An intelligent pruning decision-making method for oil tea trees based on digital twin

Abstract

The present invention provides an intelligent pruning decision-making method for oil tea trees based on digital twins. First, real-time data obtained from the physical space is used to establish the digital space for oil tea tree pruning, which includes an oil tea tree pruning twin database, an oil tea tree digital model, and a digital oil tea tree pruning decision-making system. The oil tea tree digital model is driven by the data in the oil tea tree pruning twin database, and the data of the oil tea tree digital model is transmitted to the pruning decision-making system to formulate a preliminary oil tea tree pruning plan. Then, digital pruning of the oil tea tree is carried out according to the pruning plan. After digital pruning, the oil tea tree digital model is reconstructed and the growth prediction model of the oil tea tree is used to simulate the growth of the oil tea tree after pruning. Finally, the simulation results are fed back to the pruning decision-making system to determine whether the growth status of the oil tea tree is qualified. If it is not qualified, the pruning plan is modified in real time through the oil tea pruning expert system in the pruning decision-making system until it is qualified. If it is qualified, pruning is carried out in the physical space.

Description

Technical Field

[0001] The present invention belongs to the technical field of fruit tree pruning, and more specifically, relates to an intelligent pruning decision-making method for Camellia oleifera trees based on digital twin. Background Art

[0002] Camellia oleifera is an important economic tree species in China. The camellia oil obtained from the processing of its seeds is high-quality edible oil, and the unsaturated fatty acids and various physiological active components contained therein can ensure human health. Due to mixed varieties and extensive management, low yield and low efficiency have occurred, seriously affecting the sustainable development of the Camellia oleifera industry in China. Pruning is one of the important technical measures to ensure high and stable yields of Camellia oleifera. However, at present, most of the pruning of Camellia oleifera trees is carried out manually, and manual pruning mostly relies on experience. It is difficult to maximize the yield of the pruned Camellia oleifera trees. Even though the current pruning agronomy of Camellia oleifera trees is relatively complete, such as CN106818262A and CN106258739A relatively comprehensively introduce the pruning agronomy of Camellia oleifera trees from the seedling stage, the degree to which pruning workers master the pruning agronomy is uneven. Therefore, there is an urgent need for a method that can correctly guide manual pruning of Camellia oleifera trees, so as to reduce the impact of low yield caused by pruning. Summary of the Invention

[0003] An object of the present invention is to provide an intelligent pruning decision-making method for Camellia oleifera trees based on digital twin to improve at least some of the above problems.

[0004] The technical problems solved by the present invention are realized by adopting the following technical solutions:

[0005] An intelligent pruning decision-making method for oil tea trees based on digital twins, characterized in that first, the real-time data obtained from the physical space is used to establish the digital space for oil tea tree pruning. The digital space for oil tea tree pruning includes an oil tea tree pruning twin database, an oil tea tree digital model, and a digital oil tea tree pruning decision-making system. The oil tea tree digital model includes an oil tea tree three-dimensional solid model and an oil tea tree growth prediction model. The digital oil tea tree pruning decision-making system includes an oil tea pruning expert system and an oil tea tree light transmittance detection model. The oil tea pruning expert system includes an oil tea tree pruning determination model, an oil tea tree growth database, and an oil tea tree pruning agronomic knowledge base. Secondly, the data in the oil tea tree pruning twin database drives the oil tea tree digital model, and the data of the oil tea tree digital model is transmitted to the digital oil tea tree pruning decision-making system to formulate a preliminary oil tea tree pruning plan. Then, digital pruning of the oil tea tree is carried out according to the pruning plan. After digital pruning, the oil tea tree digital model is reconstructed and the oil tea tree growth prediction model is used to simulate the growth situation of the oil tea tree after pruning. Finally, the simulation results are fed back to the digital oil tea tree pruning decision-making system to judge whether the growth status of the oil tea tree is qualified. If it is not qualified, the oil tea tree pruning plan is modified in real time through the oil tea pruning expert system in the digital oil tea tree pruning decision-making system until it is qualified. If it is qualified, pruning is carried out in the physical space. The specific steps are as follows:

[0006] Step 1: Establish the digital space for oil tea tree pruning

[0007] Step 1.1: Obtain real-time data to establish the oil tea tree pruning twin database

[0008] Install various sensors in the physical oil tea tree planting base to obtain real-time dynamic information of physical entities such as the geometric size parameters of oil tea trees and their branches, the growth of oil tea tree fruits, light intensity, humidity, temperature, soil, air, and staff, and transmit them to the digital space for oil tea tree pruning in real time to establish the oil tea tree pruning twin database;

[0009] Step 1.2: Establish the oil tea tree digital model

[0010] Establish an oil tea tree digital model according to the oil tea tree pruning twin database obtained in Step 1.1, including an oil tea tree three-dimensional solid model and an oil tea tree growth prediction model;

[0011] Step 1.3: Establish the digital oil tea tree pruning decision-making system

[0012] Establish a digital oil tea tree pruning decision-making system through the oil tea tree pruning twin database obtained in Step 1.1 and the agronomic requirements for oil tea tree pruning. The digital oil tea tree pruning decision-making system includes two parts: an oil tea tree light transmittance detection model and an oil tea pruning expert system. The oil tea pruning expert system includes an oil tea tree pruning determination model, an oil tea tree growth database, and an oil tea tree pruning agronomic knowledge base. The oil tea tree pruning determination model is a determination model formed by machine learning through collecting a large number of picture samples of branches to be pruned;

[0013] Step 1.4: Preliminary determination of the oil tea tree pruning plan

[0014] By transmitting the oil tea tree twin data to the digital oil tea tree pruning decision-making system established in Step 1.3, the corresponding oil tea tree light transmittance, the positions and quantities of the oil tea tree branches to be pruned can be obtained. Combining with the oil tea tree pruning agronomic knowledge base, the system formulates a preliminary pruning plan;

[0015] Step 1.5: Perform digital pruning of the oil tea tree and growth simulation of the oil tea tree

[0016] After performing digital pruning according to the preliminary pruning plan determined in Step 1.4, return to the digital model of the oil tea tree again, revise the three-dimensional solid model of the oil tea tree, and then use the oil tea tree growth prediction model to perform growth simulation on the pruned oil tea tree, and finally obtain the simulation results;

[0017] Step 1.6: Analyze the simulation results to verify the feasibility of the pruning plan

[0018] Transmit the calculation and simulation results obtained in Step 1.5 to the oil tea pruning expert system in the digital oil tea tree pruning decision-making system again. Through the comparison of the growth status indicators of the oil tea tree by the oil tea pruning expert system, judge whether the pruning plan is feasible. If the plan is feasible, proceed to the next step. If the plan is not feasible, repeat Step 1.5 to Step 1.6 according to the modification suggestions given by the oil tea pruning expert system until the plan passes;

[0019] Step 2: Execute the pruning plan in the physical space

[0020] According to the final pruning plan obtained in Step 1.6, guide the staff to perform physical pruning operations in the physical space.

[0021] Furthermore, in Step 1, the physical entity dynamic information includes but is not limited to the geometric dimension parameters of the oil tea tree and its branches, the growth of oil tea tree fruits, light intensity, humidity, temperature, soil, air, and the staff.

[0022] Further, in the step 1, the oil tea pruning expert system in the digital oil tea pruning decision-making system can give suggestions on oil tea pruning while receiving data, formulate pruning plans, and judge the simulation results of the digital model. The oil tea pruning agronomic knowledge base contains the pruning agronomic knowledge of all varieties of oil tea trees, and the oil tea tree growth database contains the standard intervals of the growth condition indicators of all varieties of oil tea trees every year.

[0023] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are as follows:

[0024] 1. The present invention can obtain real-time information such as the geometric size parameters of oil tea trees and oil tea branches, the growth of oil tea tree fruits, light intensity, humidity, temperature, soil, air, and staff. And through the digital oil tea pruning decision-making system in the digital oil tea pruning space, a relatively high-yield pruning plan can be formulated, and through the verification and judgment of the simulation results of the oil tea tree digital model in the digital oil tea pruning space, the pruning plan can be modified in real time, and finally a reasonable pruning plan can be obtained.

[0025] 2. The digital oil tea pruning decision-making system in the present invention can give relatively reliable suggestions for oil tea tree pruning in real time, conduct simulations of the oil tea tree digital model, and make judgment decisions on the simulation results. Finally, a relatively high-yield pruning plan is obtained, which increases the rationality and feasibility of pruning in the physical space and reduces the risk of low yield of oil tea trees caused by incorrect pruning. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0027] Figure 1 It is a flowchart of the intelligent oil tea pruning decision-making method based on digital twin in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] In order to make the technical means, creative features, achieved purposes, and functions of the present invention easy to understand and clear, the present invention will be further described below in conjunction with specific embodiments.

[0029] An intelligent pruning decision-making method for oil tea trees based on digital twins, characterized in that, first, the real-time data obtained from the physical space is used to establish the digital space for oil tea tree pruning. The digital space for oil tea tree pruning includes an oil tea tree pruning twin database, an oil tea tree digital model, and a digital oil tea tree pruning decision-making system. The oil tea tree digital model includes an oil tea tree three-dimensional solid model and an oil tea tree growth prediction model. The digital oil tea tree pruning decision-making system includes an oil tea pruning expert system and an oil tea tree light transmittance detection model. The oil tea pruning expert system includes an oil tea tree pruning determination model, an oil tea tree growth database, and an oil tea tree pruning agronomic knowledge base. Secondly, the data in the oil tea tree pruning twin database drives the oil tea tree digital model, and the data of the oil tea tree digital model is transmitted to the digital oil tea tree pruning decision-making system to formulate a preliminary oil tea tree pruning plan. Then, digital pruning of the oil tea tree is carried out according to the pruning plan. After digital pruning, the oil tea tree digital model is reconstructed and the oil tea tree growth prediction model is used to simulate the growth situation of the oil tea tree after pruning. Finally, the simulation results are fed back to the digital oil tea tree pruning decision-making system to judge whether the growth status of the oil tea tree is qualified. If it is not qualified, the oil tea tree pruning plan is modified in real time through the oil tea pruning expert system in the digital oil tea tree pruning decision-making system until it is qualified. If it is qualified, pruning is carried out in the physical space. The specific steps are as follows:

[0030] Step 1: Establish the digital space for oil tea tree pruning

[0031] Step 1.1: Obtain real-time data to establish the oil tea tree pruning twin database

[0032] Install various sensors in the physical oil tea tree planting base to obtain real-time dynamic information of physical entities including the geometric size parameters of the oil tea tree and its branches, the growth of oil tea tree fruits, light intensity, humidity, temperature, soil, air, and staff, and transmit it to the digital space for oil tea tree pruning in real time to establish the oil tea tree pruning twin database;

[0033] Step 1.2: Establish the oil tea tree digital model

[0034] Establish an oil tea tree digital model according to the oil tea tree pruning twin database obtained in Step 1.1, which includes an oil tea tree three-dimensional solid model and an oil tea tree growth prediction model;

[0035] Step 1.3: Establish the digital oil tea tree pruning decision-making system

[0036] A digital oil tea tree pruning decision-making system is established through the oil tea tree pruning twin database obtained in Step 1.1 and the agronomic requirements for oil tea tree pruning. The digital oil tea tree pruning decision-making system includes two parts: an oil tea tree light transmittance detection model and an oil tea pruning expert system. The oil tea pruning expert system includes an oil tea tree pruning determination model, an oil tea tree growth database, and an oil tea tree pruning agronomic knowledge base. The oil tea tree pruning determination model is a determination model formed by machine learning through collecting a large number of picture samples of branches to be pruned;

[0037] Step 1.4: Initial determination of the oil tea tree pruning plan

[0038] By transmitting the oil tea tree twin data to the digital oil tea tree pruning decision-making system established in Step 1.3, the corresponding oil tea tree light transmittance, the positions and quantities of the oil tea tree branches to be pruned can be obtained. Combining with the oil tea tree pruning agronomic knowledge base, the system formulates a preliminary pruning plan;

[0039] Step 1.5: Perform digital pruning of the oil tea tree and growth simulation of the oil tea tree

[0040] After performing digital pruning according to the preliminary pruning plan determined in Step 1.4, return to the digital model of the oil tea tree again, revise the three-dimensional solid model of the oil tea tree, and then use the oil tea tree growth prediction model to perform growth simulation on the pruned oil tea tree, and finally obtain the simulation result;

[0041] Step 1.6: Analyze the simulation result to verify the feasibility of the pruning plan

[0042] Transmit the calculation and simulation results obtained in Step 1.5 to the oil tea pruning expert system in the digital oil tea tree pruning decision-making system again. Through the comparison of the oil tea tree growth status indicators by the oil tea pruning expert system, judge whether the pruning plan is feasible. If the plan is feasible, proceed to the next step. If the plan is not feasible, repeat Steps 1.5 to 1.6 according to the modification suggestions given by the oil tea pruning expert system until the plan is passed;

[0043] Step 2: Execute the pruning plan in the physical space

[0044] According to the final pruning plan obtained in Step 1.6, guide the staff to perform physical pruning operations in the physical space.

[0045] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent pruning decision-making method for oil tea trees based on digital twins, characterized in that, First, establish the digital space for Camellia oleifera pruning from the real-time data obtained from the physical space. The digital space for Camellia oleifera pruning includes the Camellia oleifera pruning twin database, the digital model of Camellia oleifera, and the digital decision-making system for Camellia oleifera pruning. The digital model of Camellia oleifera includes the three-dimensional solid model of Camellia oleifera and the growth prediction model of Camellia oleifera. The digital decision-making system for Camellia oleifera pruning includes the expert system for Camellia oleifera pruning and the light transmittance detection model of Camellia oleifera. The expert system for Camellia oleifera pruning includes the pruning determination model of Camellia oleifera, the growth database of Camellia oleifera, and the pruning agronomic knowledge base of Camellia oleifera. Secondly, the data in the Camellia oleifera pruning twin database drives the digital model of Camellia oleifera, and the data of the digital model of Camellia oleifera is transmitted to the digital decision-making system for Camellia oleifera pruning to formulate a preliminary pruning plan for Camellia oleifera. Then, perform digital pruning on Camellia oleifera according to the pruning plan. After digital pruning, reconstruct the digital model of Camellia oleifera and use the growth prediction model of Camellia oleifera to simulate the growth of Camellia oleifera after pruning. Finally, feedback the simulation results to the digital decision-making system for Camellia oleifera pruning to judge whether the growth status of Camellia oleifera is qualified. If it is unqualified, the pruning plan of Camellia oleifera is modified in real time through the expert system for Camellia oleifera pruning in the digital decision-making system for Camellia oleifera pruning until it is qualified. If it is qualified, pruning is carried out in the physical space. The specific steps are as follows: Step 1: Establish the digital space for Camellia oleifera pruning Step 1.1: Obtain real-time data to establish the Camellia oleifera pruning twin database Install various sensors in the physical Camellia oleifera planting base to obtain real-time dynamic information of physical entities such as the geometric size parameters of Camellia oleifera and its branches, the growth of Camellia oleifera fruits, light intensity, humidity, temperature, soil, air, and workers, and transmit it to the digital space for Camellia oleifera pruning in real time to establish the Camellia oleifera pruning twin database; Step 1.2: Establish the digital model of Camellia oleifera Establish the digital model of Camellia oleifera according to the Camellia oleifera pruning twin database obtained in Step 1.1, including the three-dimensional solid model of Camellia oleifera and the growth prediction model of Camellia oleifera; Step 1.3: Establish the digital decision-making system for Camellia oleifera pruning Establish the digital decision-making system for Camellia oleifera pruning through the Camellia oleifera pruning twin database obtained in Step 1.1 and the agronomic requirements for Camellia oleifera pruning. The digital decision-making system for Camellia oleifera pruning includes two parts: the light transmittance detection model of Camellia oleifera and the expert system for Camellia oleifera pruning. The expert system for Camellia oleifera pruning includes the pruning determination model of Camellia oleifera, the growth database of Camellia oleifera, and the pruning agronomic knowledge base of Camellia oleifera. The pruning determination model of Camellia oleifera is a determination model formed by machine learning by collecting a large number of picture samples of branches to be pruned; Step 1.4: Preliminary determination of the pruning plan for Camellia oleifera By transmitting the twin data of Camellia oleifera to the digital decision-making system for Camellia oleifera pruning established in Step 1.3, the corresponding light transmittance of Camellia oleifera, the positions and quantities of branches to be pruned of Camellia oleifera can be obtained, and a preliminary pruning plan is formulated by the system in combination with the pruning agronomic knowledge base of Camellia oleifera; Step 1.5: Perform digital pruning on Camellia oleifera and simulate the growth of Camellia oleifera After performing digital pruning according to the preliminary pruning plan determined in Step 1.4, the digital model of the oil tea tree is returned again, the three-dimensional solid model of the oil tea tree is corrected again, and then the growth prediction model of the oil tea tree is used to simulate the growth of the pruned oil tea tree, and finally the simulation results are obtained; Step 1.6: Analyze the simulation results to verify the feasibility of the pruning plan Transmit the calculation and simulation results obtained in Step 1.5 to the oil tea pruning expert system in the digital oil tea tree pruning decision-making system again. Through the oil tea pruning expert system, compare the growth condition indicators of the oil tea tree to determine whether the pruning plan is feasible. If the plan is feasible, proceed to the next step. If the plan is not feasible, repeat Steps 1.5 to 1.6 according to the modification suggestions given by the oil tea pruning expert system until the plan is passed; Step 2: Execute the pruning plan in the physical space According to the final pruning plan obtained in Step 1.6, guide the staff to perform physical pruning operations in the physical space.

2. The intelligent oil tea tree pruning decision-making method based on digital twin according to claim 1, wherein The oil tea pruning expert system in the digital oil tea tree pruning decision-making system can give suggestions on oil tea tree pruning, formulate pruning plans, and judge the simulation results of the digital model while receiving data. The oil tea pruning agronomic knowledge base contains the pruning agronomic knowledge of all varieties of oil tea trees, and the oil tea tree growth database contains the standard intervals of the growth condition indicators of all varieties of oil tea trees every year.

Images