Intelligent manufacturing system and method for lotus root quality-improving synergist based on digital twinborn technology

Abstract

The invention belongs to agricultural intelligent manufacturing, and provides an intelligent manufacturing system and method for a lotus root quality-improving synergist based on digital twinning. The system comprises a data acquisition module, a digital twinborn decision module, a quality improvement synergist module and an intelligent application device. Collecting water depth, water temperature, conductivity, illumination and growth data; the decision-making module constructs a twinborn model, and generates a formula, a dose and a path in combination with growth response, time sequence prediction and rolling optimization; the synergist contains a pH response growth regulator and porous slow-release full-nutrient particles; the application device has a spraying mode and an injection mode which are automatically switched. According to the scheme, sensing-modeling-closed loop release is realized, the quality and the yield are improved, and the bad lotus root rate is reduced.

Description

Technical Field

[0001] This invention relates to the intersection of agricultural biotechnology, intelligent agricultural equipment, and digital twin technology, and more specifically to an intelligent manufacturing system and method for lotus root quality improvement and efficiency enhancement agents based on digital twin technology. Background Technology

[0002] Lotus root, as one of my country's important aquatic economic crops, not only has high edible and nutritional value but also has wide applications in food processing, medicine, and health care. In recent years, with increasing market demand and expanding planting areas, the lotus root industry has gradually become an important part of specialty agriculture in some regions. However, under the existing cultivation model, lotus root production still faces several prominent problems.

[0003] First, lotus roots have a unique growing environment, typically found in shallow water or muddy conditions. Their yield and quality are influenced by a combination of environmental factors, including water depth, water temperature, light, electrical conductivity, and pH. Current cultivation methods rely primarily on manual experience and lack refined monitoring and dynamic analysis of environmental parameters, resulting in often delayed and incomplete implementation measures.

[0004] Secondly, current fertilization and regulation methods are relatively extensive. Common fertilizers or regulators are often applied in a single application or in fixed quantities, lacking matching with the needs of lotus roots at different growth stages, easily leading to over- or under-application. On the one hand, over-application can lead to nutrient leaching, eutrophication of water bodies, and even exacerbate lotus root deformities and rotten roots; on the other hand, under-application can result in slow lotus root growth, decreased quality, and inability to meet the high-quality demands of the market.

[0005] Secondly, conventional fertilizers and regulators suffer from rapid dissolution and low utilization rates. Especially in saline-alkali soils or high-conductivity environments, some nutrients are easily fixed or lost, leading to decreased fertilizer efficiency and low crop absorption efficiency. Although there is research on slow-release fertilizers and controlled-release formulations in existing technologies, there is still a lack of precise control methods coupled with environmental factors in the practical application of aquatic crops, especially lotus root.

[0006] Furthermore, existing decision support methods are relatively outdated. Although some regions have explored the application of information management platforms or agricultural IoT, most are still at the stage of data collection and manual analysis, lacking dynamic modeling and prediction based on big data and intelligent algorithms, and thus unable to achieve virtual simulation and real-time optimization of the lotus root growth process.

[0007] In summary, existing lotus root cultivation techniques suffer from problems such as incomplete environmental perception, insufficient decision support, limited application methods, low nutrient utilization efficiency, and poor adaptability to complex environments such as saline-alkali land. There is an urgent need to propose a new system that integrates environmental monitoring, digital twin modeling, intelligent decision-making, and precise application to improve the quality and yield of lotus roots and enhance their adaptability to complex environments. Summary of the Invention

[0008] This invention provides an intelligent manufacturing system and method for lotus root quality-enhancing and efficiency-enhancing agents based on digital twin technology. Environmental and growth data are collected through multi-source sensors and crop monitoring devices to establish a digital twin model of the lotus root. Combining growth response functions, time series prediction, and rolling optimization, a dynamic application plan is output. Application is executed through a dual-mode structure of atomized spraying and mud injection. Combined with a pH-responsive growth regulator and porous slow-release nutrient granules, quality and efficiency enhancement are achieved.

[0009] To achieve the above objectives, the present invention provides the following technical solution:

[0010] A smart manufacturing system for lotus root quality-enhancing and efficiency-enhancing agents based on digital twin technology includes:

[0011] A. Data acquisition module, consisting of multi-source sensors, crop growth monitoring unit, data acquisition and preprocessing unit and environmental / crop database, is used to acquire and process water depth, electrical conductivity, light intensity, water temperature and crop growth feedback data;

[0012] B. Digital twin decision-making module, which virtually maps the lotus root growth process based on the information output by the data acquisition module, including a growth response function, a time series prediction submodule and a rolling optimization submodule, used to output the application dosage, ratio and operation path;

[0013] C. Quality and efficiency enhancement module, including growth regulators and complete nutrient adjuvants, wherein the growth regulators are encapsulated in a pH-responsive carrier and the complete nutrient adjuvants are porous slow-release particles;

[0014] D. Intelligent release device, including atomizing spraying unit, mud injection unit and control module, wherein the control module switches between two release modes according to water depth parameters and executes operations according to instructions from digital twin decision module.

[0015] Preferably, the multi-source sensor includes a water depth sensor, a conductivity sensor, a light sensor, and a water temperature sensor.

[0016] Preferably, the crop growth monitoring unit includes at least one of a remote sensing imaging device, a visual acquisition device, or a manual sampling module.

[0017] Preferably, the data acquisition and preprocessing unit is used to filter, normalize and format the sensor and crop monitoring data, and store it in the environment / crop database.

[0018] Preferably, the growth regulator includes brassinolides, amides, and growth inhibitors, all of which are in a synergistic range with relatively small differences in magnitude.

[0019] Preferably, the complete nutritional adjuvant includes organic chelated trace elements, a silicon-calcium-magnesium inorganic framework, polyglutamic acid, phosphorus- and potassium-solubilizing microorganisms, and a potassium phosphate source, which are spray-dried and coated into porous slow-release particles.

[0020] Preferably, the atomizing spraying unit is suitable for application in shallow water environments, and the mud injection unit is suitable for application in deep water or thick mud environments. The control module automatically switches between the two modes according to the water depth threshold.

[0021] Preferably, when the digital twin decision-making module receives new environmental and crop feedback data, it triggers the rolling optimization submodule to perform iterative updates and outputs the adjusted deployment plan.

[0022] The methods for improving the quality and efficiency of lotus root based on the above system include:

[0023] S1 acquires environmental and crop growth parameters through a data acquisition module and stores them in a database;

[0024] S2 inputs the parameters into the digital twin decision module, and generates a deployment plan through the growth response function, time series prediction submodule and rolling optimization submodule;

[0025] The S3 control system is used to perform the operation of the intelligent application device. The atomizing spraying unit is used in shallow water environments, while the mud injection unit is used in deep water or thick mud environments.

[0026] S4 performs rolling iterative optimization in a loop based on real-time updated data.

[0027] Preferably, the rolling iteration is automatically triggered using a fixed time window or when preset conditions are met, in order to ensure robustness and release economy.

[0028] As can be seen from the above technical solution, compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. This invention achieves comprehensive perception of the lotus root growth environment and crop status through multi-source data acquisition and processing, solving the problem of insufficient environmental monitoring in existing technologies.

[0030] 2. This invention constructs a digital twin decision-making model, which combines growth response function, time series prediction and rolling optimization methods to realize virtual modeling and dynamic optimization of the lotus root growth process. It can promptly correct the planting plan when environmental conditions fluctuate, thereby improving the intelligence level of the system.

[0031] 3. The intelligent application device of the present invention adopts a dual-mode design, which can automatically select the spraying or injection method according to different water depths and mud layer conditions, thereby enhancing the adaptability and flexibility of the application method and avoiding the limitations of a single application mode.

[0032] 4. The pH-responsive growth regulator used in this invention can be rapidly released under near-neutral conditions, while its release is delayed under acidic or alkaline conditions, thus achieving adaptive regulation of the aquatic environment and improving the utilization efficiency of the regulator.

[0033] 5. The fully nutritious slow-release granules of the present invention can gradually release nutrients over a longer period of time, improving nutrient utilization efficiency, reducing loss and waste, and providing a stable source of nutrients for the continuous growth of lotus root.

[0034] 6. This invention can maintain high efficiency under complex stress conditions such as normal environment and saline-alkali land, significantly reduce the rate of bad lotus roots, and improve the quality and yield of lotus roots, and has good prospects for promotion and application. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0036] Figure 1 This is a schematic diagram of the overall system architecture of the present invention.

[0037] Figure 2 This is a logic diagram of the system implementation method of the present invention. Detailed Implementation

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Example 1

[0040] like Figure 1As shown, the overall architecture of the intelligent manufacturing system for lotus root quality improvement and efficiency enhancement agent based on digital twin technology of the present invention includes three parts: perception layer, digital twin decision layer, and manufacturing and execution layer.

[0041] The perception layer consists of multi-source sensors, a crop growth monitoring unit, a data acquisition and preprocessing unit, and an environmental / crop database. The multi-source sensors are used to collect environmental parameters such as water depth, conductivity, light intensity, and water temperature in real time. The crop growth monitoring unit acquires growth status data of lotus plants through remote sensing imagery, visual imaging, or manual sampling. The data acquisition and preprocessing unit filters, normalizes, and formats the sensor and monitoring data, and stores the results in the environmental / crop database, providing reliable input for subsequent modeling.

[0042] The digital twin decision-making layer consists of a digital twin decision-making module. This module establishes a virtual model of lotus root growth, simulates the coupling relationship between light, water temperature and fertility through a growth response function, uses a time series prediction submodule to predict the yield and quality of lotus roots, and a rolling optimization submodule combines environmental and crop feedback data to output the optimal dosage, ratio and operation path, achieving dynamic optimization and closed-loop control.

[0043] The manufacturing and execution layer includes a quality-enhancing agent module and an intelligent dispensing device. The quality-enhancing agent module consists of a growth regulator and a complete nutrient adjuvant. The growth regulator is a pH-responsive encapsulated formulation, and its cumulative release curves under different water conditions are shown in the figure: the release rate is significantly accelerated in the neutral range of pH 1 to 1, while the release is relatively slow under pH 1 conditions, thus ensuring rapid onset of action under suitable conditions and delayed release under slightly acidic conditions, improving environmental adaptability. The complete nutrient adjuvant is a slow-release particle with a porous structure, capable of gradually releasing nutrients over a longer period, improving utilization.

[0044] The intelligent application device includes an atomizing spraying unit, a mud injection unit, and a control module. The control module can automatically switch the application mode according to the water depth threshold. When the water depth is shallow, it drives the atomizing spraying unit to perform spraying operations. When the water depth is deep or the mud layer is thick, it drives the mud injection unit to perform fixed-depth application, thereby ensuring accurate application under different environmental conditions.

[0045] Through the above design, the system of the present invention can realize a complete closed-loop process from environmental perception, digital twin modeling to synergist release, which not only ensures the quality and yield of lotus root growth, but also improves release efficiency and resource utilization.

[0046] Example 2

[0047] In practical applications, the lotus root quality improvement and efficiency enhancement method based on digital twin technology provided by this invention can be implemented according to the following steps:

[0048] First, environmental and crop growth parameters are acquired through the data acquisition module. Multi-source sensors collect aquatic environmental information such as water depth, conductivity, light intensity, and water temperature in real time. The crop growth monitoring unit collects growth status parameters of lotus plants through remote sensing images or visual imaging devices. The relevant data are then filtered and normalized by the data acquisition and preprocessing unit before being stored in the environment / crop database.

[0049] Then, parameters from the environmental / crop database are input into the digital twin decision-making module. The digital twin establishes the coupling relationship between light, water temperature, and fertility through a growth response function, and uses the time series prediction submodule to predict the changing trends of lotus root yield and quality. Based on this, the rolling optimization submodule integrates environmental disturbances and historical data to dynamically output appropriate application dosage, ratio, and operation path. Simultaneously, it combines... Figure 2 The release pattern of the growth regulator shown is that the release rate is significantly increased under neutral proximity conditions of pH 6.5–7.2, while the release is slow under pH 5.0 conditions, thus enabling the digital twin decision results to better match the actual water conditions.

[0050] Next, based on the output scheme of the digital twin decision module, the intelligent delivery device is controlled to perform the delivery operation. When the water depth is detected to be lower than the preset threshold, the control module drives the atomizing spraying unit to spray the synergist evenly; when the water depth is detected to be higher than or equal to the threshold and the mud layer is thick, the mud layer injection unit is driven to inject the synergist into the silt layer at a fixed depth, thus taking into account the delivery needs under different environmental conditions.

[0051] Finally, after deployment, the system continues to acquire new environmental and growth feedback data through multi-source sensors and crop growth monitoring units, triggering the rolling optimization submodule to perform iterative updates, so that the deployment plan can be continuously adjusted according to changes in the environment and crop status, achieving closed-loop control and intelligent management throughout the entire process.

[0052] Through the above methods, the present invention not only ensures the quality and yield of lotus root under different growing conditions, but also improves the efficiency of application and resource utilization, and avoids waste and quality fluctuations caused by excessive or insufficient application.

[0053] Example 3

[0054] In the saline-alkali environment of Guangdong Harbor, the intelligent manufacturing system for lotus root quality improvement and efficiency enhancement based on digital twin technology of this invention was applied and verified in a test.

[0055] First, during the data acquisition phase, the basic environmental conditions of the cultivation area were: a water depth of approximately 0.5 m, a silt conductivity (EC value) of 7.8 mS / cm, and a water pH of 8.1, representing a typical high-salt, high-alkaline environment. Traditionally, such environments easily lead to hindered root and stem enlargement, insufficient starch accumulation, and a high rate of spoiled lotus roots, severely impacting marketability. This invention's system uses multi-source sensors to monitor the aforementioned parameters such as water depth, conductivity, light intensity, and water temperature in real time. Simultaneously, the crop growth monitoring unit uses hyperspectral imagery from a UAV and ground-based visual acquisition devices to quantitatively analyze the leaf color, crown width, and coverage of the lotus plants. The data acquisition and preprocessing unit performs noise filtering and normalization on the raw data and stores it in a unified format in the environmental / crop database to ensure the accuracy and stability of subsequent modeling.

[0056] Secondly, in the model decision-making stage, the digital twin decision-making module operates based on data from the environmental / crop database. Through the growth response function, it simulates the coupled effects of light, water temperature, and fertility on lotus root growth under high salinity conditions, analyzing the inhibitory effect of increased soil conductivity on nutrient absorption rates. The time series prediction submodule uses a Long Short-Term Memory (LSTM) neural network algorithm to predict future yield and quality. The results show that the potential yield per lotus root plant is 2.8 kg, significantly lower than the control value under normal freshwater conditions. The rolling optimization submodule further generates the optimal application plan based on the Q-learning algorithm, determining the dosage of growth regulator to be 80 g / mu and the dosage of total nutrient adjuvant 11 to be 15 kg / mu, and recommending the use of injection mode to avoid rapid nutrient loss in high salinity. The optimization module also provides operational path planning to ensure uniform coverage and reasonable dosage distribution of the drone in complex terrain.

[0057] Secondly, during the execution phase, the intelligent application device, controlled by the control module, dispatches a drone platform to carry out the application operation. The drone first activates the mud injection unit, whose injection needle operates at a rotation speed of 200 rpm, capable of breaking up shallow soil and precisely delivering granules. Under the control module's guidance, the total nutrient adjuvant granules are injected at a fixed depth to 18 cm into the silt layer, thus achieving a high degree of compatibility with the lotus root distribution area and preventing nutrients from being adsorbed by salt or prematurely lost on the surface. Simultaneously, the atomizing spraying unit remains in standby mode, only activating when encountering shallow water or locally low-salinity areas to ensure that resource input matches environmental conditions. The entire application process achieves precise, depth-controlled, and quantitative closed-loop control.

[0058] Finally, in the effect evaluation phase, the system continues to acquire environmental and crop feedback data through multi-source sensors and crop growth monitoring units, and the rolling optimization submodule iteratively corrects the scheme to ensure dynamic matching between nutrient supply and lotus root growth needs. After a complete growth cycle of comparative experiments, the results show that the system of this invention significantly improved the quality and yield of lotus roots under saline-alkali soil conditions. Specifically, the rate of bad lotus roots decreased to 4.3%, a reduction of about 11 percentage points compared to the control group; the content of active substances and starch in the lotus root was greater than 17%, an increase of 15% to 20%; and the yield per mu reached 2830 kg, an increase of about 38% compared to the control group that did not use this system.

[0059] As can be seen from the above application examples, the system of this invention not only performs well in conventional freshwater environments, but also maintains high efficiency in typical saline-alkali environments such as Guangdong Harbor. The key lies in using a digital twin model for prediction and optimization, combined with pH-responsive growth regulators and porous slow-release nutrient granules, to achieve closed-loop control across the entire chain from environmental perception and virtual decision-making to precise delivery. Ultimately, this achieves the dual goals of improving quality and increasing yield in complex stress environments.

[0060] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A smart manufacturing system for lotus root quality improvement and efficiency enhancement agents based on digital twin technology, characterized in that, include: A. Data acquisition module, consisting of multi-source sensors, crop growth monitoring unit, data acquisition and preprocessing unit and environmental / crop database, is used to acquire and process water depth, electrical conductivity, light intensity, water temperature and crop growth feedback data; B. Digital twin decision-making module, which virtually maps the lotus root growth process based on the information output by the data acquisition module, including a growth response function, a time series prediction submodule and a rolling optimization submodule, used to output the application dosage, ratio and operation path; C. Quality and efficiency enhancement module, including growth regulators and complete nutrient adjuvants, wherein the growth regulators are encapsulated in a pH-responsive carrier and the complete nutrient adjuvants are porous slow-release particles; D. Intelligent release device, including atomizing spraying unit, mud injection unit and control module, wherein the control module switches between two release modes according to water depth parameters and executes operations according to instructions from digital twin decision module.

2. The system according to claim 1, characterized in that, The multi-source sensors include a water depth sensor, a conductivity sensor, a light sensor, and a water temperature sensor.

3. The system according to claim 1, characterized in that, The crop growth monitoring unit includes at least one of remote sensing imaging equipment, visual acquisition device, or manual sampling module.

4. The system according to claim 1, characterized in that, The data acquisition and preprocessing unit is used to filter, normalize, and format sensor and crop monitoring data, and store it in the environment / crop database.

5. The system according to claim 1, characterized in that, The growth regulators include brassinolides, amides, and growth inhibitors, all of which are in a synergistic range with relatively small differences in magnitude.

6. The system according to claim 1, characterized in that, The complete nutritional additive includes organic chelated trace elements, a silicon-calcium-magnesium inorganic framework, polyglutamic acid, phosphorus- and potassium-solubilizing microorganisms, and a potassium phosphate source, which are spray-dried and coated into porous slow-release particles.

7. The system according to claim 7, characterized in that, The atomizing spraying unit is suitable for application in shallow water environments, while the mud injection unit is suitable for application in deep water or thick mud environments. The control module automatically switches between the two modes based on the water depth threshold.

8. The system according to claim 1, characterized in that, When the digital twin decision-making module receives new environmental and crop feedback data, it triggers the rolling optimization submodule to perform iterative updates and output the adjusted deployment plan.

9. A method for improving the quality and efficiency of lotus root based on the system described in the claims, characterized in that, include: S acquires environmental and crop growth parameters through a data acquisition module and stores them in a database; S inputs the parameters into the digital twin decision module, and generates a deployment plan through the growth response function, time series prediction submodule and rolling optimization submodule; S controls the intelligent application device to perform the operation. In shallow water environments, the atomizing spraying unit is used, while in deep water or thick mud environments, the mud injection unit is used. S4 performs rolling iterative optimization in a loop based on real-time updated data.

10. The method according to claim 9, characterized in that, The rolling iteration is automatically triggered by a fixed time window or when preset conditions are met, in order to ensure robustness and release economy.

Images