Industrial sensor layout optimization method and system based on cross breeding optimization algorithm
By optimizing sensor layout through hybridization breeding algorithms, the problem of traditional methods being unable to adapt to changes in complex industrial environments has been solved, achieving efficient and low-cost sensor layout and improving monitoring accuracy and reliability.
Patent Information
- Application Number
- CN202510933123.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-08
- Publication Date
- 2025-11-07
AI Technical Summary
Traditional sensor deployment methods that rely on engineers' experience are difficult to adapt to changes in complex industrial environments, resulting in monitoring blind spots, data redundancy, or omission of key parameters, and failing to achieve a balance between cost and performance.
An optimization algorithm based on hybridization breeding is adopted. The initial population is generated through numerical modeling and chaotic mapping. Individual selection and population division are carried out by combining fitness function and tournament strategy. The population is updated iteratively by hybridization and self-pollination operations, and finally the optimal sensor layout scheme is generated.
It achieves optimal sensor deployment in dynamic and complex industrial environments, improves monitoring efficiency, reduces deployment costs, and enhances the coverage, energy consumption control, and signal interference suppression capabilities of the sensor network.
Smart Images
Figure CN120911657A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of industrial automation and Internet of Things, and in particular to an industrial sensor layout optimization method and system based on a hybrid breeding optimization algorithm. BACKGROUND
[0002] In modern industrial production and operation processes, industrial sensors, as the core carriers of data acquisition, their layout design directly affects the accuracy and reliability of production process monitoring, equipment state evaluation and safety warning. However, industrial scenarios have strong dynamic, high complexity and multi-interference characteristics, and the traditional sensor deployment method relying on engineers' experience often lacks systematic theoretical support, and it is difficult to adapt to complex environmental changes. Specifically, industrial sites often face problems such as equipment vibration, electromagnetic interference, limited space structure, and multi-physical field (such as temperature, pressure, flow field, etc.) coupling effects, which easily lead to monitoring blind spots, data redundancy or missing key parameters in sensor layout, and thus affect the integrity and effectiveness of data acquisition.
[0003] At the same time, sensor deployment also needs to balance the cost and performance. On the one hand, blindly increasing the number of sensors can improve data coverage and accuracy, but will significantly increase the cost of hardware procurement, wiring installation and later maintenance; on the other hand, excessive compression of sensor configuration may lead to missing key data, reducing the reliability of state monitoring and fault diagnosis, and even causing production risks.
[0004] Therefore, how to scientifically optimize the sensor layout in a dynamic and complex industrial environment to minimize the deployment cost and maximize the monitoring efficiency has become one of the key technical bottlenecks restricting the intelligent upgrading of industry. There is an urgent need for a solution that integrates environment modeling, multi-objective optimization and intelligent algorithms to meet the fine and dynamic requirements of industrial scenarios for sensor layout. SUMMARY
[0005] The present application provides an industrial sensor layout optimization method and system based on a hybrid breeding optimization algorithm, to solve the problem that the sensor experience-based deployment method in the prior art is difficult to adapt to complex environmental changes, and to achieve scientific optimization of sensor layout in a dynamic and complex industrial environment to minimize deployment cost and maximize monitoring efficiency.
[0006] In a first aspect, the present application provides an industrial sensor layout optimization method based on a hybrid breeding optimization algorithm, comprising: S1, numerically modeling a to-be-detected region to obtain a region model; S2, encoding sensor layout information into a vector, and generating an initial population based on a solution space defined by the region model using chaotic mapping; S3, based on a designed fitness function, calculate the fitness value of all individuals in the current population, perform individual screening and population division based on the fitness value and a tournament strategy, and obtain an optimal individual and multiple sub-populations; S4, generate offspring by using hybridization and / or selfing operation on the multiple sub-populations, and iteratively update the population; S5, output the optimal population when the iteration termination condition is reached, and convert the optimal population into a corresponding sensor layout scheme.
[0007] According to the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm provided by the application, step S1 comprises: S101, scan the to-be-detected region, and determine the solution space range of the region model based on the scanning result; S102, determine the position of each to-be-detected target in the to-be-detected region based on the scanning result.
[0008] According to the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm provided by the application, step S2 comprises: S201, generate a chaotic value of each dimension in the solution space based on the initialization parameter of the hybrid breeding optimization algorithm; S202, linearly map the chaotic value of each dimension to the actual solution space, and combine all dimensions to obtain the initial population.
[0009] According to the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm provided by the application, in step S3, based on the designed fitness function, the fitness value of all individuals in the current population is calculated, which comprises: S301, based on the sensor layout information represented by the current population, calculate the area coverage rate of each sensor, the total distance between the sensor and the to-be-detected target, and the number of constraint violations of the sensor; S302, weight and sum the area coverage rate, total distance and constraint violation number to obtain the fitness value of each individual.
[0010] According to the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm provided by the application, in step S3, based on the tournament strategy and the fitness value, individual screening and population division are performed to obtain an optimal individual and multiple sub-populations, which comprises: S303, randomly extract a preset number of individuals from the current population to form a tournament set, perform individual screening based on the fitness value of each candidate individual in the tournament set, and obtain the optimal individual; S304, sort the candidate individuals in the tournament set according to the fitness value, divide the population based on the sorting result and a preset proportion, and obtain a development population, a balance population and an exploration population.
[0011] According to the hybrid breeding optimization algorithm-based industrial sensor layout optimization method provided by the application, step S4 comprises the following steps of: S401, for the randomly selected genes in the balanced population and the exploration population, a hybrid operation is used to generate new individual genes; S402, for the individual genes in the development population, a selfing operation is used to generate new individuals; S403, for the individual genes in the exploration population and the optimal individual genes in the development population, a hybrid operation is used to generate new individuals; S404, when the individual fitness is lower than the median of the current population fitness and the current iteration number is greater than half of the preset maximum iteration number, an individual elimination strategy is executed.
[0012] According to the hybrid breeding optimization algorithm-based industrial sensor layout optimization method provided by the application, the iteration termination condition in step S5 comprises the following conditions: The maximum iteration number is reached, or the change of the fitness in continuous generations is within a preset range.
[0013] In a second aspect, the application further provides a hybrid breeding optimization algorithm-based industrial sensor layout optimization system, comprising: A numerical modeling unit is configured to perform numerical modeling on a to-be-detected region to obtain a region model; A population generation unit is configured to encode sensor layout information into a vector and generate an initial population by using chaotic mapping based on a solution space defined by the region model; A population division unit is configured to calculate the fitness values of all individuals in a current population based on a designed fitness function, perform individual screening and population division based on a tournament strategy and the fitness values, and obtain an optimal individual and a plurality of subpopulations; A population updating unit is configured to generate offspring by using hybridization and / or selfing operations on the plurality of subpopulations and iteratively update the population; A scheme conversion unit is configured to output an optimal population when an iteration termination condition is reached and convert the optimal population into a corresponding sensor layout scheme.
[0014] In a third aspect, the application further provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the hybrid breeding optimization algorithm-based industrial sensor layout optimization method according to any one of the above aspects when executing the computer program.
[0015] In a fourth aspect, the application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the hybrid breeding optimization algorithm-based industrial sensor layout optimization method according to any one of the above aspects.
[0016] In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements any of the above-mentioned methods for optimizing industrial sensor layout based on hybrid breeding optimization algorithm.
[0017] The present application provides a method and system for optimizing industrial sensor layout based on hybrid breeding optimization algorithm. The method and system optimize the layout scheme by mathematical modeling and improved multi-objective hybrid breeding algorithm, thereby improving the practicability of industrial sensor layout. The technology solves the problem of layout optimization of sensor network in complex industrial scenarios under multiple constraint conditions such as coverage range, energy consumption control and signal interference suppression by fusing the ideas of co-evolution and multi-objective optimization strategy. The application of hybrid breeding optimization algorithm to sensor layout scenarios fills the gap in this technology and is expected to promote the evolution of the perception layer of industrial Internet of Things towards higher precision, lower cost and stronger adaptability. BRIEF DESCRIPTION OF DRAWINGS
[0018] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.
[0019] Figure 1 is a flowchart of the method for optimizing industrial sensor layout based on hybrid breeding optimization algorithm provided by the present application.
[0020] Figure 2 is a schematic diagram of the sensor layout before optimization provided by the present application.
[0021] Figure 3 is a schematic diagram of the sensor layout after optimization provided by the present application.
[0022] Figure 4 is a structural schematic diagram of the system for optimizing industrial sensor layout based on hybrid breeding optimization algorithm provided by the present application.
[0023] Figure 5 is a structural schematic diagram of the electronic device provided by the present application. DETAILED DESCRIPTION
[0024] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the protection scope of the present application.
[0025] As an intelligent optimization algorithm based on genetic and hybrid mechanisms, hybrid breeding optimization (HRO) can effectively deal with complex constraint problems in high-dimensional nonlinear space due to its balance between global search ability and local search ability, thus showing significant potential in the field of industrial sensor layout optimization. By simulating the principles of biological reproduction and evolution, HRO uses hybridization, selection, selfing, and mutation operations to simultaneously optimize the spatial position, number configuration, and type combination of sensors in a multi-objective coupled industrial scenario, which can not only avoid monitoring blind spots or redundant coverage caused by traditional experience design, but also dynamically adapt to the influence of environmental disturbances such as equipment vibration and electromagnetic interference on data acquisition quality. By combining the algorithm with a digital twin model, a high-precision simulation model of the factory physical space, equipment operating state, and multi-physical field distribution can be generated, and a sensor layout scheme that balances cost-effectiveness and data completeness can be generated, providing a high-value data foundation for real-time monitoring, fault warning, and energy efficiency optimization.
[0026] In view of the core problems such as dynamic environment response, heterogeneous sensor collaborative deployment, and Pareto optimal solution under resource constraint conditions in the industrial sensor layout scene, an embodiment of the present application provides an industrial sensor layout optimization method based on hybrid breeding optimization algorithm. In the method, first, a numerical model of the to-be-detected region is obtained; the sensor layout information is encoded into a vector, and the initial population is generated based on the solution space defined by the region model using chaotic mapping; based on the designed fitness function, the fitness values of all individuals in the current population are calculated, and individual screening and population division are performed based on the tournament strategy and fitness values to obtain an optimal individual and multiple subpopulations; hybridization and / or selfing operations are performed on the multiple subpopulations to generate offspring, and the population is iteratively updated; when the iteration termination condition is reached, the optimal population is output, and the optimal population is converted into a corresponding sensor layout scheme.
[0027] The embodiment of the application realizes the optimization of the layout scheme by mathematical modeling and improved multi-objective hybrid breeding algorithm, thereby improving the practicability of industrial sensor layout. The technology solves the layout optimization problem of sensor network in a complex industrial scene under multiple constraint conditions such as coverage range, energy consumption control and signal interference suppression by fusing the idea of co-evolution and multi-objective optimization strategy. The application of hybrid breeding optimization algorithm to the sensor layout scene fills the gap of this technology and is expected to promote the evolution of the perception layer of industrial Internet of Things to higher precision, lower cost and stronger adaptability.
[0028] The embodiment of the application can be applied to a scene requiring industrial sensor layout optimization. The execution subject of the method can be a terminal device, a computer, a server, a server cluster or a specially designed industrial sensor layout optimization device, etc. electronic device, or an industrial sensor layout optimization system provided in the electronic device, which can be realized by software, hardware or a combination of both.
[0029] In the description of the embodiment of the application, the meaning of "multiple" is two or more, unless otherwise explicitly specified. The following will be described in detail Figures 1-5 The application describes an industrial sensor layout optimization method and system based on hybrid breeding optimization algorithm.
[0030] Figure 1 is the flowchart of the industrial sensor layout optimization method based on hybrid breeding optimization algorithm provided by the application, as Figure 1 shown, the method comprises the following steps: S1, numerical modeling is performed on the to-be-detected region to obtain a region model.
[0031] Specifically, the to-be-detected region refers to a region where sensors need to be deployed for data collection, for example, a 100m x 100m square region, and 20 sensors need to be laid out in the region. The region model refers to a digital description formed by abstractly expressing the physical environment, geometric structure, interference factors (such as vibration, electromagnetic field) and target parameter distribution characteristics of the to-be-detected region by mathematical methods or simulation techniques.
[0032] In order to ensure the accuracy of the industrial sensor layout optimization, the detection region needs to be scanned first, data is collected to establish a data set, numerical modeling is performed on the to-be-detected region, mathematical modeling is made, thereby converting the layout problem into a mathematical model, and the region model obtained is , all data is stored in an external archive.
[0033] In one possible embodiment, step S1 comprises S101-S102: S101, scan the to-be-detected region, and determine the solution space range of the region model based on the scanning result; S102, determine the position of each to-be-detected target in the to-be-detected region based on the scanning result.
[0034] Specifically, the solution space range of the region model is a set of all potential sensor layout schemes that meet the monitoring requirements, and is a search domain for searching for an optimal solution by a subsequent optimization algorithm. By scanning the to-be-detected region, such as using a laser radar, a structured light scanner, or a high-definition camera carried by a drone, a high-precision geometric boundary of the to-be-detected region is obtained, and the maximum / minimum coordinate range of the physical space is determined. The boundary value is recorded, represents the upper bound of the d-dimensional solution space, represents the lower bound of the d-dimensional solution space.
[0035] The to-be-detected target refers to a specific object in an industrial scene that needs to be monitored by a sensor, such as a key component of equipment, a pipeline interface, a chemical reaction region, etc. The position of the to-be-detected target refers to the geometric coordinates (x, y, z) of the to-be-detected target in three-dimensional space and its spatial distribution characteristics (such as point-like targets, linear distribution, or planar coverage area). x y z The position of the to-be-detected target is one of the core constraint conditions for sensor layout optimization, and directly affects the design of the coverage range and the number configuration of the sensor.
[0036] All to-be-detected targets are recorded, and their coordinates are recorded, represented as .
[0037] S2, encode the sensor layout information into a vector, and generate an initial population based on the solution space defined by the region model.
[0038] In this step, the sensor layout information includes parameters such as position, type, and number, and the sensor layout information is encoded into a vector to facilitate efficient search and evaluation by a hybrid breeding optimization algorithm. Each vector element corresponds to a decision variable of a layout scheme, such as a sensor coordinate or a type number, and the vector as a whole represents a complete layout configuration.
[0039] Through the ergodicity and randomness of the chaotic system, an initial layout vector set that satisfies the solution space constraint is generated, i.e., an initial population. Compared with random initialization, chaotic mapping can more uniformly explore the solution space, avoid the algorithm from falling into local optimum, and improve the global search ability.
[0040] In some possible implementation manners, step S2 includes: S201, generate chaotic values for each dimension in the solution space based on the initialization parameters of the hybrid breeding optimization algorithm; S202 linearly maps the chaotic value of each dimension to the actual solution space and combines all dimensions to obtain the initial population.
[0041] Specifically, the initialization parameters include population size, maximum number of iterations, external archive capacity, and chaos parameters. The values of these initial parameters can be flexibly adjusted according to the actual scenario. For example, the population size of the algorithm can be set. =20, total number of iterations =100, external archive capacity is 10, chaos parameter =0.367.
[0042] To ensure that the generated individuals are completely random, "chaotic value generation" is used to generate individuals. The formula for calculating the chaotic value of each dimension in the solution space is as follows: (1)
[0043] In the formula, This represents the chaotic value generated in the kth iteration. Let D represent the chaotic value generated in the (k+1)th iteration, and let D represent the dimension of the solution space. This represents the chaos parameter.
[0044] The chaotic values of each dimension constitute a chaotic sequence, represented as follows: (2)
[0045] In this embodiment, This represents the generated d-th dimension chaotic sequence. It is a chaotic sequence Elements within, Indicates the first A chaotic value, Indicates population size.
[0046] The chaotic values are linearly mapped to the actual solution space as follows: (3)
[0047] In the formula, Denotes the upper bound of the d-dimensional solution space. Denotes the lower bound of the d-dimensional solution space. Represents an individual The Solution in 3D space.
[0048] Combining all dimensions yields the initial population: (4)
[0049] (5)
[0050] represents the generated initial population. Table 1 shows the initial population characterization of the sensor initial layout scheme, and all data is stored in an external archive.
[0051] Table 1 Initial position of sensor and index
[0052] S3, based on the designed fitness function, calculates the fitness value of all individuals in the current population, and based on the tournament strategy and the fitness value, individual screening and population division are performed to obtain the optimal individual and multiple subgroups.
[0053] Specifically, the fitness function is used to measure the pros and cons of the sensor layout scheme. According to the randomly generated population, the following three basic data are recorded: the sensor coverage rate , the sensor distance to its target distance , the number of constraint violations of the sensor . . Figure 2 is the schematic diagram of the sensor layout before optimization provided by the present application, as shown in Figure 2 , the black dots are sensors, the horizontal axis represents the horizontal coordinate of the sensor, and the vertical axis represents the vertical coordinate of the sensor. The unit of the horizontal axis and the vertical axis is m, wherein the coverage rate is 68.2%, the total communication distance is 1240m, and the constraint violation times is 15.
[0054] In some possible implementation manners, in step S3, based on the designed fitness function, the fitness value of all individuals in the current population is calculated, including: S301, based on the sensor layout information characterized by the current population, the area coverage rate of each sensor, the total distance between the sensor and the target to be detected, and the constraint violation times of the sensor are calculated; S302, the area coverage rate, the total distance and the constraint violation times are weighted and summed to obtain the fitness value of each individual.
[0055] Specifically, the current population is the population corresponding to the current iteration number. From each individual in the current population, i.e. the sensor layout vector, the layout parameters are extracted, and the following three indexes are calculated in combination with the region model and the target position: area coverage rate, distance between sensor and target to be detected, and constraint violation times of sensor.
[0056] Among them, the area coverage rate reflects the effective monitoring degree of the sensor to the target space. The higher the coverage rate, the stronger the monitoring ability of the sensor to the region. The area coverage rate is expressed by the formula: (6)
[0057] wherein, is the area coverage ratio of the sensor , is the monitoring area of the sensor , is the total area to be detected.
[0058] The distance between the sensor and the target to be detected reflects the closeness of the sensor to the target. The smaller the distance, the higher the monitoring accuracy of the sensor to the target. The distance between the sensor and the target to be detected is calculated as follows: (7)
[0059] (8)
[0060] wherein, is the number of targets to be communicated by the sensor , is the distance from the sensor to its communication target , is the total distance from the sensor to the target to be detected.
[0061] The number of constraint violations of the sensor reflects the compliance and feasibility of the layout scheme. The more the number of violations, the less desirable the scheme. The number of constraint violations of the sensor is calculated as follows: (9)
[0062] wherein, is the number of constraint violations of the sensor , is the number of times the sensor violates the interference constraint.
[0063] The final fitness function expression is and the formula of the combination of the three: (10)
[0064] wherein, is the weight of the coverage ratio, is the weight of the distance from the sensor to its target, is the weight of the number of times the sensor violates the interference constraint, is the smoothing factor.
[0065] After the fitness values of all individuals in the current population are calculated according to the above fitness function, the tournament principle can be adopted to divide the population, and the candidate individuals are divided into development populations , balanced population and exploration population , select the optimal individual by ranking the individual objective function value and elite individual , to balance the elite retention and diversity introduction, all data are stored in external archives. Specifically, it includes: S303, randomly select a preset number of individuals from the current population to form a tournament set, and select individuals based on the fitness value of each candidate individual in the tournament set to obtain the optimal individual; S304, sort the candidate individuals in the tournament set according to the fitness value, and divide the population based on the sorting result and the preset proportion to obtain the development population, the balanced population and the exploration population.
[0066] Specifically, randomly select individuals from the current population to form a tournament set: (11)
[0067] Select the individual with the best fitness from the tournament set , which can be understood as the greater the fitness value, the better the individual. The individual with the largest fitness value in the tournament set can be selected as the optimal individual, which can be expressed by the formula: (12)
[0068] Add the winning individual to the elite candidate set : (13)
[0069] The best individual in the elite set, i.e. the optimal individual, is denoted as .
[0070] In step S304, the candidate individuals in the tournament candidate set are sorted from high to low according to the fitness, and then divided into three subgroups according to the preset proportion, which are the development population , the balanced population and the exploration population , the purpose is to make the population both retain elite genes and ensure diversity.
[0071] Development population : high comprehensive fitness population, accounting for 30% of the population size, mainly used for focusing on local development and converging to the global optimal solution; Balanced population : medium comprehensive fitness population, accounting for 40% of the population size, mainly used for maintaining population diversity and coordinating exploration and development; Exploration population : Low overall fitness populations, accounting for 30% of the population, are mainly used to focus on global exploration and introduce diversity through cross-population hybridization.
[0072] S4 involves using crossbreeding and / or self-pollination operations on multiple subpopulations to generate offspring, and then iteratively updating the population.
[0073] Specifically, hybridization involves selecting parent individuals from different subpopulations and generating new offspring with characteristics of both parents through gene recombination, mimicking the genetic recombination mechanism of biological hybridization. Hybridization can integrate the superior traits of different subpopulations, promote population information exchange, and avoid premature convergence. Self-pollination involves selecting parent individuals within the same subpopulation and generating offspring through self-replication and local variation. Self-pollination can strengthen the inheritance of superior genes within a subpopulation while introducing controllable variation to maintain diversity, making it suitable for localized fine-grained searches.
[0074] In each generation of evolution, the target value for all individuals is calculated, and the external archive and the globally optimal individual are updated. The offspring population is generated through hybridization and / or self-pollination, and the offspring are produced to iteratively update the population.
[0075] In some possible implementations, S4 specifically includes: S401 uses hybridization to generate new individual genes for genes randomly selected in balanced and exploratory populations. S402, which uses self-pollination to generate new individuals based on the genes of individuals in the development population; S403, aimed at exploring the individual genes in the population and developing the optimal individual genes in the population, uses hybridization to generate new individuals; S404: When an individual's fitness is lower than the median fitness of the current population and the current iteration count is greater than half of the preset maximum iteration count, an individual elimination strategy is executed.
[0076] Specifically, regarding "balanced populations" "and "exploring populations" The gene vector of a new individual is updated using a hybridization operation. The formula is: (14)
[0077] in It refers to the genes of new individuals generated through hybridization. For the exploration population The first one selected randomly k One gene, For those from balanced populations The first one selected randomly k One gene, and is the crossover factor, which is introduced to adjust the contribution ratio of the genes of the individuals in the exploration population and the equilibrium population, respectively, to determine the proportion of genes inherited from these two sources by the new individual.
[0078] For the "development population ", self-crossing operation is adopted to enhance local search. The formula is as follows: (15)
[0079] wherein is the new individual generated by self-crossing operation, is the gene of the individual in the current development population, is the gene of the individual different from in the current development population, is the optimal individual in the current population, is the self-crossing factor, and is introduced into a dynamic adjustment mechanism to improve the local search ability and avoid excessive convergence. The updating formula is as follows: (16)
[0080] wherein represents the initial value of the factor, represents the final value of the factor, represents the maximum number of iterations, represents the current number of iterations, represents a hyperparameter to control the decay speed to achieve the adjustment strategy of slow decay in the early stage and fast decay in the later stage.
[0081] For the "exploration population " and the "development population ", hybrid operation is adopted to update the gene vector. The formula is as follows: (17)
[0082] wherein is the new individual generated by hybridization, is the gene of the best individual in the development population, is the gene of the individual in the exploration population, is the hybridization factor.
[0083] When the fitness of the individual is lower than the median of the fitness of the current population , and the number of iterations , the elimination strategy is executed, and the formula is as follows:
[0084] In the formula, is the newly generated individual, is the minimum fitness value of the current population, is a random number, usually uniformly distributed in [0, 1], is the maximum fitness value of the current population.
[0085] S5, output the optimal population when the iteration termination condition is reached, and convert the optimal population into a corresponding sensor layout scheme.
[0086] Specifically, stop searching when the iteration termination condition is reached, output the Pareto front stored in the external archive, and convert the solution into a corresponding sensor layout scheme, otherwise, continue iteration.
[0087] After updating the population, recalculate the fitness value and update the optimal solution, if the maximum number of iterations or the fitness value has no significant improvement in continuous generations, stop iteration, i.e. reach the iteration termination condition, output the optimal sensor layout scheme. The final solution obtained is converted into a layout scheme . Table 2 shows the optimized sensor layout scheme.
[0088] Table 2 Sensor position and index after optimization
[0089] Figure 3 is the schematic diagram of the optimized sensor layout provided by the present application, wherein the coverage rate is 98.5%, the total communication distance is 920m, and the number of constraint violations is 0. Compared with the layout scheme before optimization, the monitoring efficiency is obviously improved.
[0090] The industrial sensor layout optimization system based on hybrid breeding optimization algorithm provided by the present application is described below. Figure 4 is a structure schematic diagram of the industrial sensor layout optimization system based on hybrid breeding optimization algorithm provided by the present application, as Figure 4 shown, the system comprises: a numerical modeling unit 410 for numerically modeling the region to be detected to obtain a region model; a population generation unit 420 for encoding sensor layout information into a vector, and generating an initial population based on the solution space defined by the region model using chaotic mapping; a population division unit 430 for calculating the fitness value of all individuals in the current population based on the designed fitness function, and performing individual screening and population division based on the tournament strategy and the fitness value to obtain an optimal individual and multiple subpopulations; a population updating unit 440 for generating offspring by hybridization and / or selfing operation on the multiple subpopulations, and iteratively updating the population; The scheme conversion unit 450 is configured to output the optimal population when the iteration termination condition is reached, and convert the optimal population into a corresponding sensor layout scheme.
[0091] It can be understood that the industrial sensor layout optimization system based on the hybrid breeding optimization algorithm provided by the present application corresponds to the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm provided by the aforementioned embodiments. The related technical features of the industrial sensor layout optimization system based on the hybrid breeding optimization algorithm can refer to the related technical features of the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm, which will not be repeated here.
[0092] Based on the above embodiments, the numerical modeling unit is specifically configured to: scan the to-be-detected region, and determine the solution space range of the region model based on the scanning result; determine the positions of each to-be-detected target in the to-be-detected region based on the scanning result.
[0093] Based on the above embodiments, the population generation unit is specifically configured to: generate a chaotic value of each dimension in the solution space based on the initialization parameters of the hybrid breeding optimization algorithm; linearly map the chaotic value of each dimension to the actual solution space, and combine all dimensions to obtain the initial population.
[0094] Based on the above embodiments, the population division unit is specifically configured to: based on the sensor layout information represented by the current population, calculate the area coverage rate of each sensor, the total distance between the sensor and the to-be-detected target, and the number of constraint violations of the sensor; weight and sum the area coverage rate, the total distance, and the constraint violation number to obtain the fitness value of each individual.
[0095] Based on the above embodiments, the population division unit is specifically configured to: randomly extract a preset number of individuals from the current population to form a tournament set, and perform individual screening based on the fitness value of each candidate individual in the tournament set to obtain the optimal individual; sort the candidate individuals in the tournament set according to the fitness value, and perform population division based on the sorting result and a preset proportion to obtain a development population, a balance population, and an exploration population.
[0096] Based on the above embodiments, the population update unit is specifically configured to: for the randomly selected genes in the balance population and the exploration population, generate new individual genes using hybrid operation; for the individual genes in the development population, generate new individuals using self-crossing operation; For exploring the individual gene in the population and developing the optimal individual gene in the population, a hybrid operation is used to generate a new individual; When the individual fitness is lower than the median of the current population fitness, and the current iteration number is greater than half of the preset maximum iteration number, an individual elimination strategy is executed.
[0097] Based on the above embodiment, the iteration termination condition includes: reaching the maximum iteration number, or the fitness change in the continuous generations is within the preset range.
[0098] Figure 5 An example of a schematic diagram of the physical structure of an electronic device is shown as Figure 5 As shown, the electronic device can include a processor 510, a communications interface 520, a memory 530, and a communications bus 540, wherein the processor 510, the communications interface 520, and the memory 530 complete mutual communication through the communications bus 540. The processor 510 can invoke the logic instructions in the memory 530 to execute an industrial sensor layout optimization method based on a hybrid breeding optimization algorithm, which includes: S1, numerically modeling a to-be-detected region to obtain a region model; S2, encoding sensor layout information into a vector, and generating an initial population based on a solution space defined by the region model using chaotic mapping; S3, calculating the fitness values of all individuals in the current population based on a designed fitness function, performing individual screening and population division based on a tournament strategy and the fitness values, obtaining an optimal individual and multiple subpopulations; S4, generating offspring by hybridization and / or selfing operation on the multiple subpopulations, and iteratively updating the population; and S5, outputting the optimal population when the iteration termination condition is reached, and converting the optimal population into a corresponding sensor layout scheme.
[0099] In addition, the logic instructions in the memory 530 described above can be implemented in the form of a software functional unit and sold or used as an independent product, which can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.
[0100] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer readable storage medium, and the computer program can be executed by a processor to enable a computer to perform the hybrid breeding optimization algorithm-based industrial sensor layout optimization method provided by the above-mentioned methods, which comprises: S1, performing numerical modeling on a region to be detected to obtain a region model; S2, encoding sensor layout information into a vector, and generating an initial population using chaotic mapping based on a solution space defined by the region model; S3, calculating the fitness values of all individuals in the current population based on a designed fitness function, performing individual screening and population division based on a tournament strategy and the fitness values, and obtaining an optimal individual and a plurality of subpopulations; S4, generating offspring by hybridization and / or selfing operation on the plurality of subpopulations, and iteratively updating the population; and S5, outputting the optimal population when the iteration termination condition is reached, and converting the optimal population into a corresponding sensor layout scheme.
[0101] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, which can be executed by a processor to implement the hybrid breeding optimization algorithm-based industrial sensor layout optimization method provided by the above-mentioned methods, which comprises: S1, performing numerical modeling on a region to be detected to obtain a region model; S2, encoding sensor layout information into a vector, and generating an initial population using chaotic mapping based on a solution space defined by the region model; S3, calculating the fitness values of all individuals in the current population based on a designed fitness function, performing individual screening and population division based on a tournament strategy and the fitness values, and obtaining an optimal individual and a plurality of subpopulations; S4, generating offspring by hybridization and / or selfing operation on the plurality of subpopulations, and iteratively updating the population; and S5, outputting the optimal population when the iteration termination condition is reached, and converting the optimal population into a corresponding sensor layout scheme.
[0102] The apparatus embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.
[0103] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0104] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. An industrial sensor layout optimization method based on hybrid breeding optimization algorithm, characterized in that, The method comprises the following steps: S1, numerical modeling of the region to be detected is performed to obtain a region model; S2, sensor layout information is encoded into a vector, and an initial population is generated based on a solution space defined by the region model using chaotic mapping; S3, the fitness values of all individuals in the current population are calculated based on a designed fitness function, individual selection and population division are performed based on a tournament strategy and the fitness values, and an optimal individual and a plurality of subpopulations are obtained; S4, offspring are generated by hybridization and / or selfing operation on the plurality of subpopulations, and the population is iteratively updated; S5, when the iteration termination condition is reached, the optimal population is output, and the optimal population is converted into a corresponding sensor layout scheme.
2. The hybridization breeding optimization algorithm based industrial sensor layout optimization method according to claim 1, characterized in that, Step S1 comprises: S101, the region to be detected is scanned, and the solution space range of the region model is determined based on the scanning result; S102, the positions of each target to be detected in the region to be detected are determined based on the scanning result.
3. The hybridization breeding optimization algorithm based industrial sensor layout optimization method according to claim 1, characterized in that, Step S2 comprises: S201, chaotic values of each dimension in the solution space are generated based on the initialization parameters of the hybrid breeding optimization algorithm; S202, the chaotic values of each dimension are linearly mapped to the actual solution space, and all dimensions are combined to obtain the initial population.
4. The hybridization breeding optimization algorithm based industrial sensor layout optimization method according to claim 1, characterized in that, In step S3, the fitness values of all individuals in the current population are calculated based on a designed fitness function, which comprises: S301, based on the sensor layout information represented by the current population, the area coverage rate of each sensor, the total distance between the sensor and the target to be detected, and the number of constraint violations of the sensor are calculated; S302, the area coverage rate, the total distance and the number of constraint violations are weighted and summed to obtain the fitness value of each individual.
5. The hybridization breeding optimization algorithm based industrial sensor layout optimization method according to claim 1, wherein, In step S3, individual selection and population division are performed based on a tournament strategy and the fitness values, and an optimal individual and a plurality of subpopulations are obtained, which comprises: S303, a predetermined number of individuals are randomly selected from the current population to form a tournament set, individual selection is performed based on the fitness values of each candidate individual in the tournament set, and the optimal individual is obtained; S304, the candidate individuals in the tournament set are sorted according to the fitness values, the population is divided based on the sorting result and a preset proportion, and a development population, a balance population and an exploration population are obtained.
6. The hybridization breeding optimization algorithm based industrial sensor layout optimization method according to claim 5, characterized in that, Step S4 comprises: S401, hybridization operation is performed on randomly selected genes in the balance population and the exploration population to generate new individual genes; S402, selfing operation is performed on the individual genes in the development population to generate new individuals; S403, hybridization operation is performed on the individual genes in the exploration population and the optimal individual genes in the development population to generate new individuals; S404, when the individual fitness is lower than the median of the current population fitness and the current iteration number is greater than half of the preset maximum iteration number, an individual elimination strategy is executed.
7. The hybridization breeding optimization algorithm based industrial sensor layout optimization method according to claim 1, wherein, The iteration termination condition in step S5 comprises: The maximum iteration number is reached, or the change in fitness in a plurality of consecutive generations is within a preset range.
8. An industrial sensor layout optimization system based on hybrid breeding optimization algorithm characterized in that, The method comprises the following steps: A numerical modeling unit is configured to perform numerical modeling on a region to be detected to obtain a region model; A population generating unit is configured to encode the sensor layout information into a vector, and generate an initial population by using a chaotic mapping based on a solution space defined by the area model; A population dividing unit is configured to calculate fitness values of all individuals in the current population based on a designed fitness function, and perform individual screening and population division based on a tournament strategy and the fitness values to obtain an optimal individual and a plurality of sub-populations; A population updating unit is configured to generate offspring by using crossbreeding and / or self-breeding operations on the plurality of sub-populations, and iteratively update the population; A scheme converting unit is configured to output the optimal population when an iteration termination condition is reached, and convert the optimal population into a corresponding sensor layout scheme.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, The processor implements the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm as claimed in any one of claims 1 to 7 when executing the computer program. 10.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the industrial sensor layout optimization method based on the hybrid breeding optimization algorithm as claimed in any one of claims 1 to 7 when executed by the processor.