Multi-station data fusion method and system of intelligent total station

Abstract

The invention relates to the technical field of intelligent surveying and mapping, in particular to a multi-observation-station data fusion method and system for an intelligent total station, and the method comprises the steps: constructing a dynamic edge weight model which represents the spatial-temporal dynamic association between observation stations, and generating an edge weight; wherein the dynamic edge weight model generates an edge weight by setting adaptive adjustment parameters, adjusting the distance between observation stations and the proportion of the variance of observation station coordinate data; and performing adaptive adjustment on the adaptive adjustment parameters through chaotic adaptive collaborative optimization to obtain optimal adaptive adjustment parameters, generating edge weights according to the optimal adaptive adjustment parameters, and performing weighted fusion on the data of the multiple observation stations according to the edge weights. According to the scheme, by constructing the model for representing the space-time dynamic association between the survey stations and chaos adaptive collaborative optimization, the weight can be dynamically allocated, the dynamic environment change can be adapted, and the error can be reduced, so that the accuracy and robustness of multi-survey station data fusion can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent surveying and mapping, in particular to a multi-station data fusion method and system of an intelligent total station. BACKGROUND

[0002] As the core equipment of engineering surveying, the multi-station cooperative surveying technology of the total station has always been a research hotspot. However, the existing technology has the following key problems in multi-station data fusion: Limitations of static fusion model: traditional methods, such as least squares method and Kalman filter, rely on fixed mathematical models to assign station weights, which cannot adapt to dynamic environmental changes; for example, in a shielding scenario, the data confidence of a certain station drops sharply, but the traditional model still fuses the data according to the preset weight, leading to error accumulation; Error propagation and accumulation problem: multi-station data fusion usually needs to realize global alignment through a coordinate conversion model, but existing models such as seven-parameter conversion method are sensitive to local errors; Lack of real-time and automation: the existing technology relies on manual screening of abnormal data or adjustment of model parameters, which is inefficient.

[0003] The main reason for the above problems is that the existing technology has not effectively modeled the spatiotemporal dynamic correlation characteristics of total station data, and lacks a systematic solution to non-uniform error distribution, dynamic environmental interference, and multi-objective (such as precision and real-time) cooperative optimization.

[0004] Therefore, there is an urgent need for a multi-station data fusion method and system of an intelligent total station, which can dynamically assign weights, adapt to dynamic environmental changes, and reduce errors by building a model representing the spatiotemporal dynamic correlation between each station and chaotic adaptive cooperative optimization, to improve the accuracy and robustness of multi-station data fusion. SUMMARY

[0005] One of the purposes of the present application is to provide a multi-station data fusion method of an intelligent total station, which can dynamically assign weights, adapt to dynamic environmental changes, and reduce errors by building a model representing the spatiotemporal dynamic correlation between each station and chaotic adaptive cooperative optimization, to improve the accuracy and robustness of multi-station data fusion.

[0006] The present application provides a basic scheme one: a multi-station data fusion method of an intelligent total station, including the following contents: A dynamic edge weight model representing the spatiotemporal dynamic correlation between each station is constructed to generate edge weights between each station; wherein the dynamic edge weight model adjusts the proportion of the distance between stations and the variance of station coordinate data by setting adaptive adjustment parameters to generate edge weights; The adaptive adjustment parameter is adaptively adjusted through chaotic adaptive collaborative optimization, optimal adaptive adjustment parameters are obtained, edge weights generated according to the optimal adaptive adjustment parameters, and data of multiple measuring stations are weightedly fused according to the edge weights.

[0007] The second object of the present application is to provide an intelligent total station multi-station data fusion system, which can dynamically allocate weights, adapt to dynamic environmental changes, reduce errors, and improve the accuracy and robustness of multi-station data fusion by constructing a model representing the spatio-temporal dynamic correlation between each station and chaotic adaptive collaborative optimization.

[0008] The present application provides a basic scheme two: an intelligent total station multi-station data fusion system for executing the above-mentioned intelligent total station multi-station data fusion method, comprising: a server; The server is connected with each station and is used for constructing a dynamic edge weight model representing the spatio-temporal dynamic correlation between each station, generating edge weights between each station; wherein the dynamic edge weight model generates edge weights by setting adaptive adjustment parameters to adjust the proportion of the distance between stations and the variance of station coordinate data. The adaptive adjustment parameter is adaptively adjusted through chaotic adaptive collaborative optimization, optimal adaptive adjustment parameters are obtained, edge weights generated according to the optimal adaptive adjustment parameters, and data of multiple measuring stations are weightedly fused according to the edge weights.

[0009] Beneficial effects: this scheme converts the data fusion problem between each station into a graph node fusion problem, and the proportion of data between stations in the fusion process can be regarded as edge weight, so a dynamic edge weight model of each station representing the spatio-temporal dynamic correlation between each station is constructed, which is used to dynamically generate edge weights to adapt to dynamic environmental changes, reallocate weights, reduce errors and error accumulation in the data fusion process; Specifically, the dynamic edge weight model generates edge weights by setting adaptive adjustment parameters to adjust the proportion of the distance between stations and the variance of station coordinate data, wherein the stability of variance data, and the adaptive adjustment parameters can adjust the proportion of different indicators (distance and variance, etc.), accurately reflect the spatio-temporal dynamic correlation; wherein the adaptive adjustment parameters can be searched in space through chaotic adaptive collaborative optimization, adaptively adjust the adaptive adjustment parameters, obtain optimal adaptive adjustment parameters, generate edge weights according to the optimal adaptive adjustment parameters, and weightedly fuse data of multiple measuring stations according to the edge weights, thereby improving the accuracy and robustness of multi-station data fusion. Especially in the occlusion scenario, through chaotic adaptive collaborative optimization, the fusion accuracy can be more obviously improved. In a specific application process, the scheme is suitable for complex scenes, and for urban dense areas, through dynamic edge weight distribution, signal shielding and multipath interference are effectively coped with; for disaster monitoring, unmanned aerial vehicle rapid deployment station is supported, chaos adaptive cooperative optimization realizes autonomous fusion in a network-free environment; without manual intervention in abnormal data processing, manpower cost is saved.

[0010] To sum up, through the construction of the model representing the spatio-temporal dynamic correlation between each station and the chaos adaptive cooperative optimization, the scheme can dynamically distribute weights, adapt to dynamic environment changes, reduce errors, and solve the real-time fusion problem of total station multi-source data in unstructured environments (such as dynamic shielding, signal fluctuation, instrument drift, etc.), especially suitable for urban dense areas, mine monitoring, disaster emergency, etc. High-precision measurement scenarios, through dynamic modeling and intelligent optimization, the data accuracy and system robustness are improved. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 It is a flowchart of an embodiment of the intelligent total station multi-station data fusion method of the application. DETAILED DESCRIPTION

[0012] The following will be further described in detail through specific embodiments: Embodiment one This embodiment is basically as shown in the accompanying drawings Figure 1 An intelligent total station multi-station data fusion method is provided, including the following contents: Collect the data and attributes of each station, and the associated data between each station; wherein the data includes: coordinates; the associated data includes: the distance between each station; the attributes of the station, including: real-time position, environmental interference factor; wherein the environmental interference factor includes: temperature, humidity, vibration amplitude; in other embodiments, the station can be mapped as a node; the data is set according to the actual need of the data to be fused, which can fuse other data except coordinates; in this embodiment, the data is coordinates, that is, the coordinates of the multi-station are fused; A dynamic edge weight model representing the spatio-temporal dynamic correlation between each station is constructed, and the edge weight between each station is generated; The dynamic edge weight model adjusts the proportion of the variance of the distance between the stations and the station coordinate data by setting an adaptive adjustment parameter, to generate the edge weight; The dynamic edge weight model is: Wherein, is the distance between the stations and , unit: meter; and is the distance between the stations and Variance of coordinate data, reflecting data stability, unit: mm 2 ; , , Adaptive adjustment parameter.

[0013] The adaptive adjustment parameter is adaptively adjusted through chaotic adaptive collaborative optimization, optimal adaptive adjustment parameters are obtained, edge weights generated according to the optimal adaptive adjustment parameters, and data of multiple stations are weighted and fused according to the edge weights; The specific process is as follows: Chaotic initialization step: set chaotic mapping relationship, initialize iteration times , generate initial adaptive adjustment parameters, and then generate initial weight distribution; The chaotic mapping relationship is: Wherein is the chaotic state value of the m-th mapping, and the value range is (0, 1); The number of chaotic mapping represents the mapping times; Indicates the initial value, and the value range is (0, 1), and the initial assignment is =0.4, at this time, the data dispersion type is maximum, which maximizes the demand of optimization algorithm, based on the mathematical characteristics of the new chaotic mapping, the point can maximize the chaotic dispersion, and the existing Sine mapping is less sensitive to the initial value, which may lead to insufficient initialization diversity; The initial adaptive adjustment parameter is: ; The new chaotic mapping relationship set by the scheme generates the initial weight distribution and enhances the diversity of the search space.

[0014] Real-time weight calculation and data fusion step: the current adaptive adjustment parameter is brought into the dynamic edge weight model, the edge weight is calculated, and the data is weighted and fused according to the edge weight to generate fused data; The specific process is as follows: The global fusion data in the fused data , that is, the global fusion coordinate data, is calculated by weighted average of the coordinates of all stations: ; Wherein, for the station , its fusion weight is the sum of the edge weights of all adjacent stations ; , the station​ The original coordinates, Indicates the station The set of neighboring nodes.

[0015] The adaptive adjustment parameter optimization steps are as follows: The chaotic control parameters are updated according to the environmental disturbance factor, and the adaptive adjustment parameters are iteratively optimized. If the termination condition is met, the adaptive adjustment parameters of the current iteration are taken as the optimal adaptive adjustment parameters. Edge weights are generated according to the optimal adaptive adjustment parameters, and the data from multiple stations are fused in a weighted manner according to the edge weights. The termination condition is that the number of iterations is met, or the fusion difference between the fused data and the measured data is less than a preset threshold. The specific process is as follows: Calculate the fusion difference : ; in This represents the average of the measured values. Determine if the termination condition is met; if so, adjust the current adaptive parameters. The optimal adaptive adjustment parameter is selected and output; otherwise, it is updated. Update the chaotic control parameters, generate new adaptive adjustment parameters, and then perform real-time weight calculation and data fusion steps. The termination condition is as follows: ; in To preset the threshold for the difference between the before and after fusion, In this embodiment, the threshold number of iterations is used. , .

[0016] The current adaptive adjustment parameter is output. That is, the entire optimization process The minimum group parameter (adaptive adjustment parameter), and the global fused coordinates corresponding to the optimal adaptive adjustment parameter. The final fused coordinates are obtained by weighting and fusing data from multiple stations based on edge weights.

[0017] This involves updating the chaotic control parameters and generating new adaptive adjustment parameters: Update chaos control parameters: ; Chaos control parameters Used to control the convergence speed, with an initial value of 0.1. Decreasing this value refines the local development. The environmental stability index is calculated from vibration amplitude, temperature, and humidity data, ranging from [0,1], with larger values ​​indicating greater stability; specifically: ; wherein is a weight coefficient, which is set to 0.2, 0.5, 0.3 in the embodiment; is a vibration amplitude, unit: g; is a temperature change rate, is a humidity change rate; is a learning rate, which is preset to 0.1 in the embodiment; The scheme couples the environmental stability with the chaotic parameters, improving the convergence speed compared with the traditional method; A new adaptive adjustment parameter is generated by chaotic disturbance : ; The chaotic mapping relationship set in the scheme is a new type of chaotic mapping relationship, which is improved in many aspects compared with the traditional Sine chaotic mapping, wherein is an external control parameter, generally 4), and the specific improvements are as follows: Nonlinear enhancement: the new chaotic mapping relationship introduces an additional nonlinear term inside the sine function , which is similar to the core structure of the Logistic Map. This combination creates more complex dynamic behavior, while the existing Sine chaotic mapping only relies on a simple sine function; Parameter simplification: the existing Sine chaotic mapping requires an external control parameter , while the new mapping does not require any external parameters, reducing the complexity of parameter tuning and improving the adaptability of the chaotic mapping; Initial value optimization: based on the mathematical properties of the new mapping, the scheme can set a more appropriate initial value when initializing, such as x(1)=0.4, which maximizes the chaotic discreteness. The existing Sine mapping is less sensitive to the initial value, which may lead to insufficient initialization diversity.

[0018] The new chaotic mapping relationship brings significantly better results in the chaotic initialization and optimization process, including: Higher chaos and diversity: the new chaotic mapping relationship has a wider chaotic range and higher Lyapunov exponent, making the generated sequence more random and uniformly covering the search space, directly enhancing the diversity of the initial weight distribution and avoiding premature convergence of the optimization algorithm and falling into local optimum.

[0019] Faster convergence speed: In the chaos adaptive collaborative optimization, the new chaotic mapping relationship can generate effective parameter candidate values faster , thus reducing the number of iterations of global fusion difference ; The efficient chaotic disturbance of the new chaotic mapping relationship improves the convergence speed compared to traditional methods; Better stability: The new chaotic mapping relationship is more smooth in its dependence on initial values, and can generate chaotic sequences more stably when the environmental stability index changes, reducing the risk of algorithm divergence due to environmental disturbances.

[0020] Because of the mathematical properties and structural design of the new chaotic mapping relationship, the above better effects are produced. Specifically, nonlinear superposition effect: the sine function provides periodic traversal, while the logistic mapping introduces nonlinear feedback, and the superposition of the two enhances the hybridity and ergodicity of the chaotic mapping, which makes the sequence more difficult to predict and less likely to fall into a periodic orbit; Complexity of dynamical system: By analyzing the Lyapunov exponent, the new chaotic mapping relationship usually maintains a positive value (indicating chaos) in the range of x(t)∈(0,1), and the value is higher, while the existing Sine mapping is chaotic when the parameter a=4, but the chaos intensity is weak; The derivative of the new chaotic mapping is more complex and has stronger sensitivity.

[0021] Optimization of initial value: The choice of x(1)=0.4 is based on the bifurcation analysis of the new mapping, and near this point, the mapping can quickly enter a chaotic state, maximizing the dispersion of the initial population.

[0022] The new chaotic mapping relationship, as a core component of the chaos adaptive collaborative optimization, has a profound impact on the scheme, including: Improve global optimization ability: In chaotic initialization, the new chaotic mapping relationship generates a more diverse set of initial parameters, which makes the subsequent weight calculation and data fusion more accurate, reducing the impact of initial bias on global fusion coordinates; Enhance dynamic adaptability: In the chaos adaptive collaborative optimization, the chaotic disturbance of the new chaotic mapping relationship is coupled with the environmental stability index , making parameter updates more intelligent, and when environmental disturbances (such as temperature, vibration, humidity) change, the parameters can be quickly adjusted to maintain fusion accuracy; Improve termination efficiency: Due to the improved convergence speed, the iteration meets the termination condition earlier, saving computing resources and improving system real-time performance.

[0023] The new chaotic mapping relationship interacts closely with other steps in the scheme, forming a synergistic effect: ​The adaptive adjustment parameters generated during the initialization of the chaotic mapping relationship are substituted into the dynamic edge weight model to calculate the edge weights. ,in Depends on , , Therefore, the initialization is more diverse, and the edge weight calculation can better reflect the real spatiotemporal relationship between the stations, thereby improving the foundation of data fusion; Chaotic mappings indirectly affect edge weights by optimizing chaotic control parameters. and global fusion coordinates Better adaptive adjustment parameters can lead to more accurate weighted fusion and reduce fusion error. ; The novel chaotic mapping relationship can be directly used to generate new candidate values ​​for adaptive adjustment parameters. Furthermore, by coupling chaotic control parameters with environmental stability, a feedback loop is formed: environmental changes affect... , Adjusting the chaotic perturbation updates the adaptive adjustment parameters, which in turn optimize the edge weights and data fusion results. The novel chaotic mapping relationship leads to faster convergence, which means reaching the termination condition earlier and outputting the optimal parameters. The final fusion coordinates improved overall efficiency.

[0024] In summary, the novel chaotic mapping relationship enhances the chaotic characteristics by introducing nonlinear superposition, thereby improving the diversity, convergence speed, and stability of optimization. It not only directly improves chaotic initialization but also affects the performance of the dynamic edge weight model through parameter optimization chain. Compared with the existing Sine mapping, the novel chaotic mapping relationship is more suitable for the real-time data fusion needs in complex environments.

[0025] Taking emergency monitoring of dangerous rockfalls as an example: First, the monitoring stations are deployed: based on the terrain and visibility, five intelligent total stations (with built-in temperature, humidity, and vibration sensors) are set up around the dangerous rock as monitoring stations; for each monitoring point, the five intelligent total stations simultaneously measure its coordinates, once every 0.5 hours. The power supply for the monitoring stations adopts a hybrid mode of solar energy and lithium batteries to ensure long-term continuous operation, and the data is automatically transmitted.

[0026] Next, multi-station data fusion of the intelligent total station is performed: the data collected by each station is mapped to nodes; a dynamic edge weight model between nodes is constructed to represent the spatiotemporal dynamic relationship between each station; through chaotic adaptive collaborative optimization, the adaptive adjustment parameters are adaptively adjusted to obtain the optimal adaptive adjustment parameters, the edge weights generated based on the optimal adaptive adjustment parameters, and the data from multiple stations are weighted and fused based on the edge weights. Chaos initialization: = 0.3, = 0.03, = 0.1; Real-time weight calculation and data fusion: For each station , calculate its edge weight with neighbor stations , for example, the edge weight of station 3 with its neighbor station 5: ; Aggregate the total edge weight of station 3: When station 3 is blocked ( from 0.4 to 2.1), its total weight drops to = 0.483 (60% drop); Calculate the global fusion coordinates using the updated edge weights.

[0027] Adaptive adjustment parameter optimization: Optimization process, as shown in Table 1: Table 1: Iteration Schematic Table Edge weight application and data fusion output: using the optimal adaptive adjustment parameter, calculate the final edge weight, aggregate the fusion weight of each station, and output the final fusion coordinate result.

[0028] The embodiment also provides an intelligent total station multi-station data fusion system for executing the intelligent total station multi-station data fusion method, comprising: a server; The server is connected with each station, and is used for mapping the data collected by each station as a node; A dynamic edge weight model of each node representing the spatio-temporal dynamic correlation between each station is constructed to generate an edge weight; wherein the dynamic edge weight model generates the edge weight by setting an adaptive adjustment parameter to adjust the proportion of the distance between stations and the variance of station coordinate data; Through chaotic adaptive collaborative optimization, the adaptive adjustment parameter is adaptively adjusted to obtain the optimal adaptive adjustment parameter, the edge weight generated according to the optimal adaptive adjustment parameter, and the data of the multi-station weighted fused according to the edge weight.

[0029] ​The above-mentioned are only embodiments of the present application, and the common knowledge of specific structures and characteristics in the scheme is not described too much herein. The ordinary skilled person in the art knows all the ordinary technical knowledge in the field of the present application before the application date or the priority date, can know all the prior art in the field, and has the ability to apply conventional experimental means before that date. The ordinary skilled person in the art can perfect and implement the present scheme under the guidance of the present application, combined with their own ability. Some typical known structures or known methods should not be an obstacle for the ordinary skilled person in the art to implement the present application. It should be noted that, for those skilled in the art, without departing from the structure of the present application, a number of modifications and improvements can be made, which should also be considered as the protection scope of the present application. These will not affect the effect and practicality of the patent. The protection scope of the present application should be subject to the content of its claims, and the specific implementation mode and the like in the specification can be used to explain the content of the claims.

Claims

1. A multi-station data fusion method of an intelligent total station, characterized in that, The application relates to a method for intelligently fusing multi-station data of a total station, and belongs to the field of total station data fusion. The method comprises the following steps: The dynamic edge weight model is used to set an adaptive adjustment parameter, adjust the proportion of the distance between stations and the variance of station coordinate data, and generate the edge weight. The adaptive adjustment parameter is adaptively adjusted through chaotic adaptive collaborative optimization to obtain an optimal adaptive adjustment parameter, and the edge weight generated according to the optimal adaptive adjustment parameter and the data of multiple stations are fused according to the edge weight.

2. The intelligent total station multi-station data fusion method according to claim 1, characterized in that: The dynamic edge weight model is as follows: wherein is the station to ; and is the station and coordinate data of the station , , is an adaptive adjustment parameter.

3. The intelligent total station multi-station data fusion method of claim 1, wherein: The adaptive adjustment is performed through chaotic adaptive collaborative optimization, and comprises the following steps: A chaotic mapping relationship is set, the iteration times are initialized, and the initial adaptive adjustment parameter is generated; The current adaptive adjustment parameter is brought into the dynamic edge weight model to calculate the edge weight, and the data are fused according to the edge weight to generate fused data; The adaptive adjustment parameter is iteratively optimized according to the obtained environmental interference factor, and the adaptive adjustment parameter is updated.

4. The intelligent total station multi-station data fusion method according to claim 3, characterized in that: The chaotic control parameter is updated to generate a new adaptive adjustment parameter.

5. The intelligent total station multi-station data fusion method according to claim 3, characterized in that: The chaotic control parameter is updated to generate a new adaptive adjustment parameter. wherein is the first chaotic state value of the n-th mapping.

6. The intelligent total station multi-station data fusion method according to claim 5, characterized in that: the number of initialization iterations ; The server is used to execute the intelligent multi-station data fusion method of the total station. 。 7. The intelligent total station multi-station data fusion method according to claim 6, characterized in that: The server is connected with the stations and is used to construct the dynamic edge weight model representing the spatio-temporal dynamic correlation between the stations, and generate the edge weight. Global fusion data is calculated by weighted average of coordinates from all stations : ； where the station its fusion weight is the sum of its edge weights with all adjacent stations ​ the original data of the station, the original data of the station, a set of neighboring stations of the station, a set of neighboring stations of the station.

8. The intelligent total station multi-station data fusion method according to claim 7, characterized in that: The adaptive adjustment parameter is adaptively adjusted through chaotic adaptive collaborative optimization to obtain an optimal adaptive adjustment parameter, and the edge weight generated according to the optimal adaptive adjustment parameter and the data of multiple stations are fused according to the edge weight. Computing the fusion difference : ； wherein is the average of the measured values; determining whether the termination condition is satisfied, if yes, taking the adaptive adjustment parameter of the current iteration as the optimal adaptive adjustment parameter as the optimal adaptive adjustment parameter, obtaining the edge weight generated according to the optimal adaptive adjustment parameter, and fusing the data of multiple stations according to the edge weight; if no, updating , updating the chaos control parameter, generating a new adaptive adjustment parameter, and then performing the real-time weight calculation and data fusion steps.

9. The intelligent total station multi-station data fusion method of claim 8, wherein: ​ ​ ； wherein the chaos control parameters for controlling the convergence speed; is an environmental stability index, calculated from the amplitude of the vibrations, the temperature and the humidity; Generating new adaptive adjustment parameters by chaotic perturbation : 。 10. An intelligent total station multi-station data fusion system, characterized in that, ​ ​ ​

Images