Artificial turf grass planting process parameter regulation system and method based on big data

Abstract

The application discloses an artificial turf grass planting process parameter regulation and control system and method based on big data, relates to the grass planting height and area measurement field, and optimizes the process of the artificial turf from the initial height and initial area of the grass planted in the artificial turf, so that the endurance time of the artificial turf is maximized. Wherein, by constructing a height difference mapping model and an area difference mapping model, a mapping model is provided for the difference before and after the influence of natural factors and human factors on the grass planting height and area of each sub-region in the artificial turf area to be laid, and then the final value of the grass planting height can be calculated from the initial value of the grass planting height, so that whether the initial value of the set grass planting height and area meets the requirements is determined according to the final value of the grass planting height and area of the artificial turf to be laid, and optimization is further performed.

Description

Technical Field

[0001] This invention belongs to the field of grass planting height and area measurement, and specifically relates to a system and method for controlling artificial turf planting process parameters based on big data. Background Technology

[0002] When planting artificial turf, the initial height and initial planting area are two aspects that need to be carefully considered. If the initial height and initial planting area are not reasonable, the artificial turf may be severely affected by natural and human factors over time, resulting in serious damage to the artificial turf, low durability, more maintenance operations, or even inability to continue using it, thus causing losses to the company. Summary of the Invention

[0003] To address the problems in related technologies, this invention proposes a system and method for controlling artificial turf planting process parameters based on big data, in order to overcome the aforementioned technical problems existing in the existing related technologies.

[0004] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0005] This invention relates to a method for controlling artificial turf planting process parameters based on big data, comprising the following steps:

[0006] S1. Collect initial average grass height data, initial grass area data, durability natural influencing factor data and durability human influencing factor data for each sub-region in multiple existing artificial turf areas, and obtain the existing grass initial average height data matrix, the existing grass initial area data matrix, the historical turf durability natural influencing factor data matrix set and the historical turf durability human influencing factor data matrix.

[0007] S2. Construct a height difference mapping model and an area difference mapping model using the existing average initial grass height data matrix, the existing initial grass area data matrix, the historical natural influencing factors data matrix set, the historical human influencing factors data matrix set, and the corresponding final grass height and area data.

[0008] S3. Collect data on the natural and human factors affecting durability of each sub-region in the area where artificial turf is to be laid, and obtain the data matrix of the natural and human factors affecting durability of the artificial turf to be laid.

[0009] S4. Combine the data matrix of natural influencing factors of durability to be laid, the data matrix of human influencing factors of durability to be laid, the height difference mapping model, and the area difference mapping model to optimize the initial height data and area data of each sub-region in the area to be laid artificial turf, so as to obtain the final initial height dataset and the final initial area dataset of grass to be laid.

[0010] The initial average grass height in artificial turf refers to the average height of the grass before any human or natural influences after the turf is newly laid. Similarly, the initial grass area refers to the area of ​​the turf before any human or natural influences after the turf is newly laid. The grass height and turf area change over time and under the influence of various natural and human factors. Based on the above, this solution collects initial average grass height data, initial grass area data, durability natural influence factor data, durability human influence factor data, and grass area data after various influencing factors in each sub-region of multiple existing artificial turf areas. The grass height and area data provide data support for the subsequent construction of height difference mapping models and area difference mapping models. By constructing height difference mapping models and area difference mapping models, a mapping model is provided for obtaining the differences in grass height and area of ​​each sub-region in the area to be laid artificial turf before and after the influence of natural and human factors. Then, the final value of grass height can be calculated from the initial value of grass height. Based on the final value of grass height and area of ​​the artificial turf to be laid, it can be determined whether the initial value of grass height and area meets the requirements, and then optimization can be carried out. Among them, the distribution of the initial grass height and initial grass area has a significant impact on the durability of artificial turf.

[0011] Preferably, step S1 includes the following steps:

[0012] S11. Define multiple existing artificial turf regions to obtain a set of existing artificial turf regions; divide each artificial turf region in the set of existing artificial turf regions to obtain an existing artificial turf sub-region matrix a; as follows.

[0013]

[0014] Among them, a ijLet a1' represent the j-th artificial turf sub-region obtained by dividing the i-th artificial turf region in the existing artificial turf region set, and let a'2 represent the total number of existing artificial turf regions. The initial average grass height and initial grass area data of each artificial turf sub-region in the existing artificial turf sub-region matrix are measured to obtain the existing average initial grass height data matrix. and the existing initial area data matrix of grass planting They are as follows:

[0015]

[0016] in, These represent the initial average grass height and initial grass area data of the j-th sub-region of the i-th artificial turf region in the existing artificial turf area concentration, respectively.

[0017] S12, Set the set of natural factors affecting lawn durability and a set of human factors affecting lawn durability b1 represents the set natural influencing factor of lawn durability for the i-th type, and b1 represents the total number of set natural influencing factor types of lawn durability. b1 represents the i-th type of human-induced factor affecting lawn durability, and b2 represents the total number of types of human-induced factors affecting lawn durability. Multiple historical data collection time points are set to obtain the historical data collection time point set. b1′ i This represents the i-th historical data collection time point. This indicates the total number of historical data collection points set.

[0018] Based on the aforementioned set of natural influencing factors for turf durability and the set of historical data collection time points, data on each type of natural influencing factor for turf durability was collected from each existing artificial turf area at each historical data collection time point, resulting in a historical turf durability natural influencing factor data matrix set. This represents the historical natural influencing factors data matrix of the artificial turf area for the i-th existing artificial turf area in the existing artificial turf area set; as follows:

[0019]

[0020] in, This represents the data on the natural influencing factors of lawn durability for the kth type of artificial turf in the i-th existing artificial turf area at the j-th historical data collection point.

[0021] Based on the aforementioned set of anthropogenic factors affecting turf durability and the set of historical data collection time points, data on each type of anthropogenic factor affecting turf durability within each existing artificial turf sub-region of the existing artificial turf sub-region matrix at each historical data collection time point are collected to obtain the historical turf durability anthropogenic factor data matrix. as follows,

[0022]

[0023] in, This represents the data matrix of human factors influencing the durability of artificial turf in the j-th sub-region of the i-th artificial turf region within the existing artificial turf area cluster. express Data on natural influencing factors of lawn durability for the k′th type of lawn at the kth historical data collection point;

[0024] S13. At the last historical data collection point in the set of historical data collection points, collect the average grass height data and grass area data of each sub-region in the existing artificial turf sub-region matrix to obtain the final average grass height data matrix. and the final area data matrix of existing grass planting They are as follows:

[0025]

[0026] in, These represent the average grass height and grass area data of the j-th sub-region of the i-th artificial turf region in the set of existing artificial turf regions at the last historical data collection point in the historical data collection time point set.

[0027] The difference between each data point in the average final height of existing grass in the average final height data matrix and the corresponding data point in the average initial height data matrix of existing grass is calculated, and the absolute value is taken to obtain the average height difference data matrix of existing grass. The difference between each current grass area final area data in the existing grass final area data matrix and the corresponding current grass initial area data in the existing grass initial area data matrix is ​​calculated, and the absolute value is taken to obtain the existing grass area difference data matrix. They are as follows:

[0028]

[0029] in, Let $\mathbf$ represent the difference in average existing grass height and the difference in existing grass area between the $j$ sub-regions of the $i$-th artificial turf region. The calculation formulas are as follows:

[0030]

[0031] Natural factors affecting turf durability include ultraviolet radiation, temperature changes, rainfall, and humidity. Ultraviolet radiation damages grass fibers, causing fading and reduced strength. Temperature changes, especially extreme ones, can cause artificial turf materials to expand and contract, affecting their stability and lifespan. Excessive rainfall leads to high soil moisture, hindering root growth, and high humidity accelerates turf degradation. Human factors affecting turf durability include maintenance frequency, usage frequency and intensity, usage methods, frequency of exposure to chemicals, frequency of contact with sharp objects, and frequency of proximity to heat sources. Since people are not evenly distributed across artificial turf, dividing the turf into zones allows for more precise analysis of the reasons for differences in planting data.

[0032] Preferably, step S2 includes the following steps:

[0033] S21. Construct a height difference mapping model using the existing average initial height data matrix of grass planting, the historical natural influencing factors data matrix set of lawn durability, the historical human influencing factors data matrix of lawn durability, and the existing average height difference data matrix of grass planting.

[0034] S22. Construct an area difference mapping model using the existing initial grass planting area data matrix, the historical lawn durability natural influencing factor data matrix set, the historical lawn durability human influencing factor data matrix, and the existing grass planting area difference data matrix.

[0035] A height difference mapping model was constructed using existing average initial grass height data matrix, historical natural factors affecting turf durability data matrix, historical anthropogenic factors affecting turf durability data matrix, and existing average grass height difference data matrix. This model demonstrates good mapping capability between initial grass height, natural factors affecting turf durability data, and anthropogenic factors affecting turf durability data and grass height difference data. Similarly, an area difference mapping model was constructed using existing initial grass area data matrix, historical natural factors affecting turf durability data, historical anthropogenic factors affecting turf durability data, and existing area difference data matrix. This model demonstrates good mapping capability between initial grass area data, natural factors affecting turf durability data, and anthropogenic factors affecting turf durability data and grass area difference data.

[0036] Preferably, step S3 includes the following steps:

[0037] S31. Define the area to be laid with artificial turf; divide the area to be laid with artificial turf into sub-areas to obtain a set of sub-areas; define multiple current data collection time points to obtain a set of current time points; predict the natural and human factors affecting durability of each sub-area in the set of sub-areas to be laid with artificial turf based on the set of current time points, the set of natural factors affecting turf durability, and the set of human factors affecting turf durability, to obtain the data matrix c1 of natural factors affecting durability and the set of human factors affecting durability data c2 = {c 21 ,c 22 ,...,c 2i ,...,c 2c′}, c 2i This represents the data matrix of human-induced factors affecting the durability of the i-th sub-region of the artificial turf to be laid sub-region set; c′ represents the total number of sub-regions in the artificial turf to be laid sub-region set; c1, c 2i They are as follows:

[0038]

[0039] Among them, c 1ij This represents the data on the natural influencing factors of lawn durability for the j-th type of turf at the i-th current data collection point in the area to be laid with artificial turf; c 1ijk This represents the data on human factors affecting the durability of the k-th type of turf at the j-th current data collection point in the i-th sub-region to be laid artificial turf.

[0040] S32. Preset the initial height data for planting artificial turf in each sub-region of the artificial turf to be laid in the set of sub-regions, and obtain the initial height dataset for planting artificial turf. This represents the preset initial planting height data of the i-th sub-region in the set of sub-regions to be covered with artificial turf; the initial area data of each sub-region in the set of sub-regions to be covered with artificial turf are measured to obtain the initial planting area dataset. This represents the initial area data of the i-th sub-region in the set of sub-regions where artificial turf is to be laid;

[0041] By predicting the durability of natural and human factors affecting the area to be laid with artificial turf and its sub-areas, and pre-setting the initial planting height and initial planting area, data support is provided for obtaining the difference data between the planting height and planting area data after the effects of natural and human factors at multiple time points, and the current planting height and planting area data, using the height difference mapping model and area difference mapping model.

[0042] Preferably, step S4 includes the following steps:

[0043] S41. Input the initial height dataset of grass to be laid, the data matrix of natural influencing factors for durability to be laid, and the data matrix of human influencing factors for durability to be laid into the height difference mapping model for mapping to obtain the initial height difference dataset; input the initial area dataset of grass to be laid, the data matrix of natural influencing factors for durability to be laid, and the data matrix of human influencing factors for durability to be laid into the area difference mapping model for mapping to obtain the initial area difference dataset;

[0044] The difference between the initial height dataset of the grass to be laid and the dataset of differences between the initial heights to be laid is calculated to obtain the final height dataset of the grass to be laid. This represents the final planting height data of the i-th sub-region in the set of sub-regions to be covered with artificial turf; then, the difference between the data corresponding to the initial planting area dataset and the initial planting area difference dataset is calculated to obtain the final planting area dataset. This represents the final grass planting area data of the i-th sub-region in the set of sub-regions to be covered with artificial turf;

[0045] S42. Adjust the initial height dataset and initial area dataset of the grass to be laid according to the final height dataset and the final area dataset of the grass to be laid to obtain the final initial height dataset and the final initial area dataset of the grass to be laid.

[0046] Since the final height and area of ​​the grass to be laid may contain data that do not meet the requirements, it means that the damage to the artificial turf exceeds the predetermined level within a certain time range, thus requiring adjustments to the initial height and area of ​​the grass.

[0047] Preferably, step S42 includes the following steps:

[0048] S421. Based on the initial height dataset of grass to be laid and the initial area dataset of grass to be laid, set the corresponding final grass height threshold and final grass area threshold to obtain the final grass height threshold set and the final grass area threshold set.

[0049] S422. When there is a final grass height data in the final grass height dataset that is less than the final grass height threshold corresponding to the final grass height threshold set, or a final grass area data in the final grass area dataset that is less than the final grass area threshold corresponding to the final grass area threshold set, the initial grass height dataset and the initial grass area dataset are adjusted until there is no final grass height data in the final grass height dataset that is less than the final grass height threshold corresponding to the final grass height threshold set, and no final grass area data in the final grass area dataset that is less than the final grass area threshold corresponding to the final grass area threshold set, thus obtaining the final initial grass height dataset and the final initial grass area dataset.

[0050] By setting a final grass height threshold set and a final grass area threshold set, a quantitative standard is provided for determining whether the grass height data and grass area data of each area in the artificial turf meet the requirements.

[0051] Preferably, adjusting the initial height dataset and the initial area dataset of the grass to be laid in S422 includes the following steps:

[0052] S4221. Optimize tuna population by constructing grass planting height and area. Let d represent the i-th tuna in the grass height and area optimization tuna population, and let d represent the size of the grass height and area optimization tuna population; set the maximum number of iterations for the grass height and area optimization tuna population as d1′ and the current number of iterations as d2′; set the search space dimension of the grass height and area optimization tuna population as 2·c′.

[0053] S4222: Set the range of planting height for laying artificial turf in the area to be laid and the range of area for each sub-area in the area to be laid, to obtain the planting height range. and the set of sub-region area intervals These represent the lower limit and upper limit of the planting height for laying artificial turf in the area to be covered, respectively. as follows,

[0054]

[0055] in, These represent the lower limit and upper limit of the area of ​​the i-th sub-region in the area to be laid artificial turf, respectively;

[0056] Based on the grass height range and the sub-region area range set, the initial position of each tuna in the tuna population is optimized by setting the grass height and area, resulting in an initial position matrix set. The matrix representing the initial position of the i-th tuna in the tuna population optimized by the grass planting height-area ratio is as follows:

[0057]

[0058] in, The initial position of the i-th tuna in the tuna population in the grass height area optimization is represented by the position component of the initial grass height dimension in the j-th sub-region of the artificial turf area to be laid; The component representing the initial position of the i-th tuna in the tuna population within the area of ​​the j-th sub-region in the area to be covered by the artificial turf is the area dimension of the area where the grass planting height and area optimization is performed. The calculation formulas are as follows:

[0059]

[0060] In the formula, rand i1j rand i2j They represent respectively targeting Generate random numbers between 0 and 1;

[0061] S4223, Based on the dataset of the final height of the grass to be laid. and the final area dataset of grass to be laid The fitness function e for optimizing the grass planting height and area of ​​a tuna population is constructed as follows:

[0062]

[0063] S4224. Start the iteration. Before the iteration, set the current iteration number d2′ to 1. In the first iteration, the fitness function e of the tuna population is optimized by grass planting height and area. The fitness value of the initial position matrix of each tuna in the initial position matrix set is calculated by using the height difference mapping model and the area difference mapping model, and a first fitness value set is obtained. The fitness value with the largest fitness value in the first fitness value set and the corresponding initial position matrix of the tuna are taken as the first global best fitness and the first global best position. The initial position matrix of each tuna in the initial position matrix set is updated according to the first global best fitness and the first global best position. After the update is completed, the current iteration number d2′ is incremented by 1 and the next iteration is started.

[0064] In each iteration, the fitness function e of the grass-planting height-area optimization tuna population is used, along with the height difference mapping model and the area difference mapping model, to calculate the fitness value of the position matrix of each tuna in the grass-planting height-area optimization tuna population updated in the previous iteration, thus obtaining a second fitness value set. The fitness value with the largest fitness value in the second fitness value set and the corresponding tuna position matrix are taken as the second global best fitness and the second global best position. The position matrix of each tuna in the grass-planting height-area optimization tuna population updated in the previous iteration is updated again based on the second global best fitness and the second global best position. After the update is completed, the current iteration number d2′ is incremented by 1 and the next iteration begins.

[0065] S4225. When d2′≥d1′, stop the iteration and obtain the final global optimal position matrix; otherwise, continue the iteration until d2′≥d1′; divide the data in the final global optimal position to obtain the optimized initial height dataset and the optimized initial area dataset; input the optimized initial height dataset, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability into the height difference mapping model for mapping to obtain the optimized height difference dataset; and input the optimized initial height dataset, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability into the height difference mapping model for mapping to obtain the optimized height difference dataset; The initial area dataset to be laid, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability are input into the area difference mapping model for mapping to obtain the optimized area difference dataset. The difference between the optimized initial height dataset and the optimized height difference dataset, and the difference between the optimized initial area dataset and the optimized area difference dataset, are calculated to obtain the optimized final height dataset and the optimized final area dataset.

[0066] If the optimized final height dataset for grass to be laid does not contain any final grass height data that is less than the final grass height threshold corresponding to the final grass height threshold set, and the optimized final area dataset for grass to be laid does not contain any final area data that is less than the final grass area threshold corresponding to the final grass area threshold set, then the optimized initial height dataset for grass to be laid and the optimized initial area dataset for grass to be laid are respectively used as the final initial height dataset for grass to be laid and the final initial area dataset for grass to be laid; otherwise, return to S4224 to continue iterating until the optimized final height dataset for grass to be laid does not contain any final grass height data that is less than the final grass height threshold corresponding to the final grass height threshold set, and the optimized final area dataset for grass to be laid does not contain any final area data that is less than the final grass area threshold corresponding to the final grass area threshold set.

[0067] The Tuna Optimization Algorithm can effectively search the entire solution space during the exploration phase, avoiding premature entrapment in local optima. During the pursuit and foraging phases, it can quickly converge to the optimal solution, exhibiting high search efficiency. Furthermore, it requires only a small number of parameters, making its implementation relatively simple. Based on these advantages, this scheme uses the Tuna Optimization Algorithm to iteratively optimize the grass height and area data of each sub-region within the area to be laid artificial turf. The fitness function is the sum of the minimum values ​​of the final grass height and area of ​​each sub-region within the area to be laid. Therefore, as the iteration progresses, the final grass height and area of ​​each sub-region within the area to be laid artificial turf increase, resulting in less wear on the artificial turf over the corresponding time frame, ultimately meeting the requirements.

[0068] The artificial turf planting process parameter control system based on big data includes an existing artificial turf area division module, an existing planting data acquisition module, a first durability influencing factor data acquisition module, a planting data difference calculation and acquisition module, a mapping model construction module, a second durability influencing factor data acquisition module, a final planting data calculation module for the artificial turf to be laid, and a planting initial parameter optimization module.

[0069] The present invention has the following beneficial effects:

[0070] 1. This invention optimizes the artificial turf process from the perspectives of two parameters: the initial height and initial area of ​​the grass planted, thereby maximizing the durability of the artificial turf. Specifically, by constructing a height difference mapping model and an area difference mapping model, a mapping model is provided for obtaining the differences in grass planting height and area of ​​each sub-region in the area to be laid under the influence of natural and human factors. Then, the final value of the grass planting height can be calculated from the initial value of the grass planting height. Based on the final value of the grass planting height and area of ​​the artificial turf to be laid, it can be determined whether the initial value of the grass planting height and area meets the requirements, and then optimization can be carried out.

[0071] 2. The final height dataset and final area dataset of the grass to be laid obtained in this invention may contain data that does not meet the requirements, which means that the damage to the artificial turf exceeds the predetermined level, thus requiring adjustment of the initial height and initial area of ​​the grass.

[0072] 3. In this invention, the Tuna optimization algorithm is used to iteratively optimize the grass height and area data of each sub-region in the area to be laid with artificial turf. The fitness function is the sum of the minimum values ​​of the final grass height and final area of ​​each sub-region in the area to be laid with artificial turf. Therefore, as the iteration proceeds, the final grass height and final area of ​​each sub-region in the area to be laid with artificial turf become higher and higher, and the wear on the artificial turf on the surface becomes smaller and smaller within the corresponding time range, thus finally meeting the requirements.

[0073] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0074] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, the drawings can be obtained from these drawings without creative effort.

[0075] Figure 1 This is a flowchart illustrating the method for controlling artificial turf planting process parameters based on big data, as described in this invention. Detailed Implementation

[0076] The technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, and not all embodiments. Based on the embodiments of the invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the invention.

[0077] In the description of this invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc., which indicate orientation or positional relationship, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the invention.

[0078] Example 1

[0079] Please see Figure 1 This embodiment describes a method for adjusting artificial turf planting process parameters based on big data, including the following steps:

[0080] S1. Collect initial average grass height data, initial grass area data, durability natural influencing factor data and durability human influencing factor data for each sub-region in multiple existing artificial turf areas, and obtain the existing grass initial average height data matrix, the existing grass initial area data matrix, the historical turf durability natural influencing factor data matrix set and the historical turf durability human influencing factor data matrix.

[0081] S1 includes the following steps:

[0082] S11. Define multiple existing artificial turf regions to obtain a set of existing artificial turf regions; divide each artificial turf region in the set of existing artificial turf regions to obtain an existing artificial turf sub-region matrix a; as follows.

[0083]

[0084] Among them, a ij Let a1' represent the j-th artificial turf sub-region obtained by dividing the i-th artificial turf region in the existing artificial turf region set, and let a'2 represent the total number of existing artificial turf regions. The initial average grass height and initial grass area data of each artificial turf sub-region in the existing artificial turf sub-region matrix are measured to obtain the existing average initial grass height data matrix. and the existing initial area data matrix of grass planting They are as follows:

[0085]

[0086] in, These represent the initial average grass height and initial grass area data of the j-th sub-region of the i-th artificial turf region in the existing artificial turf area concentration, respectively.

[0087] S12, Set the set of natural factors affecting lawn durability and a set of human factors affecting lawn durability b1 represents the set natural influencing factor of lawn durability for the i-th type, and b1 represents the total number of set natural influencing factor types of lawn durability. b1 represents the i-th type of human-induced factor affecting lawn durability, and b2 represents the total number of types of human-induced factors affecting lawn durability. Multiple historical data collection time points are set to obtain the historical data collection time point set. b1′ i This represents the i-th historical data collection time point. This indicates the total number of historical data collection points set.

[0088] Based on the aforementioned set of natural influencing factors for turf durability and the set of historical data collection time points, data on each type of natural influencing factor for turf durability was collected from each existing artificial turf area at each historical data collection time point, resulting in a historical turf durability natural influencing factor data matrix set. This represents the historical natural influencing factors data matrix of the artificial turf area for the i-th existing artificial turf area in the existing artificial turf area set; as follows:

[0089]

[0090] in, This represents the data on the natural influencing factors of lawn durability for the kth type of artificial turf in the i-th existing artificial turf area at the j-th historical data collection point.

[0091] Based on the aforementioned set of anthropogenic factors affecting turf durability and the set of historical data collection time points, data on each type of anthropogenic factor affecting turf durability within each existing artificial turf sub-region of the existing artificial turf sub-region matrix at each historical data collection time point are collected to obtain the historical turf durability anthropogenic factor data matrix. as follows,

[0092]

[0093] in, This represents the data matrix of human factors influencing the durability of artificial turf in the j-th sub-region of the i-th artificial turf region within the existing artificial turf area cluster. express Data on natural influencing factors of lawn durability for the k′th type of lawn at the kth historical data collection point;

[0094] S13. At the last historical data collection point in the set of historical data collection points, collect the average grass height data and grass area data of each sub-region in the existing artificial turf sub-region matrix to obtain the final average grass height data matrix. and the final area data matrix of existing grass planting They are as follows:

[0095]

[0096] in, These represent the average grass height and grass area data of the j-th sub-region of the i-th artificial turf region in the set of existing artificial turf regions at the last historical data collection point in the historical data collection time point set.

[0097] The difference between each data point in the average final height of existing grass in the average final height data matrix and the corresponding data point in the average initial height data matrix of existing grass is calculated, and the absolute value is taken to obtain the average height difference data matrix of existing grass. The difference between each current grass area final area data in the existing grass final area data matrix and the corresponding current grass initial area data in the existing grass initial area data matrix is ​​calculated, and the absolute value is taken to obtain the existing grass area difference data matrix. They are as follows:

[0098]

[0099] in, Let $\mathbf$ represent the difference in average existing grass height and the difference in existing grass area between the $j$ sub-regions of the $i$-th artificial turf region. The calculation formulas are as follows:

[0100]

[0101] S2. Construct a height difference mapping model and an area difference mapping model using the existing average initial grass height data matrix, the existing initial grass area data matrix, the historical natural influencing factors data matrix set, the historical human influencing factors data matrix set, and the corresponding final grass height and area data.

[0102] S2 includes the following steps:

[0103] S21. Construct a height difference mapping model using the existing average initial height data matrix of grass planting, the historical natural influencing factors data matrix set of lawn durability, the historical human influencing factors data matrix of lawn durability, and the existing average height difference data matrix of grass planting.

[0104] S21 includes the following steps:

[0105] S211. Construct a first initial SVM mapping model and set a first training data ratio; according to the first training data ratio, divide the existing average initial height data matrix, the historical lawn durability natural influencing factor data matrix set, the historical lawn durability human influencing factor data matrix, and the existing average height difference data matrix to obtain the existing average initial height training data matrix, the first historical lawn durability natural influencing factor training data matrix set, the first historical lawn durability human influencing factor training data matrix, the existing average height difference training data matrix, the existing average initial height test data matrix, the first historical lawn durability natural influencing factor test data matrix set, the first historical lawn durability human influencing factor test data matrix, and the existing average height difference test data matrix.

[0106] S212. Set a first training error threshold; input the existing average initial height training data matrix, the first historical lawn durability natural influencing factor training data matrix set, the first historical lawn durability human influencing factor training data matrix as training data, and the existing average height difference training data matrix as training labels into the first initial SVM mapping model for training; during the training process, when the training error is less than the first training error threshold, stop training and obtain the first trained SVM mapping model; otherwise, continue training until the training error is less than the first training error threshold.

[0107] S213. Set a first test accuracy threshold; input the existing average initial height test data matrix, the first historical lawn durability natural influencing factor test data matrix set, the first historical lawn durability human influencing factor test data matrix as test data, and the existing average height difference test data matrix as test labels into the first trained SVM mapping model for testing; after the test is completed, obtain the first test accuracy; when the first test accuracy is greater than or equal to the first test accuracy threshold, use the first trained SVM mapping model as the height difference mapping model; otherwise, return to S212 to continue iterating until the first test accuracy is greater than or equal to the first test accuracy threshold, and obtain the height difference mapping model.

[0108] S22. Construct an area difference mapping model using the existing initial grass planting area data matrix, the historical lawn durability natural influencing factor data matrix set, the historical lawn durability human influencing factor data matrix, and the existing grass planting area difference data matrix.

[0109] S22 includes the following steps:

[0110] S221. Construct a second initial SVM mapping model and set a second training data ratio; according to the second training data ratio, divide the existing initial grass planting area data matrix, the historical lawn durability natural influencing factor data matrix set, the historical lawn durability human influencing factor data matrix, and the existing grass planting area difference data matrix into the following data: existing initial grass planting area training data matrix, second historical lawn durability natural influencing factor training data matrix set, second historical lawn durability human influencing factor training data matrix, existing grass planting area difference training data matrix, existing initial grass planting area test data matrix, second historical lawn durability natural influencing factor test data matrix set, second historical lawn durability human influencing factor test data matrix, and existing grass planting area difference test data matrix.

[0111] S222. Set a second training error threshold; input the existing initial grass planting area training data matrix, the second historical lawn durability natural influencing factor training data matrix set, the second historical lawn durability human influencing factor training data matrix as training data, and the existing grass planting area difference training data matrix as training labels into the second initial SVM mapping model for training; during the training process, when the training error is less than the second training error threshold, stop training and obtain the second trained SVM mapping model; otherwise, continue training until the training error is less than the second training error threshold.

[0112] S223. Set a second test accuracy threshold; input the existing initial grass planting area test data matrix, the second historical lawn durability natural influencing factor test data matrix set, the second historical lawn durability human influencing factor test data matrix as test data, and the existing grass planting area difference test data matrix as test labels into the second trained SVM mapping model for testing; after the test is completed, obtain the second test accuracy; when the second test accuracy is greater than or equal to the second test accuracy threshold, use the second trained SVM mapping model as the height difference mapping model; otherwise, return to S222 to continue iterating until the second test accuracy is greater than or equal to the second test accuracy threshold, and obtain the height difference mapping model;

[0113] S3. Collect data on the natural and human factors affecting durability of each sub-region in the area where artificial turf is to be laid, and obtain the data matrix of the natural and human factors affecting durability of the artificial turf to be laid.

[0114] S3 includes the following steps:

[0115] S31. Define the area to be laid with artificial turf; divide the area to be laid with artificial turf into sub-areas to obtain a set of sub-areas; define multiple current data collection time points to obtain a set of current time points; predict the natural and human factors affecting durability of each sub-area in the set of sub-areas to be laid with artificial turf based on the set of current time points, the set of natural factors affecting turf durability, and the set of human factors affecting turf durability, to obtain the data matrix c1 of natural factors affecting durability and the set of human factors affecting durability data c2 = {c 21 ,c 22 ,...,c 2i ,...,c 2c′}, c 2i This represents the data matrix of human-induced factors affecting the durability of the i-th sub-region of the artificial turf to be laid sub-region set; c′ represents the total number of sub-regions in the artificial turf to be laid sub-region set; c1, c 2i They are as follows:

[0116]

[0117] Among them, c 1ij This represents the data on the natural influencing factors of lawn durability for the j-th type of turf at the i-th current data collection point in the area to be laid with artificial turf; c 1ijk This represents the data on human factors affecting the durability of the k-th type of turf at the j-th current data collection point in the i-th sub-region to be laid artificial turf.

[0118] S32. Preset the initial height data for planting artificial turf in each sub-region of the artificial turf to be laid in the set of sub-regions, and obtain the initial height dataset for planting artificial turf. This represents the preset initial planting height data of the i-th sub-region in the set of sub-regions to be covered with artificial turf; the initial area data of each sub-region in the set of sub-regions to be covered with artificial turf are measured to obtain the initial planting area dataset. This represents the initial area data of the i-th sub-region in the set of sub-regions where artificial turf is to be laid;

[0119] S4. Combine the data matrix of natural influencing factors of durability to be laid, the data matrix of human influencing factors of durability to be laid, the height difference mapping model, and the area difference mapping model to optimize the initial height data and area data of each sub-region in the area to be laid artificial turf, so as to obtain the final initial height dataset and the final initial area dataset of grass to be laid.

[0120] S4 includes the following steps:

[0121] S41. Input the initial height dataset of grass to be laid, the data matrix of natural influencing factors for durability to be laid, and the data matrix of human influencing factors for durability to be laid into the height difference mapping model for mapping to obtain the initial height difference dataset; input the initial area dataset of grass to be laid, the data matrix of natural influencing factors for durability to be laid, and the data matrix of human influencing factors for durability to be laid into the area difference mapping model for mapping to obtain the initial area difference dataset;

[0122] The difference between the initial height dataset of the grass to be laid and the dataset of differences between the initial heights to be laid is calculated to obtain the final height dataset of the grass to be laid. This represents the final planting height data of the i-th sub-region in the set of sub-regions to be covered with artificial turf; then, the difference between the data corresponding to the initial planting area dataset and the initial planting area difference dataset is calculated to obtain the final planting area dataset. This represents the final grass planting area data of the i-th sub-region in the set of sub-regions to be covered with artificial turf;

[0123] S42. Adjust the initial height dataset and initial area dataset of the grass to be laid according to the final height dataset and the final area dataset of the grass to be laid to obtain the final initial height dataset and the final initial area dataset of the grass to be laid.

[0124] S42 includes the following steps:

[0125] S421. Based on the initial height dataset of grass to be laid and the initial area dataset of grass to be laid, set the corresponding final grass height threshold and final grass area threshold to obtain the final grass height threshold set and the final grass area threshold set.

[0126] S422. When there is a final grass height data in the final grass height dataset that is less than the final grass height threshold corresponding to the final grass height threshold set, or a final grass area data in the final grass area dataset that is less than the final grass area threshold corresponding to the final grass area threshold set, the initial grass height dataset and the initial grass area dataset are adjusted until there is no final grass height data in the final grass height dataset that is less than the final grass height threshold corresponding to the final grass height threshold set, and no final grass area data in the final grass area dataset that is less than the final grass area threshold corresponding to the final grass area threshold set, thus obtaining the final initial grass height dataset and the final initial grass area dataset.

[0127] The adjustment of the initial height dataset and the initial area dataset of the grass to be laid in S422 includes the following steps:

[0128] S4221. Optimize tuna population by constructing grass planting height and area. Let d represent the i-th tuna in the grass height and area optimization tuna population, and let d represent the size of the grass height and area optimization tuna population; set the maximum number of iterations for the grass height and area optimization tuna population as d1′ and the current number of iterations as d2′; set the search space dimension of the grass height and area optimization tuna population as 2·c′.

[0129] S4222: Set the range of planting height for laying artificial turf in the area to be laid and the range of area for each sub-area in the area to be laid, to obtain the planting height range. and the set of sub-region area intervals These represent the lower limit and upper limit of the planting height for laying artificial turf in the area to be covered, respectively. as follows,

[0130]

[0131] in, These represent the lower limit and upper limit of the area of ​​the i-th sub-region in the area to be laid artificial turf, respectively;

[0132] Based on the grass height range and the sub-region area range set, the initial position of each tuna in the tuna population is optimized by setting the grass height and area, resulting in an initial position matrix set. The matrix representing the initial position of the i-th tuna in the tuna population optimized by the grass planting height-area ratio is as follows:

[0133]

[0134] in, The initial position of the i-th tuna in the tuna population in the grass height area optimization is represented by the position component of the initial grass height dimension in the j-th sub-region of the artificial turf area to be laid; The component of the initial position of the i-th tuna in the tuna population in the area to be laid artificial turf is represented by the area dimension of the j-th sub-region in the area to be laid artificial turf. The calculation formulas are as follows:

[0135]

[0136] In the formula, rand i1j rand i2j They represent respectively targeting Generate random numbers between 0 and 1;

[0137] S4223, Based on the dataset of the final height of the grass to be laid. and the final area dataset of grass to be laid The fitness function e for optimizing the grass planting height and area of ​​a tuna population is constructed as follows:

[0138]

[0139] S4224. Start the iteration. Before the iteration, set the current iteration number d2′ to 1. In the first iteration, the fitness function e of the tuna population is optimized by grass planting height and area. The fitness value of the initial position matrix of each tuna in the initial position matrix set is calculated by using the height difference mapping model and the area difference mapping model, and a first fitness value set is obtained. The fitness value with the largest fitness value in the first fitness value set and the corresponding initial position matrix of the tuna are taken as the first global best fitness and the first global best position. The initial position matrix of each tuna in the initial position matrix set is updated according to the first global best fitness and the first global best position. After the update is completed, the current iteration number d2′ is incremented by 1 and the next iteration is started.

[0140] In each iteration, the fitness function e of the grass-planting height-area optimization tuna population is used, along with the height difference mapping model and the area difference mapping model, to calculate the fitness value of the position matrix of each tuna in the grass-planting height-area optimization tuna population updated in the previous iteration, thus obtaining a second fitness value set. The fitness value with the largest fitness value in the second fitness value set and the corresponding tuna position matrix are taken as the second global best fitness and the second global best position. The position matrix of each tuna in the grass-planting height-area optimization tuna population updated in the previous iteration is updated again based on the second global best fitness and the second global best position. After the update is completed, the current iteration number d2′ is incremented by 1 and the next iteration begins.

[0141] S4225. When d2′≥d1′, stop the iteration and obtain the final global optimal position matrix; otherwise, continue the iteration until d2′≥d1′; divide the data in the final global optimal position to obtain the optimized initial height dataset and the optimized initial area dataset; input the optimized initial height dataset, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability into the height difference mapping model for mapping to obtain the optimized height difference dataset; and input the optimized initial height dataset, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability into the height difference mapping model for mapping to obtain the optimized height difference dataset; The initial area dataset to be laid, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability are input into the area difference mapping model for mapping to obtain the optimized area difference dataset. The difference between the optimized initial height dataset and the optimized height difference dataset, and the difference between the optimized initial area dataset and the optimized area difference dataset, are calculated to obtain the optimized final height dataset and the optimized final area dataset.

[0142] If the optimized final height dataset for grass to be laid does not contain any final grass height data that is less than the final grass height threshold corresponding to the final grass height threshold set, and the optimized final area dataset for grass to be laid does not contain any final area data that is less than the final grass area threshold corresponding to the final grass area threshold set, then the optimized initial height dataset for grass to be laid and the optimized initial area dataset for grass to be laid are respectively used as the final initial height dataset for grass to be laid and the final initial area dataset for grass to be laid; otherwise, return to S4224 to continue iterating until the optimized final height dataset for grass to be laid does not contain any final grass height data that is less than the final grass height threshold corresponding to the final grass height threshold set, and the optimized final area dataset for grass to be laid does not contain any final area data that is less than the final grass area threshold corresponding to the final grass area threshold set.

[0143] Example 2

[0144] This embodiment discloses a big data-based artificial turf planting process parameter control system. The system can implement the methods of the above embodiment, including an existing artificial turf area division module, an existing planting data acquisition module, a first durability influencing factor data acquisition module, a planting data difference calculation and acquisition module, a mapping model construction module, a second durability influencing factor data acquisition module, a final planting data calculation module for the artificial turf to be laid, and a planting initial parameter optimization module.

[0145] The existing artificial turf area division module is used to divide multiple existing artificial turf areas to obtain an existing artificial turf sub-region matrix.

[0146] The existing grass planting data acquisition module is used to collect the initial average grass planting height data and the initial grass planting area data of each sub-region in the existing artificial turf sub-region matrix, and to obtain the existing grass planting initial average height data matrix and the existing grass planting initial area data matrix.

[0147] The first durability influencing factor data acquisition module is used to collect the durability natural influencing factor data and durability human influencing factor data of each sub-region in the existing artificial turf sub-region matrix, and obtain the historical turf durability natural influencing factor data matrix set and the historical turf durability human influencing factor data matrix.

[0148] The grass planting data difference calculation and acquisition module is used to calculate the difference between the existing grass initial height average data matrix and the existing grass initial area data matrix and the corresponding final height average data and area data, and take the absolute value to obtain the existing grass average height difference data matrix and the existing grass area difference data matrix.

[0149] The mapping model construction module is used to construct a height difference mapping model and an area difference mapping model using the existing grass initial average height data matrix, the existing grass initial area data matrix, the historical lawn durability natural influencing factor data matrix set, the historical lawn durability human influencing factor data matrix, the existing grass average height difference data matrix, and the existing grass area difference data matrix.

[0150] The second durability influencing factor data acquisition module is used to collect durability natural influencing factor data and durability human influencing factor data for each sub-area in the area where artificial turf is to be laid, and to obtain the durability natural influencing factor data matrix and the durability human influencing factor data matrix set.

[0151] The final data calculation module for artificial turf to be laid is used to use the initial height data, area data, natural influencing factor data matrix, and human influencing factor data matrix set of each sub-region in the area to be laid artificial turf, and to map and calculate the final data of artificial turf to be laid in conjunction with the height difference mapping model and the area difference mapping model, so as to obtain the final height dataset and the final area dataset of artificial turf to be laid.

[0152] The initial grass planting parameter optimization module is used to optimize the initial grass planting height data and area data of each sub-region in the artificial turf area to be laid based on the final grass planting height dataset and the final grass planting area dataset, so as to obtain the final initial grass planting height dataset and the final initial grass planting area dataset.

[0153] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0154] The preferred embodiments of the invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method for controlling artificial turf planting process parameters based on big data, characterized in that, Includes the following steps: S1. Collect initial average grass height data, initial grass area data, durability natural influencing factor data and durability human influencing factor data for each sub-region in multiple existing artificial turf areas, and obtain the existing grass initial average height data matrix, the existing grass initial area data matrix, the historical turf durability natural influencing factor data matrix set and the historical turf durability human influencing factor data matrix. S2. Construct a height difference mapping model and an area difference mapping model using the existing average initial grass height data matrix, the existing initial grass area data matrix, the historical natural influencing factors data matrix set, the historical human influencing factors data matrix set, and the corresponding final grass height and area data. S3. Collect data on the natural and human factors affecting durability of each sub-region in the area where artificial turf is to be laid, and obtain the data matrix of the natural and human factors affecting durability of the artificial turf to be laid. S4. Combine the data matrix of natural influencing factors for durability to be laid, the data matrix of human influencing factors for durability to be laid, the height difference mapping model, and the area difference mapping model to optimize the initial height data and area data of each sub-region in the area to be laid artificial turf, so as to obtain the final initial height dataset and the final initial area dataset of the grass to be laid.

2. The method for controlling artificial turf planting process parameters based on big data according to claim 1, characterized in that, S1 includes the following steps: S11. Measure the initial average grass height data and initial grass area data in multiple artificial turf sub-regions to obtain the existing grass initial average height data matrix and the existing grass initial area data matrix. S12. Set a set of natural factors affecting lawn durability and a set of anthropogenic factors affecting lawn durability; set multiple historical data collection time points to obtain a set of historical collection time points; collect data on each type of natural factor affecting lawn durability in each existing artificial turf area at each historical collection time point according to the set of natural factors affecting lawn durability and the set of historical collection time points to obtain a set of historical natural factors affecting lawn durability data; collect data on each type of anthropogenic factors affecting lawn durability in each existing artificial turf sub-area at each historical collection time point according to the set of anthropogenic factors affecting lawn durability and the set of historical collection time points to obtain a set of historical anthropogenic factors affecting lawn durability data. S13. At the last historical collection time point in the historical collection time point set, collect the average grass height data and grass area data of each sub-region to obtain the current average grass height data matrix and the current average grass area data matrix; subtract the current average grass height data matrix from the current average grass height data matrix and take the absolute value to obtain the current average grass height difference data matrix; subtract the current average grass area data matrix from the current average grass area data matrix and take the absolute value to obtain the current average grass area difference data matrix.

3. The method for controlling artificial turf planting process parameters based on big data according to claim 2, characterized in that, S2 includes the following steps: S21. Construct a height difference mapping model using the existing average initial height data matrix of grass planting, the historical natural influencing factors data matrix set of lawn durability, the historical human influencing factors data matrix of lawn durability, and the existing average height difference data matrix of grass planting. S22. Construct an area difference mapping model using the existing initial grass planting area data matrix, the historical lawn durability natural influencing factor data matrix set, the historical lawn durability human influencing factor data matrix, and the existing grass planting area difference data matrix.

4. The method for controlling artificial turf planting process parameters based on big data according to claim 3, characterized in that: The height difference mapping model uses an SVM model.

5. The method for controlling artificial turf planting process parameters based on big data according to claim 3, characterized in that, The area difference mapping model uses the SVM model.

6. The method for controlling artificial turf planting process parameters based on big data according to claim 5, characterized in that, S3 includes the following steps: S31. Define the area to be laid with artificial turf; divide the area to be laid with artificial turf into sub-areas to obtain a set of sub-areas for artificial turf; define multiple current data collection time points to obtain a set of current time points; predict the natural and human factors affecting durability of each sub-area in the set of sub-areas for artificial turf to be laid based on the set of current time points, the set of natural and human factors affecting turf durability, and obtain a set of natural and human factors affecting durability data to be laid. S32. Preset the initial height data of artificial turf planting in each sub-region of the artificial turf to be laid sub-region set to obtain the initial height dataset of artificial turf to be laid; measure the initial area data of each sub-region of the artificial turf to be laid sub-region set to obtain the initial area dataset of artificial turf to be laid.

7. The method for controlling artificial turf planting process parameters based on big data according to claim 6, characterized in that, S4 includes the following steps: S41. Input the initial height dataset of the grass to be laid, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability into the height difference mapping model for mapping to obtain the initial height difference dataset; input the initial area dataset of the grass to be laid, the data matrix of natural influencing factors for durability, and the data matrix of human influencing factors for durability into the area difference mapping model for mapping to obtain the initial area difference dataset; subtract the data corresponding to the initial height dataset of the grass to be laid and the initial height difference dataset to obtain the final height dataset of the grass to be laid; then subtract the data corresponding to the initial area dataset of the grass to be laid and the initial area difference dataset to obtain the final area dataset of the grass to be laid. S42. Adjust the initial height dataset and initial area dataset of the grass to be laid according to the final height dataset and the final area dataset of the grass to be laid to obtain the final initial height dataset and the final initial area dataset of the grass to be laid.

8. The method for controlling artificial turf planting process parameters based on big data according to claim 7, characterized in that, S42 includes the following steps: S421. Based on the initial height dataset of grass to be laid and the initial area dataset of grass to be laid, set the corresponding final grass height threshold and final grass area threshold to obtain the final grass height threshold set and the final grass area threshold set. S422. When there is a final grass height data in the final grass height dataset that is less than the final grass height threshold corresponding to the final grass height threshold set, or when there is a final grass area data in the final grass area dataset that is less than the final grass area threshold corresponding to the final grass area threshold set, the initial grass height dataset and the initial grass area dataset to be laid are adjusted to obtain the final initial grass height dataset and the final initial grass area dataset to be laid.

9. The method for controlling artificial turf planting process parameters based on big data according to claim 8, characterized in that, The adjustment of the initial height dataset and the initial area dataset of the grass to be laid in S422 includes the following steps: S4221. Construct a grass-planted height-area optimized tuna population; set the maximum number of iterations for the grass-planted height-area optimized tuna population as d1′ and the current number of iterations as d2′; S4222. Set the range of grass planting height for laying artificial turf in the area to be laid and the range of area values ​​for each sub-region in the area to be laid, to obtain a set of grass planting height ranges and sub-region area ranges; set the initial position of each tuna in the tuna population based on the grass planting height ranges and sub-region area ranges, to obtain an initial position matrix set. S4223. Construct a fitness function for optimizing the grass height and area of ​​the tuna population based on the final height dataset of the grass to be laid and the final area dataset of the grass to be laid. S4224. Start the iteration; in each iteration, the fitness function of the grass height and area optimization tuna population is used, and the fitness value of the position matrix of each tuna in the grass height and area optimization tuna population updated in the previous iteration is calculated in conjunction with the height difference mapping model and the area difference mapping model. The position matrix of each tuna in the grass height and area optimization tuna population updated in the previous iteration is then updated. S4225. When d2′≥d1′, stop the iteration and obtain the final global optimal position matrix; otherwise, continue the iteration until d2′≥d1′; based on the final global optimal position, obtain the final initial height dataset of grass to be laid and the final initial area dataset of grass to be laid.

10. A system for implementing the method for controlling artificial turf planting process parameters based on big data as described in any one of claims 1-9.

Images