Multi-objective optimization site selection method for road surface ice and snow condition monitoring stations

Abstract

The invention belongs to the field of construction, and particularly relates to a multi-objective optimization site selection method for a road surface ice and snow condition monitoring station. The existing road surface ice and snow condition monitoring station site selection method has the problems of strong subjectivity and lack of scientific basis, so that the site selection scheme is unreasonable. The method comprises the following steps: step 1, collecting road historical data; 2, establishing a road traffic safety risk point location set under the ice and snow condition according to the road historical data collected in the step 1; 3, according to the road historical data obtained in the step 1 and the road traffic safety risk point location set under the ice and snow conditions obtained in the step 2, constructing a multi-objective optimization site selection model; step 4, constructing constraint conditions of the multi-objective optimization site selection model; step 5, generating an initial population improved by an NSGAII algorithm according to constraint conditions of the multi-objective optimization site selection model; and then solving the multi-objective optimization site selection model by using an NSGAII algorithm, and outputting a site selection result of the road surface ice and snow condition monitoring station.

Description

Technical Field

[0001] The invention belongs to the field of construction, and in particular relates to a multi-objective optimization site selection method for a road surface ice and snow condition monitoring station. Background Art

[0002] In most parts of my country, low temperatures, precipitation and other meteorological factors often cause snow and ice on the road in winter, especially in special sections such as shaded areas and tunnel entrances, where there is hidden ice that is difficult to detect, which seriously restricts the safe and efficient operation of road facilities. Therefore, many scholars have developed a road surface ice and snow condition monitoring system, which can collect meteorological data such as temperature, humidity, visibility, and road surface water, ice and snow thickness, video images and other road condition information, providing a data basis for road surface ice and snow condition assessment, and has broad application scenarios in the field of roads where ice and snow disasters are frequent.

[0003] In recent years, Shandong, Hebei, Zhejiang and more than a dozen provinces and cities have issued technical specifications for the construction of highway traffic meteorological monitoring stations. These specifications put forward corresponding technical requirements for the equipment selection, site selection, data collection and processing, operation and maintenance of monitoring stations. However, for the site selection of monitoring stations, certain requirements and suggestions are put forward based on engineering experience, lacking scientific research support. This has increased the blindness of initial construction and later operation to a certain extent, greatly affecting the actual application effect of this technology; at the same time, at this stage, there is a lack of research on the factors affecting the site selection of monitoring stations, and the calculation of construction costs and monitoring effects lacks scientificity and systematicity, which also restricts the actual application of this technology to a certain extent.

[0004] In summary, the existing site selection method for road surface ice and snow condition monitoring stations is highly subjective and lacks scientific basis, which leads to unreasonable site selection plans and a high incidence of traffic accidents. Summary of the invention

[0005] The purpose of this invention is to solve the problem that the existing site selection method for road surface ice and snow condition monitoring stations is highly subjective and lacks scientific basis, which leads to a high rate of traffic accidents due to the site selection scheme. We propose a multi-objective optimization site selection method for road surface ice and snow condition monitoring stations. It includes:

[0006] Step 1: Collect road history data;

[0007] Step 2: Establish a set of road traffic safety risk points under ice and snow conditions based on the historical data collected in step 1;

[0008] Step 3: Based on the historical road data obtained in step 1 and the set of road traffic safety risk points under ice and snow conditions obtained in step 2, a multi-objective optimization site selection model is constructed;

[0009] Step 4: Construct the constraints of the multi-objective optimization site selection model;

[0010] Step 5: Generate the initial population improved by the NSGAII algorithm according to the constraints of the multi-objective optimization site selection model; then use the NSGAII algorithm to solve the multi-objective optimization site selection model and output the site selection results of the road surface ice and snow condition monitoring station.

[0011] The road historical data in step 1 includes: road mileage pile number data, road linear data, road special terrain data, road bridge structure data, road traffic accident high-incidence point data under ice and snow conditions, road snow and ice prone point data, road fog prone point data, road existing meteorological observation station location data, and road power supply network location data;

[0012] In step 1, historical road data is collected; the specific process is as follows:

[0013] Step 11: Collect the design files of the road, and obtain the road mileage pile number data, road line shape data, road special terrain point data, and road bridge structure data according to the road design files;

[0014] The special terrain and feature point data of the road include: sharp bend and steep slope point data of the road, and bridge and tunnel point data of the road;

[0015] Step 12: Collect road infrastructure construction data from the transportation investment department; determine the location data of existing meteorological observation stations on the road and the location data of power supply network along the entire road based on the road infrastructure construction data provided by the transportation investment department;

[0016] Step 13: Collect historical road traffic accident survey data; obtain information on road traffic accident high-incidence points under ice and snow conditions based on the historical road traffic accident survey data in the past 10 years;

[0017] The above-mentioned high-incidence locations of road traffic accidents under ice and snow conditions are locations where the number of road traffic accidents under ice and snow conditions in the past 10 years exceeded 5 or more;

[0018] Step 14: Determine the meteorological observation stations within a straight-line distance of 20 km along the road based on the existing meteorological observation station location data;

[0019] Collect historical meteorological data from meteorological observation stations within a straight-line distance of 20 km along the road;

[0020] According to the historical meteorological data of the past 20 years observed by meteorological observation stations within a straight-line distance of 20km along the road, the data of road meteorological disaster prone points are obtained; the data of road meteorological disaster prone points include: road snow and ice prone point data, road fog prone point data,

[0021] The road meteorological disaster-prone locations are locations where meteorological disasters have occurred more than 5 times in the past 20 years;

[0022] Step 15: Take the special terrain and landform points on the road and the points prone to meteorological disasters on the road as the points prone to ice and snow disasters on the road.

[0023] The set of road traffic safety risk points under ice and snow conditions in step 2 includes: road traffic safety level 1 risk points and road traffic safety level 2 risk points;

[0024] The specific process of collecting historical data in step 1 to establish a set of road traffic safety risk points under ice and snow conditions in step 2 is as follows:

[0025] The points where road traffic accidents are more likely to occur under icy and snowy conditions are regarded as the first-level risk points for road traffic safety under icy and snowy conditions;

[0026] Set the road ice and snow disaster prone points as the second-level risk points for road traffic safety under ice and snow conditions

[0027] The beneficial effects of the present invention are:

[0028] (1) Four factors influencing the site selection, namely, people, vehicles, roads, and environment, were introduced into the layout of road ice and snow condition monitoring stations, which effectively improved the objectivity and representativeness of the site selection.

[0029] The site selection and construction of existing road surface ice and snow condition monitoring stations are mostly determined by the experience of decision makers, and there are problems such as strong subjectivity and lack of scientific basis. The present invention makes full use of road alignment, topography, traffic, meteorology and infrastructure data, establishes a set of road traffic safety risk points under ice and snow conditions, clarifies important points that need to be monitored urgently, effectively improves the objectivity and representativeness of site selection, helps to clarify the ice and snow condition information in the entire monitoring section, and enhances disaster response capabilities.

[0030] (2) Taking into account the three major goals of total cost, traffic volume, and monitoring effect, a set of trade-offs and optimal solutions was obtained, achieving comprehensive and maximized target benefits.

[0031] The four factors affecting site selection, namely people, vehicles, roads and environment, are quantified to establish a set of road traffic safety risk points under icy and snowy conditions. The three objective functions of minimum total cost, maximum monitoring coverage index and maximum traffic volume are comprehensively considered, and the trade-offs and optimal solution sets under multiple objective functions are obtained through the non-dominated sorting and congestion comparison mechanism of the NSGAII algorithm, thus achieving comprehensive and maximized target benefits. These three types of objectives are closely related to the actual project, providing a multi-faceted evaluation for the site selection plan, and have good application effects in actual projects.

[0032] (3) The population initialization method was improved in the NSGAII algorithm, which greatly improved the efficiency of site selection and the rationality of site selection.

[0033] In the multi-objective optimization model for site selection of road surface ice and snow condition monitoring stations, the existing initialization population method is extremely random, with problems such as slow solution speed and poor convergence. By limiting the minimum distance between adjacent stations, the diversity and rationality of the initialization population are improved, thereby effectively improving the efficiency of the algorithm.

[0034] (4) Based on the improved NSGAII algorithm, a variety of site selection schemes are provided to adapt to the preferences of different decision makers, which significantly improves the applicability of this method. By constraining the number and distance of sites, it is ensured that this method has good results in different road application scenarios.

[0035] Based on the improved NSGAII algorithm, the massive randomly generated site selection plans are optimized and iterated, and an objective and diverse set of site selection plans is obtained; the objective function value of each solution in the Pareto solution set is displayed based on the coordinates, color and point size, and the multi-dimensional visualization output of the optimal site selection plan is completed. Decision makers can choose the corresponding optimal plan according to different preferences; the two constraints of minimum spacing and maximum number are introduced, so that this method can maintain a good solution effect when dealing with different cases, and has a broad scope of application and good application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The overall logic diagram of the multi-objective optimization model for site selection of road surface ice and snow condition monitoring stations;

[0037] Figure 2 The site selection map of the initial population before algorithm improvement;

[0038] Figure 3 Initialize the site selection map of the population after the algorithm is improved;

[0039] Figure 4 Flowchart of the NSGAII algorithm;

[0040] Figure 5 Visualization result diagram of Pareto solution set;

[0041] Figure 6 A diagram showing the location selection plan under the decision maker's target preference X;

[0042] Figure 7 A diagram showing the site selection plan under decision maker Y’s target preference. DETAILED DESCRIPTION

[0043] Specific implementation method 1: Combination Figure 1 The invention is described, comprising:

[0044] Step 1: Collect road history data;

[0045] Step 2: Collect historical road data according to step 1 to establish a set of road traffic safety risk points under ice and snow conditions;

[0046] Step 3: Based on the historical road data obtained in step 1 and the set of road traffic safety risk points under ice and snow conditions obtained in step 2, a multi-objective optimization site selection model is constructed;

[0047] Step 4: Construct the constraints of the multi-objective optimization site selection model;

[0048] Step 5: Generate the initial population improved by the NSGAII algorithm according to the constraints of the multi-objective optimization site selection model; then use the NSGAII algorithm to solve the multi-objective optimization site selection model and output the site selection results of the road surface ice and snow condition monitoring station.

[0049] Implementation 2: This implementation differs from Implementation 1 in that:

[0050] The road historical data in step 1 includes: road mileage pile number data, road linear data, road special terrain data, road bridge structure data, road traffic accident high-incidence point data under ice and snow conditions, road snow and ice prone point data, road fog prone point data, road existing meteorological observation station location data, and road power supply network location data;

[0051] In step 1, historical road data is collected; the specific process is as follows:

[0052] Step 11: Collect the design files of the road, and obtain the road mileage pile number data, road line shape data, road special terrain point data, and road bridge structure data according to the road design files;

[0053] The special terrain and feature point data of the road include: sharp bend and steep slope point data of the road, and bridge and tunnel point data of the road;

[0054] Step 12: Collect road infrastructure construction data from the transportation investment department; determine the location data of existing meteorological observation stations on the road and the location data of power supply network along the entire road based on the road infrastructure construction data provided by the transportation investment department;

[0055] Step 13: Collect historical road traffic accident survey data; obtain information on road traffic accident high-incidence points under ice and snow conditions based on the historical road traffic accident survey data in the past 10 years;

[0056] The above-mentioned high-incidence locations of road traffic accidents under ice and snow conditions are locations where the number of road traffic accidents under ice and snow conditions in the past 10 years exceeded 5 or more;

[0057] Step 14: Determine the meteorological observation stations within a straight-line distance of 20 km along the road based on the existing meteorological observation station location data;

[0058] Collect historical meteorological data from meteorological observation stations within a straight-line distance of 20 km along the road;

[0059] According to the historical meteorological data of the past 20 years observed by meteorological observation stations within a straight-line distance of 20km along the road, the data of road meteorological disaster prone points are obtained; the data of road meteorological disaster prone points include: road snow and ice prone point data, road fog prone point data,

[0060] The road meteorological disaster-prone locations are locations where meteorological disasters have occurred more than 5 times in the past 20 years;

[0061] Step 15: taking the special terrain and terrain points on the road and the points prone to meteorological disasters on the road as the points prone to ice and snow disasters on the road; the other steps and parameters are the same as those in the first specific implementation mode.

[0062] Specific implementation method three: This implementation method is different from the specific implementation method one in that:

[0063] The set of road traffic safety risk points under ice and snow conditions in step 2 includes: road traffic safety level 1 risk points and road traffic safety level 2 risk points;

[0064] The specific process of collecting historical data in step 1 to establish a set of road traffic safety risk points under ice and snow conditions in step 2 is as follows:

[0065] The points where road traffic accidents are more likely to occur under icy and snowy conditions are regarded as the first-level risk points for road traffic safety under icy and snowy conditions;

[0066] The points prone to road ice and snow disasters are regarded as the second-level risk points for road traffic safety under ice and snow conditions;

[0067] The present invention introduces four factors affecting site selection, namely, people, vehicles, roads and environment, into the problem of setting up road surface ice and snow condition monitoring stations, thereby effectively improving the objectivity and representativeness of site selection.

[0068] The site selection and construction of existing road surface ice and snow condition monitoring stations are mostly determined by the experience of decision makers, and there are problems such as strong subjectivity and lack of scientific basis. The present invention makes full use of road alignment, terrain, traffic, meteorology and infrastructure data, establishes a set of road traffic safety risk points under ice and snow conditions, clarifies important points that need to be monitored urgently, effectively improves the objectivity and representativeness of site selection, helps to clarify the ice and snow condition information in the entire monitoring section, and enhances disaster response capabilities. Other steps and parameters are the same as the second specific implementation method.

[0069] Specific implementation method 4: This implementation method is different from the specific implementation method 1 in that:

[0070] In step 3, a multi-objective optimization site selection model is constructed based on the road historical data obtained in step 1 and the road traffic safety risk point set under ice and snow conditions obtained in step 2; the specific process is:

[0071] The set of road traffic safety risk points under ice and snow conditions is used as the nodes of the multi-objective optimization site selection model;

[0072] The total cost, monitoring coverage index and traffic volume are used as the three objective functions of the multi-objective optimization site selection model;

[0073] The objective function of the total cost in the multi-objective optimization location selection model is expressed as follows:

[0074]

[0075] Where min means minimization, Cost means the total cost of building a road surface ice and snow condition monitoring station, including the fixed construction cost of the monitoring station (including equipment cost and construction cost) and the cost of laying cables and construction between the station and the power supply network point; c i is the fixed construction cost of building a road surface ice and snow condition monitoring station at node i; x i is a 0-1 variable, indicating that if node i is selected as a road surface ice and snow condition monitoring station, then x i =1, otherwise 0, i = 1, 2, ..., I; I represents the total number of nodes; G n represents the mileage stake number of node n selected to be built as a road surface ice and snow condition monitoring station, n = 1, 2, ..., N; N represents the total number of nodes selected to be built as road surface ice and snow condition monitoring stations, B j Indicates the mileage post number of the power supply network point j, j = 1, 2, ..., J; J represents the total number of power supply network points;

[0076] The monitoring coverage index in the multi-objective optimization site selection model includes: the monitoring coverage index of the level 1 risk point and the monitoring coverage index of the level 2 risk point;

[0077] The objective function of the monitoring coverage index in the multi-objective optimization site selection model is expressed as follows:

[0078] Monitoring coverage index of level 1 risk points:

[0079]

[0080] Monitoring coverage index of level 2 risk points:

[0081]

[0082] Among them, MCI1 represents the monitoring coverage ratio of all road surface ice and snow condition monitoring stations for road traffic safety level 1 risk points, and MCI2 represents the monitoring coverage ratio of all road surface ice and snow condition monitoring stations for road traffic safety level 2 risk points; k is a 0-1 variable, indicating that if there is at least one road surface ice and snow condition monitoring station monitoring the traffic safety risk point k, then y k =1, otherwise 0,

[0083] When there is a road surface ice and snow condition monitoring station within 2 kilometers of a road traffic safety risk point under ice and snow conditions, the point is considered to be covered by monitoring; k = 1, 2, ..., K; K represents the total number of road traffic safety risk points; S is the total number of road traffic accident-prone points under ice and snow conditions; P is the total number of road ice and snow disaster-prone points;

[0084] The objective function of traffic volume in the multi-objective optimization site selection model is expressed as follows:

[0085]

[0086] Among them, WMADT is the average daily traffic volume in winter for all road sections monitored by all road surface ice and snow condition monitoring stations; WMADT i represents the average daily traffic volume in winter on the road section where node i is located; N is the total number of nodes selected to be built as road surface ice and snow condition monitoring stations; other steps and parameters are the same as those in specific implementation method three.

[0087] Specific implementation method 5: This implementation method is different from the specific implementation method 1 in that:

[0088] The constraints of the multi-objective optimization site selection model in step 4 include site quantity constraints and site distance constraints.

[0089] The constraints of constructing the multi-objective optimization site selection model are as follows:

[0090] The construction site quantity constraint is expressed as:

[0091]

[0092] Among them, x i is a 0-1 variable, indicating that if node i is selected as a site, then x i =1, otherwise 0, i=1,2,…,I; Q is the maximum number of road surface ice and snow condition monitoring stations allowed to be built during this construction period;

[0093] The construction site distance constraint is expressed as:

[0094]

[0095] in, Indicates that any one of the n represents the distance between road surface ice and snow condition monitoring station n1 and road surface ice and snow condition monitoring station n2, n1∈1,2,…,N-1; n2∈1,2,…,N-1; D represents the minimum allowable distance between two adjacent road surface ice and snow condition monitoring stations.

[0096] The present invention comprehensively considers the three major objectives of total cost, traffic volume, and monitoring effect, obtains a set of trade-offs and optimal solutions, and realizes comprehensive and maximized target benefits.

[0097] The four factors affecting site selection, namely people, vehicles, roads and environment, are quantified to establish a set of road traffic safety risk points under icy and snowy conditions. The three objective functions of minimum total cost, maximum monitoring coverage index and maximum traffic volume are comprehensively considered, and the trade-offs and optimal solution sets under multiple objective functions are obtained through the non-dominated sorting and congestion comparison mechanism of the NSGAII algorithm, thus achieving comprehensive and maximized target benefits. These three types of objectives are closely related to the actual project, providing a multi-faceted evaluation for the site selection plan, and have good application effects in actual projects.

[0098] The other steps and parameters are the same as those in the fourth specific implementation method.

[0099] Specific implementation method 6: This implementation method is different from the specific implementation method 1 in that:

[0100] In step 5, the initial population improved by the NSGAII algorithm is generated according to the constraint conditions of the multi-objective optimization site selection model; then the multi-objective optimization site selection model is solved by the NSGAII algorithm, and the site selection result of the road surface ice and snow condition monitoring station is output; the specific process is:

[0101] Step 51, generating an initial population P improved by the NSGAII algorithm according to the constraint conditions of the multi-objective optimization site selection model;

[0102] Step 52, performing non-dominated sorting on the individuals of the initial population P improved by the NSGAII algorithm, and dividing the individuals of the initial population P improved by the NSGAII algorithm into Z frontiers according to the result of the non-dominated sorting, where Z is a positive integer; and assigning a rank to the individuals in each frontier according to the ranking of the frontier sorting;

[0103] All individuals in the first front are assigned a rank of 1, individuals in the second front are assigned a rank of 2, and individuals in the Zth front are assigned a rank of Z;

[0104] Then the crowding degree in each front is calculated;

[0105] The frontier is similar to a taxonomic group, which is an academic term in a multi-objective optimization algorithm and is well known to those skilled in the art;

[0106] Step 53: The initial population P improved by the NSGAII algorithm is used as the parent population, and the three basic operations of selection, crossover, and mutation are sequentially performed on the parent population to obtain the child population;

[0107] Among them, the parent population of the tth iteration is represented by P t , the offspring population of the tth iteration is denoted as Qt;

[0108] Step 54: merge the parent population and the offspring population to generate a merged population.

[0109] Generate the parent population for the next round of iteration based on the merged population;

[0110] Step 55, repeating steps 52 to 54 until the maximum number of iterations is reached or a set of satisfactory populations is obtained, then the iteration is stopped to obtain the final population;

[0111] Step 56: The individuals in the final population are used as the site selection results of the road surface ice and snow condition monitoring station. The population initialization method is improved in the NSGAII algorithm, which greatly improves the site selection efficiency and the rationality of the site selection.

[0112] In the multi-objective optimization model for site selection of road surface ice and snow condition monitoring stations, the existing initialization population method is extremely random, with problems such as slow solution speed and poor convergence. By limiting the minimum distance between adjacent stations, the diversity and rationality of the initialization population are improved, thereby effectively improving the efficiency of the algorithm.

[0113] The other steps and parameters are the same as those in the fifth specific implementation manner.

[0114] Specific implementation method 7: This implementation method is different from the specific implementation method 1 in that:

[0115] The specific process of generating the initial population P improved by the NSGAII algorithm according to the constraint conditions of the multi-objective optimization site selection model in step 51 is as follows:

[0116] Step 511: Set the size N of the initial population * , crossover probability nMu, mutation probability, maximum number of iterations M;

[0117] Step 512: setting initial population generation constraints according to the constraints of the multi-objective optimization site selection model;

[0118] Step 513: According to the initial population generation constraints of step 512, randomly generate N * Individuals of the population are obtained to obtain the initial population P improved by the NSGAII algorithm;

[0119] N *is 200, the crossover probability nMu is 65%, the maximum number of iterations is 150, and N is randomly generated. * individuals, and the whole is regarded as the initial population P

[0120] In the multi-objective optimization model for the site selection of road surface ice and snow condition monitoring stations, any node may be selected as a site, which is prone to the occurrence of an initialization population with great randomness, slow solution speed, and poor convergence. Figure 2 As shown; at the same time, this type of population will be eliminated only after non-dominated sorting and congestion calculation due to failure to meet the model constraints, which greatly slows down the efficiency of the algorithm. Therefore, when generating the initialization population, two constraints, "minimum distance between sites" and "maximum number of sites per 100 kilometers", are introduced to improve the diversity and rationality of the initialization population, thereby effectively improving the efficiency of the algorithm, see Figure 3 As shown; the improvement principle is consistent with the site quantity constraint and site distance constraint in step 4. Other steps and parameters are the same as those in specific implementation mode 6.

[0121] Specific implementation method 8: This implementation method is different from the specific implementation method 1 in that:

[0122] In step 52, the individuals of the initial population P improved by the NSGAII algorithm are non-dominatedly sorted, and the individuals of the initial population P improved by the NSGAII algorithm are divided into Z frontiers according to the result of the non-dominated sorting, where Z is a positive integer; the individuals in each frontier are assigned a rank according to the ranking of the frontier sorting; and then the congestion degree in each frontier is calculated; the specific process is:

[0123] Step 521: Calculate the objective function value of each individual in the initial population P; the i-th individual in the initial population P is represented by pi

[0124] Step 522: According to the obtained objective function values ​​of all individuals and the dominance relationship in the NSGAII algorithm, all individuals are divided into Z frontier layers.

[0125] The individuals in the first frontier layer are those that are not dominated by any individual, and the individuals in the next frontier layer are those that are dominated by the individuals in the previous frontier layer.

[0126] For example, the individuals in the second frontier are individuals dominated by the individuals in the first frontier, and so on, and finally Z frontiers are obtained; the dominance relationship between the individuals is determined according to the dominance relationship in the NSGAII algorithm;

[0127] Step 523: According to the objective function value of the individuals in each frontier and the crowding calculation method in the NSGAII algorithm, the crowding is calculated for the individuals in each layer of the frontier, and the crowding value of each individual in each layer of the frontier is obtained by sorting the individuals on each target and calculating the distance between adjacent individuals.

[0128] The other steps and parameters are the same as those in the seventh embodiment.

[0129] Specific implementation method 9: This implementation method is different from the specific implementation method 1 in that:

[0130] In step 53, the parent population is subjected to three basic operations of selection, crossover and mutation in sequence to obtain the offspring population; the specific process is as follows:

[0131] Step 531: Select two parent individuals from the parent population according to the non-dominated level of the parent population individuals and the congestion degree in each frontier.

[0132] The method for selecting the parent individual according to the non-dominated level and the congestion degree in step 531 includes: using any method such as tournament selection, roulette selection, and sorting selection;

[0133] Step 532: Perform a crossover operation on the selected parent individuals according to the set crossover probability nMu to generate offspring individuals.

[0134] The crossover method includes: simulated binary crossover, uniform crossover, multi-point crossover, etc.

[0135] Step 533: performing mutation operations on all the generated offspring individuals according to the set mutation probability to obtain an offspring population;

[0136] The mutation method may use any one of polynomial mutation, displacement mutation, non-uniform mutation and the like.

[0137] The other steps and parameters are the same as those in the eighth specific implementation manner.

[0138] Specific implementation method 10: The difference between this implementation method and specific implementation method 9 is that

[0139] In step 54, the parent population P of the tth iteration is t and the t-th iteration offspring population Q t Merge to generate the t-th round iterative merge population R t ;

[0140] According to the tth round of iteration, the population R is merged t Generate the parent population R for the t+1th iteration t+1 ; The specific process is:

[0141] Step 541: The parent population P of the tth iteration t and the t-th iteration offspring population Q t Merge to generate the t-th round of iterative merge population R t ; expressed as:

[0142] Rt=Pt∪Qt, which means ∪union;

[0143] The parent has N * individuals, and the number of offspring is N * individuals, and the combined population contains 2N * individual;

[0144] Step 542: Merge population R for the tth round of iterations t The individuals are non-dominated and sorted; r frontiers are obtained, and the individuals in each frontier are ranked according to the ranking of the frontier sorting;

[0145] All individuals in the first front are assigned a rank of 1, individuals in the second front are assigned a rank of 2, and individuals in the rth front are assigned a rank of r;

[0146] Individuals will be divided into multiple non-dominated layers (frontiers). The individuals in the first frontier are the best, the individuals in the second frontier are slightly worse, and so on;

[0147] Step 543: Select N according to the level of the individual * Individuals constitute the population P of the t+1th iteration t+1 ;

[0148] The present invention gives priority to individuals with lower ranks, that is, first select all individuals in the first front, then select individuals in the second front, and so on, until N individuals are selected. * The individuals constitute the next generation population P t+1 .

[0149] Based on the improved NSGAII algorithm, the present invention provides a variety of site selection schemes to adapt to the preferences of different decision makers, significantly improving the scope of application of the method; through the number and distance constraints of sites, it is ensured that the method has good effects in different road application scenarios.

[0150] Based on the improved NSGAII algorithm, the randomly generated massive site selection schemes are optimized and iterated, and an objective and diverse set of site selection schemes is obtained; the objective function value of each solution in the Pareto solution set is displayed based on the coordinates, color and point size, and the multi-dimensional visualization output of the optimal site selection scheme is completed. Decision makers can choose the corresponding optimal scheme according to different preferences; the introduction of the minimum spacing and maximum number of constraints enables this method to maintain a good solution effect when dealing with different cases, and has a broad scope of application and good application prospects.

[0151] See Figure 5The Pareto solution set for calculating the optimal location solution is shown. The objective function value of each solution in the Pareto solution set is displayed based on the coordinates, color, and point size, and the multi-dimensional visualization output of the optimal location solution is completed, so that decision makers can choose the optimal location solution according to different target preferences. For example, in the Harbin-Yabuli section of Suiman Expressway in this embodiment:

[0152] If decision maker X requires the primary monitoring coverage index to be ≥90% and the secondary monitoring coverage index to be ≥80%, and the total cost is minimized and the traffic volume is maximized, the optimal solution is shown in Figure 6 As shown, the total cost of the solution is 1.041 million yuan, and the traffic volume is 29,500 vehicles per day.

[0153] If decision maker Y requires the primary monitoring coverage index to be ≥80% and the secondary monitoring coverage index to be ≥65%, and the total cost is minimized and the traffic volume is maximized, the optimal solution is shown in Figure 7 As shown, the total cost of the solution is 841,000 yuan, and the traffic volume is 30,600 vehicles / day. Other steps and parameters are the same as those of the ninth embodiment.

[0154] The above only describes the preferred embodiments of the present invention. It should be understood that the present invention is not limited to the above specific implementation methods. Although the present invention has been disclosed as above in the preferred embodiments, it is not used to limit the present invention. Any technician familiar with the profession can make some changes or modify the technical contents disclosed above into equivalent embodiments with equivalent changes without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent replacement and improvement made to the above embodiments without departing from the content of the technical solution of the present invention, based on the technical essence of the present invention, within the spirit and principles of the present invention, still fall within the protection scope of the technical solution of the present invention.

Claims

1. A multi-objective optimization site selection method for road surface ice and snow condition monitoring stations, characterized in that: The method comprises: Step 1: Collect road history data; Step 2: Establish a set of road traffic safety risk points under ice and snow conditions based on the historical data collected in step 1; Step 3: Based on the historical road data obtained in step 1 and the set of road traffic safety risk points under ice and snow conditions obtained in step 2, a multi-objective optimization site selection model is constructed; Step 4: Construct the constraints of the multi-objective optimization site selection model; Step 5: Generate the initial population improved by the NSGAII algorithm according to the constraints of the multi-objective optimization site selection model; then use the NSGAII algorithm to solve the multi-objective optimization site selection model and output the site selection results of the road surface ice and snow condition monitoring station.

2. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 1 is characterized in that: The road historical data in step 1 includes: road mileage pile number data, road linear data, road special terrain data, road bridge structure data, road traffic accident high-incidence point data under ice and snow conditions, road snow and ice prone point data, road fog prone point data, road existing meteorological observation station location data, and road power supply network location data; In step 1, historical road data is collected; the specific process is as follows: Step 11: Collect the design files of the road, and obtain the road mileage pile number data, road line shape data, road special terrain point data, and road bridge structure data according to the road design files; The special terrain and feature point data of the road include: sharp bend and steep slope point data of the road, and bridge and tunnel point data of the road; Step 12: Collect road infrastructure construction data from the transportation investment department; determine the location data of existing meteorological observation stations on the road and the location data of power supply network along the entire road based on the road infrastructure construction data provided by the transportation investment department; Step 13: Collect historical road traffic accident survey data; obtain information on road traffic accident high-incidence points under ice and snow conditions based on the historical road traffic accident survey data in the past 10 years; The above-mentioned high-incidence locations of road traffic accidents under ice and snow conditions are locations where the number of road traffic accidents under ice and snow conditions in the past 10 years exceeded 5 or more; Step 14: Determine the meteorological observation stations within a straight-line distance of 20 km along the road based on the existing meteorological observation station location data; Collect historical meteorological data from meteorological observation stations within a straight-line distance of 20 km along the road; According to the historical meteorological data of the past 20 years observed by meteorological observation stations within a straight-line distance of 20km along the road, the data of road meteorological disaster prone points are obtained; the data of road meteorological disaster prone points include: road snow and ice prone point data, road fog prone point data, The road meteorological disaster-prone locations are locations where meteorological disasters have occurred more than 5 times in the past 20 years; Step 15: Take the special terrain and landform points on the road and the points prone to meteorological disasters on the road as the points prone to ice and snow disasters on the road.

3. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 2 is characterized in that: The set of road traffic safety risk points under ice and snow conditions in step 2 includes: road traffic safety level 1 risk points and road traffic safety level 2 risk points; The specific process of collecting historical data in step 1 to establish a set of road traffic safety risk points under ice and snow conditions in step 2 is as follows: The points where road traffic accidents are more likely to occur under icy and snowy conditions are regarded as the first-level risk points for road traffic safety under icy and snowy conditions; Road ice and snow disaster-prone points are identified as Level 2 risk points for road traffic safety under ice and snow conditions.

4. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 3 is characterized in that: In step 3, a multi-objective optimization site selection model is constructed based on the road historical data obtained in step 1 and the road traffic safety risk point set under ice and snow conditions obtained in step 2; the specific process is: The set of road traffic safety risk points under ice and snow conditions is used as the nodes of the multi-objective optimization site selection model; The total cost, monitoring coverage index and traffic volume are used as the three objective functions of the multi-objective optimization site selection model; The objective function of the total cost in the multi-objective optimization location selection model is expressed as follows: Among them, min means minimization, Cost means the total cost of building a road surface ice and snow condition monitoring station, and c i is the fixed construction cost of building a road surface ice and snow condition monitoring station at node i; x i is a 0-1 variable, indicating that if node i is selected as a road surface ice and snow condition monitoring station, then x i =1, otherwise 0, i = 1, 2, ..., I; I represents the total number of nodes; G n represents the mileage stake number of node n selected to be built as a road surface ice and snow condition monitoring station, n = 1, 2, ..., N; N represents the total number of nodes selected to be built as road surface ice and snow condition monitoring stations, B j Indicates the mileage post number of the power supply network point j, j = 1, 2, ..., J; J represents the total number of power supply network points; The monitoring coverage index in the multi-objective optimization site selection model includes: the monitoring coverage index of the level 1 risk point and the monitoring coverage index of the level 2 risk point; The objective function of the monitoring coverage index in the multi-objective optimization site selection model is expressed as follows: Monitoring coverage index of level 1 risk points: Monitoring coverage index of level 2 risk points: Among them, MCI1 represents the monitoring coverage ratio of all road surface ice and snow condition monitoring stations for road traffic safety level 1 risk points, and MCI2 represents the monitoring coverage ratio of all road surface ice and snow condition monitoring stations for road traffic safety level 2 risk points; k is a 0-1 variable, indicating that if there is at least one road surface ice and snow condition monitoring station monitoring the traffic safety risk point k, then y k =1, otherwise 0, When there is a road surface ice and snow condition monitoring station within 2 kilometers of a road traffic safety risk point under ice and snow conditions, the point is considered to be covered by monitoring; k = 1, 2, ..., K; K represents the total number of road traffic safety risk points; S is the total number of road traffic accident-prone points under ice and snow conditions; P is the total number of road ice and snow disaster-prone points; The objective function of traffic volume in the multi-objective optimization site selection model is expressed as follows: Among them, WMADT is the average daily traffic volume in winter for all road sections monitored by all road surface ice and snow condition monitoring stations; WMADT i represents the average daily traffic volume in winter on the road section where node i is located; N is the total number of nodes selected to be built as road surface ice and snow condition monitoring stations.

5. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 4 is characterized in that: The constraints of the multi-objective optimization site selection model in step 4 include site quantity constraints and site distance constraints. The constraints of constructing the multi-objective optimization site selection model are as follows: The construction site quantity constraint is expressed as: Among them, x i is a 0-1 variable, indicating that if node i is selected as a site, then x i =1, otherwise 0, i = 1, 2, ..., I; Q is the maximum number of road surface ice and snow condition monitoring stations allowed to be built; The construction site distance constraint is expressed as: in, Indicates that any one of the n represents the distance between road surface ice and snow condition monitoring station n1 and road surface ice and snow condition monitoring station n2, n1∈1,2,…,N-1; n2∈1,2,…,N-1; D represents the minimum allowable distance between two adjacent road surface ice and snow condition monitoring stations.

6. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 5 is characterized in that: In step 5, the initial population improved by the NSGAII algorithm is generated according to the constraint conditions of the multi-objective optimization site selection model; then the multi-objective optimization site selection model is solved by the NSGAII algorithm, and the site selection result of the road surface ice and snow condition monitoring station is output; the specific process is: Step 51, generating an initial population P improved by the NSGAII algorithm according to the constraint conditions of the multi-objective optimization site selection model; Step 52, performing non-dominated sorting on the individuals of the initial population P improved by the NSGAII algorithm, and dividing the individuals of the initial population P improved by the NSGAII algorithm into Z frontiers according to the result of the non-dominated sorting, where Z is a positive integer; and assigning a rank to the individuals in each frontier according to the ranking of the frontier sorting; Then the crowding degree in each front is calculated; Step 53: The initial population P improved by the NSGAII algorithm is used as the parent population, and the three basic operations of selection, crossover, and mutation are sequentially performed on the parent population to obtain the child population; Among them, the parent population of the tth iteration is represented by P t , the offspring population of the tth iteration is represented by Qt Step 54: merge the parent population and the offspring population to generate a merged population. Generate the parent population for the next round of iteration based on the merged population; Step 55, repeating steps 52 to 54 until the maximum number of iterations is reached or a set of satisfactory populations is obtained, then the iteration is stopped to obtain the final population; Step 56: Use the individuals in the final population as the site selection results for road ice and snow condition monitoring stations.

7. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 6 is characterized in that: The specific process of generating the initial population P improved by the NSGAII algorithm according to the constraint conditions of the multi-objective optimization site selection model in step 51 is as follows: Step 511: Set the size N of the initial population * , crossover probability nMu, mutation probability, maximum number of iterations M; Step 512: setting initial population generation constraints according to the constraints of the multi-objective optimization site selection model; Step 513: According to the initial population generation constraints of step 512, randomly generate N * The individuals of the population are obtained to obtain the initial population P improved by the NSGAII algorithm.

8. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 7 is characterized in that: In step 52, the individuals of the initial population P improved by the NSGAII algorithm are non-dominatedly sorted, and the individuals of the initial population P improved by the NSGAII algorithm are divided into Z frontiers according to the result of the non-dominated sorting, where Z is a positive integer; the individuals in each frontier are assigned a rank according to the ranking of the frontier sorting; and then the congestion degree in each frontier is calculated; the specific process is: Step 521: Calculate the objective function value of each individual in the initial population P; the i-th individual in the initial population P is represented by pi Step 522: According to the obtained objective function values ​​of all individuals and the dominance relationship in the NSGAII algorithm, all individuals are divided into Z frontier layers. The individuals in the first frontier layer are those that are not dominated by any individual, and the individuals in the next frontier layer are those that are dominated by the individuals in the previous frontier layer. Step 523: According to the objective function value of the individuals in each frontier and the crowding calculation method in the NSGAII algorithm, the crowding is calculated for the individuals in each layer of the frontier to obtain the crowding value of each individual in each layer of the frontier.

9. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 8 is characterized in that: In step 53, the parent population is subjected to three basic operations of selection, crossover and mutation in sequence to obtain the offspring population; the specific process is as follows: Step 531: Select two parent individuals from the parent population according to the non-dominated level of the parent population individuals and the congestion degree in each frontier. Step 532: Perform a crossover operation on the selected parent individuals according to the set crossover probability nMu to generate offspring individuals. Step 533: Perform mutation operations on all generated offspring individuals according to the set mutation probability to obtain an offspring population.

10. The multi-objective optimization site selection method for road surface ice and snow condition monitoring stations according to claim 9 is characterized in that: In step 54, the parent population P of the tth iteration is t and the t-th iteration offspring population Q t Merge to generate the t-th round iterative merge population R t ; According to the tth round of iteration, the population R is merged t Generate the parent population R for the t+1th iteration t+1 ; The specific process is: Step 541: The parent population P of the tth iteration t and the t-th iteration offspring population Q t Merge to generate the t-th round of iterative merge population R t ; Step 542: Merge population R for the tth round of iterations t The individuals are non-dominated and sorted; r frontiers are obtained, and the individuals in each frontier are ranked according to the ranking of the frontier sorting; Step 543: Select N according to the level of the individual * Individuals constitute the population P of the t+1th iteration t+1 .

Images