545results about How to "Improve representation" patented technology

The invention discloses a large-scale point cloud registration method, system and device based on a power grid power transmission line and a storage medium, and the method comprises the steps: collecting point cloud data of the power transmission line under different visual angles, and forming a source point cloud set and a target point cloud set; down-sampling point cloud data in the source point cloud set and the target point cloud set, dynamically adjusting the sampling granularity of different density regions, and obtaining representative point cloud data from the source point cloud set and the target point cloud set; extracting point cloud feature points, accelerating neighborhood search through a KD-Tree structure, and adaptively adjusting a neighborhood search radius; constructing a geometric topology model; performing coarse registration based on an improved RANSAC algorithm, selecting non-collinear feature points, and optimizing a transformation model; an improved ICP algorithm is adopted to carry out fine registration, and normal vector features are utilized to introduce weighting factors to optimize registration precision. According to the invention, large-scale power transmission line point cloud data can be efficiently and accurately processed, and the method is especially suitable for power inspection, three-dimensional modeling and maintenance scenes.

The invention relates to the technical field of machine learning, in particular to a supervised time sequence water level data generation method and system and a storage medium. The method comprises the following steps: acquiring multi-source hydrological monitoring data; performing abnormal value identification and data preprocessing according to the hydrological monitoring data to generate standardized hydrological basic data; constructing a data generation model of the conditional generative adversarial network based on the standardized hydrological basic data; hydrological variable driven condition feature regulation and control are carried out on the data generation model, parameter optimization of the generation network is carried out, and hydrological adaptability enhanced condition input feature data are generated; and injecting the condition input characteristic data into the data generation model to generate initial water level time sequence data. According to the method, the rare extreme hydrological events are oversampled by using a hierarchical importance sampling and self-service method (Bootstrap), so that the performance of the generative model in rare event prediction is remarkably enhanced.

The invention relates to the technical field of wire harness intelligent evaluation, in particular to a wire harness connection performance intelligent test method and system. The method comprises the following steps: collecting wire harness test data generated by a wire harness test device and a wire harness sensor in real time through an edge computing node; performing electrical performance detection extraction and mechanical performance detection extraction according to the wire harness test data to respectively obtain wire harness electrical performance detection data and wire harness mechanical performance detection data; performing electrical performance deep evaluation according to the wire harness electrical performance detection data to obtain wire harness electrical performance evaluation data, and performing mechanical performance deep evaluation on the wire harness mechanical performance detection data to obtain wire harness mechanical performance evaluation data; and performing environment pressure cross reference according to the wire harness electrical performance evaluation data and the wire harness mechanical performance evaluation data to obtain wire harness connection performance test evaluation data. According to the method, the accuracy of wire harness performance evaluation is improved, and reliable performance data can be obtained in different application fields.

The invention relates to the technical field of data processing, and discloses a real-time data integration method and system based on ground observation data. The method comprises the following steps: performing multi-dimensional preprocessing on original marine observation data to obtain time-space standardized observation data; performing multi-parameter cross comparison analysis on the time-space standardized observation data to obtain stratification deviation characteristic data; constructing an adaptive multi-factor correction rule based on the layered deviation characteristic data to obtain a dynamic correction parameter; based on the dynamic correction parameters, performing nonlinear correction on the real-time temperature profile data, and performing intelligent fusion with a preset reference data set to obtain preliminary integrated observation data; performing multi-level quality control and probability uncertainty evaluation on the preliminarily integrated observation data to obtain refined observation data with a credibility index; and performing closed-loop feedback processing on the refined observation data to obtain target integration correction observation data. According to the invention, the efficiency and precision of real-time data integration based on ground observation data are improved.

The invention relates to the technical field of side slope monitoring and early warning, in particular to a mine site side slope remote online real-time monitoring and early warning system which comprises a multi-source data monitoring unit, a data processing and analyzing unit, a side slope instability judging unit, an instability grading early warning unit and an early warning verification pushing unit. The method comprises the following steps: collecting monitoring data of a plurality of data sources to obtain time sequence monitoring data of each data source, carrying out noise reduction on the time sequence monitoring data, then decomposing the time sequence monitoring data, calculating a time-frequency feature vector through an energy density function, and optimizing the time-frequency feature vector through feature screening; calculating a slope stability evaluation index by optimizing the time-frequency feature vector, constructing an instability risk index to judge a slope instability risk level, constructing an early warning index, and combining the early warning index with the slope instability risk level to establish a graded early warning mechanism to obtain a slope instability early warning level; and verifying the slope instability early warning grade, and performing early warning according to the slope instability early warning grade passing the verification. According to the invention, the false alarm rate of slope monitoring and early warning can be reduced.

The invention discloses a power grid toughness evaluation method and system, and the method comprises the steps: inputting the collected monitoring index data and environment index data of a target regional power grid into a pre-trained power grid toughness evaluation model for evaluation and recognition, so as to obtain a toughness evaluation result; the monitoring index data comprises voltage data, current data, harmonic data and power data, and the environment index data comprises temperature and humidity data, line loss data and frequency data; wherein the construction process of the power grid toughness evaluation model comprises the step of respectively training a data expansion process, a feature extraction model, a feature dimension reduction model and a classifier model in the power grid toughness evaluation model, so as to obtain the power grid toughness evaluation model. The evaluation accuracy of the evaluation model is improved by optimizing the training process of the model.

The invention discloses a lithium battery life prediction method and system based on a Mama model, and relates to the field of energy storage of a new energy power system, and the method comprises the steps: obtaining aging feature matrixes of a plurality of lithium batteries, substituting the aging feature matrixes into the Mama model for training, extracting a hidden state matrix sequence of each lithium battery according to the trained model, and obtaining a hidden state matrix sequence of each lithium battery; through norm calculation and variational mode decomposition, a cycle number sequence corresponding to the target cycle life prediction point of each lithium battery is obtained; on the basis of the cycle number sequences corresponding to the target health states of all the lithium batteries and the cycle number sequences corresponding to the target cycle life prediction points of all the lithium batteries, constructing a linear relation model of lithium battery life prediction; and according to the linear relation model for lithium battery life prediction, calculating to obtain a cycle number sequence corresponding to the target health state of the to-be-predicted lithium battery. The interpretability and calculation efficiency of lithium battery life prediction are improved, and the application range of the prediction model is expanded.

The invention discloses a short-term power load prediction method based on deep learning, and the method comprises the steps: S1, collecting historical power load data and corresponding weather and holiday and festival information, S2, carrying out the preprocessing of the historical data based on the historical power load data and the change of a power utilization behavior mode of a user, reducing the data inconsistency, and carrying out the prediction of a short-term power load. The method comprises the following steps: S1, processing historical power load data, weather information and holiday and festival information, S3, constructing a deep learning model which inputs processed historical power load data, weather information and holiday and festival information, S4, training the constructed deep learning model by using a training data set and optimizing model parameters, and S5, carrying out short-term power load prediction by using the trained deep learning model and generating a prediction result. According to the short-term power load prediction method based on deep learning, the problem of inconsistency of historical data caused by frequent change of power utilization habits of users in a changeable user behavior mode in the prior art is solved.

The invention relates to a source load time sequence matching typical scene identification and construction method. The method comprises the following steps: step 1, a multi-time scale wind-light-load scene generation method of source load matching time sequence characteristics; 2, constructing a typical scene set and an extreme scene set oriented to supply and consumption; step 3, typical example analysis, including wind and light load characteristic analysis, typical scene set construction, extreme scene set construction and guarantee supply and consumption oriented scene analysis; the method has the advantages that multi-time-scale modeling is achieved, dynamic changes are better reflected, supply and consumption demands are effectively balanced, and stability and economical efficiency are improved.

The invention relates to the technical field of artificial intelligence, in particular to a wheat abiotic stress character SNP (Single Nucleotide Polymorphism) prediction method based on an automatic CNN (Convolutional Neural Network) model, which comprises the following steps of: collecting GWAS data related to wheat from a GWAS Atlas database, and constructing a high-quality mutation site data set; performing feature extraction on the data set by using a DNA original sequence, text-based features and structure-based features, sorting the importance of input features by using an SHAP method, assisting feature selection, and explaining the result of the prediction model; then, an automatic architecture search framework is constructed, automatic neural architecture search is adopted, the model is evolved in a specified search space, the optimal performance is achieved on a verification set, and the accuracy, the AUPR and the AUC of the model are evaluated on a test set. The invention provides a deep learning framework which is efficient, accurate and explainable, and is used for predicting the SNP related to the wheat biological stress, so that the development of wheat stress resistance breeding and genomics research is promoted.

The invention discloses a self-adaptive construction method of a database index. The method comprises the following steps: S1, extracting a query information set based on a database log; s2, obtaining a high-frequency query statement based on TF through the information set; s3, obtaining importance values of all fields in the high-frequency query statement; s4, constructing a database index according to the importance value of the field; and S5, periodically obtaining the importance value of the database log constructed in the step S4, and dynamically adjusting the database index so as to improve the query efficiency and adaptability of the database system.

The invention belongs to the technical field of material production detection, and particularly discloses a contact lens production defect detection method based on artificial intelligence, which comprises the following steps: collecting environmental information in a defect detection area; judging whether the detected environment is matched or not, if yes, executing the next step, and otherwise, regulating and controlling the environment; acquiring a plurality of images at different light source angles and different light source intensities; judging whether the image preprocessing mode needs to be changed or not, if so, confirming the changed preprocessing scheme, and otherwise, preprocessing the image; building a defect detection model, and training; defect feature detection is carried out; and performing functional defect detection and analysis on the contact lenses to be detected, and outputting a production defect report. According to the method, the problem of insufficient attention in the current image processing process is effectively solved, the sufficiency, representativeness and detection efficiency of contact lens production defect detection are improved, and meanwhile, the effectiveness of a subsequent detection result is guaranteed.

The invention provides a photoelectric sensing smart home linkage control method and system, and relates to the technical field of data processing, and the method comprises the steps: receiving first electric data and second electric data which represent the illumination intensity of a first data point and the illumination intensity of a second data point respectively; calculating a cross data value of the illumination intensity of the first data point and the second data point; comparing the cross data value with a preset illumination demand threshold value to judge the overall illumination demand of the current home environment; generating a corresponding adjustment instruction based on the overall illumination demand of the current home environment; sending the adjusting instruction to an actuator connected with the household equipment, wherein the actuator comprises an intelligent bulb and an intelligent curtain motor; and after receiving the adjusting instruction, the actuator automatically executes corresponding operations, including turning on light, turning off light or adjusting a curtain, so as to realize automatic adjustment of the household equipment. According to the invention, the intelligent level of home illumination adjustment is improved.

The invention discloses a tunnel lining structure crack sound wave detection device and method, and belongs to the field of tunnel crack detection. The tunnel lining structure crack sound wave detection device comprises a moving seat, the top of the moving seat is fixedly connected with an annular track, the bottom of the moving seat is provided with a walking part for pushing the moving seat to advance, the tunnel lining structure crack sound wave detection device further comprises a detection seat, the detection seat is installed on the annular track, and the top of the detection seat is fixedly connected with a sound wave detector, a reciprocating part for driving the detection seat to slide back and forth along the annular track is arranged on the movable seat; according to the invention, the swing rod drives the detection seat and the sound wave detector to swing back and forth along the annular track, so that the reciprocating detection of the section of the tunnel lining structure is rapidly completed, and the detection efficiency and the representativeness of the detection result are improved; and meanwhile, the cleaning roller is driven to rotate during swinging, so that the crack is cleaned before detection, dust and attachments in the crack are prevented from shielding sound waves, and the detection precision is effectively improved.

The invention provides an ultrasonic sound velocity image generation method, ultrasonic equipment and a storage medium. The generation method comprises the following steps: transmitting ultrasonic waves through a probe of ultrasonic equipment, and receiving echoes of the ultrasonic waves to generate echo signals; based on the receiving delay of each preset sound velocity, performing beam forming processing on the echo signal to obtain an enhanced signal corresponding to each preset sound velocity; and based on the pixel value of each first pixel in the respective sound velocity image of each preset sound velocity, determining the pixel value of a second pixel corresponding to the first pixel in the target image to obtain the target image. On one hand, the sound velocity image obtained by the method is high in representativeness, so that the representativeness of the target image can be improved, and the accuracy of the detection result of the detected object can be improved; and on the other hand, the target image can be generated based on different sound velocity images, so that the information breadth of the target image can be improved, and the display flexibility is higher.

The invention provides a method for characterizing the heterogeneity of a millimeter-level shale oil and gas reservoir. The method mainly solves the problem that the reliability and accuracy of a reservoir evaluation result of an existing volume sampling method are low. The method is characterized by comprising the following steps that S1, shale millimeter-level mineral components are recognized and drilled; s2, based on the obtained powdery sample, oil-containing and non-oil-containing tests are carried out; determining occurrence pore size distribution to carry out reservoir characterization through comparison before and after pumping; s3, on the basis of the obtained powdery sample, carrying out oiliness characterization on different lamina / layered components; and S4, carrying out millimeter-level shale oil reservoir heterogeneity characterization on the basis of the reservoir property and oiliness results of the different strata / layered components. According to the method provided by the invention, the identification precision of the shale formation / stratified structure can be enhanced, millimeter-level fine representation of lithology of different formation / strata is realized, and favorable support is provided for shale oil enrichment mechanism, sweet spot prediction and the like.

The invention belongs to the technical field of federated learning, and particularly relates to a decentralized federated learning method and system oriented to a computing power network. The method comprises the steps that a model demand side in a computing power network uploads a federated learning task to a block chain network, screening computing power nodes according to a reputation score and a data score, and taking the screened computing power nodes as computing nodes to participate in training; the trained local model is verified through the block chain network and then is sent to a model demand side; and the model demander uses a weighted aggregation algorithm based on data fairness to aggregate the local models received in the current round and updates the global model by using an aggregation result. According to the method, the block chain is combined with federated learning under the background of the computing power network, and the universality of the model and the fairness of data are improved while the availability of the federated learning model and the node training enthusiasm are ensured.

Belonging to the technical field of soil sampling, the invention relates to an efficient soil sample sampling mechanism, which comprises a walking trolley body for soil sample sampling, a sampling barrel and an electric lifting column fixedly mounted on the upper surface of the walking trolley body and used for driving the sampling barrel to lift. An upper mounting table and a lower mounting table which are distributed up and down are arranged outside the electric lifting column; a mechanism for driving the sampling barrel to rotate is arranged on the lower mounting table; a vibrating mechanism and a water conveying mechanism are arranged on the lower mounting table, and a first transmission structure and a second transmission structure which are used in linkage with the vibrating mechanism and the water conveying mechanism are mounted on an output shaft at the bottom of the double-shaft motor. According to the efficient sampling mechanism for the soil sample, the pushing block and a knocking mode are linked and matched for use, and then a spraying function is matched, so that the discharging of the sample can be improved, the inner wall of the sampling barrel can be flushed, the sampling efficiency is remarkably improved, the sampling time is shortened, the labor cost is reduced, and the efficient sampling mechanism has the advantages of high efficiency, convenience and high applicability.

The invention discloses a double-domain combined narrow-band radar moving target classification and identification method and related products. Processing a target echo signal received by the radar to obtain a distance Doppler spectrum; obtaining a micro-Doppler time-frequency spectrum based on a target echo signal received by a radar; respectively cutting the distance Doppler spectrum and the micro Doppler time-frequency spectrum to obtain distance Doppler domain characteristic data and micro Doppler domain characteristic data; and inputting the distance Doppler domain feature data and the micro Doppler domain feature data into a pre-constructed RFICNet to obtain a target classification result. According to the method, dual-domain data features of the distance Doppler domain and the micro-Doppler domain are combined, the method does not depend on complex echo data preprocessing operation and excessive prior physical assumptions, dual-domain joint feature information can make up for the deficiency of feature basis during classification, and the classification recognition precision of the narrow-band radar moving target is improved.

The invention discloses an enterprise supply chain side evaluation method and system based on big data, and provides an innovative solution for the problems of low data processing efficiency, weak analysis and prediction ability, insufficient causal relationship analysis, decision support lag and the like in supply chain management. The method comprises the steps of integrating and processing real-time data, deeply analyzing the data by using an advanced analysis and prediction module in combination with a mathematical model and a machine learning algorithm, deeply understanding a causal relationship in a supply chain through a causal relationship analysis and optimization module, and finally accelerating a decision process through a visualization and decision support module. According to the system, through modular design and an advanced algorithm, the supply chain management efficiency and scientificity are remarkably improved, and comprehensive evaluation and optimization of the supply chain are achieved. The invention aims to solve the problem of improving the efficiency, accuracy and scientificity of enterprise supply chain management under the background of big data so as to adapt to rapidly changing market demands and a complex supply chain network.

The invention provides a map positioning and constructing method based on laser SLAM (Simultaneous Localization and Mapping), the method proposes a point cloud registration algorithm fusing semantic and distribution information, the algorithm can utilize semantic label information of point cloud to optimize a correlation process of the point cloud, different down-sampling parameters can be distributed to the point cloud through the semantic label information, and the correlation process of the point cloud is optimized. Therefore, the information loss of the point cloud is reduced, and the probability of mismatching in registration is reduced. According to the method, optimization is carried out from the point cloud registration link of the SLAM method, and the positioning precision and the mapping quality of the SLAM method can be improved.

The invention relates to the technical field of image recognition, in particular to an online examination invigilation system based on image recognition, and the system comprises an image collection unit; the image analysis unit is used for determining the video state of the to-be-analyzed video according to the video duration reference value and the fuzzy reference value and determining an analysis mode according to the video state of the to-be-analyzed video; the association processing unit is used for determining the association state of the fuzzy frames according to the distance interval reference values between the fuzzy frames and determining a frame extraction point setting mode according to the association state of the fuzzy frames; the adjustment analysis unit is used for determining the category of the video frame according to the limb point change degree and the limb point change quantity reference value; and the adjustment processing unit is used for determining an adjustment mode according to the video frame aggregation area. According to the method, the selection positions of the video frames in the sports examination with complex actions can be optimized, so that the selection number of the video frames and the image quality effectively meet examination judgment requirements.

The invention discloses a circuit breaker anti-tripping function test method and system, and belongs to the field of power system protection and control, and the test method specifically comprises the following steps: I, extracting circuit breaker data, and constructing an anti-tripping function map through a relation analysis technology; according to the method, the model optimization efficiency is improved, the local optimization problem is avoided, the model can make more accurate response to the state change of the circuit breaker under the actual operation condition, the flexibility and instantaneity of a test system are improved, the sample representativeness is optimized, the anti-tripping test effect is more reliable, the data processing cost is reduced, and the data processing time is shortened. According to the method, errors caused by human intervention are reduced, the intelligent level of a test process is improved, hysteresis of static assessment can be avoided, misjudgment caused by a single factor is reduced, the accuracy of health assessment is improved, the risk management and control capability of the system is enhanced, the possibility of fault occurrence is reduced, and the overall stability of the power system is improved.

The invention discloses an outdoor environment monitoring method and system, a storage medium and a program product, and the method comprises the steps: obtaining a plurality of initial detection sub-regions; performing preliminary sampling at the central point of the initial detection sub-region to obtain initial environment data; constructing an environment parameter space distribution model; calculating a variation coefficient, and determining a high-variation sub-region; judging whether the area of the high-variation sub-region is greater than a preset minimum area or not; if yes, the minimum sub-region is divided, and the center point serves as a sampling point; if not, increasing a preset number of sampling points; controlling the detection unmanned aerial vehicle to perform secondary sampling at the sampling points to obtain initial environment data, and updating the environment parameter spatial distribution model; calculating an updated overall prediction error, and judging whether the updated overall prediction error is greater than a preset error; and if not, determining the initial environment data with the maximum similarity, and determining the region corresponding to the sampling point as a candidate experiment region. According to the invention, the accuracy of the environmental parameters detected in different outdoor environments is improved.

The invention discloses an uplink power adjustment method, apparatus and device, and a computer storage medium, and relates to the technical field of satellite communication. The method comprises the following steps: acquiring a signal transmission data sequence before a first moment; determining a weight of the signal transmission data according to the network quality parameter of the signal transmission data and a preset network quality parameter, and determining a first feature data sequence based on the signal transmission data and the corresponding weight; determining first signal transmission data sent to the satellite by the terminal at the corresponding second moment according to the corresponding relation between the feature data sequence and the signal transmission data sent to the satellite by the terminal at the target time; determining second signal transmission data corresponding to an uplink parameter influencing a network quality parameter according to the first signal transmission data; calculating predicted power based on the second signal transmission data; and adjusting the uplink power according to the predicted power. According to the embodiment of the invention, the influence of signal data transmission time on uplink power adjustment is reduced, and the real-time performance of uplink power adjustment is improved.

The invention provides a method and system for detecting the waterproof performance of communication equipment, and the method comprises the steps: monitoring the motion track and aggregation state of liquid drops on the surface of the equipment in real time through employing a high-speed camera technology in an atomization process, and recognizing the aggregation region of the liquid drops through an image processing algorithm according to the image information obtained through high-speed camera shooting; dynamically adjusting the angle and the position of the atomizing nozzle according to the identified gathering area and the gathering degree thereof so as to avoid the situation that the water vapor gathering affects the waterproof performance detection result; a plurality of temperature and humidity sensors are arranged in the atomization cavity, temperature and humidity data of the atomization environment are collected in real time, and the influence of the data on the atomization effect is analyzed; a correlation model between the temperature and humidity data and the droplet evaporation rate is established through a machine learning algorithm, and the model considers and calculates a fluid dynamics simulation result and an image monitoring result at the same time.

The invention discloses an oil-immersed power transformer monitoring method, and relates to the field of power systems, and the method comprises the steps: collecting data, collecting historical operation data, and carrying out the preprocessing; performing feature extraction on the preprocessed sensor data and historical operation data to form a sensor data feature vector and a historical operation data feature vector; fusing the sensor data feature vector and the historical operation data feature vector to form a comprehensive feature data set; establishing a fault threshold based on the historical operation data; establishing a transformer fault prediction model based on the comprehensive feature data set, and outputting a transformer fault occurrence probability; automatically adjusting a fault threshold according to a transformer fault prediction result; generating an environment state report based on the current environment state; formulating and executing a dynamic compensation strategy according to the environment state report; according to the invention, early warning of potential faults of the transformer is realized. Preventive measures can be taken before the fault occurs, and the influence of the fault on the power grid is reduced.

The present application discloses a lithium battery life prediction method and system based on the Mamba model, which relates to the field of energy storage of new energy power systems, including: obtaining aging feature matrices of multiple lithium batteries, substituting them into the Mamba model for training, and extracting the hidden state matrix sequence of each lithium battery according to the trained model, and obtaining the cycle number sequence corresponding to the target cycle life prediction point of each lithium battery through norm calculation and variational mode decomposition; based on the cycle number sequence corresponding to the target health state of all lithium batteries, and the cycle number sequence corresponding to the target cycle life prediction point of all lithium batteries, a linear relationship model for lithium battery life prediction is constructed; according to the linear relationship model for lithium battery life prediction, the cycle number sequence corresponding to the target health state of the lithium battery to be predicted is calculated. The present application improves the interpretability and computational efficiency of lithium battery life prediction and expands the scope of application of the prediction model.

The invention discloses a time sequence production model deduction method and apparatus, a terminal device and a storage medium. The method comprises the steps of obtaining a first time sequence production model of a power system; four different thinking chains are constructed; wherein the thinking chain is solved by using time decomposition, space decomposition or parallel calculation; the first time sequence production model is solved according to the four thinking chains, and a fourth solving result is obtained; the result with the minimum Euclidean distance sum with all the solving results is calculated and serves as a target result; and planning and scheduling the power system according to the numerical value of the decision variable in the target result. According to the method, the simulation precision is remarkably improved through time decomposition and space decomposition. Through parallel calculation, the solving speed is improved, important details are reserved, and errors caused by simplification are reduced. In addition, the thinking chain integration effectively integrates the results of a plurality of reasoning paths, and the representativeness and accuracy of the simulation result are improved.

The invention relates to the technical field of stable isotope tracing, in particular to a simple 13CO2 pulse marking device with adjustable volume and height and a method thereof.The simple 13CO2 pulse marking device comprises an incubator, a preparation structure is arranged on one side of the incubator, a pulse marking structure is arranged above the incubator, and a detection structure is arranged on the side adjacent to the preparation structure; a circulation structure is arranged on the side, away from the preparation structure, of the detection structure, a rising structure is arranged at the bottom of the incubator, a plant culture base is arranged above the rising structure, a volume regulation and control structure is arranged above the plant culture base, and an exhaust structure is arranged on the side, away from the detection structure, of the incubator; through organic integration of all the structures, the whole process from plant culture to pulse marking can be achieved in the same device, all the parts are matched with one another, the convenience and efficiency of experimental operation are greatly improved, errors and inconvenience caused by device conversion are reduced, and the experimental efficiency is improved. And an integrated solution is provided for accurately researching plants in different growth stages and related physiological processes.