Physiological index dynamic monitoring system in sugarcane flowering phase induction process

Abstract

The invention discloses a physiological index dynamic monitoring system in a sugarcane flowering phase induction process, and relates to the technical field of agricultural intelligent monitoring, and the system comprises a data collection module which integrates multiple sensors to collect and transmit physiological and environmental data; the threshold calculation module is used for judging a flowering induction stage by using multi-stage feature matching and calculating a dynamic threshold in combination with parents and environmental factors; the regulation and control module is used for comparing data to trigger early warning, and linkage equipment regulation and control is performed if intervention is not performed; the interaction module is used for locally and cloud displaying data and analyzing and predicting the flowering phase in combination with parent growth period information and environmental factors; according to the invention, by integrating multiple sensors and LoRa transmission and combining multistage feature matching and dynamic threshold calculation, the physiological and environmental indexes of the sugarcane flowering phase are accurately monitored, the flowering induction stage is scientifically judged, and the monitoring comprehensiveness and accuracy are improved; meanwhile, a three-level early warning and equipment linkage regulation and control mechanism is constructed, multi-terminal interaction and ARIMA flowering phase prediction are matched, intelligent regulation and control and whole-process visual management are achieved, and the problem of regulation and control lag is solved.

Description

Technical Field

[0001] This invention relates to the field of agricultural intelligent monitoring technology, specifically a dynamic monitoring system for physiological indicators during the sugarcane flowering induction process. Background Technology

[0002] Sugarcane, as a globally important sugar and energy crop, plays a crucial role in ensuring sugar supply and developing bioenergy. In sugarcane breeding, artificial flowering induction is a core step in parental hybridization. Because natural flowering of sugarcane is limited by geographical and climatic factors, most cultivated parents cannot flower autonomously in non-native environments, requiring artificial induction to obtain hybrid parental materials. The effectiveness of flowering induction directly depends on the synergistic adaptation of sugarcane physiological indicators and environmental parameters. Leaf ABA and GA3 content, and their ratio, affect the initiation of flower bud differentiation; stalk soluble sugar content and C / N ratio determine the nutrient accumulation required for flowering; photosynthetic efficiency reflects sugarcane's ability to synthesize substances; and environmental factors such as light intensity, ambient temperature, and relative humidity indirectly affect the induction process by regulating physiological metabolism. Therefore, real-time, multi-dimensional monitoring of physiological indicators and environmental parameters during sugarcane flowering induction, and accurate determination of the flowering induction stage based on monitoring data, are the technical foundation for improving the success rate of artificial flowering induction and ensuring breeding efficiency. This is also a key technological direction that urgently needs breakthroughs in the current sugarcane breeding field.

[0003] Current sugarcane flowering period induction monitoring and regulation technologies have significant limitations and cannot meet the needs of precision breeding. First, the monitoring dimensions are singular and fragmented: traditional technologies often employ single sensors or laboratory detection methods, such as determining hormone content solely through chemical analysis or using portable instruments to detect photosynthetic efficiency. This fails to simultaneously acquire physiological indicators and environmental parameters, resulting in a lack of a synergistic analysis system and an inability to comprehensively reflect the sugarcane's induction state. Second, the determination of flowering induction stages and the setting of thresholds lack scientific rigor: stage division relies heavily on staff experience and observation, lacking a standardized feature matching mechanism, making stage misjudgment prone to occur. Furthermore, indicator thresholds are often fixed values, failing to consider the specificity of different sugarcane parents and dynamic environmental changes, leading to poor threshold adaptability and an inability to accurately guide regulation. Third, the regulation response is lagging and lacks precision: traditional regulation lacks an early warning mechanism, requiring manual intervention after abnormal indicators are detected, resulting in a lag of several hours to days. Moreover, the regulation amount is set based solely on experience, without incorporating a comprehensive physiological state index and environmental correction coefficient, easily leading to insufficient or excessive regulation. This not only affects the induction effect but may also damage sugarcane growth, severely restricting the stability and efficiency of sugarcane flowering induction. Therefore, it is necessary to develop a dynamic monitoring system for physiological indicators during sugarcane flowering induction to address these issues. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a dynamic monitoring system for physiological indicators during sugarcane flowering induction. This system integrates multiple sensors such as Raman spectroscopy and chlorophyll fluorescence spectrometer, combines data transmission via the LoRa protocol, uses multi-level feature matching to determine the flowering induction stage, and dynamically calculates thresholds to achieve accurate monitoring. The system also constructs a three-level early warning and equipment linkage control mechanism, coupled with multi-terminal interaction and the ARIMA flowering prediction model, to improve the level of intelligent control. This system effectively solves the problems of single monitoring dimensions and lagging control in traditional methods, and significantly improves the success rate and management efficiency of sugarcane flowering induction.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a dynamic monitoring system for physiological indicators during sugarcane flowering induction, the system comprising:

[0006] Data acquisition module: integrates Raman spectroscopy sensor, chlorophyll fluorometer, near-infrared spectroscopy sensor and integrated meteorological sensor to collect sugarcane leaf hormone content, photosynthetic efficiency parameters, stem carbon and nitrogen metabolism indicators and environmental parameters of the monitoring area, and transmits the collected data to the next module through LoRa protocol at fixed intervals;

[0007] Threshold calculation module: After receiving the collected data, it performs cleaning and uses multi-level feature matching judgment technology to infer the current flowering induction stage of sugarcane. This technology achieves stage determination by combining basic feature initial judgment and collaborative feature fine judgment. Then, combined with the parent offset coefficient and environmental factor correction logic, it obtains the dynamic threshold range of each physiological indicator through the dynamic threshold basic formula, environmental coupling factor calculation formula and physiological state comprehensive index calculation formula, and transmits preprocessed data, flowering induction stage and dynamic threshold.

[0008] Control module: Compares preprocessed data with dynamic thresholds, determines the compliance status of each indicator and triggers a three-level warning. If no manual intervention is performed within a set time after the warning, it will link external supplemental lighting, water and fertilizer, and temperature control equipment. It will calculate the control amount through the control amount decision formula and execute the control, while simultaneously recording the operation log.

[0009] Interactive module: Receives data from the flowering induction stage, dynamic thresholds, and operation logs. The local touchscreen terminal displays real-time data, achievement status, and change curves. The cloud platform provides data query and trend analysis, and uses the ARIMA time series model to predict flowering period.

[0010] Furthermore, the threshold calculation module employs multi-level feature matching and judgment technology to infer the current flowering induction stage of sugarcane. Specific steps include: establishing a database of basic and synergistic feature intervals for each sugarcane parent throughout the entire induction cycle; basic features include ABA content, GA3 content, soluble sugar content, and C / N ratio; synergistic features include the coupling relationship between the ABA / GA3 ratio and light intensity, and the linkage relationship between soluble sugar content and net photosynthetic rate; extracting the aforementioned basic and synergistic features from the collected data; firstly, making a preliminary judgment based on whether the basic features fall within the corresponding preset interval; then, making a fine judgment based on the matching degree of the synergistic features. The matching degree is calculated by the percentage deviation between the actual feature value and the interval median. When the preliminary judgment result of the basic features matches the fine judgment result of the synergistic features, the corresponding early, middle, and late flowering induction stages are output.

[0011] Furthermore, the basic formula for calculating the dynamic threshold in the threshold calculation module is as follows: ,in, Let t be the dynamic threshold of the i-th type of physiological index under the j-th sugarcane parent at time t; Let be the baseline threshold for the i-th index on the j-th sugarcane parent; Let be the specificity coefficient of the j-th sugarcane parent; Let be the environmental coupling factor at time t; This represents the attenuation coefficient during the flowering induction stage.

[0012] Furthermore, the environmental coupling factor The calculation formula is: , Let be the environmental coupling factor at time t; , , , These are the weighting coefficients; The actual light intensity of the monitored area at time t; This serves as a reference value for suitable light intensity induced during the sugarcane flowering period; The actual ambient temperature of the monitored area at time t; This is a reference value for the suitable temperature for inducing sugarcane flowering. The actual relative humidity of the monitored area at time t; This is a reference value for suitable relative humidity induced during the sugarcane flowering period; It is a natural constant.

[0013] Furthermore, the formula for calculating the comprehensive physiological state index in the threshold calculation module is as follows: , for The comprehensive physiological state index of sugarcane at any given time; n is the total number of physiological indicators involved in the physiological state assessment; , where is the weighting coefficient of the i-th type of physiological indicator; Let t be the actual measured value of the i-th type of physiological index under the j-th sugarcane parent at time t; This represents the minimum value of the i-th type of physiological indicator; The maximum value of the i-th type of physiological indicator; The summation symbol represents a weighted summation operation performed on the normalized results of n physiological indicators.

[0014] Furthermore, in the three-level early warning system of the control module, the triggering condition for the first-level early warning is that a single indicator deviates from the dynamic threshold by 5% to 10% for 1 hour; the second-level early warning is that a single indicator deviates from the threshold by 10% to 20% or two indicators deviate from the threshold by 5% to 10% for 30 minutes; and the third-level early warning is that a single indicator deviates from the threshold by ≥20% or three or more indicators deviate from the threshold by ≥5% for 15 minutes.

[0015] Furthermore, the formula for calculating the control amount decision in the control module is as follows: , The amount of sucrose solution sprayed per unit area of ​​sugarcane at time t is the control amount. This is the baseline spraying amount for the sucrose solution; The deviation of the soluble sugar index at time t; This is an environmental correction factor; Let t be the comprehensive index of the physiological state of sugarcane at time t.

[0016] Furthermore, the ARIMA time series model calculation formula in the interaction module is as follows: ,in, This is a stationary sequence of physiological indicators after d-order differencing; For model constants; The order of autoregression; Let i be the i-th autoregressive coefficient; for The value of the d-th order difference stationary sequence at time t; The white noise error term at time t; The moving average order; Let be the coefficient of the j-th moving average; for Time-based white noise error term; It is the difference order; The sign for the summation of the autoregressive terms; The summation symbol for the moving average term.

[0017] Compared with existing technologies, this dynamic monitoring system for physiological indicators during sugarcane flowering induction has the following beneficial effects:

[0018] I. This invention utilizes a multi-dimensional data acquisition module integrating a Raman spectroscopy sensor, a chlorophyll fluorometer, a near-infrared spectroscopy sensor, and an integrated meteorological sensor. Combined with a fixed-period transmission mechanism based on the LoRa protocol and a threshold calculation module incorporating multi-level feature matching and dynamic threshold calculation models, it achieves precise monitoring of physiological and environmental indicators during sugarcane flowering induction and scientific determination of the flowering induction stage. Multiple sensors simultaneously collect data on leaf hormone content, photosynthetic efficiency, stem carbon and nitrogen metabolism, and environmental parameters, addressing the problems of single-dimensional monitoring and fragmented data in traditional methods. Multi-level feature matching, combined with parental offset coefficients and environmental factor corrections, makes the flowering induction stage division more closely aligned with parental characteristics. The dynamic threshold formula allows indicator thresholds to be dynamically adjusted over time, by parental factors, and by the environment, avoiding the adaptability defects of fixed thresholds. This provides precise data support for subsequent regulation, significantly improving the comprehensiveness of monitoring and the accuracy of stage determination.

[0019] II. This invention achieves intelligent control and full-process visual management of sugarcane flowering induction by constructing a three-level early warning mechanism with hierarchical triggering logic and a control module with equipment linkage and regulation functions, combined with a multi-terminal interactive module integrating the ARIMA time series model. The three-level early warning is triggered according to the degree of deviation of indicators and the duration, reducing false alarms and missed alarms. When there is no manual intervention, the system automatically links supplemental lighting, water and fertilizer, and temperature control equipment. The control amount decision formula combines the comprehensive physiological state index and the environmental correction coefficient to ensure that the control amount is accurately adapted to the real-time physiological state of sugarcane. The interactive module displays real-time data and change curves through a local touch screen, and supports query and analysis through a cloud platform. The ARIMA model enables flowering period prediction, which allows users to keep track of the induction progress in real time and plan management in advance. This solves the problems of lagging traditional control and reliance on experience in management, and effectively improves the success rate of flowering induction and management efficiency.

[0020] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0022] Figure 1 A flowchart of a dynamic monitoring system for physiological indicators during sugarcane flowering induction;

[0023] Figure 2This is a framework diagram of a dynamic monitoring system for physiological indicators during the sugarcane flowering induction process. Detailed Implementation

[0024] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0025] Example 1: Experimental field for inducing flowering period in sugarcane with multiple parent lines in research institutes

[0026] This embodiment was applied to a sugarcane hybrid breeding experimental field of a provincial agricultural research institute. The experimental field covered an area of ​​10 mu (approximately 1.65 acres) and planted two main parent lines, Guitang 42 and Yuetang 55. The aim was to accurately monitor the physiological changes induced by different parent lines during flowering using the system of this invention, providing data support for optimizing parent-specific induction programs. The specific steps are as follows: Figure 1 As shown.

[0027] First, the system was deployed, with five data acquisition modules installed according to the principle of "one acquisition unit per 2 mu for each parent variety": a Raman spectroscopy sensor fixed in the middle of the sugarcane leaf to stably collect hormone indicators such as ABA and GA3 content, while avoiding data distortion caused by leaf position deviation; a chlorophyll fluorometer corresponding to the functional leaf of the same plant to ensure that photosynthetic efficiency parameters and hormone indicators come from the same monitoring object, laying the foundation for subsequent synergistic feature analysis; a near-infrared spectroscopy sensor attached to the middle of the stem to accurately capture carbon and nitrogen metabolism indicators such as soluble sugar content and C / N ratio; and an integrated meteorological sensor installed on a 1.5-meter-high support in the center of the experimental field to obtain uniform light, temperature, and humidity data across the entire area. All sensors collected data at a cycle of 1 hour and transmitted it to the threshold calculation module via the LoRa protocol. This protocol can adapt to the complex environment of the experimental field, reduce signal interference, and ensure continuous and real-time data.

[0028] After receiving the raw data, the threshold calculation module first cleans and removes outliers caused by temporary sensor malfunctions to avoid invalid data interfering with subsequent analysis and ensure the reliability of stage determination and threshold calculation. Then, a multi-level feature matching and determination technique is initiated: It calls a pre-established database of dedicated basic and synergistic features for Guitang 42 and Yuetang 55. Due to the significant differences in the physiological characteristics of the two parents, the dedicated database avoids stage misjudgments caused by general standards. Basic and synergistic features are extracted. Initial stage ranges are narrowed down using basic features, and then refined using synergistic feature matching. Ultimately, it is determined that Guitang 42 is in the mid-induction stage and Yuetang 55 is in the early induction stage. Afterwards, combining the parental offset coefficients of the two parents with real-time environmental parameters, the dynamic threshold basic formula, environmental coupling factor calculation formula, and physiological state comprehensive index calculation formula are called to ensure that the thresholds fully adapt to the parental characteristics and the actual environment, obtaining the dynamic threshold range for each indicator. The dynamic threshold basic formula is as follows: ,in, Let t be the dynamic threshold of the i-th type of physiological index under the j-th sugarcane parent at time t; Let be the baseline threshold for the i-th index on the j-th sugarcane parent; Let be the specificity coefficient of the j-th sugarcane parent; Let be the environmental coupling factor at time t; The decay coefficient during the flowering induction stage; environmental coupling factor. The calculation formula is: , Let be the environmental coupling factor at time t; , , , These are the weighting coefficients; The actual light intensity of the monitored area at time t; This serves as a reference value for suitable light intensity induced during the sugarcane flowering period; The actual ambient temperature of the monitored area at time t; This is a reference value for the suitable temperature for inducing sugarcane flowering. The actual relative humidity of the monitored area at time t; This is a reference value for suitable relative humidity induced during the sugarcane flowering period; The natural constant is used; the formula for calculating the comprehensive physiological state index is: , for The comprehensive physiological state index of sugarcane at any given time; n is the total number of physiological indicators involved in the physiological state assessment; , where is the weighting coefficient of the i-th type of physiological indicator; Let t be the actual measured value of the i-th type of physiological index under the j-th sugarcane parent at time t; This represents the minimum value of the i-th type of physiological indicator; The maximum value of the i-th type of physiological indicator; The summation symbol indicates a weighted summation operation on the normalized results of n physiological indicators; then the preprocessed data, flowering induction stage, and dynamic threshold are transmitted to the regulation module and the interaction module.

[0029] The control module compared actual data with dynamic thresholds and found that the soluble sugar content of Guitang 42 deviated from the threshold by 5%-10% for one hour, triggering a level one warning. A notification was sent to staff via local terminals to promptly alert them to the slight anomaly and prevent it from escalating into a serious problem. If no manual intervention was performed within one hour, the system automatically activated the integrated water and fertilizer system, using the control amount decision formula to calculate the sucrose solution control amount. This ensured precise matching of the dosage to the mid-term nutrient requirements of Guitang 42, avoiding both over-discharge and under-discharge that could hinder accumulation. Spraying was then carried out according to the calculated results, and the control time, equipment, and target were simultaneously recorded in the operation log for subsequent effect tracking. The control amount decision calculation formula is as follows: , The amount of sucrose solution sprayed per unit area of ​​sugarcane at time t is the control amount. This is the baseline spraying amount for the sucrose solution; The deviation of the soluble sugar index at time t; This is an environmental correction factor; Let t be the comprehensive index of the physiological state of sugarcane at time t.

[0030] The interactive module continuously receives data: the local touchscreen in the experimental field displays real-time physiological indicators, environmental parameters, compliance status, and change curves of the two parents over the past 72 hours, allowing staff to quickly grasp the dynamics on-site without frequent sampling and testing; researchers can remotely query historical data and perform trend analysis through the laboratory cloud platform to deeply explore the physiological characteristics of the parents; simultaneously, the ARIMA time-series model is activated to predict the flowering period. The ARIMA time-series model calculation formula is: ,in, This is a stationary sequence of physiological indicators after d-order differencing; For model constants; The order of autoregression; Let i be the i-th autoregressive coefficient; for The value of the d-th order difference stationary sequence at time t; The white noise error term at time t; The moving average order; Let be the coefficient of the j-th moving average; for Time-based white noise error term; It is the difference order; The sign for the summation of the autoregressive terms; The symbol for the summation of the moving average term; results such as "Guitang 42 is expected to enter its full bloom period in 15 days" are synchronized to the cloud to help researchers plan the hybridization and pollination time in advance and avoid missing the best window.

[0031] In summary, in the scenario of multi-parent sugarcane flowering induction experiment fields in research institutes, the system of this invention, through the targeted deployment of multiple sets of data acquisition modules and the combination of the LoRa protocol, achieves stable acquisition of hormone, photosynthetic efficiency, carbon and nitrogen metabolism, and environmental parameters, laying a data foundation for multi-parent monitoring. The threshold calculation module, through data cleaning and multi-level feature matching judgment technology, accurately distinguishes the flowering induction stages of Guitang 42 and Yuetang 55, and generates threshold ranges adapted to parental characteristics and the environment through dynamic threshold correlation formulas. The control module's graded early warning and automatic linkage with water and fertilizer equipment can promptly correct abnormal indicators. The interactive module's local display, cloud analysis, and ARIMA time-series prediction not only facilitate researchers' real-time monitoring of dynamics but also provide data support for optimizing parental-specific induction programs, effectively meeting the needs of precise monitoring and program optimization in research scenarios.

[0032] Example 2: Flowering period induction management in large-scale sugarcane planting bases

[0033] This embodiment is applied to a 100-mu (approximately 6.7 hectares) large-scale sugarcane planting base, uniformly planting the Xintai Sugar 22 parent variety—which requires artificial induction of flowering to purify and rejuvenate the parent variety. The system of this invention achieves unmanned management, reduces labor costs, and improves the induction success rate. Specific steps are as follows: Figure 2 As shown.

[0034] During the system deployment phase, 20 data acquisition modules were installed and connected to an IoT gateway at a density of one acquisition unit per 5 mu (approximately 0.8 hectares). This density ensures full monitoring coverage while avoiding cost waste caused by excessive sensor density. Specifically, Raman spectroscopy sensors were arranged with one functional leaf selected for every 10 plants to ensure that hormone indicators represent the overall level of the region and reduce the impact of individual plant abnormalities. Chlorophyll fluorometers and Raman spectroscopy sensors corresponded to the same monitoring sample, ensuring the correlation between photosynthetic efficiency parameters and hormone indicators. Near-infrared spectroscopy sensors were installed with one stem sample collected for every 20 plants, balancing acquisition efficiency and data accuracy. Five integrated meteorological sensors were evenly distributed throughout the base to capture environmental differences in different areas, avoiding data distortion caused by single monitoring points and providing a comprehensive basis for subsequent environmental coupling factor calculations. All sensors collected data every 2 hours and transmitted it to the threshold calculation module in the control room via the LoRa protocol, adapting to the long-distance transmission requirements of the base and ensuring data stability.

[0035] The threshold calculation module first cleans and removes abnormal data caused by wind and rain interference, eliminating external interference and ensuring that the analysis is based on the actual physiological and environmental conditions. Then, a multi-level feature matching and judgment technology is activated: it calls upon the exclusive basic and synergistic feature interval library of New Taiwan Sugar 22 to adapt to the specific physiological patterns of this parent strain, avoiding misjudgments using general standards; it extracts basic and synergistic features, and after initial and refined judgments, determines that the base is in the late stage of induction. Next, combining the parent strain offset coefficient of New Taiwan Sugar 22 with the average environmental parameters from five meteorological sensors, it calls three types of threshold calculation formulas to ensure that the dynamic thresholds align with the needs of the parent strain in the late stage of induction and the actual environment of the base, obtaining the threshold ranges for each indicator. Finally, the relevant data is transmitted to the control module and the interaction module.

[0036] After comparing data, the control module found that the ABA content in the eastern area of ​​the base deviated from the threshold by ≥20% for 15 minutes, triggering a level-three warning. Immediately, a message stating "ABA content in the eastern area is severely deviated, requiring urgent action" was pushed to management personnel via a mobile app. This breaks down spatial limitations, ensuring that management personnel can receive the message promptly even when not in the control room, thus shortening response time. If no manual intervention is initiated within 30 minutes, the system automatically activates the temperature control and supplemental lighting equipment in the eastern area, using the control quantity decision formula to calculate the temperature adjustment range and supplemental lighting duration. This ensures that measures are precisely adapted to the degree of ABA anomaly, avoiding insufficient or excessive control. Simultaneously, the system controls the equipment to adjust the temperature and supplement lighting, improving the environment from two dimensions and assisting in restoring the ABA content to normal. The entire process is logged synchronously for subsequent analysis of the control effectiveness.

[0037] The local touchscreen of the interactive module is installed in the control room, allowing staff to view the status of physiological indicators and environmental parameter curves across the entire area in real time, eliminating the need for on-site inspections and significantly reducing labor costs. Managers can access trend analysis reports for the past month through a cloud platform to compare differences in induction effects in different areas, providing a basis for optimizing regional management strategies. The ARIMA time series model predicts the peak flowering time of the base and synchronizes it to the production management system, helping to arrange pollination teams and materials in advance, adapting to the high-efficiency operation needs of a 100-acre scale base, avoiding pollination delays due to insufficient manpower and materials, and ensuring the purification and rejuvenation effect of parent lines.

[0038] In summary, in large-scale sugarcane planting bases, the system of this invention deploys data acquisition modules at a reasonable density and connects to an IoT gateway, balancing monitoring coverage with cost control. Multiple regional meteorological sensors and specific sampling methods ensure data representativeness. The threshold calculation module, after removing interfering data, accurately determines the flowering induction stage of the new Taisugar 22 variety based on a dedicated interval library and dynamic threshold formula. The control module's three-level early warning system, mobile APP push notifications, and automatic linkage with temperature control and supplemental lighting equipment enable unmanned operation and rapid response. The interactive module's control room display, cloud-based trend analysis, and flowering period prediction significantly reduce labor costs, helping large-scale bases efficiently arrange pollination work, effectively improving the success rate of sugarcane flowering induction, and providing reliable technical support for parent line purification and rejuvenation.

[0039] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A dynamic monitoring system for physiological indicators during sugarcane flowering induction, characterized in that, The system includes: Data acquisition module: integrates Raman spectroscopy sensor, chlorophyll fluorometer, near-infrared spectroscopy sensor and integrated meteorological sensor to collect sugarcane leaf hormone content, photosynthetic efficiency parameters, stem carbon and nitrogen metabolism indicators and environmental parameters of the monitoring area, and transmits the collected data to the next module through LoRa protocol at fixed intervals; Threshold calculation module: After receiving the collected data, it performs cleaning and uses multi-level feature matching judgment technology to infer the current flowering induction stage of sugarcane. This technology achieves stage determination by combining basic feature initial judgment and collaborative feature fine judgment. Then, combined with the parent offset coefficient and environmental factor correction logic, it obtains the dynamic threshold range of each physiological indicator through the dynamic threshold basic formula, environmental coupling factor calculation formula and physiological state comprehensive index calculation formula, and transmits preprocessed data, flowering induction stage and dynamic threshold. Control module: Compares preprocessed data with dynamic thresholds, determines the compliance status of each indicator and triggers a three-level warning. If no manual intervention is performed within a set time after the warning, it will link external supplemental lighting, water and fertilizer, and temperature control equipment. It will calculate the control amount through the control amount decision formula and execute the control, while simultaneously recording the operation log. Interactive module: Receives data from the flowering induction stage, dynamic thresholds, and operation logs, displays real-time data, achievement status, and change curves on the local touchscreen terminal, and provides data query and trend analysis on the cloud platform, and realizes flowering period prediction through the ARIMA time series model.

2. The dynamic monitoring system for physiological indicators during sugarcane flowering induction according to claim 1, characterized in that, The threshold calculation module employs multi-level feature matching and judgment technology to infer the current flowering induction stage of sugarcane. Specific steps include: establishing a database of basic and synergistic feature intervals for each sugarcane parent throughout the entire induction cycle; basic features include ABA content, GA3 content, soluble sugar content, and C / N ratio; synergistic features include the coupling relationship between the ABA / GA3 ratio and light intensity, and the linkage relationship between soluble sugar content and net photosynthetic rate; extracting the aforementioned basic and synergistic features from the collected data; firstly, making a preliminary judgment based on whether the basic features fall within the corresponding preset interval; then, making a fine judgment based on the matching degree of the synergistic features. The matching degree is calculated by the percentage deviation between the actual feature value and the interval median. When the preliminary judgment result of the basic features matches the fine judgment result of the synergistic features, the corresponding early, middle, and late flowering induction stages are output.

3. The dynamic monitoring system for physiological indicators during sugarcane flowering induction according to claim 1, characterized in that, The basic formula for calculating the dynamic threshold in the threshold calculation module is as follows: ,in, Let t be the dynamic threshold of the i-th type of physiological index under the j-th sugarcane parent at time t; Let be the baseline threshold for the i-th index on the j-th sugarcane parent; Let be the specificity coefficient of the j-th sugarcane parent; Let be the environmental coupling factor at time t; This represents the attenuation coefficient during the flowering induction stage.

4. The dynamic monitoring system for physiological indicators during sugarcane flowering induction according to claim 3, characterized in that, The environmental coupling factor The calculation formula is: , Let be the environmental coupling factor at time t; , , , These are the weighting coefficients; The actual light intensity of the monitored area at time t; This serves as a reference value for suitable light intensity induced during the sugarcane flowering period; The actual ambient temperature of the monitored area at time t; This is a reference value for the suitable temperature for inducing sugarcane flowering. The actual relative humidity of the monitored area at time t; This is a reference value for suitable relative humidity induced during the sugarcane flowering period; It is a natural constant.

5. The dynamic monitoring system for physiological indicators during sugarcane flowering induction according to claim 1, characterized in that, The formula for calculating the comprehensive physiological state index in the threshold calculation module is as follows: , for The comprehensive physiological state index of sugarcane at any given time; n is the total number of physiological indicators involved in the physiological state assessment; , where is the weighting coefficient of the i-th type of physiological indicator; Let t be the actual measured value of the i-th type of physiological index under the j-th sugarcane parent at time t; The minimum value of the i-th type of physiological indicator; The maximum value of the i-th type of physiological indicator; The summation symbol represents a weighted summation operation performed on the normalized results of n physiological indicators.

6. The dynamic monitoring system for physiological indicators during sugarcane flowering induction according to claim 1, characterized in that, In the three-level early warning system of the control module, the trigger condition for the first-level early warning is that a single indicator deviates from the dynamic threshold by 5% to 10% for 1 hour; the second-level early warning is that a single indicator deviates from the dynamic threshold by 10% to 20% or two indicators deviate from the dynamic threshold by 5% to 10% for 30 minutes; and the third-level early warning is that a single indicator deviates from the dynamic threshold by ≥20% or three or more indicators deviate from the dynamic threshold by ≥5% for 15 minutes.

7. The dynamic monitoring system for physiological indicators during sugarcane flowering induction according to claim 1, characterized in that, The formula for calculating the control amount decision in the control module is as follows: , The amount of sucrose solution sprayed per unit area of ​​sugarcane at time t is the control amount. This is the baseline spraying amount for the sucrose solution; The deviation of the soluble sugar index at time t; This is an environmental correction factor; Let t be the comprehensive index of the physiological state of sugarcane at time t.

8. The dynamic monitoring system for physiological indicators during sugarcane flowering induction according to claim 1, characterized in that, The ARIMA time series model calculation formula in the interaction module is as follows: ,in, This is a stationary sequence of physiological indicators after d-order differencing; For model constants; The order of autoregression; Let i be the i-th autoregressive coefficient; for The value of the d-th order difference stationary sequence at time t; The white noise error term at time t; The moving average order; Let be the coefficient of the j-th moving average; for Time-based white noise error term; It is the difference order; The sign for the summation of the autoregressive terms; The summation symbol for the moving average term.

Images