Tunnel fault prediction method and device, equipment and storage medium

Abstract

The invention relates to the technical field of tunnel detection, and discloses a tunnel fault prediction method, device and equipment and a storage medium, and the method comprises the steps: obtaining an accumulation sequence based on a historical tunnel fault data sequence in combination with a preset accumulation algorithm; based on the historical tunnel fault data sequence and the accumulation sequence, processing the historical tunnel fault data sequence and the accumulation sequence in combination with a preset gray differential equation to obtain a gray model development coefficient and a gray action quantity; and obtaining a tunnel fault prediction value based on the gray model development coefficient, the gray action quantity and the preset gray differential equation. According to the invention, a tunnel future fault prediction result can be obtained through a small amount of tunnel fault data.

Description

Technical Field

[0001] The present application relates to the field of tunnel detection technology, and in particular to a tunnel fault prediction method, device, equipment and storage medium. Background Art

[0002] Tunnels are an important form of human use of underground space. They are mainly buried in the ground, which makes full use of underground space and rationally arranges urban traffic development. Tunnels play different roles in different regions, but they all solve problems in traffic construction; for example, some tunnels are the carriers of urban rail subways, some tunnels need to pass through mountains, and some tunnels are built on the bottom of rivers. Generally speaking, no matter what kind of tunnel, the construction environment is relatively complex, so it is also difficult to monitor tunnel faults. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a tunnel fault prediction method, apparatus, device and storage medium, which can obtain future tunnel fault prediction results through a small amount of tunnel fault data.

[0004] In a first aspect, an embodiment of the present application provides a tunnel fault prediction method, comprising: Based on the historical tunnel fault data sequence combined with a preset accumulation algorithm, an accumulation sequence is obtained; Based on the historical tunnel fault data sequence and the cumulative sequence, the historical tunnel fault data sequence and the cumulative sequence are processed in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action; A tunnel fault prediction value is obtained based on the grey model development coefficient, the grey action and the preset grey differential equation.

[0005] In some embodiments, the step of obtaining the accumulation sequence based on the historical tunnel fault data sequence in combination with a preset accumulation algorithm includes: The accumulated data corresponding to each historical tunnel fault data is calculated in sequence according to the preset accumulation algorithm; wherein the historical tunnel fault data in the historical tunnel fault data sequence are sorted according to the time series; each accumulated data is obtained by weighted summing the corresponding historical tunnel fault data and the historical tunnel fault data before the corresponding historical tunnel fault data; A plurality of the accumulated data constitute the accumulated sequence.

[0006] In some embodiments, when calculating each of the accumulated data, the weight corresponding to each of the historical tunnel fault data is determined according to the time length from the predicted time point.

[0007] In some embodiments, when calculating each of the accumulated data, among the various historical tunnel fault data, the weight corresponding to the historical tunnel fault data with a longer time distance from the predicted time point is smaller than the weight corresponding to the historical tunnel fault data with a shorter time distance from the predicted time point.

[0008] In some embodiments, the processing of the historical tunnel fault data sequence and the cumulative sequence based on the historical tunnel fault data sequence and the cumulative sequence in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action comprises: Determine a production sequence close to the mean value according to the accumulated data in the accumulated sequence; constructing a data matrix according to the adjacent mean production sequence, and constructing a vector according to the historical tunnel failure data sequence; Based on the data matrix and the vector, the preset grey differential equation is combined to obtain the parameter column of the grey model development coefficient and the grey action.

[0009] In some embodiments, before constructing a data matrix according to the adjacent mean production sequence and constructing a vector according to the historical tunnel fault data sequence, the method further includes: constructing the preset grey differential equation according to the historical tunnel fault data sequence and the adjacent mean production sequence, and derivatizing the preset grey differential equation to obtain a whitening equation; The step of obtaining the parameter list of the grey model development coefficient and the grey action based on the data matrix and the vector and combining the preset grey differential equation comprises: Based on the data matrix and the vector, the whitening equation is combined to obtain the parameter column of the grey model development coefficient and the grey action.

[0010] In some embodiments, the step of obtaining a tunnel fault prediction value based on the grey model development coefficient, the grey action and the preset grey differential equation includes: Obtaining an initial prediction value of tunnel failure at each time point according to the grey model development coefficient, the grey action and the preset grey differential equation; The initial prediction value of the tunnel failure at each time point is subjected to a cumulative inverse generation operation to obtain the tunnel failure prediction value.

[0011] In a second aspect, an embodiment of the present application provides a tunnel fault prediction device, including: An accumulation sequence acquisition module is used to obtain an accumulation sequence based on a historical tunnel fault data sequence combined with a preset accumulation algorithm; A parameter calculation module, used for processing the historical tunnel fault data sequence and the cumulative sequence based on the historical tunnel fault data sequence and the cumulative sequence in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action; The tunnel fault prediction value obtaining module is used to obtain the tunnel fault prediction value based on the grey model development coefficient, the grey action and the preset grey differential equation.

[0012] In a third aspect, an embodiment of the present application provides a terminal device, the terminal device comprising a processor and a memory, the memory storing a computer program, and the processor being used to execute the computer program to implement the above-mentioned tunnel fault prediction method.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed on a processor, implements the above-mentioned tunnel fault prediction method.

[0014] The embodiments of the present application have the following beneficial effects: in the present application, firstly, a cumulative sequence is obtained by combining a historical tunnel fault data sequence with a preset cumulative algorithm, and then the historical tunnel fault data sequence and the cumulative sequence are processed according to the historical tunnel fault data sequence and the cumulative sequence in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action, and finally, a tunnel fault prediction value is obtained based on the grey model development coefficient, the grey action and the preset grey differential equation. In this way, the present application realizes the prediction of tunnel faults by using less monitoring data, which is a relatively concise, effective and accurate method for predicting faults in complex environments such as tunnels, and the cost is also low. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A first flow chart of the tunnel fault prediction method according to an embodiment of the present application is shown; Figure 2 A schematic diagram of tunnel detection in an embodiment of the present application is shown; Figure 3 A second flow chart of the tunnel fault prediction method according to an embodiment of the present application is shown; Figure 4 A third flow chart of the tunnel fault prediction method according to an embodiment of the present application is shown; Figure 5 A fourth flow chart of the tunnel fault prediction method according to an embodiment of the present application is shown; Figure 6 A schematic diagram of the structure of a tunnel fault prediction device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0018] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0019] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0020] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0021] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0022] Safety evaluation of in-service structures, such as buildings, bridges, tunnels, dams and other infrastructure, and timely investigation and disposal of risk hazards in key areas and key fields are very important for ensuring public safety. Safety evaluation of in-service structures can detect hidden dangers at an early stage. Regular safety evaluation can help to detect potential defects and hidden dangers of structures, such as cracks, corrosion, material aging, etc., so as to take necessary maintenance and reinforcement measures to avoid accidents. Through a comprehensive evaluation of the structure, high-risk areas and weak links can be identified, and corresponding risk management strategies can be formulated to reduce the probability of accidents and extend the service life.

[0023] For in-service structures, due to the complex construction environment of tunnels and the short time available for tunnel operations, it is often necessary to quickly make an accurate safety assessment of the in-service tunnels in a short period of time. However, some fault prediction methods in existing technologies usually require more data as support. Some tunnels were built relatively early, so there are problems with incomplete basic information and irregular data in the maintenance and monitoring process. As a result, there are fewer data required for safety assessment, which makes it more difficult to conduct structural safety assessment of in-service tunnels.

[0024] Normally, tunnel structure deformation monitoring often requires a long period of continuous monitoring to obtain sufficient data, and requires understanding of the distribution type of the tunnel to select the appropriate function form for fitting and study its deformation law. However, this work is not only time-consuming and laborious, but also often requires quick judgment during emergency rescue, which cannot guarantee a long enough monitoring time.

[0025] Based on this, the present application proposes a tunnel fault prediction method, device, equipment and storage medium. The tunnel fault prediction method is based on improved grey system theory, and can predict future tunnel fault conditions through a small amount of incomplete data.

[0026] The tunnel fault prediction method is described below with reference to some specific embodiments.

[0027] Figure 1 A schematic diagram of a flow chart of a tunnel fault prediction method according to an embodiment of the present application is shown. Exemplarily, the tunnel fault prediction method comprises the following steps: Step S100, obtaining an accumulation sequence based on a historical tunnel fault data sequence combined with a preset accumulation algorithm.

[0028] Before evaluating the tunnel safety situation by the tunnel fault prediction method of the present application, it is necessary to first obtain the recent detection data of the target detection point on the tunnel. According to the characteristics of the tunnel structure damage, the arch settlement or the peripheral convergence is generally selected to evaluate the stability of the tunnel structure. The determination of the target detection point can be as follows: Figure 2 As shown, Figure 2A is the detection point for the vault sinking, and B is the detection point for the surrounding displacement. During the test, you can use paint, short steel bars, etc. to mark the measuring points, and then use a laser tracker or total station to record the position changes of the measuring points. In order to reduce the impact on traffic, the measurement work can be carried out at night when the traffic flow is small, and each observation generally does not last more than 10 minutes. Under normal circumstances, the measurement time interval can be selected to be once every 12 hours or 24 hours. When predicting tunnel failures through the gray system theory of this application, in order to ensure the accuracy of the prediction, the data of the required target detection points must exceed six data.

[0029] The historical tunnel fault data sequence in this step is a sequence composed of the fault data of the selected tunnel target detection points detected by the above method, and the sequence is arranged in time.

[0030] In some embodiments, Figure 3 As shown, step S100 includes steps S110 to S120: Step S110, calculating the accumulated data corresponding to each historical tunnel fault data in sequence according to a preset accumulation algorithm.

[0031] Each accumulated data is obtained by weighted summing the corresponding historical tunnel failure data and the historical tunnel failure data before the corresponding historical tunnel failure data.

[0032] Step S120: multiple accumulated data form an accumulated sequence.

[0033] For example, if the historical tunnel fault data sequence is obtained ,in, They respectively represent the i-th data of the target detection point in the detected tunnel, and these detection data are arranged in chronological order, that is, these data can reflect the certain rules of the change of the tunnel fault point over time.

[0034] In this embodiment, tunnel failure prediction is based on grey system theory, and its historical tunnel failure data series The historical tunnel failure data in the present invention is relatively small and incomplete data, which may contain noise and random fluctuations, and these noises and fluctuations may affect the accuracy of the prediction. Therefore, in order to make the prediction result more accurate and reliable, in this embodiment, the historical tunnel failure data is accumulated by using a preset accumulation algorithm to obtain an accumulation sequence , thereby improving the smoothness of the data, making the accumulated sequence have better trend and regularity, which makes it easier to identify the potential trends and patterns of tunnel failures; and in the process of accumulating the data in the historical tunnel failure data sequence, it is equivalent to filtering the original historical tunnel failure data, which can effectively reduce the influence of randomness and accidental factors in the data, which helps to improve the robustness and reliability of the model.

[0035] When calculating each accumulated data, the weight corresponding to each historical tunnel fault data used is determined according to the time length from the prediction time point. Specifically, when calculating each accumulated data, among the historical tunnel fault data used, the weight corresponding to the historical tunnel fault data with a long time length from the prediction time point is smaller than the historical tunnel fault data with a short time length from the prediction time point.

[0036] It can be understood that due to the large random volatility of tunnel structure deformation, the conditional probability distribution of its future state mainly depends on the current state, and its correlation with the past state is relatively weak. Therefore, in the accumulation process of the present invention, in order to reflect the importance of data closer to the prediction time point, it is necessary to weight each data, give larger weights to nearby data, and give lower weights to farther data, so as to improve the accuracy of tunnel prediction through time series data with large random volatility.

[0037] Exemplarily, the accumulated data in the calculation accumulation sequence is calculated using an accumulation formula, which is: ; In the formula, m is the preset value, which can be set to 0.95; k=1,2,3,···,n-1,n,k is the sequence number of the accumulated data in the accumulated sequence.

[0038] According to the above historical tunnel failure data sequence Calculate the cumulative sequence so that is equivalent to , , , and so on .

[0039] Step S200: Based on the historical tunnel fault data sequence and the cumulative sequence, the historical tunnel fault data sequence and the cumulative sequence are processed in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action.

[0040] Among them, the grey model development coefficient represents the trend of fault data changing over time in the tunnel prediction process; the grey action represents the change amplitude of fault data in the tunnel prediction process, which reflects the magnitude of fault data change within a certain period of time.

[0041] For example, Figure 4As shown, step S200 includes steps S210 to S230: Step S210, determining a production sequence adjacent to the mean value according to the accumulated data in the accumulated sequence.

[0042] After the historical tunnel fault data is processed according to the preset accumulation algorithm, in order to further improve the prediction accuracy and reduce the complexity of the subsequent grey prediction model calculation, the accumulated data in the accumulated sequence is further processed in this step. In this step, a new data sequence is generated by calculating the average value of adjacent accumulated data, thereby further reducing the random fluctuations in the original data, making the generated sequence smoother, and thus making the prediction more accurate.

[0043] By accumulating the sequence Get the production sequence close to the mean When , the formula used is: ; In the formula, due to It is calculated by adding up two adjacent accumulated data in the cumulative sequence. Therefore, the adjacent mean production sequence The number of data in is one less than the number of data in the cumulative sequence. In this case, the value range of k is 2, 3, 4, ···, n-1, n. It is used to preset the background value of grey differential equation in the subsequent process.

[0044] Step S220, constructing a data matrix according to the adjacent mean production sequence, and constructing a vector according to the historical tunnel fault data sequence.

[0045] In this step, the parameters of the grey model development coefficient and grey action are first defined as , in the parameter column, represents the grey model development coefficient, b represents the grey action, and T represents the time point of each data in the historical tunnel fault data sequence.

[0046] Then construct the data matrix B and vector Y.

[0047] Among them, the data matrix B is: .

[0048] The vector Y is: .

[0049] Before step S220, the method further includes: constructing a preset grey differential equation according to the historical tunnel fault data sequence and the adjacent mean production sequence, and derivatizing the preset grey differential equation to obtain a whitening equation.

[0050] Among them, the preset grey differential equation is used to describe and predict the time series data of tunnel failure. The grey differential equation is: .

[0051] After obtaining the grey differential equation, in order to make the grey system model more clearly express the dynamic characteristics of the tunnel fault, the present embodiment introduces the form of differential equation, that is, the grey differential equation is derived to obtain the whitening equation, which can also facilitate the subsequent calculation of the parameter column.

[0052] The whitening equation obtained by differentiating the grey differential equation is: + .

[0053] Step S230, based on the data matrix and the vector, combined with the preset grey differential equation, to obtain the parameter column of the grey model development coefficient and the grey action.

[0054] In this step, the least squares method can be used to obtain the data matrix, vector and whitening equation. , and then the parameter column can be calculated.

[0055] Step S300, obtaining a tunnel fault prediction value based on the grey model development coefficient, the grey action and the preset grey differential equation.

[0056] For example, Figure 5 As shown, step S300 includes steps S310 to S320: Step S310, obtaining the initial prediction value of tunnel failure at each time point according to the grey model development coefficient, the grey action and the preset grey differential equation.

[0057] Combined with the grey system theory, when the grey model development coefficient, grey action and grey differential equation are determined, the grey system model can be obtained, namely: ; That is, the initial predicted value at the corresponding time point of the prediction.

[0058] Step S320 , performing a cumulative inverse generation operation on the initial prediction value of the tunnel failure at each time point to obtain a tunnel failure prediction value.

[0059] In this embodiment, since the grey system model obtains the predicted value of each moment of the cumulative amount instead of the original tunnel fault data, in order to obtain the predicted value of the original tunnel fault data, it is necessary to perform an inverse generation calculation. The inverse generation process is to restore the accumulated data back to the original data. Specifically, the inverse generation can be achieved through the cumulative subtraction operation, that is, the obtained initial prediction value of the tunnel fault After reverse generation, the cumulative reduction is restored to .

[0060] because ; but .

[0061] The prediction effect of the tunnel fault prediction method of the present application is described below in conjunction with a specific embodiment. The tunnel predicted in this specific embodiment is a tunnel in Dingxi City, Gansu Province. The tunnel was completed and opened to traffic in 2020. In July 2024, the maintenance unit found that the road surface was bulging during routine inspections, and there were cracks in some cable trenches in the tunnel, but no obvious changes were found in the tunnel vault and side walls. According to the detection that the tunnel vault has a certain amount of settlement, the prediction method of this embodiment is verified through the data of the tunnel.

[0062] First, a detection point was set up on the tunnel vault. During the detection, a laser tracker was used for monitoring, and records were recorded every 12 hours. The monitoring lasted for 5 days and a total of 10 sample data were obtained. The historical tunnel fault data detected are shown in Table 1.

[0063] Table 1:

[0064] That is, the historical tunnel failure data series is (3.15, 3.01, 2.77, 2.46, 2.32, 2.15, 2.07, 1.87, 1.30, 1.18); the cumulative sequence obtained through this sequence is (3.150, 6.003, 8.472, 10.509, 12.303, 13.838, 15.216, 16.325, 16.809, 17.149); then calculate the production sequence close to the mean is (4.576, 7.237, 9.491, 11.406, 13.071, 14.527, 15.771, 16.567, 16.979); the grey model development coefficient a=0.260 and grey action b=0.069 are obtained through the above historical tunnel fault data sequence, cumulative sequence, adjacent mean production sequence and grey differential equation calculation, and then the above process is used to calculate The results obtained are shown in Table 2.

[0065] Table 2:

[0066] The actual value in Table 2 is the actual settlement value of the tunnel vault settlement obtained by detection, the predicted value of this embodiment is the predicted value obtained by prediction in the manner of this embodiment, and the relative error is the error between the predicted value and the actual value. Through the relative error calculation, it can be seen that the average simulation relative error is 3.226%, which is relatively small for tunnel prediction and meets the accuracy requirements of prediction.

[0067] Comparative Example The difference between the comparative example and the embodiment of the present application is that when the cumulative sequence is obtained based on the historical tunnel fault data sequence combined with the preset cumulative algorithm, the preset cumulative algorithm does not have a weight, that is, the weight of each detection point is regarded as the same.

[0068] That is, the historical tunnel failure data series , when calculating the cumulative sequence, the cumulative formula is: , the subsequent prediction process is the same as that in this embodiment.

[0069] Then the historical tunnel failure data sequence in the comparison example is (3.15, 3.01, 2.77, 2.46, 2.32, 2.15, 2.07, 1.87, 1.30, 1.18); the cumulative sequence obtained through this sequence is (3.150, 6.160, 8.930, 11.390, 13.710, 15.860, 17.930, 19.800, 21.100, 22.280), and then the production sequence close to the mean is calculated. is (4.655, 7.545, 10.160, 12.550, 14.785, 16.895, 18.865, 20.450, 21.690); the grey model development coefficient a=0.10 and grey action b=3.55 are calculated through the above historical tunnel fault data sequence, cumulative sequence, adjacent mean production sequence and grey differential equation, and then the grey model development coefficient a=0.10 and grey action b=3.55 are calculated through the process of this comparison ratio. The obtained results are shown in Table 3.

[0070] Table 3:

[0071] The actual value in Table 3 is the actual settlement value of the tunnel vault settlement obtained by detection, the proportional simulation value is the predicted value obtained by prediction in a proportional manner, and the relative error is the error between the predicted value and the actual value. Through the relative error calculation, it can be seen that the average simulation relative error corresponding to the proportional method is 7.218%. It can be seen from the results of Tables 2 and 3 that this embodiment adds weights to each historical tunnel failure data according to the time series when calculating the accumulated data, thereby obtaining a more accurate prediction result. It should be noted that since the prediction method is used to predict tunnel failures, the latter prediction values ​​are more referenceable than the former ones.

[0072] In the present application, the historical tunnel fault data sequence is first combined with the preset accumulation algorithm to obtain the accumulation sequence, and then the historical tunnel fault data sequence and the accumulation sequence are processed according to the historical tunnel fault data sequence and the accumulation sequence, combined with the preset gray differential equation, to obtain the gray model development coefficient and the gray action, and finally the tunnel fault prediction value is obtained based on the gray model development coefficient, the gray action and the preset gray differential equation. In this way, the present application realizes the prediction of tunnel faults with less monitoring data, which is a relatively simple, effective and accurate method for fault prediction in a complex environment such as tunnels, and the cost is also low. In addition, when calculating the accumulated data in the present application, the problem that the reference value of the data that is longer away from the prediction time point is not as great as the reference value of the data that is closer to the prediction time point is taken into account for the situation of tunnel prediction, and then the corresponding weight is added to the tunnel fault data when calculating the accumulated data, so as to make the prediction more accurate. It can be understood that when the historical tunnel fault data is particularly small (such as less than 3), the weighted processing may cause the prediction result to be biased towards certain samples, thereby affecting the generalization ability of the model and causing the prediction result to become unstable. Therefore, the present application requires that the amount of basic historical tunnel fault data shall not be less than 6.

[0073] Figure 6 A schematic diagram of the structure of a tunnel fault prediction device according to an embodiment of the present application is shown. Exemplarily, the tunnel fault prediction device includes: The accumulation sequence acquisition module 100 is used to obtain an accumulation sequence based on a historical tunnel fault data sequence in combination with a preset accumulation algorithm.

[0074] The parameter calculation module 200 is used to process the historical tunnel fault data sequence and the cumulative sequence based on the historical tunnel fault data sequence and the cumulative sequence in combination with a preset grey differential equation to obtain the grey model development coefficient and the grey action.

[0075] The tunnel fault prediction value obtaining module 300 is used to obtain the tunnel fault prediction value based on the grey model development coefficient, the grey action and the preset grey differential equation.

[0076] It can be understood that the device of this embodiment corresponds to the tunnel fault prediction method of the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described repeatedly here.

[0077] The present application also provides a terminal device. Exemplarily, the terminal device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program to enable the terminal device to execute the functions of each module in the above-mentioned tunnel fault prediction method or the above-mentioned tunnel fault prediction device.

[0078] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0079] The memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0080] The present application also provides a computer-readable storage medium for storing the computer program used in the above terminal device. For example, the computer-readable storage medium may include but is not limited to: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0081] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0082] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0083] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0084] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A tunnel fault prediction method, characterized in that: include: Based on the historical tunnel fault data sequence combined with a preset accumulation algorithm, an accumulation sequence is obtained; Based on the historical tunnel fault data sequence and the cumulative sequence, the historical tunnel fault data sequence and the cumulative sequence are processed in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action; A tunnel fault prediction value is obtained based on the grey model development coefficient, the grey action and the preset grey differential equation.

2. The tunnel fault prediction method according to claim 1, characterized in that: The method of obtaining the accumulation sequence based on the historical tunnel fault data sequence in combination with a preset accumulation algorithm includes: The accumulated data corresponding to each historical tunnel fault data is calculated in sequence according to the preset accumulation algorithm; wherein the historical tunnel fault data in the historical tunnel fault data sequence are sorted according to the time series; each accumulated data is obtained by weighted summing the corresponding historical tunnel fault data and the historical tunnel fault data before the corresponding historical tunnel fault data; A plurality of the accumulated data constitute the accumulated sequence.

3. The tunnel fault prediction method according to claim 2, characterized in that: When calculating each of the accumulated data, the weight corresponding to each of the historical tunnel fault data is determined according to the time length from the predicted time point.

4. The tunnel fault prediction method according to claim 3, characterized in that: When calculating each accumulated data, among the historical tunnel fault data, the weight corresponding to the historical tunnel fault data with a longer time distance from the predicted time point is smaller than the weight corresponding to the historical tunnel fault data with a shorter time distance from the predicted time point.

5. The tunnel fault prediction method according to claim 1, characterized in that: The method of processing the historical tunnel fault data sequence and the cumulative sequence based on the historical tunnel fault data sequence and the cumulative sequence in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action comprises: Determine a production sequence close to the mean value according to the accumulated data in the accumulated sequence; constructing a data matrix according to the adjacent mean production sequence, and constructing a vector according to the historical tunnel failure data sequence; Based on the data matrix and the vector, the preset grey differential equation is combined to obtain the parameter column of the grey model development coefficient and the grey action.

6. The tunnel fault prediction method according to claim 5, characterized in that: Before constructing a data matrix according to the adjacent mean production sequence and constructing a vector according to the historical tunnel fault data sequence, the method further includes: constructing the preset grey differential equation according to the historical tunnel fault data sequence and the adjacent mean production sequence, and derivatizing the preset grey differential equation to obtain a whitening equation; The step of obtaining the parameter list of the grey model development coefficient and the grey action based on the data matrix and the vector and combining the preset grey differential equation comprises: Based on the data matrix and the vector, the whitening equation is combined to obtain the parameter column of the grey model development coefficient and the grey action.

7. The tunnel fault prediction method according to claim 1, characterized in that: The step of obtaining a tunnel fault prediction value based on the grey model development coefficient, the grey action and the preset grey differential equation comprises: Obtaining an initial prediction value of tunnel failure at each time point according to the grey model development coefficient, the grey action and the preset grey differential equation; The initial prediction value of the tunnel failure at each time point is subjected to a cumulative inverse generation operation to obtain the tunnel failure prediction value.

8. A tunnel fault prediction device, characterized in that: include: An accumulation sequence acquisition module is used to obtain an accumulation sequence based on a historical tunnel fault data sequence combined with a preset accumulation algorithm; A parameter calculation module, used for processing the historical tunnel fault data sequence and the cumulative sequence based on the historical tunnel fault data sequence and the cumulative sequence in combination with a preset grey differential equation to obtain a grey model development coefficient and a grey action; The tunnel fault prediction value obtaining module is used to obtain the tunnel fault prediction value based on the grey model development coefficient, the grey action and the preset grey differential equation.

9. A terminal device, characterized in that: The terminal device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the tunnel fault prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer program stores a computer program, which, when executed on a processor, implements the tunnel fault prediction method according to any one of claims 1 to 7.

Images