assume that the reconstruction weight W is 0.5.

[0071] Use the formula Rec=combine(Feat,Comp,W) to calculate: Rec=combine([0.8,1.2,1.5,0.9,1.1],[0.84,1.05],0.5); The combination method can be weighted average or other methods. Here, it is assumed that the interference part is simply replaced: Rec=[0.8,0.84,1.05,0.9,1.1]; The final reconstructed signal Rec is [0.8, 0.84, 1.05, 0.9, 1.1].

[0072] Specifically, the environmental interference elimination module is connected to the dynamic threshold setting module, and is used to update the detection threshold according to real-time data; the dynamic threshold setting module includes: The real-time data acquisition submodule is used to collect clean electromagnetic signals and current operating condition data from the environmental interference elimination module; this step ensures that the system can obtain the latest, processed, high-quality signals, providing a basis for subsequent analysis.

[0073] The real-time data acquisition submodule is connected to the baseline calculation submodule, which is used to calculate the baseline value under normal operating conditions based on the clean electromagnetic signal. The formula is Base=avg(Clean), where Base represents the baseline value and Clean is the input clean electromagnetic signal. By calculating the average value, the standard signal level of the equipment during normal operation is determined, providing a reference benchmark for subsequent fluctuation analysis.

[0074] The baseline calculation submodule is followed by the fluctuation analysis submodule, which analyzes the fluctuation range of the signal according to the baseline value and determines its upper and lower limits. The formula is Lim=Base±D*std(Clean), where Lim represents the upper and lower limits, std(Clean) is the standard deviation of the signal, and D is the fluctuation coefficient. The standard deviation and fluctuation coefficient are used to calculate a reasonable fluctuation range to help identify abnormal signals.

[0075] The fluctuation analysis submodule is connected to the threshold update submodule, which compares the upper and lower limits with the existing detection threshold and updates them. The formula is NewThresh=update(OldThresh,Lim), where NewThresh represents the new detection threshold and OldThresh is the old detection threshold. The detection threshold is adjusted according to the new fluctuation range to ensure that the system can respond to slight changes in a timely manner and improve the accuracy of fault diagnosis.

[0076] Through the design and collaboration of the real-time data acquisition submodule, baseline calculation submodule, fluctuation analysis submodule and threshold update submodule, it is ensured that the dynamic threshold setting module can accurately update the detection threshold based on real-time data, thereby improving the sensitivity to changes in weak electromagnetic signals, reducing misjudgment problems, and enhancing the reliability and adaptability of the system.

[0077] Assume that there is an electromagnetic signal that needs to be dynamically thresholded after environmental interference elimination. The specific steps are as follows: Real-time data acquisition submodule: Collect the clean electromagnetic signal and current working condition data from the environmental interference elimination module. Assume that the clean electromagnetic signal Clean is [0.8, 0.9, 1.0, 1.1, 1.2], and the current working condition data includes temperature 25°C and humidity 60%.

[0078] Baseline calculation submodule: Calculate the baseline value under normal operating conditions based on the clean electromagnetic signal. Use the formula Base=avg(Clean) for calculation: Base=avg([0.8,0.9,1.0,1.1,1.2])=(0.8+0.9+1.0+1.1+1.2) / 5=1.0; The baseline value Base is 1.0.

[0079] Fluctuation analysis submodule: Analyze the fluctuation range of the signal based on the baseline value and determine its upper and lower limits. Assuming the fluctuation coefficient D is 2, first calculate the standard deviation: std(Clean)=sqrt(((0.8-1.0)^2+(0.9-1.0)^2+(1.0-1.0)^2+(1.1-1.0)^2+(1.2-1.0)^2) / 5)≈0.1414; Use the formula Lim=Base±D*std(Clean) to calculate: Lim=1.0±2*0.1414=[1.0-0.2828,1.0+0.2828]=[0.7172,1.2828]; The upper and lower limits Lim are [0.7172,1.2828].

[0080] Threshold update submodule: Compare the upper and lower limits with the existing detection threshold and update them. Assume that the old detection threshold OldThresh is [0.6, 1.4].

[0081] Use the formula NewThresh=update(OldThresh,Lim) to calculate: NewThresh=[max(0.6,0.7172),min(1.4,1.2828)]=[0.7172,1.2828]; The new detection threshold NewThresh is [0.7172, 1.2828].

[0082] Specifically, the dynamic threshold setting module is connected to the signal verification module to confirm the authenticity of the signal; the signal verification module includes: The threshold comparison submodule is used to compare the signal transmitted from the dynamic threshold setting module with the latest detection threshold; this step can identify which parts of the signal are beyond the normal range, providing a basis for further analysis.

[0083] The threshold comparison submodule is connected to the abnormal marking submodule, which is used to mark the signal part that exceeds the threshold range according to the comparison result. The formula is Mark=mark(Signal,NewThresh), where Mark represents the marked abnormal signal part, Signal is the input signal, and NewThresh is the new detection threshold. By marking the abnormal signal part, it can be clarified which signals need further analysis and processing.

[0084] The abnormal marking submodule is followed by the pattern recognition submodule, which identifies possible real fault signals and false signals by analyzing the marked abnormal signal part. The formula is Pat=recognize(Mark,Rule), where Pat represents the recognized pattern and Rule is the recognition rule. This step can distinguish between real fault signals and false signals caused by noise or other interference.

[0085] The pattern recognition submodule is connected to the signal confirmation submodule to make a final confirmation on the recognized pattern to determine whether it is a real fault signal. The formula is Conf=confirm(Pat,ConfParam), where Conf represents the result of the confirmation and ConfParam is the confirmation parameter. The final confirmation ensures that the system can accurately identify the fault and take corresponding measures.

[0086] Through the design and collaboration of the threshold comparison submodule, the abnormal marking submodule, the pattern recognition submodule and the signal confirmation submodule, it is ensured that the signal verification module can effectively confirm the authenticity of the signal, reduce false alarms caused by system noise or external interference, and improve the accuracy and reliability of fault diagnosis.

[0087] Assume that there is an electromagnetic signal that needs to be verified after dynamic threshold setting. The specific steps are as follows: Threshold comparison submodule: Compare the signal transmitted by the dynamic threshold setting module with the latest detection threshold. Assume that the input signal Signal is [0.75, 1.0, 1.3, 1.1, 1.2] and the new detection threshold NewThresh is [0.7172, 1.2828].

[0088] Use the formula Mark=mark(Signal,NewThresh) to calculate: Compare each signal value to the detection threshold range [0.7172, 1.2828]: 0.75 is within the range; 1.0 is within the range; 1.3 Exceeding the upper limit; 1.1 Within the scope; 1.2 Within the scope; The marked abnormal signal part Mark is [1.3].

[0089] Exception marking submodule: According to the comparison results, the signal part that exceeds the threshold range is marked. The marked abnormal signal part has been determined as [1.3].

[0090] Pattern recognition submodule: By analyzing the marked abnormal signal part, possible real fault signals and false signals are identified. Assume that the identification rule Rule includes checking the frequency and amplitude changes of the signal: Assume that in further analysis it is found that the signal of 1.3 is a false signal due to external mechanical electromagnetics.

[0091] Use the formula Pat=recognize(Mark,Rule) to calculate: Pat=recognize([1.3],Rule)="FalseAlarm"; The identified pattern Pat is "FalseAlarm".

[0092] Signal confirmation submodule: Perform final confirmation on the identified pattern to determine whether it is a real fault signal. Assume that the confirmation parameter ConfParam includes historical data and context information: Suppose historical data shows that similar signals have been false alarms in the past.

[0093] Use the formula Conf=confirm(Pat,ConfParam) to calculate: Conf=confirm("FalseAlarm",ConfParam)=False; The final confirmed result Conf is False (false alarm).

[0094] The signal verification module is followed by the correlation analysis module, which determines the current signal status by comparing historical data; the correlation analysis module includes: The historical data acquisition submodule is used to extract past data related to the signal confirmed by the signal verification module from the database; by acquiring historical data, background information can be provided for the current signal to facilitate subsequent comparison and analysis.

[0095] The historical data acquisition submodule is connected to the data alignment submodule, which is used to perform time alignment processing on the current signal and the historical data. The formula is Align=align(Conf,Hist), where Align represents the aligned data set, Conf is the result confirmed by the signal verification module, and Hist is the historical data. Through the alignment processing, it is ensured that data from different time periods can be compared on the same time basis, thereby improving the accuracy of the analysis.

[0096] The data alignment submodule is followed by the feature comparison submodule, which identifies abnormal patterns by comparing the feature differences between the current signal and the historical signal in the aligned data set. The formula is Diff=diff(Align,CharParam), where Diff represents the feature difference and CharParam is the feature parameter. This step can detect abnormal changes in the current signal and compare it with historical data to identify potential problems.

[0097] The feature comparison submodule is connected to the trend analysis submodule. It analyzes the change trend of the signal based on the feature difference and determines whether there is a potential fault. The formula is Trend=trend(Diff,TrendParam), where Trend represents the change trend and TrendParam is the trend coefficient. By analyzing the trend, the possible future development direction can be predicted, potential faults can be discovered in advance, and measures can be taken.

[0098] Through the design and collaboration of the historical data acquisition submodule, data alignment submodule, feature comparison submodule and trend analysis submodule, it is ensured that the correlation analysis module can effectively compare historical data and judge the current signal status, thereby improving the system's sensitivity to early faults and being able to accumulate and utilize historical data to optimize diagnostic results in long-term operation.

[0099] Assume that there is an electromagnetic signal that needs to be correlated after signal verification processing. The specific steps are as follows: Historical data acquisition submodule: Extract the past data related to the signal confirmed by the signal verification module from the database. Assume that the result Conf confirmed by the signal verification module is [0.75, 1.0, 1.3, 1.1, 1.2]; The historical data Hist includes the daily electromagnetic signal values ​​in the past month: Hist=[[0.72,0.98,1.05,1.08,1.1],[0.73,0.99,1.06,1.09,1.12],...]; Data alignment submodule: Time-align the current signal with the historical data. Assuming the timestamp alignment method is used: Use the formula Align=align(Conf,Hist) to calculate: Align=[[0.75,1.0,1.3,1.1,1.2],[0.72,0.98,1.05,1.08,1.1],[0.73,0.99,1.06,1.09,1.12],...]; The aligned dataset Align contains the time alignment results of the current signal and all historical data.

[0100] Feature comparison submodule: By comparing the feature differences between the current signal and the historical signal in the aligned data set, abnormal patterns can be identified. Assume that the feature parameter CharParam includes statistics such as mean and standard deviation: Calculate the characteristic parameters for each data set: Current signal characteristics: mean 1.06, standard deviation 0.21; Historical data characteristics (average): mean 1.0, standard deviation 0.18; Use the formula Diff=diff(Align,CharParam) to calculate: Diff=[1.06-1.0,0.21-0.18]=[0.06,0.03]; The feature difference Diff is [0.06, 0.03], indicating that the mean and standard deviation of the current signal are slightly higher than the historical average.

[0101] Trend analysis submodule: Analyze the change trend of the signal based on the characteristic difference to determine whether there is a potential fault. Assume that the trend coefficient TrendParam includes the slope and the change rate: Analyze the trend of data in the past month: Assuming the slope is positive and the rate of change is increasing Use the formula Trend=trend(Diff,TrendParam) to calculate: Trend = "Increasing"; The change trend Trend is "Increasing", indicating that the current signal shows a gradually increasing trend, and there may be a potential fault.

[0102] Specifically, the correlation analysis module is connected to the early warning generation module, and once an abnormality is found, a warning is immediately issued. The early warning generation module includes: The anomaly detection submodule is used to monitor the trend data output by the association analysis module and identify whether there are anomalies. This step can detect abnormal changes in the signal in a timely manner and provide a basis for subsequent risk assessment.

[0103] The anomaly detection submodule is connected to the risk assessment submodule, which is used to calculate the risk level based on the identified anomalies. The formula is Risk=eval(Trend,RiskParam), where Risk represents the risk level, Trend is the trend data, and RiskParam is the evaluation parameter. By evaluating the parameters, the severity of the anomaly is quantified and the measures to be taken are determined.

[0104] The risk assessment submodule is followed by the warning level setting submodule, which determines the corresponding warning level according to the risk level. The formula is WarnLevel=set(Risk,LevelParam), where WarnLevel represents the warning level and LevelParam is the level parameter. By setting different warning levels, it is ensured that the system can take appropriate response measures according to different degrees of severity.

[0105] The warning level setting submodule is connected to the notification sending submodule, and the warning information is sent to the relevant users or systems according to the set level. The formula is Notify=notify(WarnLevel,UserParam), where Notify represents the notification sent and UserParam is the identifier of the receiving user or system. This step ensures that relevant personnel can receive the warning information in time and take corresponding actions.

[0106] Through the design and collaboration of the anomaly detection submodule, risk assessment submodule, warning level setting submodule and notification sending submodule, it is ensured that the early warning generation module can immediately issue a warning when an anomaly is found, improve the response speed to potential faults, and take appropriate measures according to different severities to avoid unnecessary downtime and losses.

[0107] Assume that there is an electromagnetic signal trend data after correlation analysis that needs to be used for early warning generation. The specific steps are as follows: Anomaly detection submodule: Monitor the trend data output by the association analysis module to identify whether there is anomaly. Assume that the trend data Trend is "Increasing".

[0108] Assuming that the threshold is set so that trend data exceeding the normal range is considered abnormal, the current trend "Increasing" is identified as abnormal.

[0109] Risk Assessment Submodule: Calculate the risk level based on the identified anomalies. Assume that the evaluation parameter RiskParam includes the trend change rate, amplitude, etc.: The current trend rate of change is 0.05 units / day and the amplitude is 0.06.

[0110] Use the formula Risk=eval(Trend,RiskParam) to calculate: Risk=eval("Increasing",[0.05,0.06]); Assume that the calculated risk level Risk is 3 (medium risk).

[0111] Warning level setting submodule: Determine the corresponding warning level according to the risk level. Assume that the level parameter LevelParam defines the warning level corresponding to different risk levels: Risk level 1-2 corresponds to low-level warning (WarningLevel1); Risk level 3-4 corresponds to intermediate warning (WarningLevel2); Risk level 5 and above corresponds to advanced warning (WarningLevel3); Use the formula WarnLevel=set(Risk,LevelParam) to calculate: WarnLevel=set(3,LevelParam)=WarningLevel2; The warning level WarnLevel is a medium warning (WarningLevel2).

[0112] Notification sending submodule: Send warning information to relevant users or systems according to the set level. Assume that the receiving user or system identification UserParam includes Engineer A, Engineer B and System Administrator: Use the formula Notify=notify(WarnLevel,UserParam) to calculate: Notify=notify(WarningLevel2,[Engineer A, Engineer B, System Administrator]) The content of the notification sent is: The electromagnetic signal of the current equipment is showing a gradual increase, and there is a medium risk. Please check the status of the equipment. (Sent to Engineer A, Engineer B and system administrator); In another embodiment, the above-mentioned unit electromagnetic online monitoring analysis and fault diagnosis system further includes: a comprehensive report module for information aggregation, for providing users with detailed operating conditions and suggestions; the comprehensive report module includes: The data integration submodule is used to summarize the warning information and other relevant data from the early warning generation module; this step ensures that the system can centrally process all relevant information and provide comprehensive data support for subsequent evaluation and prediction.

[0113] The data integration submodule is connected to the status assessment submodule, which is used to assess the overall operating status of the current unit based on the summarized data. The formula is State=assess(Data,AssessParam), where State represents the overall operating status, Data is the summarized data, and AssessParam is the assessment standard. The assessment standard is used to quantify the health status of the unit and help users understand the actual operation of the equipment.

[0114] The state assessment submodule is followed by the trend prediction submodule, which analyzes possible future development trends based on the overall operating status. The formula is Pred=predict(State,PredParam), where Pred represents the development trend and PredParam is the prediction parameter. Through the prediction parameters, the future operating status of the equipment is predicted, potential problems are discovered in advance, and preventive measures are taken.

[0115] The trend prediction submodule is connected to the suggestion generation submodule, which proposes specific suggestions for maintenance and improvement based on the development trend. The formula is Sugg=suggest(Pred,SuggParam), where Sugg represents the proposed suggestion and SuggParam is the suggestion rule. Through the suggestion rules, specific maintenance and improvement suggestions are given to help users optimize equipment management.

[0116] Through the design and collaboration of the data integration submodule, status assessment submodule, trend prediction submodule and suggestion generation submodule, it is ensured that the comprehensive report module can effectively provide users with detailed operating conditions and specific suggestions, which not only improves the transparency and operability of the system, but also helps users better understand and manage the health status of the equipment. This helps to timely discover and solve problems, optimize maintenance plans, and extend the service life of equipment.

[0117] Assume that there is an electromagnetic signal data processed by the early warning generation module that needs to be used to generate a comprehensive report. The specific steps are as follows: Data integration submodule: Summarize the warning information and other relevant data from the warning generation module. Assume that the summarized data includes the following: Warning information: medium risk (WarningLevel2); Current electromagnetic signal: [0.75, 1.0, 1.3, 1.1, 1.2]; Historical data average: 1.0; Standard deviation of historical data: 0.18; Status assessment submodule: Evaluate the overall operating status of the current unit based on the summarized data. Assume that the evaluation criteria AssessParam include electromagnetic amplitude, change rate, etc.: Use the formula State=assess(Data,AssessParam) to calculate: State = assess([Medium Risk,[0.75,1.0,1.3,1.1,1.2],1.0,0.18],[Electromagnetic Amplitude,Rate of Change]); Assume that the calculated overall operating state State is "ModerateConcern".

[0118] Trend forecast submodule: Analyze the possible future development trend based on the overall operation status. Assume that the prediction parameter PredParam includes historical trends, change rates, etc.: Use the formula Pred=predict(State,PredParam) to calculate: Pred = predict("ModerateConcern",[historical trend, rate of change]); Assume that the calculated development trend Pred is "IncreasingRisk".

[0119] It is recommended to generate submodules: Make specific suggestions for maintenance and improvement based on development trends. Assume that the suggestion rule SuggParam includes inspection frequency, maintenance measures, etc.: Use the formula Sugg=suggest(Pred,SuggParam) to calculate: Sugg = suggest("IncreasingRisk", [Inspection Frequency, Maintenance Measures]); Assume the suggestion is: Increase inspection frequency to conduct equipment inspections every two weeks.

[0120] Arrange professional personnel to carry out comprehensive maintenance on the equipment, focusing on checking the electromagnetic sensors and their connecting lines.

[0121] In summary, the present invention removes background noise and amplifies weak electromagnetic signals through a filtering enhancement module to ensure signal clarity and identifiability; uses an environmental interference elimination module to adjust and eliminate the influence of external mechanical electromagnetics according to known environmental parameters to reduce the interference of false signals; and uses a dynamic threshold setting module to update the detection threshold according to real-time data to improve sensitivity to changes in weak electromagnetic signals and reduce the possibility of misjudgment.

[0122] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. 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.

Claims

1. A unit magnetic variable measurement online monitoring and analysis system, characterized in that: include: Signal acquisition module, used to collect electromagnetic signals of the unit; The signal acquisition module is connected to the filter enhancement module to remove background noise and amplify weak electromagnetic signals; The output of the filter enhancement module is connected to the feature extraction module for identifying and extracting key features in the electromagnetic signal; The feature extraction module is connected to the environmental interference elimination module, and is used to adjust and eliminate the influence of external mechanical and electromagnetic according to known environmental parameters; The environmental interference elimination module is connected to the dynamic threshold setting module to update the detection threshold according to real-time data; the dynamic threshold setting module is connected to the signal verification module to confirm the authenticity of the signal; The signal verification module is followed by the correlation analysis module, which determines the current signal status by comparing historical data; the correlation analysis module is connected to the early warning generation module, which immediately issues a warning once an abnormality is found.

2. According to claim 1, a unit magnetic variable measurement online monitoring and analysis system is characterized in that: The signal acquisition module includes: The electromagnetic sensor submodule is used to sense the electromagnetic field of the unit and convert it into an electrical signal; The electromagnetic sensor submodule is connected to the signal preprocessing submodule for amplifying and preliminarily filtering the electrical signal; the signal preprocessing submodule is followed by the frequency selection submodule for screening useful frequency signals according to a preset frequency range; The frequency selection submodule is connected to the data standardization submodule to convert the frequency signal into a unified format for subsequent processing.

3. A unit magnetic variable measurement online monitoring and analysis system according to claim 2, characterized in that: The filter enhancement module includes: The noise recognition submodule is used to detect and mark the background noise transmitted by the signal acquisition module; The noise identification submodule is connected to the dynamic filtering submodule and is used to adjust the filtering parameters according to the marking to remove the background noise; The dynamic filtering submodule is followed by a signal amplification submodule, which amplifies the filtered signal; the signal amplification submodule is connected to the signal optimization submodule, which optimizes the signal quality by adjusting the amplitude and frequency characteristics of the signal.

4. A unit magnetic variable measurement online monitoring and analysis system according to claim 3, characterized in that: The feature extraction module includes: The spectrum analysis submodule is used to convert the signal transmitted from the filtering enhancement module into a frequency domain representation; The spectrum analysis submodule is connected to the peak detection submodule, which is used to identify and mark significant peaks in the frequency domain signal; the peak detection submodule is followed by a feature selection submodule, which selects the parts related to the electromagnetic features from the peaks according to predefined rules; The feature selection submodule is connected to the feature quantization submodule to convert the selected features into numerical form for subsequent processing.

5. A unit magnetic variable measurement online monitoring and analysis system according to claim 4, characterized in that: The environmental interference elimination module includes: The environmental parameter input submodule is used to receive and process known environmental parameter data; the environmental parameter input submodule is connected to the interference identification submodule, and is used to analyze the characteristic signal transmitted by the characteristic extraction module and mark the part that can be affected by external mechanical electromagnetic influence; The interference identification submodule is followed by the interference compensation submodule, which adjusts the signal according to the marker to compensate for the external mechanical and electromagnetic effects; The interference compensation submodule is connected to the signal reconstruction submodule, which combines the compensated signal with the original signal to reconstruct a clean electromagnetic signal.

6. A unit magnetic variable measurement online monitoring and analysis system according to claim 5, characterized in that: The dynamic threshold setting module includes: A real-time data acquisition submodule, used to collect clean electromagnetic signals and current operating condition data from the environmental interference elimination module; The real-time data acquisition submodule is connected to the baseline calculation submodule and is used to calculate the baseline value under normal operating conditions based on the clean electromagnetic signal; The baseline calculation submodule is followed by the fluctuation analysis submodule, which analyzes the fluctuation range of the signal according to the baseline value and determines its upper and lower limits; the fluctuation analysis submodule is connected to the threshold update submodule, which compares the upper and lower limits with the existing detection threshold and updates them.

7. A unit magnetic variable measurement online monitoring and analysis system according to claim 6, characterized in that: The signal verification module includes: The threshold comparison submodule is used to compare the signal transmitted from the dynamic threshold setting module with the latest detection threshold; the threshold comparison submodule is connected to the abnormal marking submodule, and is used to mark the signal part exceeding the threshold range according to the comparison result; The abnormal marking submodule is followed by the pattern recognition submodule, which identifies possible real fault signals and false signals by analyzing the marked abnormal signal part; the pattern recognition submodule is connected to the signal confirmation submodule, which makes a final confirmation on the identified pattern to determine whether it is a real fault signal.

8. A unit magnetic variable measurement online monitoring and analysis system according to claim 7, characterized in that: The association analysis module includes: A historical data acquisition submodule, used to extract past data related to the signal confirmed by the signal verification module from the database; The historical data acquisition submodule is connected to the data alignment submodule, which is used to perform time alignment processing on the current signal and the historical data; the data alignment submodule is followed by the feature comparison submodule, which identifies abnormal patterns by comparing the feature differences between the current signal and the historical signal in the aligned data set; The feature comparison submodule is connected to the trend analysis submodule, and the changing trend of the signal is analyzed according to the feature difference to determine whether there is a potential fault.

9. A unit magnetic variable measurement online monitoring and analysis system according to claim 8, characterized in that: The warning generation module includes: The anomaly detection submodule is used to monitor the trend data output by the association analysis module and identify whether there are anomalies; The anomaly detection submodule is connected to the risk assessment submodule, which is used to calculate the risk level based on the identified anomalies; the risk assessment submodule is followed by the warning level setting submodule, which determines the corresponding warning level based on the risk level; The warning level setting submodule is connected to the notification sending submodule to send the warning information to the relevant users or systems according to the set level.

10. A unit magnetic variable measurement online monitoring and analysis system according to claim 1, characterized in that: Also includes: The comprehensive report module is used to summarize information and provide users with detailed operating conditions and suggestions.

Images