Wireless sensor node deployment method for bridge structure monitoring

Abstract

The present invention provides a wireless sensor node deployment method for bridge structure monitoring, comprising: constructing a bridge model and a sensor node coverage perception model; determining the sensor node position and network coverage rate using a multi-strategy improved whale optimization algorithm guided by virtual force based on the bridge model and the sensor node coverage perception model; and deploying wireless sensor nodes for bridge structure monitoring based on the determined sensor node position and network coverage rate. By using the multi-strategy improved whale optimization algorithm guided by virtual force, the convergence speed and accuracy of the wireless sensor network node coverage optimization problem are solved, thereby achieving the purpose of greatly improving the node coverage rate in the three-dimensional bridge structure.

Description

Technical Field

[0001] The invention belongs to the technical field of wireless monitoring, and in particular relates to a wireless sensor node deployment method for bridge structure monitoring. Background Art

[0002] In recent years, my country has carried out a lot of research and engineering practice in the field of bridge structure health monitoring. The monitoring information obtained from the operating bridge structure and its environment can provide real information about the structural behavior and environmental laws, and provide new technical means for the maintenance of the bridge throughout its life cycle. However, limited by the development of sensor communication technology, computer technology and data science technology, the theory and technology of bridge condition monitoring and safety warning based on intelligent processing and analysis of monitoring data has long been in the exploratory stage; in addition, most bridges are located in complex environments, and there are problems such as poor real-time and accuracy of data collection, transmission and processing, low degree of data standardization and low data sharing rate. These problems have seriously restricted the development of bridge structure health monitoring and related scientific research.

[0003] At the same time, with the development of Internet of Things (IoT) and wireless sensor networks (WSN), bridge health monitoring systems (BHMS) can already use wireless sensors to self-organize to form bridge wireless sensor networks (BWSN) to complete data collection and transmission, which can save half the cost compared to traditional wired deployment. For example, the Bill Emerson Memorial Bridge is equipped with 84 wired acceleration sensors, and the average cost of each channel exceeds $15,000, of which cable wiring accounts for 50% of the total installation cost. In addition, WSN has the advantages of easy installation, flexible deployment, and low subsequent maintenance costs. Building BWSN to complete comprehensive monitoring of bridge structures can effectively save costs and provide an effective alternative for long-term and scalable health monitoring of bridge structures.

[0004] To fully realize the health monitoring of bridge structures, the first problem is to optimize the deployment of wireless sensor nodes and use wireless ad hoc network technology to build BWSN to achieve comprehensive dynamic three-dimensional perception of bridge structures. Therefore, how to select appropriate monitoring points to deploy a limited number of sensors to achieve optimal collection and maximum coverage of structural information is one of the key technologies in bridge health monitoring. Heuristic optimization algorithms have been proven to be effective and feasible for the deployment of sensor nodes, but most of the current related research only stays in two-dimensional plane simulation models. Whether these methods can be effectively applied to the optimal deployment of wireless sensor nodes for bridge structure health monitoring still needs to be tested in practice. Secondly, due to the large number of monitoring elements, there are naturally many types of sensor nodes, so it is inevitable to consider the heterogeneous properties of nodes in the process of node optimization deployment. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a method for deploying wireless sensor nodes for bridge structure monitoring, which at least partially solves the problem of wireless sensor network coverage in a three-dimensional bridge structure existing in the prior art.

[0006] An embodiment of the present invention provides a wireless sensor node deployment method for bridge structure monitoring, comprising:

[0007] Construct bridge model and sensor node coverage perception model;

[0008] Based on the bridge model and sensor node coverage perception model, a multi-strategy improved whale optimization algorithm guided by virtual force is used to determine the sensor node location and network coverage.

[0009] Wireless sensor nodes for bridge structure monitoring are deployed based on the determined sensor node locations and network coverage.

[0010] Optionally, the method of determining the sensor node location and network coverage using a multi-strategy improved whale optimization algorithm guided by virtual force based on the bridge model and the sensor node coverage perception model includes:

[0011] Use chaotic mapping and random reverse learning to generate a uniformly distributed initialization population, and calculate the fitness value of each individual in the initialization population;

[0012] Obtaining nonlinear convergence factor, dynamic adaptive weight, iterative update coefficient A and iterative update coefficient C;

[0013] Based on the initial population, the fitness value of each individual, the nonlinear convergence factor, the dynamic adaptive weight, the iterative update coefficient A and the iterative update coefficient C, the new position of the whale is obtained using the improved whale optimization algorithm;

[0014] After obtaining the new position of the whale, the t-distribution with different degrees of freedom is used to perturb and generate a new solution of the improved whale optimization algorithm. Then, according to the Metropolis criterion, the worse solution among the new solutions is accepted with a specific probability to obtain the whale position with a worse fitness value.

[0015] By interfering with the whales with poor fitness values, the positions of the whales with poor fitness values ​​are updated;

[0016] Update the whale's fitness value;

[0017] The improved whale optimization algorithm is iteratively calculated based on the fitness value of the updated whale, so as to obtain the information of the best whale, which includes the position of the whale and the final fitness value;

[0018] The location and fitness value of the whale correspond to the location of the sensor nodes and the network coverage, respectively.

[0019] Optionally, the chaotic mapping is a Tent mapping.

[0020] Optionally, obtaining the nonlinear convergence factor includes:

[0021] An exponential decay function with a tangent function is used as the nonlinear convergence factor.

[0022] Optional, nonlinear convergence factor ,

[0023] in, is the nonlinear convergence factor, b is the scaling parameter of the function, t is the current number of iterations; iter_max is the maximum number of iterations.

[0024] Optionally, the dynamic adaptive weight is:

[0025] ,

[0026] in, is the dynamic adaptive weight, and are the maximum and minimum values ​​of weight change respectively, t is the current number of iterations; iter_max is the maximum number of iterations.

[0027] Optionally, the method of obtaining a new position of the whale by using an improved whale optimization algorithm based on the initialized population, the fitness value of each individual, the nonlinear convergence factor, the dynamic adaptive weight, the iterative update coefficient A and the iterative update coefficient C comprises:

[0028] Based on the initialization population, the fitness value of each individual, the nonlinear convergence factor, the dynamic adaptive weight, the iterative update coefficient A and the iterative update coefficient C, the action probability p is randomly generated, and the method of updating the whale's position is selected based on the action probability p.

[0029] Optionally, if the action probability p ≥ 0.5, the first method is used to update the whale's position.

[0030] If the action probability p < 0.5, the method of updating the new position of the whale is selected according to the size of |A|.

[0031] The wireless sensor node deployment method for bridge structure monitoring provided by the present invention solves the convergence speed and accuracy of the wireless sensor network node coverage optimization problem by using a multi-strategy improved whale optimization algorithm guided by virtual forces, thereby achieving the purpose of greatly improving the node coverage rate in the three-dimensional bridge structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present invention will become more apparent through a more detailed description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present invention.

[0033] Figure 1 A schematic diagram of a bridge model disclosed in an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of a 3D Boolean perception model disclosed in an embodiment of the present invention;

[0035] Figure 3 A schematic diagram of the spiral bubble net hunting behavior of a whale disclosed in an embodiment of the present invention;

[0036] Figure 4 The flowchart of the WOA algorithm disclosed in the embodiment of the present invention;

[0037] Figure 5 A schematic diagram of image comparison of the original convergence factor and the new convergence factor disclosed in an embodiment of the present invention;

[0038] Figure 6 A probability density diagram of the t-distribution disclosed in an embodiment of the present invention;

[0039] Figure 7 The MSIWOA flow chart disclosed in the embodiment of the present invention;

[0040] Among them, 1-sensor, 2-bridge pier. DETAILED DESCRIPTION

[0041] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0042] It should be clear that the following embodiments of the present invention are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present invention.

[0043] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. It should be understood by those skilled in the art based on the invention that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0044] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The illustrations only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0045] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0046] In bridge structure health monitoring, WSN nodes are usually deployed at specific locations of the bridge according to monitoring requirements to collect operating data of the bridge structure. Some sensor nodes can also be cast into the bridge body and piers during the construction of the bridge to monitor the strength, deformation and other parameters of the bridge material. These nodes are usually considered by engineers during the design and construction phases, and are deployed and installed accordingly. This effectively monitors the health of the bridge and ensures the safety and reliability of the bridge. In order to simulate the deployment characteristics of sensor nodes in the bridge space and facilitate the study of related routing algorithms, such as Figure 1 As shown, in this embodiment, the piers and part of the bridge body of the simply supported beam bridge are modeled as Z adjacent spaces (rectangular blocks with length, width and height of a, b and c respectively, and a volume of V = a*b*c), and the sensor nodes are deployed in the model, which is named SSB-SM.

[0047] At present, there are two basic perception models in the research of WSN coverage theory: Boolean perception model and probabilistic perception model. The Boolean perception model defines the coverage range from the perspective of geometric relationship. It is widely used due to its simplicity, intuitiveness, high computational efficiency, and ability to quickly verify the availability and effect of the proposed method. This embodiment extends the Boolean perception model commonly used in 2D WSN to 3D space to make it suitable for coverage method verification in SSB-SM.

[0048] like Figure 2As shown, point is the target monitoring point, node The perception range is The center of the ball is used to perceive the distance A spherical space area with a radius (determined by the hardware characteristics of the node). Only points contained in the spherical space can be covered by the node. For ease of calculation, the monitoring area is divided into grid points, assuming the target monitoring point (i.e. one grid point) The spatial coordinates of ,node The spatial coordinates of , then the mathematical expression of the Boolean perception model is shown in formula (1).

[0049] (1),

[0050] In the formula Representation Node Target monitoring point The perceived probability of Represents the Euclidean distance between two points in three-dimensional space, and its calculation formula is:

[0051] (2),

[0052] Therefore, S sensor nodes are deployed in SSB-SM. , then all sensor nodes monitor the target point The total perception probability is shown in formula (3).

[0053] (3),

[0054] Coverage / Perception Rate (CR):

[0055] Under the 3D Boolean perception model, when the target monitoring point When a point is sensed by the sensor node set S, it is considered to be covered. If all sensor nodes in the set S do not detect the monitoring point, the monitoring point is said to be uncovered. Therefore, as shown in formula (4), CR is defined as the ratio of the total number of covered grid points to the total number of grid points in SSB-S.

[0056] (4),

[0057] Covering Efficiency (CE):

[0058] CE is the ratio of the total volume of the monitoring area covered by all nodes to the total volume of all nodes, as shown in formula (5). It is used to measure the effective utilization of sensor nodes and reflects the redundancy of sensor nodes and the energy consumption of the entire network. The larger the CE value, the more uniform the node distribution and the lower the redundancy. At the same time, the higher the effective utilization of sensor nodes, that is, the highest network coverage is achieved with the least number of sensor nodes.

[0059] (5),

[0060] Overlap ratio (OR):

[0061] OR is defined as the ratio of the total number of monitoring points covered repeatedly to the total number of grid points in SSB-SM. When , the grid point is repeatedly covered. The smaller the OR, the smaller the overlapping area, the less redundancy, and the fewer wasted nodes. The OR of a monitoring point can be given by formula (6).

[0062] (6),

[0063] When monitoring point At the same time, the node and ( ) when overwritten, it means The total probability of repeated coverage of monitoring points in the entire monitoring area SSB-S can be calculated according to formula (7).

[0064] (7),

[0065] Therefore, OR can be expressed by formula (8).

[0066] (8),

[0067] like Figure 3 and Figure 4 As shown in the figure, the standard whale optimization algorithm: The whale optimization algorithm is an inspired swarm intelligence optimization algorithm proposed based on the whale hunting process. It uses three strategies to simulate the hunting behavior of whales: surrounding prey, spiral bubble net attack, and searching for prey. The position of the i-th whale after t iterations can be expressed by formula (9).

[0068] (9),

[0069] Where i = 1, 2, …, N, N and D represent the number of whales and the dimension of the problem respectively. Figure 3 shown.

[0070] Hunting strategy: When an individual in the whale population discovers prey, other individuals change their positions according to formula (10) and move toward the prey to start hunting.

[0071] (10),

[0072] in, represents the position of the best solution so far (i.e., the prey or the vicinity of the prey), and is updated in subsequent iterations if a better solution is available. A and C are correlation coefficients, which are given by formula (11).

[0073] (11),

[0074] Where r is a random number in the range [0, 1]. is the maximum number of iterations set, and a is the convergence factor.

[0075] Spiral bubble net attack strategy: Whales use bubble nets to surround and attack prey by spiraling, and this behavior can be mathematically modeled by formula (12).

[0076] (12),

[0077] Where b is a constant used to determine the shape of the spiral (the default value is 1), l is a random number in the range [-1, 1], and p is the action probability, which is randomly generated by each individual whale in the range [0, 1]. When the whale updates its position by spiraling around; When the whale approaches prey by constricting and surrounding it, When , the model is the same as formula (10), but the value range of A is different. Set ,Right now , the updated position of the whale can be anywhere between it and the current optimal individual.

[0078] Hunting strategy: When , the whales start searching for prey to increase the diversity of the population, so that the whales have the ability to search globally and avoid falling into the local optimum. Its mathematical model is shown in formula (13).

[0079] (13),

[0080] in, Randomly selected whale locations for the population.

[0081] Improved whale optimization algorithm:

[0082] The balance between the global exploration and local development capabilities of the swarm intelligence optimization algorithm is crucial. In the early stages of algorithm iteration, the global exploration capability of the algorithm needs to be enhanced to maintain the diversity of the population and prevent the algorithm from falling into the local optimal solution. As the iteration proceeds, the algorithm should gradually turn to exploring and optimizing solutions close to the global optimal solution to enhance the local development capability, thereby improving the accuracy and convergence speed of the algorithm.

[0083] In general, the whale optimization algorithm has two search modes. Mode one is to search around the optimal individual (surrounding prey and attacking with a spiral bubble net), and mode two is to search around random individuals (searching for prey).

[0084] Its usage mode 1 is to update the position to perform a local optimization operation. The position is updated using formulas (10) and (12). The parameter A in (10) is used as a threshold to adjust the whale optimization method. The value of A is mainly related to the parameter a. The convergence of the algorithm is basically determined by the parameter a. However, the original strategy of a decreasing linearly with the number of iterations can easily lead to problems such as slow convergence and being limited to local optimality.

[0085] Its usage mode 2 to update the position is to perform a global optimization operation, using formula (13) to expand the search range. Although this operation enables WOA to have a certain global search capability, its failure to jump out of the local optimal operation and the poor optimization effect on multi-peak functions indicate that there is a problem of falling into local extreme values.

[0086] In view of the above shortcomings of WOA, this embodiment proposes four optimization measures:

[0087] Chaotic random reverse learning initialization population:

[0088] The quality of the population in the initialization phase has a certain impact on the performance of the optimization algorithm. Although the random initialization method used in the standard WOA is simple and easy to implement and has wide applicability, it has the disadvantages of insufficient guidance, high randomness, and poor diversity. This embodiment integrates chaotic mapping and random reverse learning strategy to initialize the population. The advantage of the fusion method is that it combines diversity and guidance, and can make full use of the diversity and exploration of chaotic mapping and the randomness and guidance of random reverse learning strategy, so as to more effectively initialize the population and improve the performance and efficiency of the algorithm.

[0089] Logistic mapping and Tent mapping are chaotic perturbation equations commonly used in the literature. Although the probability of the middle value of Logistic mapping is relatively uniform, the probability at the two ends is high, which is not conducive to optimization when the global optimal point is not at the two ends of the design variable space. In contrast, Tent mapping has better ergodic uniformity than Logistic mapping. At the same time, random reverse learning is used for population initialization to obtain a better initial solution. Therefore, this embodiment combines the advantages of Tent mapping and random reverse learning, and uses a new method of chaotic random reverse learning to initialize the population. The mathematical model of Tent mapping is expressed as formula (14).

[0090] (14),

[0091] Parameters in the formula When , the Tent mapping is uniformly distributed. Considering the problem of the Tent mapping iterating to a fixed point, a random factor can generally be introduced to improve formula (14) to formula (15).

[0092] (15),

[0093] After obtaining the chaotic initialized population, random reverse learning is performed on it, as shown in formula (16).

[0094] (16),

[0095] Among them, Lb and Ub represent the lower and upper bounds of the solution space respectively. After obtaining the chaotic random reverse learning initialization population Then, it is combined with the chaotic initialization population Merge into new population , calculate the fitness value of the new population, and then use the greedy strategy to allow sufficient competition within the population, and then select the best N individuals as the initial population.

[0096] Nonlinear convergence factor:

[0097] The convergence speed and search accuracy of WOA are closely related to parameter a. When a is large, it has a stronger global search ability and is easy to jump out of the local optimum, but the local search ability is weak and the convergence speed is reduced; when a is small, it has a stronger local search ability and the convergence speed is accelerated, but it is easy to fall into the local optimum. In the standard WOA, a adopts a linear decrease strategy from 2 to 0, which will affect the ability of WOA to jump out of the local optimum when facing complex problems such as BWSN coverage optimization. If the value of a is relatively increased in the early stage of the algorithm, it will help improve the global exploration ability and avoid premature; if the value of a is relatively reduced in the later stage, the local development ability and convergence speed can be improved.

[0098] Therefore, this embodiment uses an exponential decay function with a tangent function as a new nonlinear convergence factor , as shown in formula (17):

[0099] (17),

[0100] Where b is the scaling parameter of the function, which determines the amplitude or magnitude of the function. Here b is set to 2 so that the amplitude of the function decreases from 2 to 0; t is the current iteration number of the algorithm; iter_max is the maximum iteration number of the algorithm. Figure 5 The new convergence factor shown Compared with the linear decrease, the new convergence factor can balance the global exploration ability and local development ability of the algorithm to a certain extent.

[0101] Dynamic Adaptive Weights:

[0102] Since the prey targets have different effects on the position update of the whale group during the hunting process of the whale updating the spiral position, this embodiment proposes a dynamic adaptive weight to improve the spiral position update of the whale, as shown in formula (18).

[0103] (18),

[0104] in, and are the maximum and minimum values ​​of the weight change, set to 1 and 0.6 respectively, t is the current iteration number of the algorithm; iter_max is the maximum iteration number of the algorithm. Therefore, the spiral update position formula of the whale changes from (12) to (19).

[0105] (19),

[0106] Weight Parameters Obtaining a larger value in the early stage of iteration enables the algorithm to maintain a stronger global search capability; obtaining a smaller value in the later stage of iteration accelerates the algorithm to converge to the optimal solution.

[0107] Adaptive t-distribution variation disturbance and acceptance difference solution:

[0108] When performing global search, the standard WOA lacks a mutation mechanism and is prone to falling into a local optimal solution. This embodiment introduces t-distribution perturbation operators with different degrees of freedom to randomly perturb individual whales, giving the algorithm diversity and stronger exploration capabilities. The adaptive t-distribution mutation perturbation formula proposed in this embodiment is shown in (20).

[0109] (20),

[0110] in, is a t distribution with 10 degrees of freedom, is a t distribution with 2 degrees of freedom. Figure 6 As shown. In the early stage of the algorithm operation, Play a leading role, making the algorithm stable in global exploration and avoiding falling into local optimal solutions; in the later stage of iteration Play a leading role, realize local precise search, and improve the optimization accuracy of the algorithm.

[0111] After using t-distribution perturbations with different degrees of freedom to generate new solutions, the simulated annealing algorithm is used to accept worse solutions with a certain probability according to the Metropolis criterion to jump out of the local optimal value, thereby making up for the algorithm defects of WOA.

[0112] The improved whale optimization algorithm of this embodiment is named MSIWOA, and its flow chart is as follows: Figure 7 As shown. Virtual force disturbance completes the optimization of wireless sensor node deployment:

[0113] In order to further obtain better convergence speed and search space, a virtual force algorithm (VFA) is introduced. The virtual force consists of forces from nearby nodes, attractive forces from grid points, and repulsive forces from boundaries. When the whale updates its position, the resultant force acting on the node acts as a disturbance to guide the node to move towards the gap. Under the action of From the original position ( ) moves to the optimal position ( ), the expression of the optimal position can be expressed as formula (21).

[0114] (twenty one),

[0115] in, , and Representing the combined force The projections on the 𝑥-axis, 𝑦-axis and z-axis directions, and 𝑀𝑜𝑣_𝑠𝑡𝑒𝑝 represents the step size of a single movement of the sensor node. In the early stage of the algorithm, a larger single movement step size is set to speed up convergence. As the number of iterations increases, a smaller step size is used to prevent the algorithm from oscillating. The virtual movement step size gradually decreases during the entire iteration process, and its change rule can be expressed by formula (22).

[0116] (twenty two),

[0117] Among them, 𝑀𝑎𝑥_𝑠𝑡 and 𝑀𝑖𝑛_𝑠𝑡 represent the maximum and minimum moving step sizes, and their values ​​are 2 and 0.1 respectively.

[0118] MSIWOA and VFA are combined into an effective bridge monitoring wireless sensor node deployment optimization strategy, called virtual force-guided multi-strategy improved whale optimization algorithm (VF-MSIWOA). The corresponding relationship between BWSN node deployment optimization and MSIWOA is shown in Table 1. Each whale corresponds to a deployment scheme of a sensor node, and the position and fitness value of the whale correspond to the location of the sensor node and the network coverage (CR), respectively.

[0119] Table 1 Correspondence between deployment optimization and MSIWOA

[0120]

[0121] VF-MSIWOA is used to solve the bounded constrained optimization problem of maximizing the BWSN node coverage, and the optimization function is formula (23).

[0122] (twenty three),

[0123] in , its pseudo code is shown in Algorithm 1, and the main steps are as follows.

[0124] Step 1: Initialize various system parameters, including SSB-SM size, number of sensor nodes, coverage, and related parameters and maximum number of iterations of the VF-MSIWOA algorithm.

[0125] Step 2: Use formula (16) to initialize the deployment plan set, and use formula (23) to calculate the fitness value of each individual. Here we need to pay attention to the conversion between maximization and minimization.

[0126] Step 3: MSIWOA starts optimization and is calculated according to formulas (17), (18) and (11) , , A and C, and randomly generate action probabilities p. If , then update the whale's position according to formula (19); otherwise, The size of is used to update the new position of the whale using formulas (10) and (13).

[0127] Step 4: After using t-distributions with different degrees of freedom to generate new solutions, the Metropolis criterion is used to accept worse solutions with a specific probability to avoid falling into the local optimum.

[0128] Step 5: Use formulas (21) and (22) to interfere with whales with poor fitness values ​​and update their positions.

[0129] Step 6: Update the fitness value of the whale and save the best individual.

[0130] Step 7: Determine whether the number of iterations has reached the upper limit. If not, return to step 3; if so, execute step 7.

[0131] Step 8: Output the information of the best whale, including the whale's position and final fitness value.

[0132] The VF-MSIWOA calculation procedure is as follows:

[0133] Require: Sensor node set: ; Perceiveddistance: ; Population size: N and Maximum iterations: iter_max.

[0134] Ensure: Sensor nodes' location and CR.

[0135] Initialize the set of deployment scheme using (16)

[0136] for do

[0137] Calculate the fitness using (23).

[0138] end for

[0139] Generate initial optimal deployment schemes: .

[0140] while

[0141] for do

[0142] Update

[0143] if1 ( )

[0144] if2 ( )

[0145] Update the current deployment scheme by (10).

[0146] else if2 ( )

[0147] Select a random search whale: .

[0148] Update the current deployment scheme by (13).

[0149] end if2

[0150] else if1 ( )

[0151] Update the current deployment scheme by (19).

[0152] end if1

[0153] end for

[0154] Generate new deployment scheme by (20).

[0155] Decide whether to accept the new deployment scheme by Metropoliscriterion.

[0156] Update the deployment schemes with poor CR by (21) and (22).

[0157] Update if there is a better solution.

[0158]

[0159] end while

[0160] return .

[0161] The main technical problems in this practical example are as follows:

[0162] (1) In view of the shortcomings of the whale optimization algorithm (WOA), such as sensitivity to parameter settings, strong dependence on the initial solution, and failure to jump out of the local optimal operation, multiple strategies are adopted to improve WOA, including: using chaotic mapping and random reverse learning to generate a uniformly distributed initialization population to improve the exploratory and stability of the algorithm; proposing a nonlinear convergence factor Instead of the linear convergence of the original algorithm, the global exploration ability and local development ability of the algorithm are balanced; dynamic adaptive weights are used to improve the spiral bubble net attack strategy of the whale; t-distributed perturbation operators with different degrees of freedom are introduced to randomly perturb individual whales, and according to the Metropolis criterion, the algorithm is helped to jump out of the local optimal value by accepting worse solutions with a certain probability.

[0163] (2) The virtual force algorithm (VFA) is introduced to combine with MSIWOA to form VF-MSIWOA, which improves the convergence speed and accuracy of the algorithm in solving the BWSN node coverage optimization problem.

[0164] (3) The optimization objective function is composed of node coverage / perception rate (CR), coverage efficiency (CE), and overlap rate (OR), and VF-MSIWOA is used to complete deployment optimization.

[0165] This embodiment is based on the simply supported beam bridge spatial model (SSB-SM), and proposes a virtual force guided multi-strategy improved whale optimization algorithm (VF-MSIWOA) for optimizing the deployment of wireless sensor nodes for bridge structural health monitoring. First, chaotic mapping and random reverse learning are used to generate uniformly distributed initialization populations to improve the exploratory and stability of the algorithm; then, a nonlinear convergence factor is proposed to replace the linear convergence of the original algorithm to balance the global exploration ability and local development ability of the algorithm; secondly, a spiral bubble net attack strategy of the whale with dynamic adaptive weights is proposed; thirdly, t-distributed perturbation operators with different degrees of freedom are introduced to randomly perturb individual whales, and according to the Metropolis criterion, the algorithm is helped to jump out of the local optimal value by accepting a poor solution with a certain probability; finally, the virtual combined force acting on the node is used as the perturbation factor for updating the whale position, which improves the convergence speed and accuracy of the algorithm in solving the WSN node coverage optimization problem. This embodiment can greatly improve the node coverage rate, and when the type and number of sensors change, VF-MSIWOA still has the best coverage performance.

[0166] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0167] In the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0168] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0169] It should also be noted that in the system and method of the present invention, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present invention.

[0170] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present invention is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0171] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0172] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A wireless sensor node deployment method for bridge structure monitoring, characterized in that: include: Construct bridge model and sensor node coverage perception model; Based on the bridge model and sensor node coverage perception model, a multi-strategy improved whale optimization algorithm guided by virtual force is used to determine the sensor node location and network coverage. Deploy wireless sensor nodes for bridge structure monitoring based on the determined sensor node locations and network coverage; The method uses a virtual force-guided multi-strategy improved whale optimization algorithm based on the bridge model and the sensor node coverage perception model to determine the sensor node location and network coverage, including: Use chaotic mapping and random reverse learning to generate a uniformly distributed initialization population, and calculate the fitness value of each individual in the initialization population; Obtaining nonlinear convergence factor, dynamic adaptive weight, iterative update coefficient A and iterative update coefficient C; Based on the initial population, the fitness value of each individual, the nonlinear convergence factor, the dynamic adaptive weight, the iterative update coefficient A and the iterative update coefficient C, the new position of the whale is obtained using the improved whale optimization algorithm; After obtaining the new position of the whale, the t-distribution with different degrees of freedom is used to perturb and generate a new solution of the improved whale optimization algorithm. Then, according to the Metropolis criterion, the worse solution among the new solutions is accepted with a specific probability to obtain the whale position with a worse fitness value. By interfering with the whales with poor fitness values, the positions of the whales with poor fitness values ​​are updated; Update the whale's fitness value; The improved whale optimization algorithm is iteratively calculated based on the fitness value of the updated whale, so as to obtain the information of the best whale, which includes the position of the whale and the final fitness value; The location and fitness value of the whale correspond to the location of the sensor nodes and the network coverage, respectively.

2. The wireless sensor node deployment method for bridge structure monitoring according to claim 1 is characterized in that: The chaotic map is a Tent map.

3. The wireless sensor node deployment method for bridge structure monitoring according to claim 1 is characterized in that: The obtaining of the nonlinear convergence factor comprises: An exponential decay function with a tangent function is used as the nonlinear convergence factor.

4. The wireless sensor node deployment method for bridge structure monitoring according to claim 3 is characterized in that: Nonlinear Convergence Factor , in, is the nonlinear convergence factor, b is the scaling parameter of the function, t is the current number of iterations; iter_max is the maximum number of iterations.

5. The wireless sensor node deployment method for bridge structure monitoring according to claim 1, characterized in that: The dynamic adaptive weight is: ， in, is the dynamic adaptive weight, and are the maximum and minimum values ​​of weight change respectively, t is the current number of iterations; iter_max is the maximum number of iterations.

6. The wireless sensor node deployment method for bridge structure monitoring according to claim 1, characterized in that: The method of obtaining the new position of the whale by using the improved whale optimization algorithm based on the initialization population, the fitness value of each individual, the nonlinear convergence factor, the dynamic adaptive weight, the iterative update coefficient A and the iterative update coefficient C comprises: Based on the initialization population, the fitness value of each individual, the nonlinear convergence factor, the dynamic adaptive weight, the iterative update coefficient A and the iterative update coefficient C, the action probability p is randomly generated, and the method of updating the whale's position is selected based on the action probability p.

7. The wireless sensor node deployment method for bridge structure monitoring according to claim 6 is characterized in that: If the action probability p ≥ 0.5, the first method is used to update the whale's position. If the action probability p < 0.5, the method of updating the new position of the whale is selected according to the size of |A|.

Images