Digital engineering implementation dynamic monitoring system and method based on internet of things

Abstract

The present application belongs to the technical field of engineering monitoring, and discloses a digital engineering implementation dynamic monitoring system and method based on the Internet of Things. The method comprises the following steps: dynamically deploying a plurality of Internet of Things sensor nodes, collecting real-time data of the engineering site, integrating the data into a data stream, and transmitting the data stream to a cloud server through a wireless communication network; on the cloud server, the incoming data stream is segmented in real time to obtain a related data group; the engineering site is divided into a plurality of grid areas, and each grid area is data modeled based on the related data group to obtain a data model in the grid area; based on the data model in the grid area, the shortest path algorithm is used to calculate an optimal progress route of the engineering implementation; the optimal progress route is used to dynamically adjust the engineering implementation scheme, and the adjusted engineering implementation scheme is fed back to a site construction guidance terminal to guide the construction operation; and the quality and safety level of the engineering implementation are comprehensively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering monitoring, and more particularly to a digital engineering implementation dynamic monitoring system and method based on the Internet of Things. BACKGROUND

[0002] With the acceleration of urbanization, the construction demand of various infrastructures, public facilities and civil buildings is increasing day by day, however, the traditional engineering implementation mode has been difficult to meet the requirements of high quality, high efficiency and high safety of modern construction.

[0003] In the traditional engineering implementation process, the engineering site monitoring means is backward, mainly relying on manual inspection and fixed-point monitoring, with limited coverage and poor real-time performance; due to the complex and changeable engineering site environment, it is difficult for the traditional monitoring method to timely discover and handle various emergency situations, which is easy to cause hidden dangers in quality, progress and safety; secondly, the on-site data collection lacks systematicness and comprehensiveness; engineering construction involves many aspects such as environment, safety, quality, weather, traffic, etc., but the existing data collection often only focuses on certain specific aspects, and cannot form the overall data portrait of the engineering site, which is difficult to support scientific decision-making; moreover, the formulation of engineering implementation scheme relies too much on manual experience and lacks data support; due to the one-time and non-repetitive characteristics of engineering construction, the actual situation of each engineering site is different, and too much reliance on experience judgment is easy to produce deviation, resulting in poor execution effect of the scheme; the engineering implementation process lacks flexibility and adaptability; once the engineering implementation scheme is formulated, it is difficult to make timely adjustments according to the actual changes of the site, which brings great challenges to the response to emergency situations and affects the quality and efficiency of engineering implementation; finally, the on-site construction guidance is formalistic and lacks standardized and quantitative support, which cannot fine-grained control the complex operation process, resulting in uneven construction quality.

[0004] In view of this, the present application proposes a digital engineering implementation dynamic monitoring system and method based on the Internet of Things to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme: a digital engineering implementation dynamic monitoring system based on the Internet of Things, comprising: a dynamic deployment module for dynamically deploying a plurality of Internet of Things sensor nodes, and collecting real-time data of an engineering site by using the Internet of Things sensor nodes;

[0006] A data middle section processing module is used for integrating the collected real-time data into a data stream, and transmitting the data stream to a cloud server through a wireless communication network; on the cloud server, the incoming data stream is segmented in real time to obtain a related data group;

[0007] The model establishing module is configured to divide the engineering site into a plurality of grid areas and perform data modeling on each grid area based on a relevant data set to obtain a data model in the grid area.

[0008] The scheme optimization module is configured to calculate an optimal progress route of the engineering implementation based on the data model in the grid area by using a shortest path algorithm, dynamically adjust the engineering implementation scheme according to the optimal progress route, and feed back the adjusted engineering implementation scheme to the site construction guidance terminal.

[0009] Further, the deployment mode of the Internet of Things sensor node comprises:

[0010] A plan view of the engineering site is obtained, and the range of the monitoring area is determined; the monitoring area is divided into a plurality of triangular sub-areas to form an initial grid; the initial grid comprises a plurality of triangular sub-areas; according to the monitoring requirement, the type and quantity of the sensor to be deployed in each triangular sub-area are determined; the area of each triangular sub-area is calculated by using the Heron formula or the vector cross product method; the inradius r and the circumradius R of the triangular sub-area are calculated; the minimum angle θmin and the maximum angle θmax of the triangular sub-area are obtained;

[0011] The shape factor SF of the triangular sub-area is calculated based on the area S of the triangular sub-area;

[0012] wherein a, b and c are the lengths of the three sides of the triangular sub-area;

[0013] The complexity index C I is calculated based on the shape factor SF of the triangular sub-area and the area S of the triangular sub-area; wherein w1, w2 and w3 are the complexity weight coefficients;

[0014] The deployment priority Pr is calculated based on the complexity index C I and the area S of the triangular sub-area; All the triangular sub-areas are arranged in descending order according to the value of the deployment priority Pr;

[0015] A virtual sensor is initialized at the barycenter of each triangular sub-area; the initial coverage range of each virtual sensor is obtained;

[0016] The sorted triangular sub-areas are traversed to check whether the triangular sub-area is covered by the initial coverage range of the virtual sensor; if the triangular sub-area is completely covered, the corresponding triangular sub-area is skipped; if the triangular sub-area is partially covered or not covered, a candidate position is searched in the triangular sub-area; for each candidate position, the newly added initial coverage range is calculated; the position with the largest newly added initial coverage range is selected as the optimal position for deploying the Internet of Things sensor node in the corresponding triangular sub-area.

[0017] Further, the initial mesh is obtained in the following way:

[0018] obtaining a boundary contour of the monitoring area, discretizing the boundary contour into a series of boundary points according to a preset mesh density parameter, and connecting the boundary points to form an initial boundary edge;

[0019] defining a double-linked list, adding all the boundary edges to the double-linked list, and calculating an ideal triangle height h for each boundary edge in the double-linked list;

[0020] wherein f is a preset global scale factor, k is a local curvature, d is a preset mesh density, I is an importance index; a, β and γ are weight coefficients, and ε is an importance influence coefficient;

[0021] selecting a boundary edge from the double-linked list as a current active edge, generating a triangle for the current active edge based on the calculated ideal triangle height h, i.e. calculating a third vertex position of the triangle, setting a threshold distance, searching whether there is an existing mesh point within the threshold distance around the vertex position, if there is, using the nearest mesh point, if not, creating a new mesh point, checking whether the triangle intersects with an existing mesh element, if it intersects, adjusting the shape of the triangle, if it cannot generate a triangle, merging adjacent boundary edges, if a triangle is generated, adding the triangle to the mesh and removing the current active edge, and then obtaining an initial mesh.

[0022] Further, the real-time data of the engineering site includes environmental data, safety data, quality data, meteorological data and traffic data.

[0023] Further, the way of integrating the collected real-time data into a data stream includes:

[0024] performing preliminary processing on the real-time data, including denoising, outlier detection and data format unification, setting a fixed-size time window and determining the step size of the time window sliding, preliminarily classifying the real-time data according to the sensor types and positions of the Internet of Things sensor nodes, aggregating the real-time data of the same sensor type and position together in each sliding time window to obtain a data group, assigning a uniform timestamp to each data group, performing aggregation operation on the data group in each time window, organizing the data group after the aggregation operation into a structured format, JSON or a custom data structure, each data structure containing a timestamp, a sensor identifier, position information and a data value after the aggregation operation, and concatenating the continuous data structures in chronological order to form a continuous data stream.

[0025] Further, the way of performing real-time segmentation on the incoming data stream includes:

[0026] Set the split parameter, the split parameter includes target value μ0, allowed offset δ and decision interval; initialize the upper cumulative sum S + and the lower cumulative sum S - 0.

[0027] Define a sliding window and update the target value μ0 using the exponential weighted moving average, calculate the standard deviation using the data in the sliding window, set the allowed offset δ as a multiple of the standard deviation; set an update interval U, after processing U data points, update the target value μ0 and the allowed offset δ once;

[0028] Traverse the data stream, for the i-th newly arrived data point x_i, calculate the upper deviation d_i = x_i - (μ0 + δ); update the upper cumulative sum based on the upper deviation d_i, the update formula of the upper cumulative sum is:

[0029] S + _new = max(0, S + +d_i); where S + _new is the updated upper cumulative sum;

[0030] For the i-th newly arrived data point x_i, calculate the lower deviation f_i = (μ0 - δ) - x_i; update the lower cumulative sum based on the lower deviation f_i; the update formula of the lower cumulative sum is:

[0031] S - _new = max(0, S - +f_i); where S - _new is the updated lower cumulative sum;

[0032] If S + _new is greater than the decision interval or S - _new is greater than the decision interval, a change point is detected, record the timestamp and corresponding data value of the change point; reset the upper cumulative sum S + and the lower cumulative sum S - 0, and detect the i+1-th newly arrived data point; based on the detected change point, divide the data stream into several segments; assign a unique identifier to each segment and record the start and end timestamps;

[0033] Extract the time series features of each segment, calculate the correlation coefficient between adjacent segments using the sliding window algorithm based on the time series features; preset a correlation threshold, combine adjacent segments with a correlation coefficient greater than the correlation threshold into a correlation data group.

[0034] Further, the way of dividing the engineering site into several grid areas comprises:

[0035] Obtaining engineering site geographic information data; projecting the geographic information data to a unified coordinate system, setting the initial edge length d0 of the grid area; selecting one corner point of the engineering site boundary as the starting point, starting from the starting point, generating a regular square grid array according to the set edge length d0, and marking the area that cannot be completely covered by the regular square grid array as a residual polygon;

[0036] For each residual polygon, calculating its area A, if A>d0 2 , then halving d0 and repeatedly generating a regular square grid array inside the residual polygon; if A≤d0 2 , then taking the residual polygon as an independent grid area and not subdividing it;

[0037] Scanning all square grids to find square grids with an edge length less than d0, and marking them as small grids; merging adjacent small grids; the merging condition is that the edge length after merging does not exceed d0; and then obtaining a plurality of grid areas.

[0038] Further, the way of modeling data for each grid area comprises:

[0039] Obtaining geographic position information of data points in each related data group, traversing all grid areas, checking the coordinates of the boundary of each grid area, associating data points falling within the boundary of the grid area with the corresponding grid area and the related data group to which the data points belong;

[0040] For each grid area, extracting all associated related data groups inside the grid area and constructing a time series; performing difference on the time series to obtain a difference sequence until the difference sequence satisfies stationarity;

[0041] Drawing an autocorrelation graph of the difference sequence, if the autocorrelation graph presents a tailing phenomenon and the autocorrelation coefficient value gradually decays to 0 after p orders, selecting an autoregressive model as an initial modeling model; if the autocorrelation graph is truncated to 0 after q orders, selecting a moving average model as an initial modeling model, if the autocorrelation graph presents both a tailing phenomenon and is truncated to 0 after q orders, selecting an autoregressive moving average model as an initial modeling model; p and q are both orders of the initial modeling model; using a least square method or a maximum likelihood estimation method to estimate parameters of the initial modeling model and obtaining a residual sequence; testing whether the residual sequence is autocorrelation-free, has a mean value of 0 and has constant variance; if the residual sequence is autocorrelation-free, has a mean value of 0 and has constant variance, recording the residual sequence as a conditional sequence;

[0042] Based on the conditional sequence, constructing a data model of the corresponding grid area, and the expression of the data model is:

[0043] σ(t) 2 =a0+∑(s(u)×|∈(t-u)|x1 )+∑(e(v)×σ(tv) 2 )+ρ×D_t; its

[0044] In the middle, σ(t) 2 Let be the conditional variance over time t, a0 be a constant term greater than 0, s(u) be the autoregressive coefficient, x1 be the exponential coefficient, e(v) be the generalized autoregressive coefficient, and σ(tv) be the generalized autoregressive coefficient. 2 denoted as tv, representing the conditional variance of the past time tv; ∈(tu) represents the value of the residual term of the time series at time tu; u is the time lag order of the autoregressive term, v is the time lag order of the generalized autoregressive term; D_t is a 0-1 dummy variable; ρ is the coefficient of the dummy variable.

[0045] Furthermore, the method for obtaining the optimal schedule route includes:

[0046] The grid regions divided at the construction site are regarded as nodes in an undirected graph. For adjacent grid regions, an undirected edge is connected between them. The weight of each undirected edge is set as the difference in the conditional variance of the two adjacent grid regions at a future time T.

[0047] Select a start point and an end point in the grid region. If there are multiple start points / end points, connect them to the neighboring grid regions with undirected edges of weight 0.

[0048] Running the shortest path algorithm on an undirected graph, with the starting point as the source, finds the shortest path from the starting point to the ending point. The sequence of nodes on the shortest path is the preliminary optimal schedule for project implementation. The preliminary optimal schedule is then smoothed to obtain the optimal schedule.

[0049] The method for dynamic monitoring of digital engineering implementation based on the Internet of Things (IoT) is implemented based on the aforementioned dynamic monitoring system for digital engineering implementation based on the IoT, including: Step 1, dynamically deploying several IoT sensor nodes and using the IoT sensor nodes to collect real-time data from the engineering site.

[0050] Step 2: Integrate the collected real-time data into a data stream and transmit it to the cloud server via a wireless communication network. On the cloud server, the incoming data stream is segmented in real time to obtain relevant data groups.

[0051] Step 3: Divide the engineering site into several grid areas, and perform data modeling for each grid area based on relevant data sets to obtain the data model within the grid area;

[0052] Step 4, based on the data model in the grid area, the shortest path algorithm is used to calculate the optimal progress route of the engineering implementation; according to the optimal progress route, the engineering implementation scheme is dynamically adjusted, and the adjusted engineering implementation scheme is fed back to the field construction guidance terminal.

[0053] The technical effects and advantages of the digital engineering implementation dynamic monitoring system and method based on the Internet of Things are as follows:

[0054] The present application brings all-round intelligent monitoring and fine management to engineering implementation, greatly improving the quality, efficiency and safety of engineering implementation. First, full coverage and real-time dynamic data collection of the engineering site are realized, eliminating the monitoring blind area and providing accurate and timely data support for subsequent decision-making. Second, through data-driven modeling and analysis, the internal laws of the engineering site are deeply mined, effectively avoiding the human experience bias under the traditional mode, and improving the scientificity and foresight of the decision-making. Third, based on the data model difference, the optimal progress route of the engineering implementation is automatically calculated, which maximizes the reduction of the cost and risk of engineering conversion, and ensures the efficient and orderly engineering implementation. In addition, the engineering implementation scheme can be dynamically optimized and adjusted according to the real-time data on site, improving the adaptability and flexibility of the engineering implementation, and quickly responding to various unexpected situations. Finally, the optimized engineering implementation scheme is decomposed into specific operation guidance for each construction area, providing fine and standardized operation process for the field construction, thereby improving the quality and safety level of the engineering implementation. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The figure is a schematic diagram of the digital engineering implementation dynamic monitoring system based on the Internet of Things of the present application.

[0056] Figure 2 The figure is a schematic diagram of the digital engineering implementation dynamic monitoring method based on the Internet of Things of the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0058] Embodiment 1

[0059] Please refer to Figure 1 The digital engineering implementation dynamic monitoring system based on the Internet of Things described in the present embodiment comprises:

[0060] A dynamic deployment module is configured to dynamically deploy a plurality of Internet of Things sensor nodes, and collect real-time data of a construction site by using the Internet of Things sensor nodes;

[0061] A data section processing module is configured to integrate the collected real-time data into a data stream, and transmit the data stream to a cloud server through a wireless communication network, and perform real-time segmentation on the incoming data stream on the cloud server to obtain a related data group;

[0062] A model establishing module is configured to divide the construction site into a plurality of grid areas, and perform data modeling on each grid area based on the related data group to obtain a data model in the grid area;

[0063] A scheme optimization module is configured to calculate an optimal progress route of the construction implementation based on the data model in the grid area by using a shortest path algorithm, dynamically adjust the construction implementation scheme according to the optimal progress route, and feed back the adjusted construction implementation scheme to a site construction guidance terminal to guide the construction operation; the modules are connected through wired and / or wireless modes to realize data transmission between the modules.

[0064] The deployment mode of the Internet of Things sensor nodes includes:

[0065] A plan view of the construction site is obtained, and a range of a monitoring area is determined; the monitoring area is divided into a plurality of triangular sub-areas to form an initial grid; specifically, a boundary contour of the monitoring area is obtained, the boundary contour is discretized into a series of boundary points according to a preset grid density parameter, and the boundary points are connected to form an initial boundary edge.

[0066] A double-linked list is defined, all boundary edges are added to the double-linked list, and an ideal triangular height h is calculated for each boundary edge in the double-linked list;

[0067] wherein f is a preset global scale factor for overall controlling the grid size, k is a local curvature reflecting a bending degree of the boundary contour at the position of the boundary edge, d is a preset grid density (which can be understood as an expected average edge length), I is an importance index which is an integer greater than 1 determined by relevant personnel based on engineering criticality, safety requirements and other factors, and an important area (I is larger) will obtain a denser grid division; a, β and γ are weight coefficients for balancing the influences of the curvature, the density and the minimum size; and ε is an importance influence coefficient for balancing the influence of the importance index.

[0068] Select a boundary edge from the double-linked list as the current active edge, generate a triangle for the current active edge based on the calculated ideal triangle height h, i.e. calculate the position of the third vertex of the triangle, set a threshold distance (e.g. 10% of the triangle height h), search whether there is an existing grid point within the threshold distance around the position of the third vertex, if there is, use the nearest grid point, if not, create a new grid point (create a new grid point based on the calculated ideal triangle height); check whether the triangle intersects with existing grid elements, if it does, adjust the shape of the triangle, if it cannot be generated, merge adjacent boundary edges; if a triangle is generated, add the triangle to the grid and remove the current active edge; then an initial grid is obtained.

[0069] It should be noted that the grid point is the vertex of the triangle, including the existing points (such as the boundary point and the previously generated internal point) and the newly generated point; the position of the third vertex of the ideal triangle is to determine the ideal position of a new point based on the current active edge and the calculated ideal triangle height, which is in the normal direction of the midpoint of the current active edge and the distance is the calculated ideal triangle height; checking whether the triangle intersects with existing grid elements can be understood as whether the newly generated triangle overlaps with the existing triangle, including the intersection of edges and the case that the point falls inside other triangles.

[0070] The initial grid contains several triangles, denoted as triangle sub-regions; according to the monitoring requirements, determine the type and number of sensors to be deployed in each triangle sub-region; the sensor types include temperature and humidity sensors, noise sensors, dust sensors, etc.

[0071] Use the Heron formula or vector cross product method to calculate the area of each triangle sub-region; calculate the inradius r and the circumradius R of the triangle sub-region; obtain the minimum angle θmin and the maximum angle θmax of the triangle; based on the area S of the triangle sub-region, calculate the shape factor SF of the triangle sub-region;

[0072] where a, b and c are the side lengths of the three sides of the triangle sub-region;

[0073] Complexity index where w1, w2 and w3 are complexity weight coefficients; the larger the value of the complexity index, the more irregular the triangle, the higher the complexity;

[0074] According to the complexity index CI and the area S of the triangle sub-region, calculate the deployment priority Arrange all triangle sub-regions in descending order of the value of the deployment priority Pr.

[0075] A virtual sensor is initialized at the center of gravity of each triangular sub-region; the initial coverage range of each virtual sensor is obtained, specifically, if it is an omnidirectional sensor, a circle is drawn with the sensor position as the center and the maximum sensing distance R_max as the radius; if it is a directional sensor, a sector is drawn with the sensor position as the vertex, R_max as the radius, and the sensing angle range θ as the angle.

[0076] The sorted triangular sub-regions are traversed to check the coverage of the initial coverage range of the virtual sensor, if it is completely covered, the corresponding triangular sub-region is skipped; if it is partially covered or not covered, a candidate position is found in the triangular sub-region (considering the vertices and midpoints of the edges of the triangle, etc.); for each candidate position, the newly added initial coverage range is calculated; the position with the largest newly added initial coverage range is selected as the optimal position for deploying the Internet of Things sensor node inside the corresponding triangular sub-region; the final sensor deployment scheme is generated, including the specific coordinate position and type of each sensor; in the engineering implementation process, according to the changes of the site situation, dynamically adjust the deployment of the sensor, such as adding, removing or repositioning the sensor node.

[0077] The real-time data of the construction site includes environmental data, safety data, quality data, meteorological data, and traffic data;

[0078] The environmental data includes temperature, humidity, noise level, dust concentration, air quality (such as CO2 concentration, VOC, etc.), and light intensity; the safety data includes harmful gas concentration (such as CO, H2S, etc.), vibration intensity, inclination angle (for monitoring structural stability), and crack width (for monitoring structural deformation); the quality data includes concrete strength, reinforcement stress, structural deformation, and settlement; the meteorological data includes wind speed, wind direction, and rainfall; the traffic data includes vehicle entry and exit frequency and construction road congestion rate per unit time.

[0079] These data types cover multiple aspects of the construction process, helping to monitor the progress, quality, safety, and environmental impact of the project in real time; the specific data types and collection frequency are adjusted according to the specific needs and importance of the project.

[0080] Continuous real-time data is collected from various IoT sensor nodes, and preliminary processing is performed on the raw real-time data, including denoising, outlier detection, and data format unification. A fixed-size time window, such as 5 minutes, 10 minutes, or 15 minutes, is set, and the step size of the time window sliding is determined, which can be half of the window size or other appropriate values. The real-time data is preliminarily classified according to the sensor type and location of the IoT sensor nodes. In each sliding time window, real-time data of the same sensor type and location is aggregated together to obtain a data group. A uniform timestamp is assigned to each data group, usually using the start or midpoint time of the time window. In each time window, aggregation operations are performed on the data group, such as calculating the average, maximum, minimum, or other statistical quantities. The data group after aggregation is organized into a structured format, such as JSON or a custom data structure, each of which contains a timestamp, sensor identifier, location information, and data value after aggregation.

[0081] The continuous data structures are concatenated in chronological order to form a continuous data stream. Each data group in the data stream has a unique identifier to facilitate subsequent processing and tracking. An appropriate communication protocol (such as MQTT, CoAP, or a custom protocol) is used to transmit the data stream to the cloud server. Encryption and security mechanisms are implemented for data transmission to protect sensitive information.

[0082] The scattered and heterogeneous sensor data is effectively integrated into a continuous and structured data stream, providing a reliable data foundation for subsequent real-time analysis and decision-making. Both the timeliness of the data and the efficiency of data processing are guaranteed.

[0083] The real-time segmentation of incoming data streams includes:

[0084] Set the segmentation parameters, including the target value μ0 (usually the expected mean of the data), the allowed offset δ (adjusted according to the engineering implementation scenario), and the decision interval (control sensitivity). Initialize the upper cumulative sum S + and the lower cumulative sum S - to 0.

[0085] Define a sliding window and use the Exponential Weighted Moving Average (EWMA) to update the target value μ0. Calculate the standard deviation σ using the data in the sliding window, and set the allowed offset δ as a multiple of the standard deviation, such as δ = k1 × σ, where k1 is an adjustable parameter (such as k = 2 or 3). Set an update interval U (such as updating once every 50 data points processed), and perform the update of the target value μ0 and the allowed offset δ once every U data points processed.

[0086] Traverse the data stream, for the i-th newly arrived data point x_i, calculate the upper deviation d_i = x_i - (μ0 + δ); update the upper cumulative sum based on the upper deviation d_i, the update formula of the upper cumulative sum is:

[0087] S + _new = max(0, S + +d_i); wherein S + _new is the updated upper cumulative sum;

[0088] For the i-th newly arrived data point x_i, calculate the lower deviation f_i = (μ0 - δ) - x_i; update the lower cumulative sum based on the lower deviation f_i; the update formula of the lower cumulative sum is:

[0089] S - _new = max(0, S - +f_i); wherein S - _new is the updated lower cumulative sum;

[0090] If S + _new is greater than the decision interval or S - _new is greater than the decision interval, a change point is detected, and the timestamp and corresponding data value of the change point are recorded; reset the upper cumulative sum S + _and the lower cumulative sum S - to 0, and detect the i+1-th newly arrived data point; based on the detected change point, divide the data stream into several segments; assign a unique identifier to each segment and record the start and end timestamps.

[0091] Extract the time series features (such as autocorrelation coefficients, spectral features, etc.) of each segment, calculate the correlation coefficient between adjacent segments based on the time series features using a sliding window algorithm; preset a correlation threshold, and combine adjacent segments with a correlation coefficient greater than the correlation threshold into a correlation data group; assign a unique identifier to each correlation data group and record the ID and time range of the segments within the data segment group.

[0092] Identifying data groups with correlation not only quickly captures important change points in data, but also adapts to dynamic changes in the environment, providing reliable data support for real-time monitoring and decision-making in engineering sites.

[0093] The way to divide the engineering site into several grid areas includes:

[0094] Obtain engineering site geographic information data (remote sensing images, geographic information system (GIS) data, etc.); project the geographic information data onto a unified coordinate system, set the initial grid area side length d0, d0 is usually set to 10-50 meters, which can be adjusted according to specific circumstances.

[0095] Select one corner point of the project site boundary as the starting point, and generate a regular square grid array from the starting point according to the set side length d0. For the area that cannot be completely covered by the regular square grid array, mark it as a residual polygon.

[0096] For each residual polygon, calculate its area A. If A > d0 2 (initial grid area), halve d0 and repeat the generation of a regular square grid array inside the residual polygon. If A ≤ d0 2 , then the residual polygon is taken as an independent grid area and no longer subdivided.

[0097] Scan all square grids to find square grids with a side length less than d0, and mark them as small grids. Merge adjacent small grids. The merging condition is that the side length of the merged grid does not exceed d0. Then obtain several grid areas. Number all grid areas according to certain rules (such as row priority or column priority) and assign them unique IDs. Record the boundary coordinates (lower left corner and upper right corner) of each grid area for subsequent spatial correlation.

[0098] The data modeling method for each grid area includes:

[0099] Obtain the geographic location information (latitude and longitude coordinates or projection coordinates) of the data points in each relevant data set. Traverse all grid areas. For each grid area, check its boundary coordinates, associate the data points falling within the boundary of the grid area with the corresponding grid area and the relevant data set to which they belong.

[0100] For each grid area, extract all associated relevant data sets and construct a time series. Perform difference (first-order difference or seasonal difference) on the time series to obtain a difference sequence until the difference sequence meets the stationarity. The stationarity test can use unit root test (ADF test) or other statistical test methods.

[0101] Draw the autocorrelation graph (ACF) of the difference sequence, if the autocorrelation graph presents a tailing phenomenon, the autocorrelation coefficient value gradually decays to 0 after p order, then select the autoregressive model (AR) as the initial modeling model; if the autocorrelation graph is truncated to 0 after q order, then select the moving average model (MA) as the initial modeling model, if the autocorrelation graph presents both a tailing phenomenon and is truncated to 0 after q order, then select the autoregressive moving average model (ARMA) as the initial modeling model; p and q are both the order of the initial modeling model; the parameters of the initial modeling model are estimated by using the least square method or the maximum likelihood estimation method, and a residual sequence is obtained; the residual sequence is tested whether it is autocorrelated, has a mean of 0 and a constant variance (Ljung-Box test, Jarque-Bera normality test, etc. can be used); if the residual sequence is autocorrelated, has a mean of 0 and a constant variance, then the residual sequence is recorded as the conditional sequence.

[0102] Based on the conditional sequence, a data model corresponding to the grid area is constructed, and the expression of the data model is:

[0103] σ(t) 2 = a0 + ∑ (s(u) x |∈(t-u) x1 ) + ∑ (e(v) x σ(t-v) 2 ) + ρ x D_t; wherein

[0104] σ(t) 2 is the conditional variance at time t, a0 is a constant term greater than 0, ensuring that the conditional variance is positive, s(u) is an autoregressive term coefficient, the value of which is greater than 0; it reflects the influence degree of the residual term ∈(t-u) on the current conditional variance, specifically, s(u) captures the influence of new information of the residual term on future volatility; x1 is an exponential coefficient, usually taking 1 or 2; e(v) is a generalized autoregressive term coefficient, the value of which is greater than 0; it reflects the influence degree of the past conditional variance on the current conditional variance, specifically, it captures the persistence and clustering characteristics of volatility; σ(t-v) 2 is the conditional variance at past time t-v; ∈(t-u) is the value of the residual term (residual / error term) representing the time sequence at time t-u; u is the time lag order of the autoregressive term, and v is the time lag order of the generalized autoregressive term; D_t is a 0-1 dummy variable, used to capture the influence of a specific event on volatility, indicating whether a specific event (such as a holiday, a major accident, etc.) occurs; ρ is the coefficient of the dummy variable, reflecting the influence degree of the event on volatility.

[0105] The grid area divided in the engineering site is regarded as a node in the undirected graph, and a undirected edge is connected between adjacent grid areas, and the weight of each undirected edge is set as the difference of the conditional variance of the two adjacent grid areas at the future T time point; according to the actual situation of the engineering implementation, the starting point and the ending point are selected in the grid area, and if there are multiple starting points / ending points, they are connected with the adjacent grid areas by undirected edges with a weight of 0.

[0106] The shortest path algorithm, such as Dijkstra algorithm, is run on the undirected graph to find the shortest path from the starting point to the ending point, and the sequence of the nodes on the shortest path constitutes the preliminary optimal progress route of the engineering implementation; since the grid area is a regular square, some unnatural corners may exist in the shortest path, and the smoothing processing is performed on the shortest path to make it more natural and smooth; the smoothing methods include cubic spline interpolation, wavelet transform, etc.

[0107] The optimal progress route of the engineering implementation is calculated by using the shortest path algorithm based on the data model difference in the grid area; this route can minimize the environmental difference between adjacent work areas, thereby reducing the cost and risk of engineering conversion, and improving the construction efficiency and quality.

[0108] The optimal progress route is parsed into a series of grid area sequences according to the order of the grid areas, and the work content, time arrangement, required resources, etc. of each engineering construction area are planned in sequence according to the grid area sequences; the overall engineering implementation plan is analyzed to identify possible conflicts, bottlenecks or risk points; for the areas with problems, the work arrangement sequence, resource allocation, etc. are adjusted according to the data model to optimize the overall implementation plan; the optimized engineering implementation plan is decomposed into specific work guidance plans for each construction area.

[0109] In this embodiment, the engineering implementation is brought full range of intelligent monitoring and fine management, which greatly improves the quality, efficiency and safety of the engineering implementation. First, full coverage and real-time dynamic data collection of the engineering site is realized, eliminating the monitoring blind area and providing accurate and timely data support for subsequent decision-making. Second, through data-driven modeling and analysis, the internal laws of the engineering site are deeply mined, effectively avoiding the human experience bias in traditional ways and improving the scientificity and foresight of decision-making. Third, based on the data model difference, the optimal progress route of the engineering implementation is automatically calculated to minimize the cost and risk of engineering conversion and ensure the efficient and orderly implementation of the engineering. Fourth, the engineering implementation plan can be dynamically optimized and adjusted according to the real-time data on site, improving the adaptability and flexibility of the engineering implementation and quickly responding to various unexpected situations. Finally, the optimized engineering implementation plan is decomposed into specific work guidance for each construction area, providing fine and standardized work processes for on-site construction, thereby comprehensively improving the quality and safety level of the engineering implementation.

[0110] Embodiment 2

[0111] Please refer to Figure 2 As shown in the figure, the embodiment does not describe some parts in detail, see the description of embodiment 1, and provides a dynamic monitoring method for digital engineering implementation based on Internet of Things, including:

[0112] Step 1, dynamically deploying a plurality of Internet of Things sensor nodes, collecting real-time data of the engineering site by using the Internet of Things sensor nodes;

[0113] Step 2, integrating the collected real-time data into a data stream, and transmitting the data stream to a cloud server through a wireless communication network, and performing real-time segmentation on the incoming data stream on the cloud server to obtain a related data group;

[0114] Step 3, dividing the engineering site into a plurality of grid areas, and performing data modeling on each grid area based on the related data group to obtain a data model in the grid area;

[0115] Step 4, based on the data model in the grid area, calculating the optimal progress route of the engineering implementation by using the shortest path algorithm; according to the optimal progress route, dynamically adjusting the engineering implementation scheme, and feeding back the adjusted engineering implementation scheme to the site construction guidance terminal to guide the construction operation.

[0116] Embodiment 3

[0117] The embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to realize the running mode of the above-mentioned dynamic monitoring method for digital engineering implementation based on Internet of Things.

[0118] Since the electronic device introduced in the embodiment is the electronic device used to implement the dynamic monitoring method for digital engineering implementation based on Internet of Things in the embodiment, the specific implementation mode of the electronic device and its various forms can be understood by those skilled in the art based on the dynamic monitoring method for digital engineering implementation based on Internet of Things introduced in the embodiment, so the method of the electronic device is not introduced in detail. As long as the electronic device used to implement the dynamic monitoring method for digital engineering implementation based on Internet of Things in the embodiment is implemented by those skilled in the art, it belongs to the scope of the present application.

[0119] The above formulas are dimensionless values, and the formulas are obtained by collecting a large amount of data to simulate the nearest real situation, and the preset parameters and threshold values in the formula are set by the person skilled in the art according to the actual situation.

[0120] The above merely describes the preferred embodiments of the present application, and the protection scope of the present application is not limited to the above-described embodiments. Any technical solution falling within the concept of the present application shall fall within the protection scope of the present application. It should be noted that, for ordinary technical users in the technical field, some improvements and refinements without departing from the principles of the present application shall also be considered as falling within the protection scope of the present application.

Claims

1. A digital engineering implementation dynamic monitoring system based on the Internet of Things, characterized in that, The application relates to a dynamic deployment module for dynamically deploying a plurality of Internet of Things sensor nodes, wherein the Internet of Things sensor nodes are used to collect real-time data of a construction site; a data middle section processing module for integrating the collected real-time data into a data stream and transmitting the data stream to a cloud server through a wireless communication network, wherein the cloud server is used to divide the incoming data stream in real time to obtain relevant data groups; a model establishing module for dividing the construction site into a plurality of grid areas and performing data modeling on each grid area based on the relevant data groups to obtain a data model of the grid area; the method for dividing the construction site into a plurality of grid areas comprises the following steps: acquiring geographic information data of the construction site; projecting the geographic information data to a unified coordinate system and setting the side length d0 of an initial grid area; selecting a corner point of the boundary of the construction site as a starting point, and generating a regular square grid array according to the set side length d0; for the area that cannot be completely covered by the regular square grid array, the area is marked as a residual polygon; scanning all the square grids to find square grids with a side length less than d0 and marking the square grids as small grids; merging adjacent small grids; the merging condition is that the side length of the merged grid does not exceed d0; and then a plurality of grid areas are obtained; the method for performing data modeling on each grid area comprises the following steps: acquiring the geographic position information of the data points in each relevant data group, traversing all the grid areas, checking the coordinates of the boundary of each grid area, associating the data points falling within the boundary of the grid area with the corresponding grid area and the relevant data group to which the data points belong; for each grid area, extracting all the associated relevant data groups in the grid area and constructing a time sequence; performing difference on the time sequence to obtain a difference sequence until the difference sequence meets the stationarity; drawing an autocorrelation graph of the difference sequence; if the autocorrelation graph presents a tailing phenomenon and the autocorrelation coefficient value gradually decays to 0 after p orders, an autoregressive model is selected as an initial modeling model; if the autocorrelation graph is truncated to 0 after q orders, a moving average model is selected as the initial modeling model; if the autocorrelation graph presents both the tailing phenomenon and the truncation to 0 after q orders, an autoregressive moving average model is selected as the initial modeling model; p and q are the orders of the initial modeling model; the least square method or the maximum likelihood estimation method is used to estimate the parameters of the initial modeling model and obtain a residual sequence; the residual sequence is tested whether the residual sequence is autocorrelated, has a mean value of 0 and has a constant variance; if the residual sequence is autocorrelated, has a mean value of 0 and has a constant variance, the residual sequence is recorded as a conditional sequence; based on the conditional sequence, a data model of the corresponding grid area is constructed, and the expression of the data model is as follows: a scheme optimization module is used to calculate an optimal progress route of the construction implementation based on the data model in the grid area by using a shortest path algorithm; the optimal progress route is used to dynamically adjust the construction implementation scheme, and the adjusted construction implementation scheme is fed back to a site construction guidance terminal; the modules are connected through wired and / or wireless modes. The deployment method of the Internet of Things sensor nodes comprises the following steps: ​ ​ ​ For each residual polygon, calculate its area If then halve d0 and repeat the regular square grid array generation inside the residual polygon; if then the residual polygon is treated as an independent grid region and no further subdivision is performed. ​ ​ ​ ​ ​ ​ ; wherein, is the conditional variance of time ; is a constant term greater than 0; is an autoregressive term coefficient; is an exponential coefficient; is a generalized autoregressive term coefficient; is the conditional variance of past time ; is the value of the residual term representing the time series at time ; is the time lag order of the autoregressive term, is the time lag order of the generalized autoregressive term; is a 0-1 dummy variable; is the coefficient of the dummy variable; ​ 2. The IoT-based dynamic monitoring system for digital engineering implementation according to claim 1, characterized in that, ​ Obtaining the plan of the construction site, and determining the range of the monitoring area; dividing the monitoring area into several triangular sub-areas to form an initial grid; the initial grid contains several triangular sub-areas; according to the monitoring requirements, determining the type and quantity of sensors needed to be deployed in each triangular sub-area; using the Helen formula or vector cross product method to calculate the area of each triangular sub-area; calculating the inradius and circumradius of the triangular sub-area ; obtaining the minimum angle and maximum angle of the triangle ;​​ based on the area of the triangular sub-region , calculating a shape factor of the triangular sub-region ; wherein , and is the length of the side of the triangle sub-region; Computational complexity index ; wherein, , and are complexity weight coefficients; According to the complexity index and the area of the triangular sub-region , the deployment priority is calculated ; all the triangular sub-regions are arranged in descending order according to the value of the deployment priority ; Initializing a virtual sensor at the barycenter of each triangular sub-region; obtaining the initial coverage range of each virtual sensor; Traversing the sorted triangular sub-regions, checking the situation of the triangular sub-regions covered by the initial coverage range of the virtual sensor, if completely covered, skipping the corresponding triangular sub-region; if partially covered or not covered, finding a candidate position in the triangular sub-region; for each candidate position, calculating the newly added initial coverage range; selecting the position with the largest newly added initial coverage range as the optimal position for deploying the Internet of Things sensor node in the corresponding triangular sub-region.

3. The IoT-based dynamic monitoring system for digital engineering implementation according to claim 2, characterized in that, The initial grid acquisition method comprises: Obtaining the boundary contour of the monitoring area, discretizing the boundary contour into a series of boundary points according to the preset grid density parameter, and connecting these boundary points to form an initial boundary edge; defining a doubly linked list, adding all the border edges to the doubly linked list, calculating an ideal triangle height for each border edge in the doubly linked list ; ; wherein, is a preset global scale factor, is a local curvature, is a preset mesh density, is an importance index; , and are weight coefficients, is an importance influence coefficient; selecting a boundary edge from the double linked list as the current active edge, and calculating the ideal triangle height based on the calculated ideal triangle height generating a triangle for the current active edge, i.e. calculating the third vertex position of the triangle, setting a threshold distance, searching whether there is an existing grid point within the threshold distance around the vertex position, if there is, using the nearest grid point, if not, creating a new grid point; checking whether the triangle intersects with the existing grid elements, if intersects, adjusting the shape of the triangle, if unable to generate the triangle, merging the adjacent boundary edges; if a triangle is generated, adding the triangle to the grid and removing the current active edge; and then obtaining an initial grid.

4. The IoT-based digital engineering implementation dynamic monitoring system according to claim 1, characterized in that, The real-time data of the construction site includes environmental data, safety data, quality data, meteorological data, and traffic data.

5. The IoT-based dynamic monitoring system for digital engineering implementation according to claim 3, wherein, The method of integrating the collected real-time data into a data stream comprises: Preliminary processing of real-time data, including denoising, outlier detection and data format unification; setting a fixed size time window and determining the step size of the time window sliding; preliminarily classifying real-time data according to sensor type and position of the Internet of Things sensor node, aggregating real-time data of the same sensor type and position in each sliding time window to obtain a data group; assigning a uniform timestamp to each data group; aggregating the data group in each time window; organizing the data group after aggregation into a structured format, JSON or a custom data structure; each data structure contains a timestamp, a sensor identifier, position information, and a data value after aggregation; sequentially concatenating consecutive data structures in chronological order to form a continuous data stream.

6. The IoT-based dynamic monitoring system for engineering digitization implementation according to claim 5, characterized in that, The method of real-time segmentation of the incoming data stream comprises: A split parameter is set, the split parameter including a target value , an allowed offset , and a decision interval; an uplink cumulative sum and a downlink cumulative sum are initialized to 0; Define a sliding window and use an exponentially weighted moving average to update the target value , compute the standard deviation using the data in the sliding window, set the allowed offset as a multiple of the standard deviation ; set an update interval U, and perform the update of the target value and the allowed offset once every U data points processed ; Traverse the data stream, calculate the up bias for the first newly arrived data point ; update the up cumulative sum based on the up bias , and the update formula of the up cumulative sum is​​ ; wherein, is the updated uplink cumulative sum; For the first Newly arrived data points Calculate the bottom-up deviation Based on bottom-up bias Update the downlink cumulative sum; the update formula for the downlink cumulative sum is: wherein, is the updated downlink cumulative sum; If the decision interval or the decision interval, a change point is detected, the time stamp and the corresponding data value of the change point are recorded; the uplink cumulative sum and the downlink cumulative sum are reset to 0, and detection is performed on the newly arrived data points; based on the detected change points, the data stream is segmented into several segments; each segment is assigned a unique identifier, and the start and end time stamps are recorded. Extracting the time series features of each segment, calculating the correlation coefficient between adjacent segments based on the time series features using a sliding window algorithm; presetting a correlation threshold, and combining adjacent segments with a correlation coefficient greater than the correlation threshold into a correlation data group.

7. The IoT-based dynamic monitoring system for engineering digitization implementation according to claim 6, characterized in that, The method of obtaining the optimal progress route comprises: Treating the grid regions divided in the construction site as nodes in an undirected graph, connecting an undirected edge between adjacent grid regions, and setting the weight of each undirected edge as the difference between the conditional variances of the two adjacent grid regions at a future T time point; Selecting a starting point and an ending point in the grid region, and connecting them with adjacent grid regions using an undirected edge with a weight of 0 if there are multiple starting points or ending points; Running a shortest path algorithm on the undirected graph, taking the starting point as the source point, finding the shortest path from the starting point to the ending point, and the sequence of nodes on the shortest path constitutes the preliminary optimal progress route of the construction implementation; smoothing the preliminary optimal progress route to obtain the optimal progress route.

8. The method for dynamic monitoring of digital engineering implementation based on Internet of Things, which is implemented based on the system for dynamic monitoring of digital engineering implementation based on Internet of Things according to any one of claims 1 to 7, characterized in that, Comprising: Step 1, dynamically deploying a plurality of Internet of Things sensor nodes, and collecting real-time data of the construction site using the Internet of Things sensor nodes; Step 2, integrate the collected real-time data into a data stream, and transmit it to the cloud server through a wireless communication network. In the cloud server, the incoming data stream is segmented in real time to obtain relevant data groups. Step 3, divide the construction site into several grid areas, and based on the relevant data groups, model the data of each grid area to obtain the data model in the grid area. Step 4, based on the data model in the grid area, use the shortest path algorithm to calculate the optimal progress route for the implementation of the project. According to the optimal progress route, dynamically adjust the implementation scheme of the project, and feed back the adjusted implementation scheme of the project to the site construction guidance terminal.

Images