Pull rope risk identification method and device fusing multi-dimensional data

Abstract

The invention discloses a pull rope risk identification method and device fused with multi-dimensional data, and the method comprises the steps: collecting the multi-dimensional operation data of a pull rope, and the multi-dimensional operation data comprise visual data, tension data, displacement data and vibration data; based on the collected multi-dimensional job data, performing preliminary anomaly analysis processing in combination with an anomaly condition corresponding to each dimension of job data, and giving a preliminary anomaly result of each dimension of job data; based on the preliminary abnormal result of each dimension of operation data, fusing the multi-dimensional operation data to carry out secondary abnormal analysis processing, and giving out a pull rope abnormal result; and based on the abnormal result of the stay rope and the preliminary abnormal result of the operation data of each dimension, giving a risk level of the stay rope to carry out stay rope risk identification. The operation states of the pull rope under different working conditions can be accurately detected, and the risk identification of the pull rope is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power construction, and specifically relates to a method and device for identifying risks of pulling ropes integrating multi-dimensional data. Background Art

[0002] During the construction and maintenance of power systems, rope pulling is one of the key steps in the erection and maintenance of transmission lines. Rope pulling is used to pull transmission cables or construction equipment to ensure the tension and stability of the line, which plays a vital role in ensuring the safety and continuity of power supply. However, rope pulling faces many challenges due to complex terrain and harsh environmental conditions.

[0003] The control of the tension of the rope is a technical problem. In different environments and working conditions, how to maintain appropriate rope tension to avoid transmission line failure or rope damage due to tension overload is a problem that requires precise monitoring and control. Secondly, the deviation of the rope path is also a common problem in rope pulling operations. In complex scenarios, the rope may deviate due to terrain undulations or external forces, which not only affects construction efficiency, but may also pose a threat to the safety of transmission lines or rope damage. In addition, adverse weather conditions, such as strong winds, heavy rains, ice and snow, may cause rope damage, and misoperation during construction may also cause rope damage. If these damages are not detected and repaired in time, they may cause more serious transmission line failures or construction accidents.

[0004] At present, the rope monitoring technology mainly relies on manual experience and lacks accurate real-time monitoring means, which makes it difficult to detect potential risks in time. In order to improve the safety and efficiency of rope pulling operations, the existing technology mainly uses a single sensor for single detection. For example, patent CN112881947A discloses an overhead ground wire detection device based on eddy current sensor, including eddy current probe, excitation signal generation module, logarithmic detection module, signal conditioning module, differential amplifier module and imaging module; the excitation signal generation module generates excitation signals of different frequencies and amplitudes, the logarithmic detection module is mainly realized by logarithmic amplifier and LPF, the signal conditioning module is realized by AD7670 digital-to-analog conversion chip and STM chip, and the differential amplifier module is realized by differential bridge circuit. It uses eddy current detection devices and methods to solve the problems of high cost, bulky equipment, cumbersome process and time-consuming in current practical use of overhead ground wire detection. It has the advantages of not damaging the performance of overhead ground wire, fast detection speed and low instrument cost. It can realize the detection of ground wire and wire rope of high-voltage transmission line, and can also be extended to the detection of wire rope, cable and OPGW strand layer damage. However, it only performs a single detection through eddy current detection device, and does not consider abnormal parameters that may cause cable damage.

[0005] Based on the above problems, how to provide a risk identification method that takes into account various abnormal data of the pull rope is a technical problem that needs to be solved urgently in this field. Summary of the invention

[0006] In view of the defects existing in the above-mentioned prior art, the present invention provides a method and device for risk identification of pull ropes by integrating multi-dimensional data, which can accurately detect the operating status of pull ropes under different working conditions and realize risk identification of pull ropes.

[0007] In a first aspect, the present invention provides a method for identifying risks of pulling ropes by integrating multi-dimensional data, comprising:

[0008] Collect multi-dimensional operation data of the pull rope, wherein the multi-dimensional operation data includes: visual data, tension data, displacement data and vibration data;

[0009] Based on the collected multi-dimensional operation data, preliminary abnormal analysis and processing are carried out in combination with the abnormal conditions corresponding to each dimension of operation data, and preliminary abnormal results of each dimension of operation data are given;

[0010] Based on the preliminary abnormal results of each dimension of operation data, the multi-dimensional operation data is integrated to perform secondary abnormal analysis and processing to give the abnormal results of the pull rope;

[0011] Based on the abnormal results of the rope pulling and the preliminary abnormal results of each dimension of operation data, the risk level of the rope pulling is given for rope pulling risk identification.

[0012] Furthermore, based on the collected multi-dimensional operation data, preliminary abnormality analysis and processing is performed in combination with the abnormal conditions corresponding to each dimension of operation data, and preliminary abnormality results of each dimension of operation data are given, including:

[0013] Perform feature extraction on visual data, or compare visual data with rope image template data to give preliminary visual abnormality results of the rope; compare tension data with preset upper and lower limits of tension thresholds to give preliminary tension abnormality results of the rope; determine the current displacement time curve based on displacement data, and compare it with the standard displacement time curve of the rope under normal working conditions to give preliminary displacement abnormality results of the rope; perform Fourier transform on vibration data to give frequency components and vibration amplitudes, which are compared with frequency range thresholds and vibration range thresholds respectively to give preliminary vibration abnormality results of the rope.

[0014] Furthermore, by comparing with the standard displacement time curve of the pull rope under normal working conditions, the preliminary displacement abnormality results of the pull rope are given, including:

[0015] Calculate the similarity between the current displacement time curve and the standard displacement time curve, and compare the similarity result with the preset similarity threshold. When the similarity result exceeds the preset similarity threshold, it is judged that the displacement of the pull rope is abnormal. Otherwise, it is judged that the displacement of the pull rope is normal.

[0016] Perform Fourier transform on the vibration data to obtain the frequency component and vibration amplitude, which are compared with the frequency range threshold and vibration range threshold respectively to give the preliminary vibration abnormality results of the pull rope, including:

[0017] Determine the time vibration signal based on the vibration data, and perform Fourier transform on the time vibration signal to generate a spectrum diagram of the rope vibration; extract the frequency components and vibration assignments based on the generated spectrum diagram; when the frequency component exceeds the frequency range threshold and / or the vibration assignment exceeds the vibration range threshold, it is judged that the rope vibration is abnormal, otherwise, it is judged that the rope vibration is normal.

[0018] Furthermore, based on the preliminary abnormal results of each dimension of operation data, the multi-dimensional operation data is integrated for secondary abnormal analysis and processing to give the abnormal results of the pull rope, including:

[0019] When the preliminary abnormal result of at least one-dimensional operation data is judged to be abnormal, a probability analysis is performed on the visual data, tension data, displacement data and vibration data, and the abnormal result of the pull rope under the current multi-dimensional operation data is given based on the probability analysis result.

[0020] Furthermore, a probability analysis is performed on the visual data, tension data, displacement data and vibration data, and based on the probability analysis results, the abnormal results of the pull rope under the current multi-dimensional operation data are given, including:

[0021] Based on visual data, tension data, displacement data and vibration data, determine the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data;

[0022] Based on the historical abnormal states of the pull rope, determine the initial probability of the pull rope being in different abnormal states;

[0023] Combining the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states, the total probability of the pull rope observing the multi-dimensional operation data under all abnormal states is given;

[0024] The probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states are jointly processed, and the ratio of the joint processing result to the total probability of the pull rope observing the multi-dimensional operation data in all abnormal states is calculated to give the probability of the pull rope being in different abnormal states;

[0025] Based on the probabilities of the pull rope being in different abnormal states and the probability thresholds corresponding to the different abnormal states, the abnormal state in which the pull rope exists and the abnormal state with the greatest probability are determined.

[0026] Furthermore, based on the visual data, tension data, displacement data and vibration data, the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data is determined, including:

[0027] Based on the neural network classification model pre-constructed through historical visual data and corresponding abnormal states of the pull rope, the probability of observing the current visual data under different abnormal states is determined in combination with the current visual data; based on the normal distribution model pre-constructed through historical tension data and corresponding abnormal states of the pull rope, the probability of observing the current tension data under different abnormal states is determined in combination with the current tension data; based on the reference displacement time curve corresponding to the historical displacement data of different abnormal states of the pull rope, the similarity calculation is performed with the current displacement time curve corresponding to the current displacement data, respectively, to determine the probability of observing the current displacement data under different abnormal states; the vibration data is converted into a frequency domain signal through fast Fourier transform to determine the spectrum diagram, and the distribution characteristics of the spectrum diagram are used to determine the probability of observing the current vibration data under different abnormal states;

[0028] The probabilities of observing the current visual data, tension data, displacement data and vibration data under the same abnormal state are jointly processed to obtain the probability that the pull rope is in different abnormal states under the current multi-dimensional operation data.

[0029] Furthermore, based on the abnormal states in the history of the pulling rope operation, the initial probabilities of the pulling rope being in different abnormal states are determined, including:

[0030] According to the abnormal state of the pulling rope in the historical operation process, determine the number of times the pulling rope is in each abnormal state and the total number of all abnormal states;

[0031] Based on the number of times the pull rope is in each abnormal state and the total number of times of all abnormal states, the initial probability of the pull rope being in different abnormal states is given.

[0032] Furthermore, the total probability of the pull rope observing the multi-dimensional operation data in all abnormal states is given by combining the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states, including:

[0033] The probabilities of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probabilities of the pull rope being in different abnormal states are jointly processed according to the categories of the abnormal states and the joint processing results are superimposed to obtain the total probability of observing the multi-dimensional operation data under all abnormal states.

[0034] Furthermore, the probability of the pull rope being in different abnormal states satisfies the following relationship:

[0035]

[0036] P(Sensor data | γ i ) = P(X | γ i ) * P(Y | γ i ) * P(W | γ i ) * P(Z | γ i )P(Sensor data)

[0037] = P(Sensor data | γ1)·P(γ1) + P(Sensor data | γ2)·P(γ2)

[0038] +... + P(Sensor data | γ n )·P(γ n )

[0039] where P(γ i | Sensor data) is the probability that the drawstring is in the i-th abnormal state, n is the number of abnormal states, i = 1, 2,..., n, P(γ i ) is the initial probability that the drawstring is in the i-th abnormal state, X, Y, W, and Z are visual data, tension data, displacement data, and vibration data respectively, P(Sensor data | γ i ) is the probability that the drawstring is in the i-th abnormal state under the current multi-dimensional operation data, P(Sensor data) is the total probability of observing the multi-dimensional operation data when the drawstring is in all abnormal states, P(X|γ i ), P(Y|γ i ), P(W|γ i ), P(Z|γ i ) are the probabilities of observing the current visual data, tension data, displacement data, and vibration data in the i-th abnormal state respectively.

[0040] Furthermore, based on the drawstring abnormality result and the preliminary abnormality results of each dimension of operation data, a risk level of the drawstring is given for drawstring risk identification, including:

[0041] Based on the drawstring abnormality result and the preliminary abnormality results of each dimension of operation data, determine the number of abnormal drawstrings;

[0042] Based on the number of abnormal drawstrings and the threshold range of the number of abnormalities corresponding to different risk levels, determine the risk level of the drawstring;

[0043] Based on the risk level of the drawstring and the abnormal state with the highest probability, determine the drawstring risk identification result.

[0044] In a second aspect, the present invention also provides a drawstring risk identification device that fuses multi-dimensional data. Using the above drawstring risk identification method, the device includes:

[0045] A data acquisition module, which is used to collect multi-dimensional operation data of the pull rope, wherein the multi-dimensional operation data includes: visual data, tension data, displacement data and vibration data;

[0046] The anomaly detection module is used to perform preliminary anomaly analysis and processing based on the collected multi-dimensional operation data and in combination with the abnormal conditions corresponding to each dimension of operation data, and to provide preliminary abnormal results for each dimension of operation data;

[0047] The data processing and fusion module is used to fuse the multi-dimensional operation data for secondary abnormal analysis and processing based on the preliminary abnormal results of each dimension of operation data, and give the abnormal results of the pull rope;

[0048] The risk warning module is used to identify the risk of rope pulling by giving the risk level of rope pulling based on the abnormal results of rope pulling and the preliminary abnormal results of each dimension of operation data.

[0049] The present invention provides a method and device for identifying risk of pulling ropes by integrating multi-dimensional data, which at least has the following beneficial effects:

[0050] Based on the preliminary abnormal analysis and processing and the secondary abnormal analysis and processing, not only can the real-time state of the pull rope be identified through a single data, but also a more accurate state prediction can be made by combining multi-dimensional data. Among them, by performing preliminary abnormal analysis and processing on the multi-dimensional operation data respectively, potential problems can be quickly identified. When an abnormality is detected, the data of other dimensions are comprehensively considered, that is, the present invention not only considers a single abnormal situation, but also comprehensively considers the entire operation state of the pull rope, so as to take appropriate safety measures, and can accurately detect the operation state of the pull rope, and perform trend prediction and abnormality identification on the pull rope state. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A flow chart of a method for identifying rope risk by integrating multi-dimensional data provided by the present invention;

[0052] Figure 2 A flowchart of abnormal results under current multi-dimensional operation data provided by an embodiment of the present invention;

[0053] Figure 3 A flow chart of a method for identifying risks of pulling a rope provided in one embodiment of the present invention;

[0054] Figure 4 A schematic diagram of a rope risk identification device integrating multi-dimensional data provided by the present invention;

[0055] Figure 5 A schematic diagram of a rope risk identification device integrating multi-dimensional data provided by an embodiment of the present invention;

[0056] Figure 6 A schematic diagram of a rope risk identification device integrating multi-dimensional data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0059] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0060] like Figure 1 As shown, the present invention provides a method for identifying rope risk by integrating multi-dimensional data, comprising:

[0061] Collect multi-dimensional operation data of the pull rope, wherein the multi-dimensional operation data includes: visual data, tension data, displacement data and vibration data;

[0062] Based on the collected multi-dimensional operation data, preliminary abnormal analysis and processing are carried out in combination with the abnormal conditions corresponding to each dimension of operation data, and preliminary abnormal results of each dimension of operation data are given;

[0063] Based on the preliminary abnormal results of each dimension of operation data, the multi-dimensional operation data is integrated to perform secondary abnormal analysis and processing to give the abnormal results of the pull rope;

[0064] Based on the abnormal results of the rope pulling and the preliminary abnormal results of each dimension of operation data, the risk level of the rope pulling is given for rope pulling risk identification.

[0065] The present invention is based on preliminary abnormal analysis and secondary abnormal analysis, and can not only identify the real-time state of the pull rope through a single data, but also combine multi-dimensional data for more accurate state prediction. Among them, by performing preliminary abnormal analysis on multi-dimensional operation data respectively, potential problems can be quickly identified, and when an abnormality is detected, data from other dimensions are comprehensively considered, that is, the present invention not only considers a single abnormal situation, but also comprehensively considers the entire operation state of the pull rope, so as to take appropriate safety measures, and can accurately detect the operation state of the pull rope, and perform trend prediction and abnormality identification on the pull rope state.

[0066] After collecting the multi-dimensional operation data of the pull rope, preliminary abnormality analysis and processing can be performed based on the collected multi-dimensional operation data and combined with the abnormal conditions corresponding to each dimensional operation data to give preliminary abnormality results for each dimensional operation data, which may specifically include:

[0067] Perform feature extraction on visual data, or compare visual data with rope image template data to give preliminary visual abnormality results of the rope; compare tension data with preset upper and lower limits of tension thresholds to give preliminary tension abnormality results of the rope; determine the current displacement time curve based on displacement data, and compare it with the standard displacement time curve of the rope under normal working conditions to give preliminary displacement abnormality results of the rope; perform Fourier transform on vibration data to give frequency components and vibration amplitudes, which are compared with frequency range thresholds and vibration range thresholds respectively to give preliminary vibration abnormality results of the rope.

[0068] Specifically, key features can be extracted from the segmented area of ​​the rope to determine the initial visual abnormality results of the rope (for example, to determine the damage type and location); for example, the texture features of the visual data, such as roughness, contrast, etc., are extracted using methods such as gray level co-occurrence matrix (GLCM) to determine whether there is abnormal wear or cracks on the rope surface. Template matching technology can also be used to compare the current visual data with the pre-established normal rope image template data to determine whether there is an abnormality to determine the initial visual abnormality results of the rope; for example, algorithms such as normalized cross correlation (NCC) or structural similarity (SSIM) are used to compare the visual data with the normal rope image template data to determine whether there is abnormal wear or cracks on the rope surface. The preset tension threshold upper and lower limits include a preset tension threshold upper limit and a preset tension threshold lower limit. When the tension of the rope exceeds the preset tension threshold upper limit, the rope is in a tension overload state, which means that the rope may face the risk of breaking; when the tension of the rope is lower than the preset tension threshold lower limit, the rope is at risk of insufficient tension, which may lead to insufficient operation stability. In either case, an early warning signal will be issued to prompt the operator to check the rope state.

[0069] By comparing with the standard displacement time curve of the pull rope under normal working conditions, the preliminary displacement abnormality results of the pull rope are given, including:

[0070] Calculate the similarity between the current displacement time curve and the standard displacement time curve, and compare the similarity result with the preset similarity threshold. When the similarity result exceeds the preset similarity threshold, it is judged that the displacement of the pull rope is abnormal. Otherwise, it is judged that the displacement of the pull rope is normal.

[0071] Perform Fourier transform on the vibration data to obtain the frequency component and vibration amplitude, which are compared with the frequency range threshold and vibration range threshold respectively to give the preliminary vibration abnormality results of the pull rope, including:

[0072] Determine the time vibration signal based on the vibration data, and perform Fourier transform on the time vibration signal to generate a spectrum diagram of the rope vibration; extract the frequency components and vibration assignments based on the generated spectrum diagram; when the frequency component exceeds the frequency range threshold and / or the vibration assignment exceeds the vibration range threshold, it is judged that the rope vibration is abnormal, otherwise, it is judged that the rope vibration is normal.

[0073] Based on the preliminary abnormal results of each dimension of operation data, the multi-dimensional operation data is integrated for secondary abnormal analysis and processing to give the abnormal results of the pull rope, including:

[0074] like Figure 2 As shown, when the preliminary abnormal result of at least one-dimensional operation data is judged to be abnormal, a probability analysis is performed on the visual data, tension data, displacement data and vibration data, and an abnormal result of the pull rope under the current multi-dimensional operation data is given based on the probability analysis result, including:

[0075] Based on visual data, tension data, displacement data and vibration data, determine the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data;

[0076] Based on the historical abnormal states of the pull rope, determine the initial probability of the pull rope being in different abnormal states;

[0077] Combining the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states, the total probability of the pull rope observing the multi-dimensional operation data under all abnormal states is given;

[0078] The probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states are jointly processed, and the ratio of the joint processing result to the total probability of the pull rope observing the multi-dimensional operation data in all abnormal states is calculated to give the probability of the pull rope being in different abnormal states;

[0079] Based on the probabilities of the pull rope being in different abnormal states and the probability thresholds corresponding to the different abnormal states, the abnormal state in which the pull rope exists and the abnormal state with the greatest probability are determined.

[0080] After obtaining the vibration data of the pull rope and making an abnormal judgment, if a vibration abnormality is detected, it will trigger a subsequent secondary abnormal judgment and risk level assessment. The pull rope is judged whether there is a vibration abnormality based on the frequency components and vibration amplitude of the spectrum graph. This is a preliminary abnormality detection, which aims to quickly identify potential problems. Once an abnormality is detected, other dimensional data (such as tension information, displacement information, etc.) and the types detected as abnormalities (such as tension overload, displacement offset, vibration abnormality) will be comprehensively considered for a more comprehensive risk assessment. By combining data from all dimensions and abnormal judgments, the overall risk level of the pull rope can be evaluated and divided into low risk, medium risk or high risk. This assessment not only takes into account a single abnormal situation, but also integrates the overall state so that appropriate safety measures can be taken. The abnormal state in the present invention may include normal and abnormal states, or may only include abnormal states.

[0081] Wherein, based on the visual data, the tension data, the displacement data and the vibration data, determining the probability that the pull rope is in different abnormal states under the current multi-dimensional operation data may include:

[0082] Based on the neural network classification model pre-constructed through historical visual data and corresponding abnormal states of the pull rope, the probability of observing the current visual data under different abnormal states is determined in combination with the current visual data; based on the normal distribution model pre-constructed through historical tension data and corresponding abnormal states of the pull rope, the probability of observing the current tension data under different abnormal states is determined in combination with the current tension data; based on the reference displacement time curve corresponding to the historical displacement data of different abnormal states of the pull rope, the similarity calculation is performed with the current displacement time curve corresponding to the current displacement data, respectively, to determine the probability of observing the current displacement data under different abnormal states; the vibration data is converted into a frequency domain signal through fast Fourier transform to determine the spectrum diagram, and the distribution characteristics of the spectrum diagram are used to determine the probability of observing the current vibration data under different abnormal states;

[0083] The probabilities of observing the current visual data, tension data, displacement data and vibration data under the same abnormal state are jointly processed to obtain the probability that the pull rope is in different abnormal states under the current multi-dimensional operation data.

[0084] In the present invention, the construction process of the neural network classification model, the normal distribution model, and the reference displacement time curve are all conventional construction methods, and the probability can be determined according to the constructed model. For the neural network classification model, the output result is the probability of different abnormal states. When the dynamic time warping method is used to determine the probability, the similarity score is determined by the similarity. The smaller the similarity value, the more similar it is, the higher the similarity score is. The similarity score is normalized to obtain its corresponding probability. When the probability is determined by fast Fourier transform, the distribution characteristics in the frequency graph (such as peak frequency, bandwidth of the spectrum, distribution shape of the spectrum, etc.) can be used as the basis for abnormal state judgment, and the probability of the distribution characteristics being an abnormal state is determined based on the distribution characteristics. Further, based on fast Fourier transform, the historical vibration data corresponding to different abnormal states can be converted to determine the reference spectrum, and the current spectrum determined by the conversion of the current vibration data is calculated to perform similarity calculation to determine the probability of observing the current vibration data under different abnormal states, wherein the calculation of the spectrum similarity can be calculated by using methods such as Euclidean distance and cosine similarity, and the similarity score is determined, and finally the probability of observing the current vibration data under different abnormal states is given. After the normal distribution model is constructed based on each dimension of operation data and abnormal state, the mean and variance of different operation data under each abnormal state can be determined by maximum likelihood estimation, and the probability of observing the current tension data under different abnormal states can be determined based on the corresponding mean and variance, satisfying the following relationship:

[0085]

[0086] In the formula, P(η|γ i ) is the probability of observing the operation data η under the i-th abnormal state, η∈{X,Y,W,Z}, γ i is the i-th abnormal state, i∈1,2,...,n, n is the number of abnormal states, σ 2 ηi is the variance of the normal distribution model constructed for the operation data η and different abnormal states, μ ηi is the mean of the normal distribution model constructed for the operation data η and different abnormal states.

[0087] Based on the abnormal states in the history of the rope pulling operation, the initial probability of the rope pulling being in different abnormal states is determined, which may include:

[0088] According to the abnormal state of the pulling rope in the historical operation process, determine the number of times the pulling rope is in each abnormal state and the total number of all abnormal states;

[0089] Based on the number of times the pull rope is in each abnormal state and the total number of times of all abnormal states, the initial probability of the pull rope being in different abnormal states is given.

[0090] Combining the probabilities of the drawstring being in different abnormal states under the current multi-dimensional operation data and the initial probabilities of the drawstring being in different abnormal states, the total probability of observing multi-dimensional operation data for the drawstring in all abnormal states is given, including:

[0091] Combining the probabilities of the drawstring being in different abnormal states under the current multi-dimensional operation data and the initial probabilities of the drawstring being in different abnormal states, and performing joint processing on the combined results according to the categories of abnormal states and then summing up the joint processing results, the total probability of observing multi-dimensional operation data for the drawstring in all abnormal states is obtained.

[0092] Among them, the probabilities of the drawstring being in different abnormal states satisfy the following relationship:

[0093]

[0094] P(sensor data | γ i ) = P(X | γ i ) * P(Y | γ i ) * P(W | γ i ) * P(Z | γ i )P(sensor data)

[0095] = P(sensor data | γ1)·P(γ1) + P(sensor data | γ2)·P(γ2)

[0096] +... + P(sensor data | γ n )·P(γ n )

[0097] Among them, P(γ i | sensor data) is the probability that the drawstring is in the i-th abnormal state, n is the number of abnormal states, i = 1, 2,..., n, P(γ i ) is the initial probability that the drawstring is in the i-th abnormal state, X, Y, W, Z are visual data, tension data, displacement data, and vibration data respectively, P(sensor data | γ i ) is the probability that the drawstring is in the i-th abnormal state under the current multi-dimensional operation data, P(sensor data) is the total probability of observing multi-dimensional operation data for the drawstring in all abnormal states, P(X|γ i ), P(Y|γ i ), P(W|γ i ), P(Z|γ i ) are the probabilities of observing the current visual data, tension data, displacement data, and vibration data in the i-th abnormal state respectively.

[0098] When calculating the initial probability that the pull rope is in the i-th abnormal state, the historical operation data of the pull rope within a certain time range can be collected to record the operation conditions under different abnormal states. For example, record the number of occurrences of normal tension, tension overload, displacement offset, abnormal vibration, etc. The collected data is classified according to different abnormal states, and the number of occurrences of each abnormal state is recorded: the number of occurrences of state A (normal operation), state B (tension overload), state C (displacement offset), state D (abnormal vibration), state E (abnormal wear), and state F (surface crack) are N respectively. A 、N B 、N C 、N D 、N E 、N F ; Calculate the total number of all abnormal states N total =N A +N B +N C +N D +N E +N F , according to the number of occurrences of each abnormal state, calculate the initial probability of each state P(Ar) = N Ar / N total , where Ar represents state A, state B, state C, state D, state E or state F.

[0099] When the present invention provides the risk level of the rope pulling based on the rope pulling abnormal result and the preliminary abnormal result of each dimension of operation data to perform rope pulling risk identification, it may include:

[0100] Based on the abnormal results of the pull rope and the preliminary abnormal results of each dimension of operation data, determine the number of abnormal pull ropes;

[0101] Determine the risk level of the pull rope based on the abnormal number of pull ropes and the abnormal number threshold ranges corresponding to different risk levels;

[0102] The pull rope risk identification result is determined based on the risk level of the pull rope and the abnormal state with the highest probability.

[0103] The determined pull rope risk identification result is the risk level of the pull rope and the abnormal state with the highest probability (the most important abnormal state), as well as its corresponding early warning and control operations, so as to facilitate subsequent early warning and control.

[0104] The risk level may include low risk, medium risk and high risk. When the number of abnormalities of the pull rope is 0, it is low risk, when the number of abnormalities of the pull rope is 1 to 3 or 1 to 2, it is medium risk, and when the number of abnormalities of the pull rope is greater than 3 or greater than 2, it is high risk. Based on the risk level of the pull rope and the abnormal state with the highest probability, the early warning operation may include determining the early warning intensity and early warning category according to the risk level and the abnormal state with the highest probability, and may include pulling the rope for normal operation when the risk is low; determining the early warning category according to the abnormal state with the highest probability when the risk is medium, for example, different abnormal states have different early warning sounds / colors / early warning methods, and alerting the operator to pay attention to the pull rope state; when the risk is high, when the warning of the corresponding early warning category is issued, it is necessary to perform safety operations simultaneously and adjust the tension parameters of the pull rope.

[0105] First, potential abnormal data is identified through preliminary abnormal judgment, which can exclude obviously normal states, and then the main abnormal state is determined based on secondary abnormal judgment. For example, if both displacement and vibration exceed the threshold, the state with the highest posterior probability is selected as the final judgment among these two abnormalities. This method can take into account both precision and accuracy, and is particularly suitable for complex rope pulling operation status assessment scenarios.

[0106] After determining the risk level of the pull rope, the present invention can also display other relevant information through the display interface, such as: the current tension, displacement and vibration data of the pull rope. Specific details of the abnormal state and treatment suggestions. Charts of historical data trends and current status. The display interface can provide intuitive risk level display and real-time data monitoring, which helps operators quickly determine the current operating status. Through detailed information and user operation functions, the display interface can support operators to make timely decisions and further enhance the safety and reliability of the system.

[0107] The multi-dimensional operation data in the present invention is detected by corresponding sensors or devices. For example, visual data, tension data, displacement data and vibration data can be detected by visual sensors, pressure sensors, displacement sensors and acceleration sensors respectively. Figure 3 As shown, the rope risk identification method can include:

[0108] S100: Detecting the operation status of the rope during the rope pulling operation;

[0109] S200: Acquire data from each sensor to form sensor information;

[0110] S300: Processing sensor information according to the Bayesian fusion algorithm to form rope state information and rope movement trend information;

[0111] S400: detecting the rope state information and rope movement trend information through threshold detection, dynamic time warping, and frequency domain analysis to identify the abnormal state of the rope;

[0112] S500: Evaluate the risk level of the rope pulling operation based on the abnormal state and the rope pulling movement trend information, and issue a warning signal if the risk level exceeds the safety threshold.

[0113] Among them, in the embodiment of the present invention, the rope pulling risk identification method integrating multi-dimensional data includes, in step S100, detecting the operation state of the rope pulling during the rope pulling operation. For specific methods, please refer to Figure 5 , Figure 6 and its corresponding description, which will not be repeated here. The rope-pulling risk identification method integrating multi-dimensional data includes, in step S200, obtaining data from each sensor to form sensor information. The rope-pulling risk identification method integrating multi-dimensional data includes, in step S300, processing sensor information according to a Bayesian fusion algorithm to form rope-pulling state information and rope-pulling movement trend information. The rope-pulling risk identification method integrating multi-dimensional data includes, in step S400, detecting rope-pulling state information and rope-pulling movement trend information through threshold detection, dynamic time warping, and frequency domain analysis to identify abnormal states of the rope. The abnormal states may include tension overload, displacement offset, and abnormal vibration, and may also include abnormal wear, surface cracks, and the like. The rope-pulling risk identification method integrating multi-dimensional data includes, in step S500, evaluating the risk level of the rope-pulling operation based on the abnormal state and rope-pulling movement trend information. If the risk level exceeds the safety threshold, a warning signal is issued.

[0114] like Figure 4 As shown, the present invention also provides a device for identifying the risk of pulling a rope by integrating multi-dimensional data, adopting the above-mentioned method for identifying the risk of pulling a rope, and the device comprises:

[0115] A data acquisition module, which is used to collect multi-dimensional operation data of the pull rope, wherein the multi-dimensional operation data includes: visual data, tension data, displacement data and vibration data;

[0116] The anomaly detection module is used to perform preliminary anomaly analysis and processing based on the collected multi-dimensional operation data and in combination with the abnormal conditions corresponding to each dimension of operation data, and to provide preliminary abnormal results for each dimension of operation data;

[0117] The data processing and fusion module is used to fuse the multi-dimensional operation data for secondary abnormal analysis and processing based on the preliminary abnormal results of each dimension of operation data, and give the abnormal results of the pull rope;

[0118] The risk warning module is used to identify the risk of rope pulling by giving the risk level of rope pulling based on the abnormal results of rope pulling and the preliminary abnormal results of each dimension of operation data.

[0119] In actual application scenarios, the device of the present invention may include: a sensor module 100, a data acquisition module 200, a data processing and fusion module 300, an anomaly detection module 400, and a risk warning module 500. The sensor module 100 includes a visual sensor 110, a pressure sensor 120, a displacement sensor 130 and an acceleration sensor 140.

[0120] In the embodiment of the present invention, the sensor module 100 is used to detect the working state of the rope during the rope pulling operation. The sensor module 100 includes a visual sensor 110, a pressure sensor 120, a displacement sensor 130 and an acceleration sensor 140. It can be understood that the sensor module 100 is distributed according to different parts of the rope.

[0121] It is understood that the visual sensor 110 is used to capture the surface deformation, wear and tear of the rope and its running posture in real time. The rope image is analyzed by computer vision technology to identify whether the rope has local wear, breakage or external interference. The visual sensor 110 is usually installed at the key nodes where the rope passes to ensure that the overall movement of the rope and the state changes at key positions can be captured.

[0122] The pressure sensor 120 is used to detect the tension of the pull rope and is arranged at the fixed end of the pull rope or at the node with greater force. When the pull rope is subjected to tension, the pressure sensor 120 senses the tension change of the pull rope in real time and outputs the tension data. Combined with the working load of the pull rope, the system can determine whether the current pull rope is overloaded or abnormally stressed. The pressure sensors can be distributed at multiple positions of the pull rope to monitor the overall force condition.

[0123] The displacement sensor 130 is used to monitor the displacement of the pull rope, especially the horizontal or vertical displacement. The displacement sensor 130 can sense the relative position change of the pull rope during the movement through optical, laser or ultrasonic technology. The displacement sensor 130 is usually distributed on the moving track of the pull rope. By continuously recording the position change of the pull rope, the movement curve of the pull rope can be drawn and its working stability can be analyzed.

[0124] The acceleration sensor 140 is used to detect the vibration state of the pull rope, and captures small vibrations and impacts by measuring the acceleration changes of the pull rope. The acceleration sensor 140 is usually arranged at key points of the pull rope, such as locations with high tension, to identify possible abnormal vibrations (such as vibrations caused by external interference or internal structural damage). These data help determine whether the pull rope is running smoothly.

[0125] In the embodiment of the present invention, the data acquisition module 200 is used to acquire data from each sensor in the sensor module 100 to form sensor information.

[0126] It can be understood that the data acquisition module 200 is used to obtain data from each sensor in the sensor module 100 to form sensor information. The sensor module 100 includes a visual sensor 110, a pressure sensor 120, a displacement sensor 130 and an acceleration sensor 140, and each sensor detects different state parameters of the pull rope through a distributed arrangement. The data acquisition module 200 will collect all these data and provide them to the data processing and fusion module 300 for further analysis and processing.

[0127] In the embodiment of the present invention, the data processing and fusion module 300 is used to process the sensor information according to the Bayesian fusion algorithm to form the rope state information and the rope movement trend information.

[0128] In an embodiment of the present invention, the data processing and fusion module 300 is also used to obtain the initial probability of the state information of the pull rope, and the initial probability is the probability of the initial state of the pull rope. The data from the visual sensor 110, the pressure sensor 120, the displacement sensor 130 and the acceleration sensor 140 are integrated to construct a likelihood function, and the likelihood function is the possibility of the current state of the pull rope. The likelihood function is processed according to the weighted average to obtain the evidence probability, and the evidence probability is the total probability of observing specific sensor data under all possible states. The posterior probability of the pull rope is calculated according to the Bayesian formula, and the posterior probability is the probability that the pull rope is in a certain state given the sensor data. The state estimate of the pull rope is updated according to the calculated posterior probability to form the state of the pull rope.

[0129] The data processing and fusion module 300 uses the Bayesian fusion algorithm to comprehensively process the data from various sensors to form the rope state information and rope movement trend information. This module can not only identify the real-time state of the rope through the data of a single sensor, but also combine the data of multiple sensors to make more accurate state predictions.

[0130] It is understandable that the data processing and fusion module 300 first obtains the initial probability of the rope pulling state information. The initial probability represents the probability of the initial state of the rope pulling, which can be based on historical data, the state of the system at initialization, or other empirical information. In the initial stage of the rope pulling operation, the initial probability is the system's preliminary estimate of the rope pulling state.

[0131] The likelihood function reflects the possible state of the rope under the current state. The data processing and fusion module 300 extracts key information from the data of the visual sensor 110, the pressure sensor 120, the displacement sensor 130 and the acceleration sensor 140, and constructs a corresponding likelihood function in combination with the kinematic model of the rope. The function represents the possibility of observing the current sensor data under a specific state.

[0132] The data processing and fusion module 300 performs weighted average processing on the likelihood function to obtain the evidence probability. The evidence probability is the total probability of observing the current sensor data under all possible states. By calculating the evidence probability, the system can understand the overall situation of each state under uncertainty.

[0133] According to the Bayesian formula, the data processing and fusion module 300 calculates the posterior probability of the pull rope, that is, the probability that the pull rope is in a certain state given the sensor data.

[0134] In an embodiment of the present invention, the abnormality detection module 400 is used to detect the rope state information and the rope movement trend information through threshold detection, dynamic time warping, and frequency domain analysis to identify the abnormal state of the rope, which includes tension overload, displacement offset, and abnormal vibration.

[0135] The main function of the abnormality detection module 400 is to detect the state information of the pull rope and the movement trend information of the pull rope through threshold detection, dynamic time warping (DTW) and frequency domain analysis, and then identify possible abnormal conditions. These abnormal conditions include but are not limited to tension overload, displacement offset and abnormal vibration. This multi-level detection method can achieve comprehensive monitoring and abnormal analysis of the pull rope state.

[0136] Please also read Figure 6 , Figure 5 Schematic diagram of a module of a rope risk identification device integrating multi-dimensional data provided by another embodiment of the present invention. Figure 5 Compared with the rope risk identification device 10 integrating multi-dimensional data shown in FIG. Figure 6 The multi-dimensional data-fused rope risk identification device 10 shown in FIG. 1 also includes a sensor module 100, a data acquisition module 200, a data processing and fusion module 300, an abnormality detection module 400, and a risk warning module 500. The sensor module 100 includes a visual sensor 110, a pressure sensor 120, a displacement sensor 130, and an acceleration sensor 140. Figure 5 The difference is that the rope risk identification device 10 integrating multi-dimensional data further includes: an automatic control module 600 and a display interface 700 , and the risk warning module 500 further includes: a threshold detection unit 510 , a dynamic time warping unit 520 , and a frequency domain analysis unit 530 .

[0137] In the embodiment of the present invention, the risk warning module 500 is used to evaluate the risk level of the rope pulling operation according to the abnormal state and the rope pulling movement trend information, and issue a warning signal if the risk level exceeds the safety threshold.

[0138] In an embodiment of the present invention, the risk warning module 500 includes a threshold detection unit 510. The threshold detection unit 510 is used to obtain the tension information and displacement information of the pull rope from the pressure sensor 120, the displacement sensor 130 and the acceleration sensor 140 respectively. An upper tension threshold and a lower tension threshold are set for the tension information, an offset threshold is set for the displacement information, and a vibration frequency threshold is set for the vibration information. If the tension of the pull rope exceeds the set upper limit or is lower than the lower limit, the pull rope is judged to be overloaded or too low in tension, and a warning signal is issued. If the displacement offset of the pull rope exceeds the offset threshold, the pull rope is judged to be abnormal in displacement offset, and a warning signal is issued.

[0139] The pressure sensor 120 monitors the tension status of the pull rope in real time. The threshold detection unit 510 sets two thresholds for the tension of the pull rope: an upper tension threshold and a lower tension threshold. When the tension of the pull rope exceeds the upper tension threshold, the threshold detection unit 510 determines that the state of the pull rope is tension overload, which means that the pull rope may face the risk of breaking. When the tension of the pull rope is lower than the lower tension threshold, the system will consider that there is a risk of insufficient tension in the pull rope, which may result in insufficient operational stability. In either case, the system will issue a warning signal to prompt the operator to check the state of the pull rope.

[0140] The displacement sensor 130 is used to detect the displacement state of the pull rope during operation, including the lateral or longitudinal offset. The threshold detection unit 510 sets a displacement offset threshold for the displacement, that is, within a certain range, the displacement of the pull rope is normal, but if the displacement exceeds the set offset threshold, the system will consider that the pull rope has an abnormal offset, which may be caused by external force or operational error. Once an abnormal displacement is detected, the system will also issue a warning signal, requiring immediate investigation and processing.

[0141] The acceleration sensor 140 is used to detect the vibration state of the pull rope, and analyzes the vibration frequency and amplitude by measuring the acceleration change of the pull rope. The threshold detection unit 510 sets a vibration frequency threshold and a vibration amplitude threshold for the vibration state. If the vibration frequency of the pull rope exceeds the set frequency range, it may mean that the pull rope is subjected to abnormal external force or the equipment is unstable. Similarly, if the vibration amplitude exceeds the set threshold, the abnormal shaking of the pull rope may be caused by mechanical problems or environmental influences. When abnormal vibration is detected, the system will issue a warning signal to prompt the operator to check whether there are any problems with the equipment and the pull rope.

[0142] The risk warning module 500 also includes a dynamic time warping unit 520. The dynamic time warping unit 520 is used to obtain the displacement time series of the pull rope under normal working conditions to form a standard reference trajectory. The risk warning module 500 obtains the displacement time series of the pull rope collected by the displacement sensor 130 to form a displacement curve at the current moment. The risk warning module 500 compares the standard reference trajectory with the displacement curve to obtain the difference between the standard reference trajectory and the displacement curve. If the difference exceeds the similarity threshold, the pull rope is judged to be abnormally displaced and a warning signal is issued.

[0143] The function of the risk warning module 500 is not limited to simple threshold detection, but also uses more complex algorithms to perform abnormal detection of displacement and vibration to improve detection accuracy and operation safety. The dynamic time warping unit 520 accurately compares the displacement time series of the pull rope through the dynamic time warping algorithm (Dynamic Time Warping, DTW) to identify abnormal situations. Under the normal working state of the pull rope, the system will continuously record the displacement time series of the pull rope through the displacement sensor 130. After a period of recording and processing, a standard displacement reference trajectory is formed, which represents the displacement change characteristics of the pull rope under normal conditions. In the actual operation process, the system will obtain the displacement data of the pull rope in real time to form a displacement curve at the current moment. This curve reflects the current actual state of the pull rope. The dynamic time warping unit 520 will compare the current displacement curve with the standard reference trajectory. Through the dynamic time warping algorithm (DTW), the system can compare the differences between the two time series. Even if there are nonlinear differences in the time series, DTW can also perform accurate matching. After comparison, the system calculates the similarity between the standard reference trajectory and the current displacement curve. When the similarity value is lower than the preset similarity threshold, the system determines that the displacement curve of the pull rope has undergone an abnormal change. If the similarity difference exceeds the threshold, the dynamic time warping unit 520 will consider that the displacement of the pull rope is abnormal and immediately issue a warning signal. This method can provide predictive warning before the pull rope is about to deviate or fail.

[0144] In the embodiment of the present invention, the risk warning module 500 also includes a frequency domain analysis unit 530. The frequency domain analysis unit 530 is used to obtain the vibration data of the pull rope from the acceleration sensor and generate a time domain signal. The risk warning module 500 performs a fast Fourier transform on the collected time domain vibration signal to obtain a frequency domain signal and generate a spectrum diagram of the pull rope vibration. The risk warning module 500 obtains the frequency component and the vibration amplitude according to the spectrum diagram. If the frequency component exceeds the frequency range threshold or the vibration amplitude exceeds the amplitude threshold, the pull rope is judged to be abnormally vibrating and a warning signal is issued.

[0145] The frequency domain analysis unit 530 is used to perform frequency domain analysis on the vibration data of the pull rope to identify abnormal vibration behavior. By converting the time domain signal into a frequency domain signal, the system can better identify the characteristics of the vibration. The system first obtains the vibration data of the pull rope through the acceleration sensor 140. These data are presented in the form of time domain signals, reflecting the vibration of the pull rope during the operation. The risk warning module 500 uses Fast Fourier Transform (FFT) to convert the vibration signal in the time domain into a frequency domain signal. FFT can decompose complex time signals into different frequency components and generate corresponding spectrum graphs. The risk warning module 500 analyzes the generated spectrum graph and extracts the frequency components and vibration amplitudes therein. These two parameters can reflect the vibration characteristics of the pull rope: Frequency component: related to the speed and frequency change of the pull rope vibration. Vibration amplitude: reflects the intensity of vibration. The system makes a judgment based on the preset frequency range threshold and amplitude threshold. If the frequency component exceeds the preset frequency range, or the amplitude exceeds the set threshold, it is considered that the pull rope has an abnormal vibration. Once abnormal vibration is detected, the risk warning module 500 immediately sends out a warning signal to remind the operator to check the working status of the pull rope.

[0146] In the embodiment of the present invention, the rope risk identification device 10 integrating multi-dimensional data further includes an automatic control module 600. The risk warning module 500 is also used to evaluate the risk level of the rope pulling operation according to the abnormal state information and movement trend information of the rope pulling operation, and the risk level includes low risk, medium risk and high risk. If the risk warning module detects a high risk, the automatic control module 600 is triggered to take safety measures. The automatic control module 600 is used to adjust the tension parameters of the rope pulling operation.

[0147] The automatic control module 600 is used to take corresponding safety measures according to the risk level evaluated by the risk warning module 500 to ensure the safety of the rope pulling operation. The module prevents possible accidents by adjusting the tension parameters of the rope pulling. The automatic control module 600 receives the risk level information of the rope pulling from the risk warning module 500. The risk level is divided into low risk, medium risk and high risk. The assessment of the risk level takes into account the abnormal state information and movement trend information of the rope pulling. According to the different risk levels, the system takes corresponding safety measures: Low risk: normal operation without intervention. Medium risk: enhanced system monitoring, warning the operator to pay attention to the rope pulling state. High risk: take safety measures immediately, adjust the tension parameters, and avoid accidents. If the risk level is high risk, the automatic control module 600 will adjust the tension parameters of the rope pulling. This includes reducing the tension: if the tension overload is detected, the system will automatically reduce the tension of the rope pulling to avoid further overload. Increase the tension: if the tension is detected to be too low, the system will automatically increase the tension of the rope pulling to ensure that the rope pulling remains within the safe working range. The automatic control module 600 adjusts the actual operating state of the rope pulling through the control system. For example, the way the tension of the cable is applied may be adjusted or other control mechanisms may be triggered to ensure the stability of the cable.

[0148] In the embodiment of the present invention, the device 10 for identifying the risk of pulling a rope by integrating multi-dimensional data further includes a display interface 700. The display interface 700 is also used to display the risk level.

[0149] It is understood that the display interface 700 is the user interface of the system, which is responsible for displaying the risk level and related information to the operator for real-time monitoring and decision-making. The display interface 700 displays risk level information in real time, including low risk, medium risk and high risk. Different risk levels are distinguished by different visual identifiers (such as colors, icons) to ensure that the operator can quickly identify the current risk status. In addition to the risk level, the display interface 700 also displays other relevant information, such as: the current tension, displacement and vibration data of the pull rope. Specific details and treatment suggestions for abnormal conditions. Charts of historical data trends and current status. When the risk level reaches a high risk, the display interface 700 will trigger an alarm prompt, including a sound alarm, a flashing indicator light, etc., to quickly attract the attention of the operator. The display interface 700 provides an intuitive risk level display and real-time data monitoring, which helps the operator to quickly determine the current operation status. Through detailed information and user operation functions, the display interface 700 can support operators to make timely decisions and further enhance the safety and reliability of the system.

[0150] The rope-pulling risk identification device 10 integrating multi-dimensional data in the embodiment of the present invention realizes comprehensive risk management and real-time monitoring through the cooperation of the automatic control module 600 and the display interface 700. The automatic control module 600 can automatically adjust the tension of the rope when a high risk is detected to reduce safety hazards; while the display interface 700 provides a clear risk level display and operation interface to support operators to conduct timely monitoring and decision-making. This comprehensive system design effectively improves the safety and efficiency of rope-pulling operations.

[0151] Although preferred embodiments of the present invention have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for identifying rope risk by integrating multi-dimensional data, characterized in that: include: Collect multi-dimensional operation data of the pull rope, wherein the multi-dimensional operation data includes: visual data, tension data, displacement data and vibration data; Based on the collected multi-dimensional operation data, preliminary abnormal analysis and processing are carried out in combination with the abnormal conditions corresponding to each dimension of operation data, and preliminary abnormal results of each dimension of operation data are given; Based on the preliminary abnormal results of each dimension of operation data, the multi-dimensional operation data is integrated to perform secondary abnormal analysis and processing to give the abnormal results of the pull rope; Based on the abnormal results of the rope pulling and the preliminary abnormal results of each dimension of operation data, the risk level of the rope pulling is given for rope pulling risk identification.

2. The method for identifying the risk of pulling a rope according to claim 1, characterized in that: Based on the collected multi-dimensional operation data, preliminary abnormal analysis and processing is performed in combination with the abnormal conditions corresponding to each dimension of operation data, and preliminary abnormal results of each dimension of operation data are given, including: Perform feature extraction on visual data, or compare visual data with rope image template data to give preliminary visual abnormality results of the rope; compare tension data with preset upper and lower limits of tension thresholds to give preliminary tension abnormality results of the rope; determine the current displacement time curve based on displacement data, and compare it with the standard displacement time curve of the rope under normal working conditions to give preliminary displacement abnormality results of the rope; perform Fourier transform on vibration data to give frequency components and vibration amplitudes, which are compared with frequency range thresholds and vibration range thresholds respectively to give preliminary vibration abnormality results of the rope.

3. The method for identifying the risk of pulling a rope according to claim 2, characterized in that: By comparing with the standard displacement time curve of the pull rope under normal working conditions, the preliminary displacement abnormality results of the pull rope are given, including: Calculate the similarity between the current displacement time curve and the standard displacement time curve, and compare the similarity result with the preset similarity threshold. When the similarity result exceeds the preset similarity threshold, it is judged that the displacement of the pull rope is abnormal. Otherwise, it is judged that the displacement of the pull rope is normal. Perform Fourier transform on the vibration data to obtain the frequency component and vibration amplitude, which are compared with the frequency range threshold and vibration range threshold respectively to give the preliminary vibration abnormality results of the pull rope, including: Determine the time vibration signal based on the vibration data, and perform Fourier transform on the time vibration signal to generate a spectrum diagram of the rope vibration; extract the frequency components and vibration assignments based on the generated spectrum diagram; when the frequency component exceeds the frequency range threshold and / or the vibration assignment exceeds the vibration range threshold, it is judged that the rope vibration is abnormal, otherwise, it is judged that the rope vibration is normal.

4. The method for identifying the risk of pulling a rope according to claim 1, characterized in that: Based on the preliminary abnormal results of each dimension of operation data, the multi-dimensional operation data is integrated for secondary abnormal analysis and processing to give the abnormal results of the pull rope, including: When the preliminary abnormal result of at least one-dimensional operation data is judged to be abnormal, a probability analysis is performed on the visual data, tension data, displacement data and vibration data, and the abnormal result of the pull rope under the current multi-dimensional operation data is given based on the probability analysis result.

5. The method for identifying the risk of pulling a rope according to claim 4, characterized in that: Probabilistic analysis is performed on visual data, tension data, displacement data, and vibration data, and based on the results of the probability analysis, abnormal results of the pull rope under the current multi-dimensional operation data are given, including: Based on visual data, tension data, displacement data and vibration data, determine the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data; Based on the historical abnormal states of the pull rope, determine the initial probability of the pull rope being in different abnormal states; Combining the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states, the total probability of the pull rope observing the multi-dimensional operation data under all abnormal states is given; The probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states are jointly processed, and the ratio of the joint processing result to the total probability of the pull rope observing the multi-dimensional operation data in all abnormal states is calculated to give the probability of the pull rope being in different abnormal states; Based on the probabilities of the pull rope being in different abnormal states and the probability thresholds corresponding to the different abnormal states, the abnormal state in which the pull rope exists and the abnormal state with the greatest probability are determined.

6. The method for identifying the risk of pulling a rope according to claim 5, characterized in that: Based on visual data, tension data, displacement data and vibration data, determine the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data, including: Based on the neural network classification model pre-constructed through historical visual data and corresponding abnormal states of the pull rope, the probability of observing the current visual data under different abnormal states is determined in combination with the current visual data; based on the normal distribution model pre-constructed through historical tension data and corresponding abnormal states of the pull rope, the probability of observing the current tension data under different abnormal states is determined in combination with the current tension data; based on the reference displacement time curve corresponding to the historical displacement data of different abnormal states of the pull rope, the similarity calculation is performed with the current displacement time curve corresponding to the current displacement data, respectively, to determine the probability of observing the current displacement data under different abnormal states; the vibration data is converted into a frequency domain signal through fast Fourier transform to determine the spectrum diagram, and the distribution characteristics of the spectrum diagram are used to determine the probability of observing the current vibration data under different abnormal states; The probabilities of observing the current visual data, tension data, displacement data and vibration data under the same abnormal state are jointly processed to obtain the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data.

7. The method for identifying the risk of pulling a rope according to claim 5 or 6, characterized in that: Based on the abnormal states of the rope pulling process in history, determine the initial probability of the rope pulling being in different abnormal states, including: According to the abnormal state of the pulling rope in the historical operation process, determine the number of times the pulling rope is in each abnormal state and the total number of all abnormal states; Based on the number of times the pull rope is in each abnormal state and the total number of times of all abnormal states, the initial probability of the pull rope being in different abnormal states is given.

8. The method for identifying the risk of pulling a rope according to claim 6, characterized in that: Combining the probability of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probability of the pull rope being in different abnormal states, the total probability of the pull rope observing the multi-dimensional operation data in all abnormal states is given, including: The probabilities of the pull rope being in different abnormal states under the current multi-dimensional operation data and the initial probabilities of the pull rope being in different abnormal states are jointly processed according to the categories of the abnormal states and the joint processing results are superimposed to obtain the total probability of observing the multi-dimensional operation data under all abnormal states.

9. The method for identifying the risk of pulling a rope according to claim 5, characterized in that: Based on the abnormal results of the rope pulling and the preliminary abnormal results of each dimension of operation data, the risk level of the rope pulling is given to identify the rope pulling risk, including: Based on the abnormal results of the pull rope and the preliminary abnormal results of each dimension of operation data, determine the number of abnormal pull ropes; Determine the risk level of the pull rope based on the abnormal number of pull ropes and the abnormal number threshold ranges corresponding to different risk levels; The pull rope risk identification result is determined based on the risk level of the pull rope and the abnormal state with the highest probability.

10. A rope risk identification device integrating multi-dimensional data, characterized in that: The method for identifying the risk of pulling a rope as claimed in any one of claims 1 to 9 is adopted, and the device comprises: A data acquisition module, which is used to collect multi-dimensional operation data of the pull rope, wherein the multi-dimensional operation data includes: visual data, tension data, displacement data and vibration data; The anomaly detection module is used to perform preliminary anomaly analysis and processing based on the collected multi-dimensional operation data and in combination with the abnormal conditions corresponding to each dimension of operation data, and to provide preliminary abnormal results for each dimension of operation data; The data processing and fusion module is used to fuse the multi-dimensional operation data for secondary abnormal analysis based on the preliminary abnormal results of each dimension of operation data, and give the abnormal results of the pull rope; The risk warning module is used to identify the risk of rope pulling by giving the risk level of rope pulling based on the abnormal results of rope pulling and the preliminary abnormal results of each dimension of operation data.

Images