Building structure safety prediction and early warning method based on grey model and related device

Abstract

The invention discloses a building structure safety prediction and early warning method based on a gray model and a related device, and relates to the field of building structure safety monitoring, in particular to a building structure safety prediction and early warning method based on the gray model, and the method uses building inclination data monitored in real time to carry out prediction and early warning on building structure safety. Processing the building inclination data collected in the first time to obtain monotonically increasing data; inputting the monotonically increasing data into a building inclination condition grey prediction model, and outputting a prediction result of building inclination data at a second time; and comparing the prediction result of the building inclination data at the second time with a preset threshold value, and performing graded early warning according to a comparison result. According to the method, building inclination data monitoring and a grey prediction model are combined, long-time prediction and early warning are realized by using monitoring data acquired in a short time, and cost reduction and benefit increase in the monitoring process are facilitated. Based on small-scale data, the grey model is selected to effectively predict building safety.

Description

Technical Field

[0001] The present application relates to the technical field of building structure safety monitoring, and in particular to a building structure safety prediction and early warning method and related devices based on a grey model. Background Art

[0002] The structural safety of buildings is directly related to the safety of people's lives and property. Therefore, it is necessary to conduct structural inspections on buildings to identify potential structural problems and safety hazards in advance so as to take appropriate preventive measures to avoid accidents.

[0003] Traditional building structure inspection relies on irregular inspections and manual assessments, which is not only time-consuming and labor-intensive, but also costly. With the development of sensing technology, data acquisition and processing technology, artificial intelligence and machine learning technology, building structure health monitoring and intelligent early warning technology are also constantly improving. Based on modern sensor networks, large amounts of data are collected in real time, and cloud computing and big data technologies can be used to efficiently process and store these data. Then, valuable information can be extracted from them through machine learning algorithms to achieve safety predictions for building structures.

[0004] However, due to the small number of dimensions and data size of monitoring data, it is difficult to effectively use cloud computing and big data technology to predict the safety of specific buildings. Therefore, there is an urgent need for a customized algorithm based on small-dimensional data to effectively predict and warn the safety of building structures. Summary of the invention

[0005] The purpose of this application is to provide a building structure safety prediction and early warning method and related devices based on a grey model, which can improve the real-time performance of building structure safety prediction and issue early warnings based on the prediction results.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a building structure safety prediction and early warning method based on a grey model, comprising:

[0008] Acquire building tilt data collected within a first period of time; wherein the building tilt data collected within the first period of time is data measured by a tilt sensor arranged in the building;

[0009] Process the building tilt data collected in the first time to obtain monotonically increasing data;

[0010] Inputting the monotonically increasing data into a grey prediction model of building tilt conditions, and outputting a prediction sequence of building tilt values ​​at a second time;

[0011] The predicted sequence of the building inclination value at the second time is compared with a preset threshold, and different levels of safety warnings are issued according to the comparison results.

[0012] In a second aspect, the present application provides a building structure safety prediction and early warning system based on a grey model, which is applied to the building structure safety prediction and early warning method based on a grey model described in the first aspect, and the system includes:

[0013] The building intelligent monitoring module is used to obtain the building tilt data collected within a first period of time; wherein the building tilt data collected within the first period of time is data measured by a tilt sensor arranged in the building.

[0014] The data preprocessing module is used to process the building tilt data collected in the first time to obtain monotonically increasing data.

[0015] The grey model prediction module is used to input the monotonically increasing data into the grey prediction model of the building inclination and output a prediction sequence of the building inclination value at a second time.

[0016] The building structure safety prediction and warning module is used to compare the predicted sequence of building inclination values ​​at the second time with a preset threshold value, and issue safety warnings of different levels according to the comparison results.

[0017] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned methods for predicting and warning building structure safety based on a gray model.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for predicting and warning building structure safety based on a grey model.

[0019] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned gray model-based building structure safety prediction and early warning methods.

[0020] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0021] The present application provides a method and related device for predicting and warning safety of building structures based on a gray model. First, the building tilt data collected within a first time is obtained, and the building tilt data collected within the first time is processed to obtain monotonically increasing data; then the monotonically increasing data is input into a gray prediction model of the building tilt situation, and a prediction sequence of the building tilt value at a second time is output; the prediction sequence of the building tilt value at the second time is compared with a preset threshold, and different levels of warnings are issued according to the comparison results.

[0022] This application combines automatic monitoring of building structures with a grey prediction model, and uses monitoring data collected in a relatively short period of time to achieve longer-term prediction and early warning, providing a feasible basis for further guidance on the timing of building safety monitoring, which helps to improve monitoring efficiency and reduce monitoring costs.

[0023] This application uses a grey prediction model to predict building safety. The grey prediction model is more suitable for processing small-dimensional data such as building tilt data, and it gets rid of the dependence of cloud computing and big data technology on data dimensions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 This is an application environment diagram of a building structure safety prediction and early warning method based on a grey model in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of a process of a building structure safety prediction and early warning method based on a grey model provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of a sliding window provided in an embodiment of the present application;

[0028] Figure 4 A schematic diagram of functional modules of a building structure safety prediction and early warning system based on a grey model provided in one embodiment of the present application;

[0029] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] In order to make the above-mentioned objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0032] The building structure safety prediction and early warning method based on the grey model provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network, and at the same time, the terminal 102 communicates with the inclination sensor through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the building inclination data collected in the first time to the server 104. After the server 104 receives the building inclination data collected in the first time, for the building inclination data, the server 104 processes the building inclination data collected in the first time to obtain monotonically increasing data; then the monotonically increasing data is input into the gray prediction model of the building inclination situation, and the prediction result of the building inclination data at the second time is output; the prediction result of the building inclination data at the second time is compared with the preset safety threshold, and different levels of safety warnings are issued according to the comparison result. The server 104 can feedback the comparison result of the prediction result of the building inclination data at the second time with the preset safety threshold to the terminal 102. In addition, in some embodiments, the building structure safety prediction and early warning method based on the gray model can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly process the building tilt data collected within the first time, or the server 104 can obtain the building tilt data collected within the first time from the data storage system and process the building tilt data collected within the first time.

[0033] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, and tablet computers. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0034] The first time is a period of time in the past, and the second time is a period of time in the future. For example, the first time can be selected from the past 30 days, 50 days or 100 days, and the second time can be selected from the future one year, three years or five years.

[0035] In an exemplary embodiment, Figure 2 As shown, a method for predicting and warning building structure safety based on a grey model is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps 201 to 208. Among them:

[0036] Step 201, obtaining the building tilt data collected within the first time.

[0037] As an optional implementation, in step 201, the building tilt data collected in the first time is data measured by a tilt sensor arranged in the building. The tilt value of the tilt sensor is monitored and recorded every Δt time, and the value of Δt is manually specified according to the specific building conditions, usually 0.5h, or any other time, but Δt should not be too large.

[0038] Step 202, processing the building inclination data collected in the first time to obtain monotonically increasing data.

[0039] The step 202 specifically includes:

[0040] The building inclination data collected during the first time are preprocessed to obtain a maximum value sequence, a minimum value sequence, an average value sequence and a median sequence corresponding to the first time.

[0041] The maximum value sequence, minimum value sequence, average value sequence and median sequence corresponding to the first time are processed respectively to obtain monotonically increasing data.

[0042] As an optional implementation, the maximum value sequence, the minimum value sequence, the average value sequence and the median sequence corresponding to the first time are processed respectively to obtain monotonically increasing data, specifically including:

[0043] The first operation is performed on the maximum value sequence, the minimum value sequence, the average value sequence and the median sequence corresponding to the first time to obtain a monotonically increasing maximum value sequence, a monotonically increasing minimum value sequence, a monotonically increasing average value sequence and a monotonically increasing median sequence.

[0044] The first operation is:

[0045] Assume {t 1 ,t 2 ,t 3 ,...,t N} is the preset unit time series, {y 1,y 2 ,y 3 ,...,y N} is a tilt value sequence corresponding to a preset unit time series; wherein the tilt value sequence is a maximum value sequence, a minimum value sequence, an average value sequence or a median sequence.

[0046] t 1 Indicates the first preset unit time, y 1 Indicates t 1 The tilt value corresponding to time.

[0047] t 2 Indicates the second preset unit time, y 2 Indicates t 2 The tilt value corresponding to time.

[0048] t 3 Indicates the third preset unit time, y 3 Indicates t 3 The tilt value corresponding to time.

[0049] t N Indicates the Nth preset unit time; y N Indicates t N The tilt value corresponding to time.

[0050] Get the maximum subsequence of the tilt value sequence {y i ,y i+1 ,y i+2 ,...y j} and the time series corresponding to the maximum subsequence {t i ,t i+1 ,t i+2 ,...t j};in,

[0051] t i represents the i-th preset unit time, y i Indicates t i The corresponding tilt value.

[0052] t i+1 Indicates the i+1th preset unit time, y i+1 Indicates t i+1 The corresponding tilt value.

[0053] t i+2 Indicates the i+2th preset unit time, y i+2 Indicates t i+2 The corresponding tilt value.

[0054] t j represents the jth preset unit time, y jIndicates t j The corresponding tilt value.

[0055] Among them, y j is the maximum value in the maximum subsequence, y i is the second largest value in the maximum subsequence; the number of the maximum subsequences is single or multiple; wherein 1≤i<j≤N.

[0056] For the largest subsequence, except y i and j Other elements y k Update, the calculation formula is:

[0057]

[0058] t k is the kth data in the preset unit time series; k is all integers between i and j, i <k<j;y k Indicates time t k The corresponding tilt value; y' k for y k The replacement value of .

[0059] It should be noted that the maximum subsequence refers to the maximum subsequence in the tilt value sequence that satisfies “y j is the maximum value, y i The purpose of this is to ensure that y i-1 <y i and j <y j+1 All are true (if there is y i-1 With y j+1 ), and can reduce the amount of calculation and improve data processing efficiency.

[0060] For example, if the tilt value sequence is {1, 1.9, 1.8, 1.6, 1.5, 1.4, 2.2, 2.3}; then, the sequence satisfies “y j is the maximum value, y i The sequences with the "second largest value" condition are:

[0061] {1.5,1.4,2.2}, at this time y i =1.5,y j =2.2,y i-1 =1.6;y i-1 <y i Not true, exclude it.

[0062] {1.6,1.5,1.4,2.2}, at this time y i =1.6,y j=2.2,y i-1 =1.8;y i-1 <y i Not true, exclude it.

[0063] {1.8,1.6,1.5,1.4,2.2}, at this time y i =1.8,y j =2.2,y i-1 =1.9;y i-1 <y i Not true, exclude it.

[0064] {1.9,1.8,1.6,1.5,1.4,2.2}, at this time y i =1.9,y j =2.2,y i-1 =1;y i-1 <y i and j <y j+1 All of them hold true, and it is determined as the maximum subsequence.

[0065] Similarly, if data with the same numerical value {1, 1.5, 1.5, 1.4, 2.2, 2.2} appear continuously in the tilt value sequence, the maximum subsequence selected should be {1.5, 1.5, 1.4, 2.2, 2.2} instead of {1.5, 1.4, 2.2}.

[0066] It should be noted that, by selecting the maximum subsequence of the tilt value sequence, the present application can achieve monotonically increasing the entire tilt value sequence through one processing, thereby improving the efficiency of data processing. On the contrary, if the non-maximum subsequence {1.5, 1.4, 2.2} is processed to become {1.5, 1.85, 2.2} and put back into the tilt value sequence, the sequence {1.6, 1.5, 1.85} still does not conform to the above rule and still needs to be processed again.

[0067] As an optional implementation, in step 202, the preset unit time can be selected as 1d (one day), and the monitoring time interval is Δt. Taking Δt as 0.5h as an example, the inclination sensor obtains 48 monitoring data in one day. After obtaining the 48 monitoring data, the 48 data are processed to obtain the maximum value, minimum value, average value and median of the inclination value, and the data are classified and stored according to these four types of data.

[0068] The first time can be selected as 100 days, that is, the total time length of the real-time monitoring of the building tilt data by the tilt sensor is 100 days. The maximum value, minimum value, average value and median value of the tilt value monitored by the tilt sensor every day are obtained, and these four types of data are sorted respectively to obtain the maximum value sequence, minimum value sequence, average value sequence and median sequence of the tilt value with days as the time unit.

[0069] Under normal circumstances, the building tilt value will gradually increase over time. However, due to the volatility of data during the monitoring process, there are cases where the building tilt value measured later is smaller than the tilt value measured earlier (for example, the tilt value measured on the 7th day is 0.3, but the tilt value measured on the 8th day is 0.25). Therefore, it is necessary to further process the maximum value sequence, minimum value sequence, average value sequence and median sequence of the tilt value with days as the time unit so that the processed data are monotonically increasing:

[0070] Taking the maximum value sequence as an example, let {t 1 ,t 2 ,t 3 ,...,t N} is the preset unit time series, {y 1 ,y 2 ,y 3 ,...,y N} is the tilt maximum value sequence corresponding to the preset unit time series;

[0071] Let the sequence {y i ,y i+1 ,y i+2 ,...y j} is the maximum subsequence in which the tilt value of the maximum value sequence fluctuates. In this sequence, y j is the maximum value, y i is the second largest value, and the other tilt values ​​are not greater than y i ; and there is y i-1 <y i ,y j <y j+1 (If there is y i-1 With y j+1 If) the sequence {y i ,y i+1 ,y i+2 ,...y j The time series corresponding to} is {y i ,y i+1 ,y i+2 ,...y j}.

[0072] For example, the maximum value sequence is: {0.1, 0.2, 0.18, 0.3}; obviously, the monitoring time of 0.18 is later than the monitoring time of 0.2, but 0.18<0.2; this means that the data of 0.18 causes the entire tilt maximum value sequence to not conform to the monotonically increasing law and needs to be processed.

[0073] Select the maximum subsequence {0.2, 0.18, 0.3} from the maximum value sequence {0.1, 0.2, 0.18, 0.3}, then y i =0.2,y j =0.3,t j =3,t i =1,t k =2, calculate y' k =0.25. The maximum value sequence after processing is {0.2, 0.25, 0.3}, which conforms to the law of monotonous increase.

[0074] Similarly, for the maximum value sequence {0.1, 0.2, 0.18, 0.19, 0.22, 0.23}, its maximum subsequence is {0.2, 0.18, 0.19, 0.22}. At this time, the two data of 0.18 and 0.19 need to be processed separately so that the processed data are monotonically increasing.

[0075] It should be understood that throughout {y 1 ,y 2 ,y 3 ,...,y N}, there may be multiple maximum subsequences of fluctuations. For example, in the sequence {0.1, 0.15, 0.12, 0.16, 0.17, 0.2, 0.18, 0.19, 0.22, 0.23}, there are two maximum subsequences that need to be processed, namely, the sequence {0.15, 0.12, 0.16} and the sequence {0.2, 0.18, 0.19, 0.22}. At this time, these two sequences need to be processed separately to make the whole sequence monotonically increasing.

[0076] The above shows how to process the maximum value sequence. The processing methods for the minimum value sequence, average value sequence and median sequence are similar and will not be described in detail here.

[0077] After the above processing, the maximum value sequence, minimum value sequence, average value sequence and median sequence of the tilt value are all monotonically increasing sequences, thereby removing the volatility of the data and being more in line with the actual situation.

[0078] Step 203, inputting the monotonically increasing data into a grey prediction model of building inclination, and outputting a prediction sequence of building inclination values ​​at a second time;

[0079] As an optional implementation, step 203 specifically includes:

[0080] The second operation is performed on the monotonically increasing maximum value sequence, the monotonically increasing minimum value sequence, the monotonically increasing average value sequence or the monotonically increasing median sequence to obtain the second time building tilt maximum value prediction sequence {A n}, the second time building tilt minimum prediction sequence {B n}、Second time building tilt average value prediction sequence {C n} and the second time building tilt median prediction series {D n};

[0081] The second operation is:

[0082] A monotonically increasing tilt value sequence is input into the sliding window; the monotonically increasing tilt value sequence is a monotonically increasing maximum value sequence, a monotonically increasing minimum value sequence, a monotonically increasing average value sequence or a monotonically increasing median sequence.

[0083] The monotonically increasing tilt value sequence is processed using a sliding window to obtain a tilt value sequence of the sliding window.

[0084] Inputting the tilt value sequence of the sliding window into a grey prediction model of building tilt conditions, and outputting a second time building tilt value prediction sequence;

[0085] The calculation formula of the second time building tilt value prediction sequence is:

[0086]

[0087] in, is the kth predicted value in the second time building tilt value prediction sequence; is the kth predicted value in the first accumulation sequence of the predicted sequence of the building inclination value at the second time; is the k-1th predicted value in the first accumulation sequence of the predicted sequence of the building inclination value at the second time;

[0088] The calculation formula is:

[0089] Among them, -a is the development coefficient of the grey prediction model of building tilt, and b is the grey action of the grey prediction model of building tilt.

[0090] Furthermore, in step 203, the calculation process of the development coefficient -a and the gray action amount b is specifically as follows:

[0091] Define the parameter vector

[0092] Using the least squares method The estimated formula is:

[0093] in,

[0094] x (0) (2) is the second element in the tilt value sequence of the sliding window.

[0095] x (0) (3) is the third element in the tilt value sequence of the sliding window.

[0096] x (0) (n) is the nth element in the tilt value sequence of the sliding window.

[0097] Among them, z (1) (2) z (1) (3) and z (1) (n) is the sequence Z (1) The elements in .

[0098] Sequence Z (1) The expression of Z is: (1) =(z (1) (2), z (1) (3), ...z (1) (n)).

[0099] Among them, the sequence Z (1) The kth element z in (1) The calculation formula for (k) is:

[0100]

[0101] Among them, x (1) (k) and x (1) (k-1) is the sequence X (1) The elements in .

[0102] Sequence X (1) The expression is: X (1) =(x (1) (1), x (1) (2), ...x (1) (n)).

[0103] Among them, the sequence X (1) The kth element x in (1) The calculation formula for (k) is:

[0104]

[0105] Among them, x (0) (i) is the sequence X (0)The i-th element in .

[0106] Sequence X (0) The expression is: X (0) =(x (0) (1), x (0) (2), ...x (0) (n)).

[0107] Among them, x (0) (1) is the first element in the tilt value sequence of the sliding window.

[0108] As an optional implementation, the unit time, the time expansion coefficient m and the sliding window size n are set, and the sliding window is as follows: Figure 3 Specifically, taking the use of the monitoring data of the last 100 days to predict the building tilt situation one year later as an example, the unit time is set to 1 day (1d), and the time expansion coefficient m is set to 10 02 , that is, the data recorded in the sliding window, the time point of the next data monitoring is 10 of the previous data 02 For example, if the monitoring data recorded in the first window is 1 day, the monitoring data recorded in the second window is 10 days. 02d , ..., the monitoring data recorded in the sixth window is 10 days... and so on. The sliding window size n can be set to 6.

[0109] The maximum value sequence, minimum value sequence, average value sequence and median sequence of the tilt value are input into the sliding window respectively, and four different grey prediction models of building tilt are established; wherein the grey prediction model of building tilt is the GM (1, 1) model.

[0110] The following is the process of establishing the GM (1, 1) model:

[0111] Assume that the data sequence X (0) =(x (0) (1), x (0) (2), ...x (0) (n)) is the tilt value sequence in the sliding window, and the sequence X (1) For sequence X (0) 1-AGO sequence (one-time accumulation sequence):

[0112] X (1) =(x (1) (1), x (1) (2), ...x (1) (n));

[0113] in,

[0114] Z (1) =(z(1) (2),z (1) (3),...z (1) (n));

[0115] in, say

[0116] x (0) (k)+az (1) (k) = b;

[0117] is the mean form of the GM(1,1) model, which is essentially a difference equation. Among them, -a is the development coefficient and b is the gray action. The parameter vector It can be estimated using the least squares method:

[0118]

[0119] in,

[0120] The cumulative reduction formula of the GM (1,1) model (i.e., the calculation formula for the second-time building tilt value prediction sequence) is:

[0121]

[0122] Among them, the skewed data accumulates the predicted value of the kth element in the sequence at a time It can be done by a, b and the first element x in the tilted sequence (0) (1) Calculation:

[0123]

[0124] The building tilt data is processed into equal distances, the corresponding GM (1,1) model is established, the development coefficient -a and the gray action b are calculated, and the According to the k value corresponding to the time to be predicted, the predicted value of the corresponding time can be calculated

[0125] The isotropic processing refers to the “isotropic” of the index. For example, the selected building tilt data is from the 10th day to the 100th day, but the data used is 10d, 10 1.2 d. 10 1.4 d. 10 1.6 d. 10 1.8 d, 100d.

[0126] Considering that the time of recording data in the sliding window does not completely coincide with the preset unit time, when the time to be predicted is not recorded in the sliding window, the mean interpolation method is needed to preprocess the data. The preprocessing process is as follows:

[0127] Assume that the time to be recorded in the sliding window is t, and the most recent time before and after time t is t 1 and t 2 , t 1 and t 2 The corresponding predicted tilt values ​​are y 1 ' and y 2 ', then the predicted tilt value y' corresponding to time t is:

[0128]

[0129] Take t = 10 1.6 Take d as an example, the time of the most recent monitoring data before and after time t is 39d and 40d, then record t 1 =39, t 2 =40, the corresponding monitoring values ​​are y 1 ' and y 2 ', calculated by the above formula, t = 10 1.6 The predicted tilt value y' corresponding to d is added to the corresponding position of the sliding window.

[0130] As an optional implementation, in step 203, the use of the monitoring data of the last 100 days to predict the building tilt situation one year later is taken as an example, that is, the current day is the 100th day, and the tilt value of the 465th day is predicted. By calculation, it can be obtained that 10 2.6 <465<10 2.8 , 10 2.6 The corresponding predicted value is 10 2.8 The corresponding predicted value is The predicted value of the tilt value for 465 days is:

[0131]

[0132] Step 204: compare the second time building tilt value prediction sequence with a preset threshold, and issue different levels of safety warnings according to the comparison result.

[0133] Furthermore, step 204 specifically includes:

[0134] Determine the second time building tilt maximum value prediction sequence {A n}Is there a predicted value a greater than the preset threshold? n , if it exists, continue to judge with a n The predicted value a adjacent to the predicted time n-1 and a n+1 Is it greater than the preset threshold? If the predicted value a n-1 and a n+1All of them are greater than the preset threshold, which means that the maximum value of the tilt value may reach the risk threshold at the time when prediction is required. It is necessary to continue to pay attention to the situation of the building structure and issue a general warning.

[0135] Determine the second time building tilt average value prediction sequence {C n} Is there a predicted value c greater than the preset threshold? n , if it exists, continue to judge with c n The predicted value c adjacent to the predicted time n-1 and c n+1 Is it greater than the preset threshold? If the predicted value c n-1 and c n+1 All of them are greater than the preset threshold, which means that the average value of the tilt value may reach the risk threshold at the time when prediction is required, and it is necessary to pay closer and continuous attention to the situation of the building structure and issue an advanced warning.

[0136] Determine the median prediction sequence of the second time building tilt {D n Is there a predicted value d greater than the preset threshold? n , if it exists, continue to judge with d n Prediction value d adjacent to the prediction time n-1 and d n+1 Is it greater than the preset threshold? If the predicted value d n-1 and d n+1 All of them are greater than the preset threshold, which means that the median of the tilt value may reach the risk threshold at the time when prediction is required, and it is necessary to pay closer and continuous attention to the situation of the building structure and issue an advanced warning.

[0137] Determine the minimum value prediction sequence of the second time building tilt {B n} Is there a predicted value b greater than the preset threshold? n , if it exists, continue to judge with b n Prediction value b adjacent to the prediction time n-1 and b n+1 Is it greater than the preset threshold? If the predicted value b n-1 and b n+1 All of them are greater than the preset threshold, which means that the minimum value of the tilt value may reach the risk threshold at the time when prediction is required, that is, the building is very likely to be at risk at the time when prediction is required, and it needs to be renovated in time, and the highest warning is issued.

[0138] It should be understood that the early warning method judgment condition of this embodiment is: to determine whether there are three consecutive preset unit time prediction values ​​that exceed the preset threshold, and the preset unit time is selected as 1 day, that is, to determine whether there are three consecutive days of prediction values ​​that exceed the threshold.

[0139] When the technical solution of the present application is actually applied, the number of consecutive preset unit time is not limited to 3, and can also be 4, 5, 7, etc. At the same time, the preset unit time can also be selected according to the construction conditions, such as half a day, 2 days or a week. In addition, the preset threshold is not a fixed value, and it will be adjusted according to the combination of engineering conditions and construction conditions when selecting.

[0140] In addition, it should be noted that the above four warning conditions may be met at the same time (for example, meeting the highest warning condition must also meet the ordinary warning condition). When multiple conditions are met at the same time, warnings are issued in the following order of priority: highest warning > advanced warning > ordinary warning.

[0141] This application combines the automatic monitoring of building structures and the gray prediction model of building inclination by implementing the above-mentioned steps 201 to 204, and uses the monitoring data collected in a relatively short period of time to achieve a long-term prediction and early warning, which provides a reliable basis for the timing of building structure safety monitoring, helps to improve monitoring efficiency and reduce monitoring costs. At the same time, this application processes the data before modeling, so that the processed data increases monotonically, which is more in line with the actual situation, and helps to improve the prediction accuracy of the model. Moreover, the present invention divides the building inclination data collected in the first time into 4 categories: maximum value, minimum value, average value and median, and uses these 4 types of data to compare with the preset safety threshold value, so as to achieve different levels of safety warning, which helps the relevant departments to take corresponding levels of response measures, avoid wasting resources, and save manpower and material resources.

[0142] In addition, this application uses a gray prediction model to predict building safety. The gray prediction model is more suitable for processing small-dimensional data such as building tilt data, and it gets rid of the dependence of cloud computing and big data technology on data dimensions.

[0143] The present application also provides an application scenario, which applies the above-mentioned gray model-based building structure safety prediction and early warning method. Specifically: The gray model-based building structure safety prediction and early warning method provided in this embodiment can be applied to the scene of building safety monitoring. It should be noted that building safety includes many indicators, such as concrete strength grade, steel yield strength and tensile strength, component cross-sectional size, aspect ratio, slenderness ratio, crack width, settlement and inclination. By predicting the inclination of the building at a certain time in the future (the inclination is an important indicator for the safety evaluation of the building structure), the present application can make a general prediction and early warning of the building safety, and provide a feasible theoretical basis for further detection or maintenance in the future. In this way, the relevant staff can carry out more comprehensive detection or maintenance of the building safety at a specific time node in a targeted manner according to the prediction results of the inclination, thereby improving the detection efficiency of the building safety and reducing the cost.

[0144] Based on the same inventive concept, the embodiment of the present application also provides a gray model-based building structure safety prediction and early warning system for implementing the gray model-based building structure safety prediction and early warning method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more gray model-based building structure safety prediction and early warning system embodiments provided below can refer to the limitations of the gray model-based building structure safety prediction and early warning method above, and will not be repeated here.

[0145] In an exemplary embodiment, Figure 4 As shown, a building structure safety prediction and early warning system based on a grey model is provided, which includes: a building intelligent monitoring module 301, a data preprocessing module 302, a grey model prediction module 303 and a building structure safety prediction and early warning module 304.

[0146] As an optional implementation, the building intelligent monitoring module 301 is used to obtain the building tilt data collected within a first period of time; wherein the building tilt data collected within the first period of time is data measured by a tilt sensor arranged in the building.

[0147] As an optional implementation, the data preprocessing module 302 is used to process the building inclination data collected within the first time to obtain monotonically increasing data.

[0148] As an optional implementation, the gray model prediction module 303 is used to input the monotonically increasing data into the gray prediction model of the building tilt condition, and output a second time building tilt value prediction sequence. As an optional implementation, the building structure safety prediction and warning module 304 is used to compare the second time building tilt value prediction sequence with a preset threshold, and issue different levels of safety warnings according to the comparison result.

[0149] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the building inclination data collected in the first time. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a building structure safety prediction and early warning method based on a gray model is implemented.

[0150] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0151] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0152] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0153] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0155] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0156] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A building structure safety prediction and early warning method based on a grey model, characterized in that: The grey model-based intelligent prediction and early warning method for building structure safety includes: Acquire building tilt data collected within a first period of time; wherein the building tilt data collected within the first period of time is data measured by a tilt sensor arranged in the building; Process the building tilt data collected in the first time to obtain monotonically increasing data; Inputting the monotonically increasing data into a grey prediction model of building tilt conditions, and outputting a prediction sequence of building tilt values ​​at a second time; The predicted sequence of the building inclination value at the second time is compared with a preset threshold, and different levels of safety warnings are issued according to the comparison results.

2. The building structure safety prediction and early warning method based on the grey model according to claim 1 is characterized in that: The building tilt data collected in the first time is processed to obtain monotonically increasing data, including: Preprocessing the building tilt data collected within the first time to obtain a maximum value sequence, a minimum value sequence, an average value sequence and a median sequence corresponding to the first time; The maximum value sequence, minimum value sequence, average value sequence and median sequence corresponding to the first time are processed respectively to obtain monotonically increasing data.

3. The building structure safety prediction and early warning method based on the grey model according to claim 2 is characterized in that: The maximum value sequence, minimum value sequence, average value sequence and median sequence corresponding to the first time are processed respectively to obtain monotonically increasing data, including: Perform the first operation on the maximum value sequence, the minimum value sequence, the average value sequence and the median sequence corresponding to the first time to obtain a monotonically increasing maximum value sequence, a monotonically increasing minimum value sequence, a monotonically increasing average value sequence and a monotonically increasing median sequence; The first operation is: Assume {t1,t2,t3,...,t N } is the preset unit time series, {y1,y2,y3,...,y N } is the tilt value sequence corresponding to the preset unit time series; Wherein, the tilt value sequence is a maximum value sequence, a minimum value sequence, an average value sequence or a median sequence; t1 represents the first preset unit time, and y1 represents the tilt value corresponding to time t1; t2 represents the second preset unit time, and y2 represents the tilt value corresponding to time t2; t3 represents the third preset unit time, and y3 represents the tilt value corresponding to time t3; t N Indicates the Nth preset unit time; y N Indicates t N The tilt value corresponding to time; Get the maximum subsequence of the tilt value sequence {y i ,y i+1 ,y i+2 ,...y j } and the time series corresponding to the maximum subsequence {t i ,t i+1 ,t i+2 ,...t j }; Among them, y j is the maximum value in the maximum subsequence, y i is the second largest value in the maximum subsequence; the number of the maximum subsequence is single or multiple; 1≤i<j≤N; For the largest subsequence, except y i and j Other elements y k Update, the calculation formula is: Among them, t k is the kth data in the preset unit time series; k is all integers between i and j, i <k<j;y k Indicates time t k The corresponding tilt value; y' k for y k The replacement value of .

4. The building structure safety prediction and early warning method based on the grey model according to claim 3 is characterized in that: Inputting the monotonically increasing data into a grey prediction model of building tilt conditions, and outputting a prediction sequence of building tilt values ​​at a second time, specifically includes: The second operation is performed on the monotonically increasing maximum value sequence, the monotonically increasing minimum value sequence, the monotonically increasing average value sequence or the monotonically increasing median sequence to obtain the second time building tilt maximum value prediction sequence {A n }, the second time building tilt minimum value prediction sequence {B n }、Second time building tilt average value prediction sequence {C n } and the second time building tilt median prediction series {D n }; The second operation is: Inputting a monotonically increasing tilt value sequence into the sliding window; the monotonically increasing tilt value sequence is a monotonically increasing maximum value sequence, a monotonically increasing minimum value sequence, a monotonically increasing average value sequence or a monotonically increasing median sequence; Processing the monotonically increasing tilt value sequence using a sliding window to obtain a tilt value sequence of the sliding window; Inputting the tilt value sequence of the sliding window into a grey prediction model of building tilt conditions, and outputting a second time building tilt value prediction sequence; The calculation formula of the second time building tilt value prediction sequence is: in, is the kth predicted value in the second time building tilt value prediction sequence; is the kth predicted value in the first accumulation sequence of the predicted sequence of the building inclination value at the second time; is the k-1th predicted value in the first accumulation sequence of the predicted sequence of the building inclination value at the second time; The calculation formula is: Among them, -a is the development coefficient of the grey prediction model of building tilt, and b is the grey action of the grey prediction model of building tilt.

5. The building structure safety prediction and early warning method based on the grey model according to claim 4 is characterized in that: The calculation process of the development coefficient -a and the grey action b is: Define the parameter vector Using the least squares method The estimated formula is: in, x (0) (2) is the second element in the tilt value sequence of the sliding window; x (0) (3) is the third element in the tilt value sequence of the sliding window; x (0) (n) is the nth element in the tilt value sequence of the sliding window; Among them, z (1) (2) z (1) (3) and z (1) (n) is the sequence Z (1) Elements in Sequence Z (1) The expression of Z is: (1) =(z (1) (2), z (1) (3), ...z (1) (n)); Among them, the sequence Z (1) The kth element z in (1) The calculation formula for (k) is: Among them, x (1) (k) and x (1) (k-1) is the sequence X (1) Elements in Sequence X (1) The expression is: X (1) =(x (1) (1), x (1) (2), ...x (1) (n)); Among them, the sequence X (1) The kth element x in (1) The calculation formula for (k) is: Among them, x (0) (i) is the sequence X (0) The i-th element in ; Sequence X (0) The expression is: X (0) =(x (0) (1), x (0) (2), ...x (0) (n)); Among them, x (0) (1) is the first element in the tilt value sequence of the sliding window.

6. The building structure safety prediction and early warning method based on the grey model according to claim 4 is characterized in that: The predicted sequence of the building tilt value at the second time is compared with a preset threshold value, and different levels of safety warnings are issued according to the comparison results, specifically including: Determine the second time building tilt maximum value prediction sequence {A n }Is there a predicted value a greater than the preset threshold? n , if it exists, continue to judge with a n The predicted value a adjacent to the predicted time n-1 and a n+1 Is it greater than the preset threshold? If the predicted value a n-1 and a n+1 If both are greater than the preset threshold, a normal warning is issued; Determine the second time building tilt average prediction sequence {C n } Is there a predicted value c greater than the preset threshold? n , if it exists, continue to judge with c n The predicted value c adjacent to the predicted time n-1 and c n+1 Is it greater than the preset threshold? If the predicted value c n-1 and c n+1 All of them are greater than the preset threshold, and an advanced warning is issued; Determine the median prediction sequence of the second time building tilt {D n Is there a predicted value d greater than the preset threshold? n , if it exists, continue to judge with d n Prediction value d adjacent to the prediction time n-1 and d n+1 Is it greater than the preset threshold? If the predicted value d n-1 and d n+1 All of them are greater than the preset threshold, and an advanced warning is issued; Determine the minimum value prediction sequence of the second time building tilt {B n } Is there a predicted value b greater than the preset threshold? n , if it exists, continue to judge with b n Prediction value b adjacent to the prediction time n-1 and b n+1 Is it greater than the preset threshold? If the predicted value b n-1 and b n+1 If all of them are greater than the preset threshold, the highest warning will be issued.

7. A building structure safety prediction and early warning system based on a grey model, applied to the building structure safety prediction and early warning method based on a grey model as claimed in claim 1, characterized in that: The building structure safety intelligent prediction and early warning system based on the grey model includes: The building intelligent monitoring module is used to obtain the building tilt data collected within a first time; wherein the building tilt data collected within the first time is data measured by a tilt sensor arranged in the building; A data preprocessing module is used to process the building tilt data collected in the first time to obtain monotonically increasing data; A grey model prediction module, used for inputting the monotonically increasing data into a grey prediction model of building tilt conditions, and outputting a prediction sequence of building tilt values ​​at a second time; The building structure safety prediction and warning module is used to compare the predicted sequence of building inclination values ​​at the second time with a preset threshold value, and issue safety warnings of different levels according to the comparison results.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the grey model-based building structure safety prediction and early warning method described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the grey model-based building structure safety prediction and early warning method described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the grey model-based building structure safety prediction and early warning method described in any one of claims 1 to 7 is implemented.

Images