Intelligent optimization method for rural garbage bin layout
Through intelligent algorithm optimization methods, electronic maps and cellular coverage methods are used to quickly generate reasonable garbage can layout solutions in rural areas, solving the problem that existing technology is difficult to take into account multiple factors, and achieving efficient rural garbage can layout.
Patent Information
- Application Number
- CN202111460669.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-03
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-12-03
AI Technical Summary
The existing rural trash can site selection and layout technology is difficult to take into account multiple influencing factors, and it is impossible to quickly give quantitative preferred solutions, especially in rural areas that lack geographical base materials.
Using intelligent algorithm optimization method, the house single body and main entrance orientation are identified through electronic maps, and the potential feasible location is searched using cellular coverage method, combining the walking distance of garbage delivery, environmental impact and coverage efficiency indicators for evaluation, and generating an initial solution group and passing random hybridization. and mutations generate next-generation solutions to determine the optimal layout solution.
It has achieved rapid and reasonable generation of rural trash can layout plans, improved computing efficiency, avoided excessively dense trash can layout, found the best balanced solution, and provided a variety of preferred solutions for experts to compare.
Smart Images

Figure CN114399520B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the fields of architecture and urban and rural planning, and in particular to a rural garbage bin layout method based on intelligent algorithm optimization. Background Art
[0002] Rural trash cans are an important rural public facility that requires careful planning and site selection. There are many factors that affect the quality of the site selection, including the population served, accessibility, and impact on the environment. Therefore, it is difficult to take into account so many influencing factors by manual planning by humans or architects.
[0003] There are few studies on the location of rural public facilities, and most of them focus on theoretical research. For example, based on the theory of life circle, guidance opinions are put forward on the location of public service facilities in small towns from the three aspects of culture, efficiency and function. There is also a method for the location and configuration of village garbage that balances the interests of three parties. Although there are some evaluation indicators for the layout of public facilities and rationality evaluation indicators, they are mostly developed from a conceptual perspective. There is a lack of research on mathematical models for the location of rural public service facilities, and it is difficult to draw quantitative conclusions. Summary of the invention
[0004] The present invention provides an intelligent optimization method for the layout of rural garbage bins, which is used to solve the problems that the existing facility site selection and layout technology cannot take into account multiple factors, cannot quantitatively give multiple preferred solutions, and is difficult to be quickly applied to vast rural areas that lack geographical base materials.
[0005] In order to solve the above technical problems, the present invention includes the following technical solutions:
[0006] An intelligent optimization method for rural garbage bin layout includes the following steps:
[0007] Step 1. Mark the houses and their outlines on the electronic map of the entire village, and mark the direction of the main entrance;
[0008] Step 2. Searching for potential feasible locations of trash cans on an electronic map of the entire village by computer;
[0009] Step 3. Use a computer to select feasible location points by cellular coverage method to form a feasible location set, and display the feasible location points on an electronic map. The number of feasible location points in the feasible location set is recorded as N;
[0010] Step 4: Determine the size of each trash can in the feasible location set, and display the size of the trash can at the feasible location point on the electronic map.
[0011] Further, the step 1 specifically includes the following steps:
[0012] Step 1.1. Use a drone to photograph the entire village and obtain an oblique photograph of the entire village with altitude;
[0013] Step 1.2. Use edge detection algorithm to identify the house unit and its outline according to the location of the roof or wall, obtain the coordinates of the center point and outline control point of each rural house, and display them on the electronic map of the entire village;
[0014] Step 1.3. From the oblique photography side image, identify the ground floor door of each house as the main entrance direction and display it on the electronic map of the entire village.
[0015] Further, the step 2 specifically includes the following steps:
[0016] First, divide the entire village into several grid units on the electronic map;
[0017] The computer presets a determination condition for the location of a potentially feasible trash can, searches each grid unit in turn, and determines whether the grid unit is a potentially feasible trash can location according to the determination condition;
[0018] The grid units meeting the determination conditions are displayed on the electronic map.
[0019] Furthermore, the determination condition of the feasible trash can location is to satisfy the following conditions at the same time:
[0020] A. The distance from all house edges is greater than or equal to a, where a is the preset value;
[0021] B. There are houses within a radius of b meters, where b is a preset value;
[0022] C. Not on a main road.
[0023] Further, the step 3 specifically includes the following steps:
[0024] Divide the entire village into hexagonal honeycombs in the electronic map, where the side length of the hexagonal honeycomb ranges from [E1, E2], where E1 is greater than or equal to 5 times the side length of the grid unit in step 2, and E2>E1;
[0025] If there are two or more feasible locations inside the hexagonal cell, one feasible location is randomly selected and displayed on the electronic map;
[0026] The feasible position points after selection form the preferred feasible position set, and the total number of feasible position points is recorded as N.
[0027] Further, E1=10, E2=30;
[0028] For areas with densely populated houses, the hexagon has a side length of 10 meters, for general areas, the side length is 20 meters, and for areas with sparsely populated houses, the side length is 30 meters.
[0029] Furthermore, in step 4, the garbage delivery walking distance equivalent and D, environmental impact equivalent and P, and total coverage efficiency deviation C are used for evaluation, and the solution with smaller D, P, and C is selected as the preferred solution;
[0030] Among them, the garbage delivery walking distance equivalent and D expression is,
[0031]
[0032] D k represents the distance between the kth house and the nearest trash can; x i ,y i is the coordinate of the trash can, x k ,y k is the geometric center coordinate of the house; T i is the size of the i-th trash bin;
[0033] Among them, the environmental impact equivalent and P expression are:
[0034]
[0035] P k represents the distance between the kth house and the nearest trash can; x i ,y i is the coordinate of the trash can, x k ,y k is the geometric center coordinate of the house; T i is the size of the trash can; A k A is the coefficient that takes into account the influence of the orientation angle. k =max{,cos(α k )}, α k is the angle between the trash can and the kth house;
[0036] Among them, the total deviation of coverage efficiency C is expressed as:
[0037]
[0038] where q i is the number of people covered by the i-th trash can, Q is the total number of people in the village, is the total size of all trash cans, T i is the size of the i-th trash bin.
[0039] Furthermore, the size of each trash bin in the feasible location set is determined by the three indicators D, P, and C in the following way:
[0040] Step 4.1. Generate an initial solution group, which includes X random initial solutions. Each solution is represented by an N-dimensional floating point single column vector (T1,…,T i ,…,TN ) is used to represent the i represents the size of the i-th trash can, i = 1, 2, ..., N; T i It is represented by a floating point number between 0 and 1. i The larger the value, the larger the size of the trash can layout. i When the value is less than k, it means that no trash can is laid out, and k is the preset value;
[0041] Step 4.2. Enter an iterative process to generate the next generation of more optimal solution group X1 through random crossover and mutation;
[0042] The crossover operation is to randomly select two solutions from the solution group, find the mean of the corresponding elements in the two sets, and get a next-generation solution.
[0043] The mutation operation is to randomly select a solution, then randomly select an element in the set and add a random number between -0.2 and 0.2 as the next generation solution;
[0044] Step 4.3. Input the solutions in solution group X1 into the index expressions of garbage delivery walking distance equivalent and D, environmental impact equivalent and P, and total coverage efficiency deviation C, and eliminate the absolutely non-dominant solutions. The remaining ones are the new solution group. Repeat step 4.2 for iteration; if no absolutely non-dominant solution can be eliminated after a certain iteration, go to step 4.4;
[0045] Step 4.4. Stop the iteration and find a solution that has at least two of the three indicators D, P, and C as the best solution, and output it as the final optimal solution.
[0046] Due to the adoption of the above technical solution, the present invention has the following advantages and positive effects compared with the prior art: the present application marks the house units and outlines and the main entrance direction on the electronic map of the entire village, then uses a computer to search for potential feasible locations of the trash cans, and uses a computer to select feasible location points by the cellular coverage method to form a feasible location set, and then determines the scale of each trash can in the feasible location set, which can quickly provide an optimization plan for the layout position and scale of the trash cans, and has the advantages of high efficiency and reasonable layout. In addition, by first dividing the entire village into a number of grid units, finding the potential locations of the trash cans, and then dividing the entire village into a larger hexagonal honeycomb, and then determining the feasible location points, the computer processing efficiency is improved, and the disadvantage of too densely arranged trash cans is avoided. Moreover, by determining the size of each trash can in the feasible location set through the three indicators of D, P, and C, the optimal balanced solution can be found; the initial solution group is used to generate the next generation of more optimized solution group through random hybridization and mutation. The more scientific initial solution batch generation method avoids the extremely complex exhaustive search, and more than one trash can layout solution is output, each with its own unique advantages, which is convenient for subsequent expert solution comparison. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 The present invention is a flowchart of an intelligent optimization method for rural garbage bin layout in one embodiment of the present invention. DETAILED DESCRIPTION
[0048] The following is a further detailed description of the intelligent optimization method for rural garbage bin layout provided by the present invention in conjunction with the accompanying drawings and specific embodiments. The advantages and features of the present invention will become clearer in conjunction with the following description. It should be noted that the accompanying drawings are all in a very simplified form and are not in precise proportions, and are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention.
[0049] like Figure 1 As shown, this embodiment provides an intelligent optimization method for rural garbage bin layout, comprising the following steps:
[0050] Step 1. Mark the houses and their outlines on the electronic map of the entire village, and mark the direction of the main entrance.
[0051] It should be noted that marking the building unit and its outline as well as the direction of the main entrance on the electronic map can be done by manual measurement or manual marking. A more preferred implementation is to perform a quick operation by drone photography and computer automatic recognition technology, specifically including:
[0052] Step 1.1. Use a drone to photograph the entire village and obtain an oblique photograph of the entire village with altitude;
[0053] Step 1.2. Use edge detection algorithm to identify the house unit and its outline according to the location of the roof or wall, obtain the coordinates of the center point and outline control point of each rural house, and display them on the electronic map of the entire village;
[0054] Step 1.3. From the oblique photography side image, identify the ground floor door of each house as the main entrance direction and display it on the electronic map of the entire village.
[0055] For example, for a village in Fujian, oblique photography of about 1,000 houses was collected. Then, an edge detection algorithm was used to identify the house units and their outlines based on the location of the roof or wall, and the coordinates of the center point and outline control point of each rural house were obtained. From the side image of the oblique photography, the ground floor door of each house was identified as the main entrance direction. Then, the house units and outlines were marked on the electronic map of the entire village, and the main entrance direction was marked.
[0056] Step 2. Use a computer to search for potential locations of trash cans on an electronic map of the entire village.
[0057] First, divide the entire village into several grid units on the electronic map, for example, into 1m×1m square grids;
[0058] The computer presets a determination condition for the location of a potentially feasible trash can, searches each grid unit in turn, and determines whether the grid unit is a potentially feasible trash can location according to the determination condition;
[0059] The grid units meeting the determination conditions are displayed on the electronic map.
[0060] For example, if the following conditions are met at the same time, the grid unit is determined to be a potential trash can location: A. The distance from all house edges is greater than or equal to a, where a is a preset value, such as a = 2m; B. There are houses within a radius of b meters, where b is a preset value, such as b = 10m; C. It is not on the main road. Based on the set conditions, a total of 570 potential trash can locations were found on the electronic map of the entire village in Fujian.
[0061] Step 3. Use a computer to select feasible location points by cellular coverage method to form a feasible location set, and display the feasible location points on an electronic map. The number of feasible location points in the feasible location set is recorded as N. Specifically, the steps are as follows:
[0062] In the electronic map, the entire village is divided into hexagonal honeycombs, where the side length of the hexagonal honeycomb ranges from [E1, E2], where E1 and E2 are preset values, where E1 is greater than or equal to 5 times the side length of the grid unit in step 2, and E2>E1. For example, the side length of the hexagonal honeycomb is between 10 and 30 meters, and it is ensured that it is fully covered and does not overlap as much as possible. If the houses are densely packed in a certain place, the hexagon has a smaller side length, otherwise it has a larger side length;
[0063] If there are two or more feasible locations inside the hexagonal cell, one feasible location is randomly selected and displayed on the electronic map;
[0064] The feasible position points after selection form the preferred feasible position set, and the total number of feasible position points is recorded as N.
[0065] As an example, for a village in Fujian, 570 potential feasible locations of trash cans are found through step 2. There are too many feasible locations, so further optimization is needed to reduce the number of feasible locations. In the electronic map, the entire village is divided into hexagonal honeycombs with larger sides, and it is ensured that they are all covered and overlap as little as possible. For the densely populated areas on the south side, the hexagon has a side length of 10 meters, 20 meters for the general area, and 30 meters for the sparse area in the north. Then, if there are 2 or more feasible locations inside the hexagonal honeycomb, one is randomly selected. There are 18 feasible locations after selection, which constitute the optimal feasible location set. At this time, N=18 is determined. That is to say, after step 3, the layout location and number of trash cans can be obtained.
[0066] Step 4: Determine the size of each trash can in the feasible location set, and display the size of the trash can at the feasible location point on the electronic map.
[0067] It should be noted that the size of each trash can is estimated based on the number of people covered by each trash can. As a preferred implementation, this embodiment provides a more reasonable evaluation method for the size of the trash can, which is evaluated by three indicators: the equivalent sum of garbage delivery walking distance D, the equivalent sum of environmental impact P, and the total deviation of coverage efficiency C. The smaller D, P, and C are preferred.
[0068] Among them, the garbage delivery walking distance equivalent and D expression is,
[0069]
[0070] D k represents the distance between the kth house and the nearest trash can; x i ,y i is the coordinate of the trash can, x k ,y k is the geometric center coordinate of the house; T iis the size of the i-th trash bin;
[0071] Among them, the environmental impact equivalent and P expression are:
[0072]
[0073] P k represents the distance between the kth house and the nearest trash can; x i ,y i is the coordinate of the trash can, x k ,y k is the geometric center coordinate of the house; T i is the size of the trash can; A k A is the coefficient that takes into account the influence of the orientation angle. k =max{,cos(α k )}, α k is the angle between the trash can and the kth house;
[0074] Among them, the total deviation of coverage efficiency C is expressed as:
[0075]
[0076] where q i is the number of people covered by the i-th trash can, Q is the total number of people in the village, is the total size of all trash cans, T i is the size of the i-th trash bin.
[0077] It should be noted that the scale of each trash bin in the feasible location set can be determined by the three indicators D, P, and C in the following preferred manner:
[0078] Step 4.1. Generate an initial solution group, which includes X random initial solutions. Each solution is represented by an N-dimensional floating point single column vector (T1,…,T i ,…,T N ) is used to represent the i represents the size of the i-th trash can, i = 1, 2, ..., N; T i It is represented by a floating point number between 0 and 1. i The larger the value, the larger the size of the trash can layout. i When the value is less than k, it means that no trash can is laid out, and k is the preset value.
[0079] For example, the initial solution group includes 100 solutions; for example, in a certain initial solution, d = (0.5, ..., 0.1, ..., 0), which means that the first feasible position needs to be laid out with a trash can of size 0.5, which is a medium-sized trash can; when the size of the smallest trash can is 0.2, the floating point number less than 0.2 means that no trash can is laid out, and a certain feasible position in the middle of 0.1 means that no trash can is laid out. Further, X = 100-200.
[0080] Step 4.2. Enter an iterative process to generate the next generation of more optimal solution group X1 through random crossover and mutation.
[0081] The crossover operation is to randomly select two solutions from the solution group, find the mean of the corresponding elements in the two sets, and get a next-generation solution; for example, d1 = (0.5, ..., 0.1, ..., 0), d2 = (0.3, ..., 0.5, ..., 0.9), then their next generation is d 10 =(0.4,…,0.3,…,0.45).
[0082] The mutation operation is to randomly select a solution, then randomly select an element in the set and add a random number between -0.2 and 0.2 as the next generation solution. For example, if d1 = (0.5, ..., 0.1, ..., 0), then the next generation has a certain probability of becoming d 20 =(0.62,…,0.08,…,0.07).
[0083] Step 4.3. Input the solutions in solution group X1 into the index expressions of garbage delivery walking distance equivalent and D, environmental impact equivalent and P, and total coverage efficiency deviation C, and eliminate the absolutely non-dominant solutions. The remaining ones are the new solution group, and repeat step 4.2 for iteration; if no absolutely non-dominant solution can be eliminated after a certain iteration, go to step 4.4. It should be noted that for a certain solution d, if there is any solution in the solution group whose three indicators are better than d, then d is called an absolutely non-dominant solution.
[0084] Step 4.4. Stop the iteration and find a solution that has at least two of the three indicators D, P, and C as the best solution, and output it as the final optimal solution.
[0085] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0086] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. An intelligent optimization method for rural garbage bin layout, characterized in that: The steps include: Step 1. Mark the houses and their outlines on the electronic map of the entire village, and mark the direction of the main entrance; Step 2. Searching for potential feasible locations of trash cans on an electronic map of the entire village by computer; Step 3. Use a computer to select feasible location points by cellular coverage method to form a feasible location set, and display the feasible location points on an electronic map. The number of feasible location points in the feasible location set is recorded as N; Step 4. Determine the size of each trash can in the feasible location set, and display the size of the trash can at the feasible location point on the electronic map; In step 4, the garbage delivery walking distance equivalent sum D, environmental impact equivalent sum P, and total coverage efficiency deviation C are used for evaluation, and the solution with smaller D, P, and C is selected as the preferred solution; Among them, the garbage delivery walking distance equivalent and D expression is, D k represents the distance between the kth house and the nearest trash can; x i ,y i is the coordinate of the trash can, x k ,y k is the geometric center coordinate of the house; T i is the size of the i-th trash bin; Among them, the environmental impact equivalent and P expressions are: P k represents the distance between the kth house and the nearest trash can; x i ,y i is the coordinate of the trash can, x k ,y k is the geometric center coordinate of the house; T i is the size of the trash can; A k A is the coefficient that takes into account the influence of the orientation angle. k =max{0,cos(α k )}, α k is the angle between the trash can and the kth house; Among them, the total deviation of coverage efficiency C is expressed as: where q i is the number of people covered by the i-th trash can, Q is the total number of people in the village, is the total size of all trash cans, T i is the size of the i-th trash bin; The size of each trash bin in the feasible location set is determined by the three indicators D, P, and C in the following way: Step 4.
1. Generate an initial solution group, which includes X random initial solutions. Each solution is represented by an N-dimensional floating point single column vector (T1,…,T i ,…,T N ) is used to represent the i represents the size of the i-th trash can, i = 1, 2, ..., N; T i It is represented by a floating point number between 0 and 1. i The larger the value, the larger the size of the trash can layout. i When the value is less than k, it means that no trash can is laid out, and k is the preset value; Step 4.
2. Enter an iterative process to generate the next generation of more optimal solution group X1 through random crossover and mutation; The crossover operation is to randomly select two solutions from the solution group, find the mean of the corresponding elements in the two sets, and get a next-generation solution. The mutation operation is to randomly select a solution, then randomly select an element in the set and add a random number between -0.2 and 0.2 as the next generation solution; Step 4.
3. Input the solutions in solution group X1 into the index expressions of garbage delivery walking distance equivalent and D, environmental impact equivalent and P, and total coverage efficiency deviation C, and eliminate the absolutely non-dominant solutions. The remaining ones are the new solution group. Repeat step 4.2 for iteration; if no absolutely non-dominant solution can be eliminated after a certain iteration, go to step 4.4; Step 4.
4. Stop the iteration and find a solution that has at least two of the three indicators D, P, and C as the best solution, and output it as the final optimal solution.
2. The intelligent optimization method for rural garbage bin layout according to claim 1, characterized in that: The step 1 specifically includes the following steps: Step 1.
1. Use a drone to photograph the entire village and obtain an oblique photograph of the entire village with altitude; Step 1.
2. Use edge detection algorithm to identify the house unit and its outline according to the location of the roof or wall, obtain the coordinates of the center point and outline control point of each rural house, and display them on the electronic map of the entire village; Step 1.
3. From the oblique photography side image, identify the ground floor door of each house as the main entrance direction and display it on the electronic map of the entire village.
3. The intelligent optimization method for rural garbage bin layout according to claim 1, characterized in that: The step 2 specifically includes the following steps: First, divide the entire village into several grid units on the electronic map; The computer presets a determination condition for the location of a potentially feasible trash can, searches each grid unit in turn, and determines whether the grid unit is a potentially feasible trash can location according to the determination condition; The grid units meeting the determination conditions are displayed on the electronic map.
4. The intelligent optimization method for rural garbage bin layout according to claim 3, characterized in that: The conditions for determining the location of a feasible trash can are to meet the following conditions at the same time: A. The distance from all house edges is greater than or equal to a, where a is the preset value; B. There are houses within a radius of b meters, where b is a preset value; C. Not on a main road.
5. The intelligent optimization method for rural garbage bin layout according to claim 3 or 4, characterized in that: The step 3 specifically includes the following steps: Divide the entire village into hexagonal honeycombs in the electronic map, where the side length of the hexagonal honeycomb ranges from [E1, E2], where E1 is greater than or equal to 5 times the side length of the grid unit in step 2, and E2>E1; If there are two or more feasible locations inside the hexagonal cell, one feasible location is randomly selected and displayed on the electronic map; The feasible location points after selection form the preferred feasible location set, and the total number of feasible location points is recorded as N.
6. The intelligent optimization method for rural garbage bin layout according to claim 5, characterized in that: E1=10, E2=30; For areas with densely populated houses, the hexagon has a side length of 10 meters, for general areas, the side length is 20 meters, and for areas with sparsely populated houses, the side length is 30 meters.
