Transmission tower bolt tightness detection method, medium and equipment

Abstract

The invention provides a power transmission tower bolt tightness detection method, a medium and equipment, and relates to the technical field of power transmission lines. Extracting characteristic parameters from the collected bolt vibration signal data by using a dynamic weighted average Hilbert envelope coefficient algorithm; constructing a Gaussian mixture model for bolt looseness detection, and training the Gaussian mixture model by using the feature parameters based on an entropy expectation maximization algorithm; bolt vibration signals collected in real time are obtained, and real-time characteristic parameters are extracted from bolt vibration signal data collected in real time through the dynamic weighted average Hilbert envelope coefficient; and inputting the real-time characteristic parameters into the trained Gaussian mixture model, outputting to obtain clustered characteristic model data, and judging whether the bolt is loosened or not and the loosening degree according to the aggregation degree of the characteristic model data. According to the method, the bolt fastening degree can be rapidly and effectively detected, and the working efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission lines, and in particular to a method, a medium and a device for detecting the tightness of bolts on a power transmission tower. Background Art

[0002] Transmission line towers are important carriers that support the safe and stable transmission of electricity. Once the tower connection becomes loose or fails, it is very likely to cause the tower to tilt, collapse, and break the line, resulting in a power outage, causing huge economic losses. Bolts are key hardware to ensure the stability and reliability of the tower connection structure. As the transmission lines are affected by strong winds and ice dancing over the years, the tightness of the bolts at the tower connection gradually decreases. At present, the inspection of the tightness of bolts mainly relies on regular inspections by operation and maintenance personnel. This is a large workload, time-consuming, and costly. As more transmission lines continue to be put into operation, this method cannot meet the detection needs. Summary of the invention

[0003] The purpose of the present invention is to provide a method, medium and equipment for detecting the tightness of bolts on transmission towers, aiming to quickly and effectively detect the tightness of bolts and improve work efficiency. The specific technical solution is as follows:

[0004] A method for detecting the tightness of bolts on a transmission tower, the method comprising the following steps:

[0005] S100, acquiring a collected bolt vibration signal;

[0006] S200, extracting characteristic parameters from the collected bolt vibration signal data using a dynamic weighted average Hilbert envelope coefficient algorithm;

[0007] S300, constructing a Gaussian mixture model for bolt loosening detection, and using the characteristic parameters to train the Gaussian mixture model based on an entropy expectation maximization algorithm;

[0008] S400, obtaining a bolt vibration signal collected in real time, and extracting a real-time characteristic parameter from the bolt vibration signal data collected in real time by using a dynamic weighted average Hilbert envelope coefficient;

[0009] S500, inputting the real-time feature parameters into the trained Gaussian mixture model, outputting the clustered feature model data, and judging whether the bolt is loose and the degree of looseness according to the degree of clustering of the feature model data.

[0010] Furthermore, in the step S100, a Lamb wave sensor is used to detect the vibration signal of the bolt.

[0011] Furthermore, the step S200 specifically includes the following steps:

[0012] S210. Decompose the collected bolt vibration signal into different sub-bands using a gammatone filter bank. The gammatone filter bank is represented by the equivalent rectangular bandwidth, and its expression is:

[0013]

[0014] where Q and B min are the Glanberg parameter and the Moore parameter respectively, and f j is the center frequency of the j th -th channel, with the unit of Hz;

[0015] The signal of each channel is expressed by the following formula:

[0016] h(t,j) = δt τ-1 exp(-2πb(f j ))t)cos(2πf j t + θ)

[0017] where δ and τ represent the magnitude and the filter order of the response respectively, b(f j ) is the filter bandwidth, and θ is the initial phase angle;

[0018] S220. Use the Hilbert transform and calculate the analytic signal output by the j th -th channel;

[0019] S230. Calculate the squared magnitude of the analytic signal to obtain the Hilbert envelope output by the j th -th channel;

[0020] S240. Smooth the Hilbert envelope using a low-pass filter;

[0021] S250. Perform a discrete cosine transform to obtain the MHEC coefficients;

[0022] S260. Respectively obtain the first-order differential coefficient ΔMHEC and the second-order differential coefficient Δ 2 MHEC of the MHEC coefficients and perform weighted processing on them to obtain the new vibration signal characteristic parameter NMHEC, that is, complete the extraction of the vibration signal characteristics. The calculation formula of the new vibration signal characteristic parameter NMHEC is as follows:

[0023] NMHEC = MHEC + a × ΔMHEC + b × Δ 2 MHEC

[0024] where a and b are weight coefficients, and the constraint condition is: 0 < b < a < 1.

[0025] Furthermore, the step S300 specifically includes the following steps:

[0026] S310. Represent the extracted feature parameters using set A, where A = [x 1 , x 2 ..., x k ,..., x n . Here, x k is a parameter sample;

[0027] S320. The GMM probability density p(x i ) of a parameter sample x i in set A is expressed as:

[0028]

[0029] where n represents the number of components included, u k , represent the mean and covariance matrix of the k-th component Gaussian distribution; λ k represents the weight coefficient of the k-th component Gaussian distribution in the mixture model, λ k ∈ [0, 1];

[0030] S330. The fitting process of the GMM probability density p(x i ) consists of two steps, namely the K-means and entropy expectation maximization algorithms. The K-means algorithm is used to calculate the initial values of the entropy expectation maximization algorithm;

[0031] S340. The entropy expectation maximization algorithm includes two steps, E-Step and M-Step. During the calculation, the parameters are repeatedly re-estimated until the model converges. The E-Step is to solve for the expected value, and the M-Step is to solve for the maximum likelihood estimate. The expression of the maximum likelihood function maxL(λ, μ, σ 2 ) based on EEM is as follows:

[0032]

[0033] where, λ is the Gaussian component weight coefficient, μ is the mean, σ is the variance, H k is the information entropy of the k-th Gaussian component, λ kt and λ kt-1 are the weight coefficients of the kt-th and kt-1-th Gaussian components, w t is the adaptive factor. The parameters calculated by the GMM model based on the EEM algorithm are as follows:

[0034]

[0035] where, z i is the hidden variable; θ kt is the parameter of the K-th component;

[0036] The S350 and the above parameters are iteratively run in sequence. The expected value is fixed and optimized in the E-Step, and the expected value is fixed and optimized in the M-Step until the change value of the log-likelihood function meets the set threshold ε. It is considered that convergence has been achieved at this time, and the iterative operation ends, completing the establishment of the bolt loosening model. The expression for convergence is as follows, which is the change amplitude between two adjacent iterations:

[0037] |L kt / L kt-1 |-1 ≤ ε

[0038] Among them, L kt and L kt-1 are the likelihood function values of the kt-th and (kt - 1)-th respectively, and ε approaches 0.

[0039] Furthermore, in the step S500, the more concentrated the feature model data is, the tighter the bolt is, and the more dispersed the feature model data is, the looser the bolt is.

[0040] Furthermore, after the step S500, the following steps are further included:

[0041] S600: Taking the center of the feature model data as a reference, determine that the range where the horizontal and vertical coordinates are within the set values is the normal area. When the number of data points exceeding the normal area in the horizontal feature model data exceeds the preset value, an alarm is given to remind the operation and maintenance personnel to perform tightening processing.

[0042] Furthermore, taking the range where the horizontal and vertical coordinates deviate from the center by within ±2 as the normal area, when the number of data points exceeding the normal area in the horizontal feature model data exceeds 1 / 4 of the total number of data points, an alarm processing is performed.

[0043] Furthermore, the alarm processing is to send a control signal to the exciter to control the exciter to perform vibration alarm.

[0044] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for detecting the tightness of bolts on a transmission tower are realized.

[0045] The present invention also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned method for detecting the tightness of bolts on a transmission tower are realized.

[0046] A method, medium, and device for detecting the tightness of bolts on a transmission tower provided by the present invention have the following

[0047] beneficial effects:

[0048] The present invention extracts the characteristic parameters of bolts by using the dynamic weighted MHEC algorithm, constructs a GMM model after the bolts are loosened, trains the data of the constructed model by using the EEM algorithm, and judges the tightness of the bolts by comparing the real-time data with the parameter model, providing a decision-making basis for whether the operation and maintenance personnel tighten the bolts. This method can quickly and effectively detect the tightening degree of bolts and helps improve work efficiency. Brief Description of the Drawings

[0049] Figure 1 is a schematic flowchart of a method for detecting the tightness of bolts on a transmission tower provided by the present invention;

[0050] Figure 2 is the overall flowchart of an embodiment of the present invention;

[0051] Figure 3 is a characteristic model data diagram under the condition of bolt loosening;

[0052] Figure 4 is another characteristic model data diagram under the condition of bolt loosening;

[0053] Figure 5 is the structural block diagram of a computer device according to an embodiment of the present invention. Detailed Embodiments

[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings provided by the present invention. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the drawings are all in a very simplified form and use non-precise scales, only for the purpose of conveniently and clearly assisting in explaining the objectives of the embodiments of the present invention.

[0055] Embodiment 1

[0056] This embodiment provides a method for detecting the tightness of bolts on a transmission tower. Refer to Figure 1 、 2 As shown, the method includes the following steps:

[0057] S100. Obtain the collected bolt vibration signals.

[0058] Specifically, use a Lamb wave sensor to detect the vibration signals of the bolts and complete the data collection work.

[0059] S200. Extract characteristic parameters from the collected bolt vibration signal data by using the dynamic weighted average Hilbert envelope coefficient (MHEC) algorithm.

[0060] In one embodiment, S200 specifically includes the following steps:

[0061] S210. Decompose the collected bolt vibration signal into different sub - bands using a gammatone filter bank. The gammatone filter bank is represented by the equivalent rectangular bandwidth (ERB), and its expression is:

[0062]

[0063] where Q and B min are the Glanberg parameter and the Moore parameter respectively, and f j is the center frequency of the j - th th channel, with the unit of Hz;

[0064] The signal of each channel is represented by the following formula:

[0065] h(t, j) = δt τ-1 exp(-2πb(f j ))t)cos(2πf j t + θ)

[0066] where δ and τ represent the magnitude and the filtering order of the response respectively, b(f j ) is the filter bandwidth, and θ is the initial phase angle;

[0067] S220. Use the Hilbert transform and calculate the analytic signal output from the j - th th channel;

[0068] S230. Calculate the squared magnitude of the analytic signal to obtain the Hilbert envelope output from the j - th th channel;

[0069] S240. Smooth the Hilbert envelope using a low - pass filter;

[0070] S250. Perform the discrete cosine transform (DCT) to obtain the MHEC coefficients;

[0071] S260. Calculate the first - order differential coefficient ΔMHEC and the second - order differential coefficient Δ 2 MHEC of the MHEC coefficients respectively and perform weighted processing on them to obtain the new vibration signal characteristic parameter NMHEC, that is, the extraction of the vibration signal characteristics is completed. The calculation formula of the new vibration signal characteristic parameter NMHEC is as follows:

[0072] NMHEC = MHEC + a×ΔMHEC + b×Δ 2 MHEC

[0073] where a and b are weight coefficients, and the constraint condition is: 0 < b < a < 1.

[0074] After the above preprocessing and the dynamic weighted MHEC algorithm, the influence of noise on the feature extraction of vibration signals can be effectively removed, the correct extraction of feature signals can be realized, and a foundation is laid for the identification and judgment of bolt tightness.

[0075] S300. Construct a Gaussian mixture model (GMM, Gaussian Mixture Model) for bolt loosening detection, and train the Gaussian mixture model based on the entropy expectation maximization algorithm using the feature parameters.

[0076] In a preferred embodiment, S300 specifically includes the following steps:

[0077] S310. Represent the extracted feature parameters with set A, A = [x 1 , x 2 ..., x k ,..., x n , where x k is a parameter sample;

[0078] S320. The GMM probability density p(x i ) of a parameter sample x i in set A is expressed as:

[0079]

[0080] where n represents the number of components included, u k , represent the mean and covariance matrix of the k-th component Gaussian distribution; λ k represents the weight coefficient of the k-th component Gaussian distribution in the mixture model, λ k ∈ [0, 1];

[0081] S330. The fitting process of the GMM probability density p(x i ) includes two steps, namely the K-means and entropy expectation maximization (EEM, Entropy Expectation Maximization) algorithms, where the K-means algorithm is used to calculate the initial value of the entropy expectation maximization algorithm;

[0082] S340. The entropy expectation maximization algorithm includes two steps, E-Step and M-Step. During the calculation, the parameters are repeatedly re-evaluated until the model converges; the E-Step is to solve the expected value, and the M-Step is to solve the maximum likelihood estimate; the maximum likelihood function maxL(λ, μ, σ 2 ) based on EEM is expressed as follows:

[0083]

[0084] Among them, λ is the Gaussian component weight coefficient, μ is the expectation, σ is the variance, and H k is the information entropy of the k-th Gaussian component, λ kt and λ kt-1 are the Gaussian component weight coefficients of the kt-th and kt-1-th, w t is the adaptive factor. The parameter calculation of the GMM model based on the EEM algorithm is as follows:

[0085]

[0086] Among them, z i is the hidden variable; θ kt is the parameter of the K-th component;

[0087] S350. The above parameters are iteratively run in sequence. The expected value is fixed and optimized in the E-Step, and the expected value is fixed and optimized in the M-Step until the change value of the log-likelihood function satisfies the set threshold ε. It is considered that convergence has been achieved at this time, and the iterative operation ends, completing the establishment of the bolt loosening model; the expression of convergence is as follows, that is, the change amplitude between two adjacent iterations:

[0088] |L kt / L kt-1 |-1 ≤ ε

[0089] Among them, L kt and L kt-1 are the likelihood function values of the kt-th and kt-1-th respectively, and ε approaches 0.

[0090] Compared with the traditional EM algorithm, the entropy expectation maximization algorithm can effectively improve the fitting accuracy of the GMM model and avoid the disadvantages of the traditional EM algorithm such as the difficulty in solving implicit parameters and strong subjectivity.

[0091] S400. Obtain the bolt vibration signal collected in real time, and extract the real-time characteristic parameters from the bolt vibration signal data collected in real time by using the dynamic weighted average Hilbert envelope coefficient.

[0092] Specifically, the specific steps of extracting the real-time characteristic parameters from the bolt vibration signal data collected in real time by using the dynamic weighted average Hilbert envelope coefficient are the same as the specific steps of step S200, which will not be elaborated here.

[0093] S500. Input the real-time characteristic parameters into the trained Gaussian mixture model, and output the clustered characteristic model data. Determine whether the detected bolt is loose and the degree of looseness according to the aggregation degree of the characteristic model data.

[0094] Specifically, the judgment basis is that the tighter the bolt, the more concentrated the characteristic model data; the more the bolt is loosened, the more dispersed the characteristic model data.

[0095] Using this method to construct models under different bolt loosening conditions and output the characteristic model data graphs, as Figure 3 、 4 shown. It can be seen from the figure that in the case of bolt loosening, the characteristic model data gradually deviates from the clustering center point, and the more the bolt is loosened, the more data points deviate from the center point.

[0096] The method for detecting the tightness of bolts on transmission towers provided by the present invention extracts the characteristic parameters of bolts by using the dynamic weighted MHEC algorithm, constructs a GMM model after bolt loosening, and the constructed model uses the EEM algorithm for data training. By comparing the real-time data with the parameter model to judge the tightness of the bolts, it provides a decision-making basis for whether the maintenance personnel need to tighten the bolts. This method can quickly and effectively detect the tightness of the bolts and helps improve work efficiency.

[0097] In one embodiment, referring to Figure 2 shown, after S500 of this method, the following steps are further included:

[0098] S600. Taking the center of the characteristic model data as a reference, determine that the range where the horizontal and vertical coordinates are within the set value is the normal area. When the number of data points exceeding the normal area in the horizontal characteristic model data exceeds the preset value, give an alarm to remind the maintenance personnel to perform tightening treatment.

[0099] In a preferred embodiment, referring to Figure 3 、 4 shown, the range where the horizontal and vertical coordinates deviate from the center (i.e., the horizontal and vertical coordinates are 0) by ±2 or less is the normal area. When the number of data points exceeding the normal area in the horizontal characteristic model data exceeds 1 / 4 of the total number of data points, perform alarm processing.

[0100] In one embodiment, the alarm processing is to send a control signal to the vibrator to control the vibrator to perform vibration alarm.

[0101] Embodiment 2

[0102] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for detecting the tightness of bolts on transmission towers described above are implemented.

[0103] Among them, the storage medium may be a magnetic disk, an optical disc, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (abbreviation: HDD), or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memories.

[0104] Embodiment 3

[0105] This embodiment provides a computer device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps of the transmission tower bolt tightness detection method described above.

[0106] As Figure 5 shown, the computer device may include: at least one processor 71, such as a CPU (Central Processing Unit, central processor), at least one communication interface 73, a memory 74, and at least one communication bus 72. Among them, the communication bus 72 is used to realize the connection and communication between these components. Among them, the communication interface 73 may include a display screen (Display) and a keyboard (Keyboard). Optionally, the communication interface 73 may also include a standard wired interface and a wireless interface. The memory 74 may be a high-speed RAM memory (Random Access Memory, volatile random access memory), or a non-volatile memory, such as at least one disk memory. Optionally, the memory 74 may also be at least one storage device located far from the aforementioned processor 71. Among them, an application program is stored in the memory 74, and the processor 71 calls the program code stored in the memory 74 to execute any of the above method steps.

[0107] Among them, the communication bus 72 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 72 may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 5 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0108] Among them, the memory 74 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 74 may further include a combination of the above types of memories.

[0109] Among them, the processor 71 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.

[0110] Among them, the processor 71 may further include a hardware chip. The above hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0111] Optionally, the memory 74 is further configured to store program instructions. The processor 71 may call the program instructions to implement the method for detecting the tightness of bolts on transmission towers according to the present invention.

[0112] Those skilled in the art of the present technology should understand that the present invention may be implemented in many other specific forms without departing from the spirit and scope of the present invention. Based on the embodiments of the present invention, any changes and modifications made by those of ordinary skill in the art of the present invention according to the above disclosure are within the protection scope of the claims.

Claims

1. A method for detecting the tightness of bolts on a transmission tower, characterized in that: The method comprises the following steps: S100, acquiring a collected bolt vibration signal; S200, extracting characteristic parameters from the collected bolt vibration signal data using a dynamic weighted average Hilbert envelope coefficient algorithm; S300, constructing a Gaussian mixture model for bolt loosening detection, and using the characteristic parameters to train the Gaussian mixture model based on an entropy expectation maximization algorithm; S400, obtaining a bolt vibration signal collected in real time, and extracting a real-time characteristic parameter from the bolt vibration signal data collected in real time by using a dynamic weighted average Hilbert envelope coefficient; S500, inputting the real-time feature parameters into the trained Gaussian mixture model, outputting the clustered feature model data, and judging whether the bolt is loose and the degree of looseness according to the degree of clustering of the feature model data.

2. The method for detecting the tightness of transmission tower bolts according to claim 1, characterized in that: In the step S100, a Lamb wave sensor is used to detect the vibration signal of the bolt.

3. The method for detecting the tightness of transmission tower bolts according to claim 1, characterized in that: The step S200 specifically includes the following steps: S210, decomposing the collected bolt vibration signal into different sub-bands using a gammatone filter bank. The gammatone filter bank is represented by an equivalent rectangular bandwidth, and its expression is: Among them, Q and B min are Graberg parameter and Moore parameter, respectively, and f j is the jth th The center frequency of the channel, in Hz; The signal of each channel is expressed by the following formula: h(t,j)=δt τ-1 exp(-2πb(f j )t)cos(2πf j t+θ) Among them, δ and τ represent the size of the response and the filter order respectively, b(f j ) is the filter bandwidth, θ is the initial phase angle; S220, use Hilbert transform and calculate j th The analytical signal of the channel output; S230, calculate the square amplitude of the analytical signal to obtain j th Hilbert envelope of the channel output; S240, smoothing the Hilbert envelope using a low-pass filter; S250, performing discrete cosine transform to obtain MHEC coefficients; S260, respectively obtain the first-order differential coefficient ΔMHEC and the second-order differential coefficient Δ 2 MHEC is weighted and processed to obtain the new vibration signal characteristic parameter NMHEC, that is, the extraction of vibration signal characteristics is completed. The calculation formula of the new vibration signal characteristic parameter NMHEC is as follows: NMHEC=MHEC+a×ΔMHEC+b×Δ 2 MECH Among them, a and b are weight coefficients, and the constraints are: 0 <b<a<1。 4. The method for detecting the tightness of bolts of a transmission tower according to claim 3, characterized in that: The step S300 specifically includes the following steps: S310, the extracted feature parameters are represented by a set A, A = [x1, x2..., x k ,...,x n ], where x k is a parameter sample; S320, a parameter sample x in set A i The GMM probability density p(x i ) is expressed as: Where n represents the number of components included, u k , represents the expectation and covariance matrix of the k-th Gaussian distribution; λ k represents the weight coefficient of the kth Gaussian distribution in the mixed model, S330, the GMM probability density p(x i )'s fitting process includes two steps, namely K-means and entropy expectation maximization algorithm, where K-means algorithm is used to calculate the initial value of entropy expectation maximization algorithm; S340, the entropy expectation maximization algorithm includes two steps, E-Step and M-Step, and the parameters are repeatedly re-estimated during calculation until the model converges; E-Step is to solve the expected value, and M-Step is to solve the maximum likelihood estimate; the maximum likelihood function maxL(λ,μ,σ based on EEM 2 ) is expressed as follows: in, λ is the Gaussian component weight coefficient, μ is the expectation, σ is the variance, H k is the information entropy of the kth Gaussian component, λ kt and λ kt-1 is the weight coefficient of the kt-th and kt-1-th Gaussian components, w t is the adaptive factor. The calculation parameters of the GMM model based on the EEM algorithm are as follows: Among them, z i is a hidden variable; θ kt is the parameter of the Kth component; S350, the above parameters are iterated in sequence, the expected value is optimized at a fixed value in E-Step, and the expected value is optimized at a fixed value in M-Step, until the change value of the log-likelihood function meets the set threshold ε, it is considered that convergence has occurred at this time, the iterative operation is completed, and the bolt loosening model is established; the convergence expression is as follows, which is the change range of two adjacent iterations: |L kt / L kt-1 |-1≤ε Among them, L kt and L kt-1 are the kt-th and kt-1-th likelihood function values ​​respectively, and ε approaches 0.

5. The method for detecting the tightness of transmission tower bolts according to claim 1, characterized in that: In the step S500 , the more concentrated the characteristic model data is, the tighter the bolt is, and the more divergent the characteristic model data is, the looser the bolt is.

6. The method for detecting the tightness of transmission tower bolts according to claim 1, characterized in that: The step S500 further includes the following steps: S600, with the center of the feature model data as a reference, determine that the horizontal and vertical coordinates are within the set value range as the normal area, and when the number of data points in the horizontal feature model data that exceed the normal area exceeds the preset value, issue an early warning to remind the operation and maintenance personnel to perform tightening processing.

7. The method for detecting the tightness of transmission tower bolts according to claim 6, characterized in that: The normal area is the range within ±2 of the horizontal and vertical coordinates from the center. When the number of data points beyond the normal area in the horizontal feature model data exceeds 1 / 4 of the total data points, early warning processing is performed.

8. The method for detecting the tightness of transmission tower bolts according to claim 7, characterized in that: The early warning process is to send a control signal to the vibration exciter to control the vibration exciter to perform a vibration alarm.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting the tightness of transmission tower bolts as described in any one of claims 1 to 8 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for detecting the tightness of transmission tower bolts according to any one of claims 1 to 8 are implemented.

Images