Rope breakage early warning system and method based on acoustic emission signal analysis

Abstract

The invention discloses a rope breakage early warning system based on acoustic emission signal analysis. The rope breakage early warning system comprises an acoustic emission sensor module used for collecting acoustic emission signals of a rope; the signal preprocessing module is used for filtering and denoising the collected acoustic emission signals; the acoustic emission mode decomposition module is used for decomposing the acoustic emission signal into a plurality of mode components; the modal energy spectrum analysis module is used for quantifying the energy of each modal component and judging the breakage risk of the rope; the environment parameter acquisition module is used for acquiring transportation environment parameters; the dynamic threshold value adjusting module is used for dynamically adjusting the risk threshold value according to the environment parameters; the acoustic emission feature matching algorithm module is used for matching acoustic emission features, triggering early warning and providing fracture position information; the early warning output module is used for outputting early warning information and providing a specific fracture position; the invention further discloses a rope breakage early warning method based on acoustic emission signal analysis. According to the rope breakage early warning method based on acoustic emission signal analysis, early warning can be conducted in time before breakage occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment transportation safety, and in particular to a rope breakage early warning system and method based on acoustic emission signal analysis. Background Art

[0002] Rope breakage is a serious safety hazard during the transportation of large electrical equipment. Traditional breakage detection methods, such as visual inspection, cannot provide early warning before a break occurs and are susceptible to interference from environmental factors. Existing vibration detection methods, while capable of detecting rope vibration signals, cannot effectively distinguish between normal vibration and precursor signals of breakage. Therefore, a technology that can monitor rope status in real time and provide timely warnings before a break occurs is urgently needed. Summary of the Invention

[0003] To solve the problems existing in the prior art, the purpose of the present invention is to provide an early warning system and method for rope breakage based on acoustic emission signal analysis. The present invention is used to monitor the acoustic emission signals of the rope in real time and provide timely warning before breakage occurs.

[0004] To achieve the above objectives, the present invention adopts a technical solution: an early warning system for rope breakage based on acoustic emission signal analysis, comprising:

[0005] Acoustic emission sensor module: used to collect the acoustic emission signal of the rope;

[0006] Signal preprocessing module: used to filter and denoise the collected acoustic emission signals;

[0007] Acoustic emission modal decomposition module: used to decompose the acoustic emission signal into multiple modal components;

[0008] Modal energy spectrum analysis module: used to quantify the energy of each modal component and determine the risk of rope breakage;

[0009] Environmental parameter collection module: used to collect transportation environmental parameters;

[0010] Dynamic threshold adjustment module: used to dynamically adjust risk thresholds based on environmental parameters;

[0011] Acoustic emission feature matching algorithm module: used to match acoustic emission features, trigger early warning and provide fracture location information;

[0012] Warning output module: used to output warning information and provide specific fracture locations.

[0013] The present invention also provides a rope breakage early warning method based on acoustic emission signal analysis, comprising the following steps:

[0014] Step 1: Collecting acoustic emission signals of power equipment during transportation;

[0015] Step 2: Preprocessing the collected acoustic emission signals;

[0016] Step 3: Perform modal decomposition on the preprocessed signal;

[0017] Step 4: Perform modal energy spectrum analysis on the modal decomposition signal to identify modal components with abnormal energy and determine whether there is a risk of rope breakage;

[0018] Step 5: Collect environmental parameters during transportation;

[0019] Step 6: Dynamically adjust the risk threshold of rope breakage based on the collected environmental parameters;

[0020] Step 7: Use the acoustic emission feature matching algorithm to calculate the similarity between the eigenvector of the abnormal modal component and the reference eigenvector. When the similarity is greater than the dynamically adjusted risk threshold, trigger an early warning and output the fracture location information.

[0021] As a further improvement of the present invention, the step 1 specifically includes the following steps:

[0022] Step 1.1: Install a high-sensitivity acoustic emission sensor at a key location on the rope, ensuring that the sensor is in close contact with the rope surface.

[0023] Step 1.2, set the sampling frequency and sampling time in seconds to ensure high-resolution acquisition of the signal;

[0024] Step 1.3: During the transportation process, the acoustic emission sensor continuously collects acoustic emission signals and transmits the collected acoustic emission signals to the signal preprocessing module.

[0025] As a further improvement of the present invention, the step 2 specifically includes the following steps:

[0026] Step 2.1, performing band-pass filtering on the collected acoustic emission signal to remove low-frequency and high-frequency noise; wherein the frequency range of the band-pass filter is 20kHz to 80kHz;

[0027] Step 2.2: Use wavelet transform to perform denoising, select db4 wavelet basis function, and decompose the data into n layers:

[0028]

[0029] Among them, ψ j,k (t) and are wavelet function and scaling function respectively, c j,k and d n,k is the wavelet coefficient;

[0030] Step 2.3: Normalize the denoised signal to ensure that the signal amplitude is within the range of [-1, 1].

[0031] As a further improvement of the present invention, the step 3 specifically includes the following steps:

[0032] Step 3.1, perform AEMD decomposition on the pre-processed acoustic emission signal to decompose it into multiple modal components IMF;

[0033] Step 3.2: Set the stopping condition of AEMD decomposition to the standard deviation of the modal component being less than the preset threshold;

[0034] Step 3.3: Extract the first n modal components as the main analysis objects:

[0035]

[0036] Among them, the IMF i (t) is the i-th modal component, r n (t) is the residual.

[0037] As a further improvement of the present invention, step 4 specifically includes the following steps:

[0038] Step 4.1. Calculate the energy E of each modal component i :

[0039] Step 4.2: Calculate the normalized value E of the modal energy i ' :

[0040] Step 4.3: Set the energy threshold E th , when E i ' >E th When , the modal component is judged to be an abnormal mode.

[0041] As a further improvement of the present invention, the step 5 specifically includes the following steps:

[0042] Step 5.1, use the wind speed sensor to collect wind speed v;

[0043] Step 5.2: Use the acceleration sensor to collect the road condition level R.

[0044] As a further improvement of the present invention, step 6 specifically includes the following steps:

[0045] Step 6.1: Dynamically adjust the rope breakage risk threshold T according to environmental parameters h :

[0046] T h =T base ×(1+αv+βR)

[0047] Among them, T base is the basic threshold, α and β are coefficients;

[0048] Step 6.2, when E i '>T h When the risk is high, it is judged as a high-risk state.

[0049] As a further improvement of the present invention, step 7 specifically includes the following steps:

[0050] Step 7.1: Extract the eigenvector F of the abnormal modal component i :

[0051] F i =[E i ',f i ,A i ]

[0052] Among them, f i is the center frequency of the modal component, A i is the amplitude of the modal component;

[0053] Step 7.2: Calculate the eigenvector and the reference eigenvector The similarity S i :

[0054]

[0055] Among them, w k is the weight coefficient, is the similarity of feature components;

[0056] Step 7.3, when S i >Dynamically adjust the risk threshold T after the rope h When the fault occurs, an early warning is triggered and the fracture location information is output.

[0057] The present invention proposes an early warning system and method for rope fracture based on acoustic emission signal analysis (AESA). By utilizing the "acoustic emission modal decomposition" (AEMD) technology, the system can monitor the acoustic emission signals of the rope in real time and issue a timely warning before the fracture occurs. The system collects the acoustic emission signals of the rope through a high-sensitivity acoustic emission sensor, and uses the AEMD technology to decompose the signal into multiple modal components to identify the precursor characteristics of the fracture (such as microcrack propagation acoustic emission). Through modal energy spectrum analysis, the system quantifies the energy of each modal component and determines the fracture risk. The system dynamically adjusts the risk threshold according to the transportation environment (such as wind speed and road conditions) to avoid false alarms and missed alarms. When the fracture risk is detected to exceed the threshold, the system triggers an early warning through the acoustic emission feature matching algorithm (AEFM) and provides specific fracture location information.

[0058] The beneficial effects of the present invention are:

[0059] The present invention can monitor the acoustic emission signal of the rope in real time, and decompose the signal into multiple modal components through the acoustic emission modal decomposition (AEMD) technology, effectively identifying the precursor characteristics of fracture such as microcrack extension. The system combines modal energy spectrum analysis to quantify the energy changes of each modal component, and dynamically adjusts the risk threshold according to the transportation environment (such as wind speed, road conditions) to avoid false alarms and missed reports. When it is detected that the fracture risk exceeds the threshold, an acoustic emission feature matching algorithm (AEFM) is used to trigger an early warning and provide specific fracture location information. The present invention realizes accurate early warning of the risk of rope fracture, effectively improves the safety of transportation of large power equipment, reduces the risk of accidents caused by rope fracture, and has significant economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a system block diagram of embodiment 1 of the present invention;

[0061] Figure 2 This is a flowchart of Example 1 of the present invention. DETAILED DESCRIPTION

[0062] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0063] Example 1

[0064] like Figure 1 As shown, a rope breakage early warning system based on acoustic emission signal analysis includes:

[0065] 1. Acoustic emission sensor module: used to collect the acoustic emission signal of the rope.

[0066] 2. Signal preprocessing module: Filter and denoise the collected acoustic emission signals.

[0067] 3. Acoustic Emission Modal Decomposition (AEMD) module: decomposes the acoustic emission signal into multiple modal components.

[0068] 4. Modal energy spectrum analysis module: quantifies the energy of each modal component and determines the risk of fracture.

[0069] 5. Environmental parameter collection module: collects transportation environment parameters (such as wind speed and road conditions).

[0070] 6. Dynamic threshold adjustment module: dynamically adjusts risk thresholds based on environmental parameters.

[0071] 7. Acoustic Emission Feature Matching (AEFM) module: matches acoustic emission features, triggers early warnings, and provides fracture location information.

[0072] 8. Warning output module: output warning information and provide specific fracture location.

[0073] like Figure 2 As shown, this embodiment also provides a rope breakage early warning method based on acoustic emission signal analysis, comprising the following steps:

[0074] Step 1: Acoustic emission signal acquisition:

[0075] 1. Install high-sensitivity acoustic emission sensors (such as PACMicro80D) at key locations on the rope (such as fixed points and stress points), ensuring that the sensor is in close contact with the rope surface.

[0076] 2. Set the sampling frequency f s =100kHz, sampling time T = 1 second, ensuring high-resolution acquisition of the signal.

[0077] 3. During transportation, the sensor continuously collects acoustic emission signals and transmits the data to the signal preprocessing module.

[0078] During the transportation of power equipment, sensors collect acoustic emission signals in real time to ensure signal continuity and integrity. During transportation, sensors are installed at the fixed points of the ropes. Multiple sensors are required to collect acoustic emission signals in real time to ensure signal continuity and integrity.

[0079] Step 2: Signal preprocessing:

[0080] 1. Bandpass filter the collected acoustic emission signal to remove low-frequency and high-frequency noise. Set the frequency range of the bandpass filter to 20kHz to 80kHz.

[0081] 2. Use wavelet transform for denoising, select db4 wavelet basis function, and set the decomposition layer number to 5.

[0082] 3. Normalize the denoised signal to ensure that the signal amplitude is in the range of [-1,1].

[0083] Algorithm formula:

[0084]

[0085] Among them, ψ j,k (t) and φ 5,k (t) are wavelet function and scaling function respectively, c j,k and d 5,k is the wavelet coefficient.

[0086] During transportation, the environmental noise is relatively high. Wavelet transform is used to remove high-frequency noise and retain valid acoustic emission signals. For example, during transportation, the environmental noise is relatively high. Wavelet transform is used to remove high-frequency noise and retain valid acoustic emission signals.

[0087] Step 3: Acoustic emission modal decomposition:

[0088] 1. Perform AEMD decomposition on the preprocessed acoustic emission signal and decompose it into multiple modal components (IMFs).

[0089] 2. Set the stopping condition of AEMD decomposition to the standard deviation of the modal component being less than 0.3.

[0090] 3. Extract the first five modal components (IMF1 to IMF5) as the main analysis objects.

[0091]

[0092] Among them, the IMF i (t) is the i-th modal component, and r5(t) is the residual.

[0093] AEMD decomposition can decompose the acoustic emission signal into multiple modal components, facilitating subsequent feature extraction and energy analysis. For example, during transportation, AEMD decomposition can decompose the acoustic emission signal into multiple modal components, facilitating subsequent feature extraction and energy analysis.

[0094] Step 4: Modal Energy Spectrum Analysis:

[0095] 1. Calculate the energy E of each modal component i :

[0096]

[0097] 2. Calculate the normalized value of modal energy Ei':

[0098]

[0099] 3. Set the energy threshold E th =0.2, when E i ' >E th When , the modal component is judged to be an abnormal mode.

[0100] By calculating the energy of each modal component, modal components with abnormal energy can be identified to determine whether there is a risk of fracture. For example, during transportation, by calculating the energy of each modal component, modal components with abnormal energy can be identified to determine whether there is a risk of fracture.

[0101] Step 5: Environmental parameter collection:

[0102] 1. Use a wind speed sensor (such as Davis6410) to collect wind speed v (unit: m / s).

[0103] 2. Use an acceleration sensor to collect road condition level R (level 1-5, level 1 is flat and level 5 is rugged).

[0104] 3. Transmit environmental parameters to the dynamic threshold adjustment module.

[0105] Dynamically adjust risk thresholds based on environmental parameters to avoid false positives and false negatives. For example, during transportation, dynamically adjust risk thresholds based on environmental parameters to avoid false positives and false negatives.

[0106] Step 6: Dynamic Threshold Adjustment:

[0107] 1. Dynamically adjust the risk threshold Th according to environmental parameters:

[0108] T h =T base ×(1+0.1v+0.2R)

[0109] Among them, T base =0.5 is the basic threshold, v is the wind speed, and R is the road condition level.

[0110] 2. When Ei'>T h When the risk is high, it is judged as a high-risk state.

[0111] In situations where wind speeds are high or road conditions are poor, the risk threshold is raised to reduce false alarms. For example, in situations where wind speeds are high or road conditions are poor, the risk threshold is raised to reduce false alarms.

[0112] Step 7: Acoustic Emission Feature Matching Algorithm:

[0113] 1. Extract the eigenvector F of the abnormal modal component i :

[0114] F i =[E i ',fi ,A i

[0115] Among them, f i is the center frequency of the modal component, A i is the amplitude of the modal component.

[0116] 2. Calculate eigenvectors and reference eigenvectors The similarity S i :

[0117]

[0118] where w k is the weight coefficient, is the similarity of the feature components.

[0119] 3. When S i When it is >0.8, an early warning is triggered and the fracture location information is output.

[0120] During transportation, feature matching algorithms are used to identify fracture precursor features, trigger early warnings, and provide specific fracture location information.

[0121] Example 2

[0122] In one large transformer transport project, the transformer weighed 50 tons and measured 5m x 3m x 4m. The entire journey covered approximately 200 kilometers, with complex and varied road conditions, including highways, mountainous roads, and rural roads. The transport vehicle was equipped with advanced navigation and environmental monitoring systems.

[0123] To ensure safety during transportation, 40 PAC Micro80D high-sensitivity acoustic emission sensors were installed on each load-bearing rope, with adjacent sensors spaced 500 mm apart. The sensors were connected to a signal acquisition device via shielded cables. The sampling frequency of the device was set to 1 MHz, ensuring high-resolution acquisition of the acoustic emission signals.

[0124] During transportation, sensors collect the rope's acoustic emission signals in real time. The signal acquisition device transmits the collected signals to the signal preprocessing module. First, the signal is bandpass filtered within a frequency range of 5kHz to 200kHz to remove low- and high-frequency noise introduced by the environment during transportation. Next, the amplification factor is dynamically adjusted based on the signal amplitude: when the signal amplitude is less than 5mV, the amplification factor is set to 20x; when the signal amplitude is between 5mV and 100mV, the amplification factor is set to 10x. Finally, the amplified signal is normalized to ensure that the signal amplitude is within the range [-1, 1], improving the accuracy and stability of subsequent processing.

[0125] For example, at a certain moment, the amplitude of the acoustic emission signal collected by the sensor is 3mV. After amplification by 20 times, the amplitude becomes 60mV. After normalization, the signal amplitude is 0.6.

[0126] The preprocessed AE signal is then fed into the AEMD module. The system uses the AEMD algorithm to decompose the signal, extracting the first five IMF components as the primary analysis targets. For example, an AEMD decomposition of an AE signal collected during transportation on a mountainous road yields five IMF components. IMF1 has the highest frequency and primarily reflects the high-frequency vibrations of the rope, while IMF5 has the lowest frequency and reflects the low-frequency, slowly changing characteristics of the rope.

[0127] Assuming that the preprocessed acoustic emission signal is x(t), the AEMD decomposition process is as follows:

[0128] 1. Find all local maxima and minima of the signal.

[0129] 2. Generate the upper envelope u(t) and lower envelope l(t).

[0130] 3. Calculate the mean of the upper and lower envelopes

[0131] 4. Subtract the mean value from the original signal to obtain the first detail component d1(t)=x(t)-m(t).

[0132] 5. Determine whether d1(t) satisfies the IMF conditions (i.e., the difference between the number of extreme points and the number of zero crossing points does not exceed 1, and the mean of the upper and lower envelopes is close to zero). If not, repeat the above process to decompose d1(t) until the first IMF component IMF1(t) is obtained.

[0133] 6. Subtract IMF1(t) from the original signal to obtain the residual signal r1(t)=x(t)-IMF1(t).

[0134] 7. Repeat the above decomposition process for r1(t) to obtain IMF2(t), IMF3(t), IMF4(t), and IMF5(t) in sequence until the residual signal r5(t) no longer contains any fluctuation components.

[0135] For each IMF component, its energy spectrum is calculated. In a mountainous road transport scenario, the system detected an abnormal increase in the energy of the IMF2 component in the 10kHz to 50kHz frequency range. Through modal energy spectrum analysis, the energy value of this component is calculated and compared with the dynamically adjusted risk threshold.

[0136] Assuming that the time domain signal of IMF2(t) is x2(t), its energy E2 is calculated as follows:

[0137]

[0138] Assume that the signal data of x2(t) between 0 and 1 second is a set of discrete points, and calculate E2' through numerical integration. Then, calculate the normalized value of the modal energy E2':

[0139]

[0140] Assuming that the energies of other IMF components are E1 = 0.1, E3 = 0.15, E4 = 0.1, and E5 = 0.05, then:

[0141]

[0142] A wind speed sensor mounted on the top of the transport vehicle collects wind speed data every second. Accelerometers on the vehicle chassis monitor road conditions and calculate the vehicle's turbulence index every second. A fuzzy control algorithm is used to correlate environmental parameters with risk thresholds. For example, when wind speeds exceed 10 m / s and the turbulence index exceeds 0.5, the risk threshold is increased by 20%.

[0143] Assuming the base threshold Tbase = 0.5, wind speed v = 12 m / s, and road condition level R = 4, the dynamic risk threshold Th is calculated as:

[0144] T h =0.5×(1+0.1×12+0.2×4)=0.5×(1+1.2+0.8)=0.5×3=1.5

[0145] When the modal energy spectrum analysis results exceed the dynamic risk threshold, the system triggers an early warning using an acoustic emission feature matching algorithm. In mountainous road transport scenarios, the system detects an abnormally high energy increase in the IMF2 component, with E2'=>Th, indicating a high-risk condition. The system immediately extracts the component's feature vector, including energy, center frequency, and amplitude. These features are then matched against a pre-stored library of rope break precursor features. Feature matching utilizes a template matching algorithm to calculate the similarity between the current features and the template features. If the similarity exceeds 80%, the match is considered successful, confirming the presence of a rope break risk.

[0146] Assume that the current eigenvector is F i =[0.333,30kHz,0.8V], the reference eigenvector is Weight coefficients w1 = 0.5, w2 = 0.3, w3 = 0.2, then the similarity S i Calculated as:

[0147] S i=0.5×sim(0.333,0.3)+0.3×sim(30kHz,30kHz)+0.2×sim(0.8V,0.7V)

[0148] Assuming similarity function but:

[0149]

[0150] Due to S i =0.925>0.8, triggering an early warning. At the same time, the system uses the signal propagation time difference positioning method to determine the specific fracture location. In mountain road transportation scenarios, the system calculates the coordinates of the fracture location by combining the time difference of the signals received by the sensors with the propagation speed of the acoustic emission signal in the rope (calibrated to 5000m / s through experiments). For example, the time difference between the signals received by sensor A and sensor B is 0.0002 seconds. Based on the propagation speed, the fracture location is calculated to be approximately 1 meter away from sensor A.

[0151] Assuming that the positions of sensor A and sensor B are (0,0,0) and (2,0,0) respectively, the signal propagation speed is v = 5000m / s, and the time difference is Deltat = 0.0002 seconds, the fracture position (x,y,z) can be calculated using the geometric positioning algorithm. Assuming that the fracture position is on the rope and the rope is arranged along the x-axis, then:

[0152]

[0153] Therefore, the fracture location is about 0.5 meters away from sensor A.

[0154] The above-described embodiments merely represent specific implementations of the present invention. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, and all such variations and improvements fall within the scope of protection of the present invention.

Claims

1. An early warning system for rope breakage based on acoustic emission signal analysis, characterized in that: include: Acoustic emission sensor module: used to collect the acoustic emission signal of the rope; Signal preprocessing module: used to filter and denoise the collected acoustic emission signals; Acoustic emission modal decomposition module: used to decompose the acoustic emission signal into multiple modal components; Modal energy spectrum analysis module: used to quantify the energy of each modal component and determine the risk of rope breakage; Environmental parameter collection module: used to collect transportation environmental parameters; Dynamic threshold adjustment module: used to dynamically adjust risk thresholds based on environmental parameters; Acoustic emission feature matching algorithm module: used to match acoustic emission features, trigger early warning and provide fracture location information; Warning output module: used to output warning information and provide specific fracture locations.

2. A rope breakage early warning method based on acoustic emission signal analysis, characterized in that: The following steps are involved: Step 1: Collecting acoustic emission signals of power equipment during transportation; Step 2: Preprocessing the collected acoustic emission signals; Step 3: Perform modal decomposition on the preprocessed signal; Step 4: Perform modal energy spectrum analysis on the modal decomposition signal to identify modal components with abnormal energy and determine whether there is a risk of rope breakage; Step 5: Collect environmental parameters during transportation; Step 6: Dynamically adjust the risk threshold of rope breakage based on the collected environmental parameters; Step 7: Use the acoustic emission feature matching algorithm to calculate the similarity between the eigenvector of the abnormal modal component and the reference eigenvector. When the similarity is greater than the dynamically adjusted risk threshold, trigger an early warning and output the fracture location information.

3. The rope breakage early warning method based on acoustic emission signal analysis according to claim 2 is characterized in that: The step 1 specifically includes the following steps: Step 1.1: Install a high-sensitivity acoustic emission sensor at a key location on the rope, ensuring that the sensor is in close contact with the rope surface. Step 1.2, set the sampling frequency and sampling time in seconds to ensure high-resolution acquisition of the signal; Step 1.3: During the transportation process, the acoustic emission sensor continuously collects acoustic emission signals and transmits the collected acoustic emission signals to the signal preprocessing module.

4. The rope breakage early warning method based on acoustic emission signal analysis according to claim 3 is characterized in that: The step 2 specifically includes the following steps: Step 2.1, performing band-pass filtering on the collected acoustic emission signal to remove low-frequency and high-frequency noise; wherein the frequency range of the band-pass filter is 20kHz to 80kHz; Step 2.2: Use wavelet transform to perform denoising, select db4 wavelet basis function, and decompose the data into n layers: Among them, ψ j,k (t) and are wavelet function and scaling function respectively, c j,k and d n,k is the wavelet coefficient; Step 2.3: Normalize the denoised signal to ensure that the signal amplitude is within the range of [-1, 1].

5. The rope breakage early warning method based on acoustic emission signal analysis according to claim 4 is characterized in that: The step 3 specifically includes the following steps: Step 3.1, perform AEMD decomposition on the pre-processed acoustic emission signal to decompose it into multiple modal components IMF; Step 3.2: Set the stopping condition of AEMD decomposition to the standard deviation of the modal component being less than the preset threshold; Step 3.3: Extract the first n modal components as the main analysis objects: Among them, the IMF i (t) is the i-th modal component, r n (t) is the residual.

6. The rope breakage early warning method based on acoustic emission signal analysis according to claim 5 is characterized in that: The step 4 specifically includes the following steps: Step 4.

1. Calculate the energy E of each modal component i : Step 4.2: Calculate the normalized value E of the modal energy i ': Step 4.3: Set the energy threshold E th , when E i '>E th When , the modal component is judged to be an abnormal mode.

7. The rope breakage early warning method based on acoustic emission signal analysis according to claim 6, characterized in that: The step 5 specifically includes the following steps: Step 5.1, use the wind speed sensor to collect wind speed v; Step 5.2: Use the acceleration sensor to collect the road condition level R.

8. The rope breakage early warning method based on acoustic emission signal analysis according to claim 7 is characterized in that: The step 6 specifically includes the following steps: Step 6.1: Dynamically adjust the rope breakage risk threshold T according to environmental parameters h : T h =T base ×(1+αv+βR) Among them, T base is the basic threshold, α and β are coefficients; Step 6.2, when E i '>T h When the risk is high, it is judged as a high-risk state.

9. The rope breakage early warning method based on acoustic emission signal analysis according to claim 8, characterized in that: The step 7 specifically includes the following steps: Step 7.1: Extract the eigenvector F of the abnormal modal component i : F i =[E i ',f i ,A i ] Among them, f i is the center frequency of the modal component, A i is the amplitude of the modal component; Step 7.2: Calculate the eigenvector and the reference eigenvector The similarity S i : Among them, w k is the weight coefficient, is the similarity of feature components; Step 7.3, when S i >Dynamically adjust the risk threshold T after the rope h When the fault occurs, an early warning is triggered and the fracture location information is output.

Images