153 results about "Nonlinear correlation" patented technology

The invention relates to the technical field of high temperature sensing and data fusion, in particular to a method for array thermocouple multi-mode compensation and DIC stress field space-time coupling fusion, which comprises the following steps: step 1, in a thermotechnical signal intelligent processing and compensation unit, completing hardware and algorithm collaborative design of an electronic cold junction compensation module; 2, constructing a multi-algorithm fusion compensation module, integrating nonlinear correction, drift compensation and interference suppression functions, and accurately coping with various interference signals through a dynamic weighting strategy; step 3, adopting a sub-pixel-level matching algorithm and a homography matrix calibration technology to realize high-precision space alignment of the temperature and stress measurement units; and establishing a nonlinear incidence relation between the temperature and the stress based on an improved Gaussian process regression model. According to the invention, based on collaborative design of the thermotechnical signal intelligent processing and compensation unit and the DIC vision and temperature data conjoint analysis module, the core precision problem of temperature and stress detection in a high-temperature environment is solved through hardware optimization and algorithm innovation.

The invention discloses a short-term power load prediction method, system and device based on multi-intelligent-model fusion and a medium, and belongs to the technical field of short-term power load prediction, and the method comprises the steps: obtaining regional historical load data and meteorological data; performing data cleaning on the obtained load data and meteorological data; measuring linear and nonlinear correlation between the power load and the meteorological factors, and screening meteorological data with high load correlation; decomposing the load data into a time sequence by using an empirical mode decomposition method based on combination of multi-scale permutation entropy to obtain a multi-scale sub-data sequence; respectively predicting the multi-scale sub-data sequences to obtain prediction results; carrying out weighted fusion on the prediction result through a long short-term memory network model to obtain a load prediction result, and optimizing model parameters to obtain a trained multi-model prediction model; and predicting the test set data by using the trained model to obtain a final load prediction result. According to the invention, the precision and adaptability of load prediction are effectively improved.

The invention provides an ecological system service flow simulation and collaborative tradeoff relation quantification method based on a graph neural network, and relates to the technical field of ecological system service simulation and quantification. According to the method, the Huaihe River basin serves as a research area, firstly, a landscape is abstracted into a graph structure, ecological patches serve as nodes and are endowed with multi-dimensional features, ecological process flow paths serve as edges, and flow attributes are quantified; then, constructing a graph neural network model, and learning inherent rules of generation, flow and consumption of an ecological system service through training; and finally, realizing ecological system service, particularly dynamic simulation of supply service and adjustment service, and quantifying the collaborative tradeoff relation by adopting a multi-index fusion method. According to the method, the nonlinear correlation of the ecological process can be accurately captured, the flow simulation and relation quantification precision is improved, scientific support is provided for ecological planning and management of the Huaihe River basin, and compared with an InVEST model, the simulation error is reduced by 20%-30%, and the collaborative tradeoff recognition accuracy is improved by 15% or above.

The invention relates to the technical field of optical communication equipment testing, in particular to an integrated optical module multi-parameter testing system and method.The method comprises the steps that a multi-channel parallel testing unit synchronously collects light spot morphology, divergence angles, insertion loss and return loss space and transmission characteristic parameters through a transmission light path and a reflection light path; the parameter collaborative analysis module performs nonlinear correlation analysis and dynamic performance threshold evaluation based on a cross-dimension correlation model; the intelligent calibration engine dynamically adjusts the test benchmark and compensation parameters according to the environment temperature and the equipment aging attenuation model; the fault diagnosis and prediction unit identifies potential defect types of the collimator, constructs a performance degradation prediction model in combination with a working state and environmental stress, and predicts a performance evolution trend according to test data; and the test report generation module automatically generates a standardized and customized dual-mode test report, a quality grade label and a performance optimization suggestion according to the prediction result and the diagnosis conclusion. Therefore, the problems of poor test precision, low test efficiency and the like in the prior art are solved.

The invention belongs to the technical field of electric power measurement, and discloses a calibration method and system of an intelligent measurement switch and a multi-switch synchronous measurement method, and the method comprises the steps: obtaining voltage and current waveform data of the intelligent measurement switch under a nonlinear load condition, and extracting a frequency spectrum feature matrix of the voltage and current waveform data; constructing an amplitude-phase coupling error model representing a nonlinear incidence relation between amplitude fluctuation and phase deviation, inputting the spectrum characteristic matrix into the amplitude-phase coupling error model, and calculating an amplitude-phase coupling error vector; performing vector decomposition on the amplitude-phase coupling error vector, and separating out an in-phase component error and an orthogonal component error; and generating a calibration compensation coefficient according to the in-phase component error and the orthogonal component error, and performing vector calibration on the intelligent measurement switch, thereby improving the calibration precision of the intelligent measurement switch.

The invention discloses a personalized physical examination period dynamic estimation system and method based on big data, and relates to the technical field of medical health data processing and intelligent evaluation. The estimation method comprises the step of constructing an integrated implementation framework including a multi-source data integration link, a multi-party cooperative processing link, a three-step modeling evaluation link and a quantitative feedback adjustment link. According to the personalized physical examination cycle dynamic estimation system and method based on big data, a medical institution, wearable equipment, family genetic disease history and government affair medical treatment are integrated through a cross-domain data fusion platform, and a multi-dimensional evaluation basis covering physiology, behavior, heredity and resource collaboration is constructed; and then through a three-step modeling process of a hybrid model training engine, the problem of insufficient data is solved through similar group data adaptation, nonlinear correlation features are mined through multiple decision trees, a risk level is finally output, and a period is dynamically adjusted in combination with medical resource assessment.

The invention discloses a foundation high-excavation low-filling operation state monitoring and early warning method based on cloud edge collaboration, and relates to the technical field of building construction.The method comprises the steps that firstly, various sensors are deployed according to topography and geology to collect multi-source data, abnormal value detection and correction processing are conducted on the collected multi-source data, and the abnormal value of the collected multi-source data is obtained; integrating the processed multi-source data to obtain multi-class feature data; step 2, constructing an improved LSTM model by taking the multi-class feature data as input and adopting historical operation state data as a training sample; the improved LSTM model focuses key time steps and key sensor features in the multi-class feature data by introducing an attention mechanism, and performs feature enhancement to optimize the state characterization capability; in the improved LSTM model, a mean square error is used as a loss function, an Adam optimizer is used for initial training, and an operation state evaluation model is obtained and used for learning nonlinear correlation between various types of feature data and operation states.

The invention relates to the technical field of electrical fault detection, in particular to an online fault judgment and automatic detection method for a marine cable, which comprises the following steps of: acquiring ground leakage current and load current in operation, extracting an active component of the leakage current and analyzing the nonlinear correlation between the active component and the load current to realize online early warning of insulation degradation; when the ship is in a working condition of allowing short-time power failure of partial non-critical loops, positioning a fault branch based on a normalization result of the ground capacitance variation before and after the power failure of each branch and the cable length; after power supply is recovered, the fault type is judged by combining the leakage current fundamental wave and phase voltage phase difference and the harmonic distortion rate; during power-off maintenance, high-frequency carrier waves are injected, the position of a fault point is determined according to current attenuation abnormity, correction is carried out by combining temperature and vibration factors, and the detection accuracy and the positioning precision are improved.

The invention discloses a storage battery abnormal state identification method, system and device and a medium, and particularly relates to the technical field of storage battery monitoring, and the technical key points are as follows: obtaining working performance parameters and engineering physical parameters of a storage battery to be identified, constructing a multi-dimensional parameter time sequence, and segmenting the multi-dimensional parameter time sequence to obtain three-dimensional data pieces; sliding on the multi-dimensional parameter time sequence by using a sliding window with a preset size, calculating a linear correlation feature, a nonlinear correlation feature and a time sequence trend feature of the multi-dimensional parameter time sequence in each sliding window, and fusing to obtain a correlation feature vector; splicing the three-dimensional data pieces and the associated feature vectors to obtain identification parameter features; inputting the identification parameter features into a pre-trained abnormal state identification model, and identifying to obtain probability distribution of an abnormal state; the abnormal state recognition model is obtained by training an AA-LSTM network; and when the probability distribution meets a preset judgment condition, outputting a corresponding state judgment result.

The invention relates to a plasma active group and microbial cell membrane action analysis system, which comprises a plasma active group diagnosis module used for acquiring plasma active group data under different conditions, and the group data comprises the type, concentration and spatial distribution of active groups; the microbial characterization analysis module is used for acquiring cell membrane data before and after plasma treatment, and the cell membrane data comprises morphological structure, component and functional change of cell membranes; and the machine learning data analysis module is used for carrying out data preprocessing, feature extraction and importance sorting on the acquired plasma active group data and cell membrane data so as to select important features to carry out regression analysis and obtain a nonlinear correlation model of the action of the plasma active group and the cell membrane. Compared with the prior art, the method has the advantages that the interaction effect and mechanism of the plasma active group and the microbial cell membrane can be quickly and accurately analyzed and predicted, and the research efficiency and precision are remarkably improved.

The invention discloses a depression detection method fusing a multi-modal attention mechanism, and relates to the technical field of auxiliary psychological health diagnosis, and the method comprises the steps: respectively extracting a facial image and a voice signal from an original video, extracting a global feature map from the facial image through a deep convolutional network, and introducing a local fusion module and a global fusion module; combining a Gaussian pyramid attention module with a spatial domain attention module; speech signals are converted into a Mel spectrogram through preprocessing, speech features are extracted through a SincNet network, and the speech features are further sent to a time-frequency attention module to highlight depression-related intonation and energy changes; in the feature fusion stage, a self-adaptive attention mechanism is adopted, self-attention modeling is performed on face and voice modes, cross-mode fusion and context modeling are completed through a Query-Key-Value structure, and a depression score is output through a full connection layer. According to the scheme, the problem that cross-modal nonlinear correlation is difficult to dynamically capture is solved, and effective technical support is provided for mental health assessment and intervention.

The invention discloses a mosquito distribution prediction method and system, a storage medium and equipment, and relates to the technical field of data processing, and is used for predicting the mosquito distribution state, and the method comprises the steps: synchronously collecting environment data and mosquito population data, carrying out the time-space alignment, building a nonlinear correlation model through combining a bidirectional LSTM model and transfer learning, and carrying out the prediction of the mosquito distribution state. Complex nonlinear correlation between environmental factors and mosquito population dynamics can be accurately captured; mosquito distribution of different time scales is predicted by using a graph neural network and a Transform architecture, and accurate modeling of a multi-scale space-time interaction rule of mosquito distribution is realized. The prediction result is calibrated through a deviation correction mechanism, the temporal-spatial resolution and accuracy of mosquito distribution prediction are remarkably improved, and reliable data support is provided for accurate prevention and control of insect-borne infectious diseases.

The invention relates to the field of cosmetic testing, in particular to a systematic evaluation method of a natural avocado extract-containing mouth fat composition, which comprises the following steps: mixing pulp with an extraction solvent, condensing and refluxing for 14-18 hours to obtain an avocado extract, adding allantoin for corrosion prevention, and storing; the fixed substrate comprises the following components: beeswax, paraffin, coconut oil, lake, lemon oil, vanillin, glyceryl monostearate, titanium dioxide, castor oil, wool fat and isopropyl palmitate, and an avocado extract is added to form a contrast formula; a multi-dimensional performance test pack is adopted, a non-linear correlation model is established, and the optimal adding proportion of the adding amount of the avocado extract is determined; and standardized testing. According to the method, three technical problems of fragmentation of evaluation dimensions, insufficient parameter association and lack of method standardization in the prior art are solved through a full-process framework of directional extraction, gradient formula, multi-dimensional test, parameter association and standardization specification.

The application discloses a current transformer magnetic characteristic test system and method and a computer program product, wherein the system comprises an original data acquisition module, a data feature generation module, a quality index evaluation module, a high load performance test module and a threshold correction determination module; core parameters are obtained by dynamically adjusting a sampling strategy, a feature vector is generated after preprocessing, a multilayer convolutional neural network model is used to mine parameter nonlinear correlation and output a quality index; a quality evaluation correction value is generated by combining temperature rise and noise data under a high load condition, an evaluation threshold is dynamically corrected, and test result determination is realized. The application effectively solves the problems of high misjudgment rate of static threshold determination in the prior art, difficulty in capturing parameter nonlinear correlation and inability to predict long-term stability, significantly improves the precision and reliability of magnetic characteristic test, accurately predicts the long-term full-load operation stability of equipment, and provides a reliable basis for power system core equipment selection and safe operation.

The application discloses a kind of machine room equipment intelligent remote operation and maintenance method and platform, it is related to intelligent operation and maintenance technical field, including, construct bayesian probability model, and combine optical signal characteristics and current harmonic characteristics, predict the failure probability distribution of machine room equipment;According to the failure probability distribution of machine room equipment, convert fault coordinates into equipment logical identifier, and detect the quantum teleportation link of machine room equipment, generate machine room equipment switching instruction according to detection result;According to machine room equipment switching instruction, send Bell state measurement command to fault equipment, and carry out quantum state reconstruction and machine room equipment switching.The application constructs multilayer bayesian probability model based on Gaussian distribution, Granger causality test and variational inference, realizes the nonlinear correlation analysis of optical signal wavelength shift and current harmonic characteristics, can accurately capture the weak signs of potential equipment failure, to significantly improve the sensitivity and reliability of failure prediction.

This invention discloses a fire-fighting pipe fitting leakage risk early warning system based on big data analysis, comprising the following steps: collecting multi-dimensional time-series data such as pressure, flow rate, temperature, and humidity; constructing a data processing and modeling workflow; employing kernel canonical correlation analysis to extract nonlinear correlation features between different monitoring parameters to identify weak correlation changes before leakage; and constructing an anomaly measurement mechanism based on the maximum correlation entropy criterion to quantify the degree of feature shift. By fusing the above correlation features and entropy information, a dynamic risk index is generated and compared with a dynamic threshold to achieve real-time early warning of leakage risk, effectively supporting early fault detection and intelligent assessment of fire-fighting pipe fittings. This invention achieves dynamic perception and intelligent judgment of fire-fighting pipe fitting leakage risk, possessing data-driven early warning capabilities.

The application relates to the field of animal genetic breeding technology, and discloses a local pig breed multi-node block chain collaborative breeding method. According to the method, key data abstracts, evaluation results, model versions and breeding decisions are chained and left marks in a window period through a permissioned consortium chain and a consensus verification mechanism, the source is clear, tamper-proof and auditable, the problem that data standards are different, difficult to trace and difficult to trust in traditional multi-subject collaboration is solved, in addition, an AI multi-factor breeding evaluation system can simultaneously process multiple traits such as meat quality, growth, reproduction, health resistance and environmental management factors, can depict the nonlinear correlation between complex traits, can improve the evaluation precision and stability of the comprehensive genetic value of local pig breeds, can reduce the risk of decision-making errors caused by single-point data or single-algorithm deviation, can realize cross-node alignment and joint use of dispersed data through a rolling window and a labeled archive, and can make up for the short board of insufficient samples of a single breeding unit.

The present application relates to water and fertilizer management technical field, specifically to a kind of agricultural water and fertilizer management method and system based on cloud platform, including the following steps, utilize sensor to collect crop image and extract chlorophyll and leaf area characteristics, analyze variation rate to determine crop growth process and time sensitivity, construct index type dynamic weight mapping relationship, task resource coupling index is calculated in combination with cloud node load and fertilization data fluctuation, based on index task sequencing and execution time delay deviation compensation, generate water and fertilizer management instruction.In the present application, by fusing multi-dimensional morphological features and environmental load data to construct a dynamic control model, a nonlinear correlation between crop demand and execution weight is established using an exponential function mapping mechanism, precise perception of crop growth demand and adaptive optimization of task execution timing are achieved, the task queue is flexibly adjusted according to the resource coupling state, resource competition conflicts are effectively avoided, and the efficiency of water and fertilizer collaborative management is improved.

The invention discloses a dual-channel optical image authentication method based on a polarization multiplexing metasurface, and the method comprises the steps: firstly, calculating an authentication phase of a dual-channel plaintext image through employing a sparse constraint-driven authentication holographic algorithm; the method comprises the following steps: firstly, obtaining a target transmission phase and a geometric phase of a polarization multiplexing metasurface according to a composite phase regulation and control principle, then carrying out parameter scanning on a basic unit of the nano-column metasurface, establishing a transmission and geometric phase database, and finally determining structural parameters of each nano-column pixel by pixel, thereby completing construction of the polarization multiplexing authentication metasurface. And an authentication step: firstly, respectively illuminating the metasurface by using left-handed circularly polarized light and right-handed circularly polarized light to obtain a far-field diffracted noise-like image, then calculating nonlinear correlation distribution of the diffracted image and a plaintext image of a corresponding channel, and judging an authentication result of each channel according to whether the signal-to-noise ratio of the nonlinear correlation distribution reaches the standard or not. The method provided by the invention has the advantages of large authentication capacity, high authentication efficiency and no plaintext information leakage.

This invention discloses a method for coupling cardiac and brain electrical signals under resting conditions, comprising the following steps: acquiring raw electrocardiogram (ECG) signals and raw brain electrical signals; performing a first preprocessing on the raw ECG signals to obtain an instantaneous heart rate power spectrum; performing a second preprocessing on the raw brain electrical signals to obtain a first brain electrical power spectrum and a second brain electrical power spectrum for each preset frequency band; determining ECG fitting power data and cardiac-brain fitting power data based on the instantaneous heart rate power spectrum and the first brain electrical power spectrum, respectively; determining the F-statistic based on the ECG fitting power data and the cardiac-brain fitting power data; determining the ECG power phase space and the brain electrical power phase space based on the instantaneous heart rate power spectrum and the second brain electrical power spectrum; and determining a first nonlinear correlation coefficient and a second nonlinear correlation coefficient based on the ECG power phase space and the brain electrical power phase space. This invention, by calculating the coupling relationship and degree of coupling between the heart and brain from both linear and nonlinear perspectives, can comprehensively and accurately characterize the complex dynamic relationship between the heart and brain.

The application discloses a kind of chronic coronary syndrome risk stratification methods based on coronary microcirculation resistance index, it is related to medical data processing technical field.The method comprises: the clinical characteristic data of patient to be evaluated is obtained;The clinical characteristic data is input into the preset risk stratification model, and the risk group of the patient to be evaluated is obtained according to preset split condition.The preset split condition determines the split priority by analyzing the nonlinear correlation and the degree of distinction of multidimensional feature data, and generates a multi-layer classification model by combining survival tree algorithm training.The application breaks through the limitation of single index evaluation, effectively captures the nonlinear interaction between clinical indicators, significantly improves the risk stratification accuracy, can accurately identify the very low risk and high-risk subgroup, avoid clinical over-treatment or insufficient intervention treatment, and the model has strong interpretability and is easy to promote clinically.

This invention discloses a comprehensive wastewater treatment management system and method, belonging to the field of wastewater treatment technology. The method acquires historical water quality parameter sequences and real-time process parameters for each monitoring node; performs phase space reconstruction on the historical water quality parameter sequences to obtain the attractor trajectory matrix of each node; calculates the maximum Lyapunov exponent difference between nodes and constructs a dynamic correlation matrix; uses the dynamic correlation matrix to drive virtual particles to randomly walk in the node space, with the movement probability determined by the local entropy of the current node's attractor trajectory matrix; inputs the walking trajectory sequence into a deep neural network based on a residual structure to output the water quality exceedance risk index for each node at future times; and adjusts the operating parameters of the wastewater treatment equipment based on the risk index. This application can dynamically capture the nonlinear correlation characteristics between nodes, improving the accuracy and timeliness of risk prediction for wastewater treatment systems.

The application provides a sintering flue gas CO emission concentration prediction method, and relates to the field of sintering process pollutant treatment. It comprises the following steps: S1, data acquisition and preliminary rejection; S2, constructing a sample data set and preprocessing it; S3, characteristic value screening, based on the preprocessed sample data set, combining a nonlinear correlation analysis method and a model-driven recursive elimination strategy, constructing an optimal feature subset; S4, integrated modeling, adopting a Stacking integrated learning framework, integrating the advantages of XGBoost, random forest and gradient boosting tree algorithms, and constructing an effluent CO concentration prediction model. Through multi-layer screening of characteristic values, the application clearly determines the dominant action mechanism of each process link on CO generation from the data level, and significantly improves the prediction accuracy and robustness compared with existing models.

This invention discloses an adaptive AC / CDC power supply control method and system based on neural networks, belonging to the field of power supply control technology. By deeply integrating neural network technology with wide voltage impedance matching control and overall dynamic control of the AC / CDC power supply, it divides voltage characteristic intervals and constructs nonlinear correlation models of input impedance, grid voltage, and output power within each interval using neural networks. This achieves adaptive impedance matching by dynamically generating impedance matching control parameters based on real-time operating conditions within each interval. A smooth switching mapping relationship of control parameters between adjacent voltage characteristic intervals is established, enabling seamless adjustment of control parameters when the input voltage switches between intervals. Using a power factor correction circuit as the core regulating component, its parameters are dynamically adjusted via neural networks to achieve real-time and accurate matching of input impedance with the grid side. Combined with output closed-loop regulation, this meets the output requirements of electrical equipment, completing the overall adaptive control of the AC / CDC power supply.

The application discloses a method for accurately evaluating the contribution of meteorological bias based on multi-technology integration of atmospheric pollutants simulation bias, which solves the technical problems of insufficient correlation and quantification of meteorological bias and pollution simulation bias, insufficient depth of bias analysis, and missing spatiotemporal contribution rule representation in the prior art. The WRF-CMAQ coupling mode is used to obtain meteorological and pollutant concentration simulation data, and combined with the observation data of the national control site, a standardized bias feature variable data set containing meteorological bias and pollutant concentration bias is constructed. The VIF factor is used to screen and eliminate parameter collinearity, and an XGBoost bias model is constructed to quantify the nonlinear correlation between meteorological bias and pollutant concentration bias. The SHAP model is introduced to analyze the contribution weight of each meteorological bias parameter. Combined with the spatiotemporal information of the site, the Kriging interpolation is used to generate the global spatiotemporal distribution atlas of the contribution of each meteorological bias parameter. The application provides a precise quantitative basis for the targeted optimization of the WRF meteorological field and the improvement of the simulation accuracy of atmospheric pollution.

The invention relates to the technical field of intelligent water affair treatment, in particular to an intelligent detection method and device for the denitrification efficiency of a denitrification reactor, and the method comprises the following steps: obtaining a to-be-detected image; performing instance segmentation processing on the to-be-detected image to obtain bubble parameters; a denitrification efficiency detection model is constructed and trained; and inputting the bubble parameters into a trained denitrification efficiency detection model to obtain a detection result. According to the embodiment of the invention, the experiment repeatability is ensured through the design of the parallel reactor, the bubble characteristics are accurately extracted in combination with the MaskFreeVIS model, and the nonlinear correlation model is constructed by using the BP neural network, so that the relative error between the detection result and the measured value of the national standard method is controlled within the engineering allowable range, and the actual detection precision requirement is met.

This invention discloses a method and system for monitoring the operating status of power transmission and transformation equipment. First, real-time operating data of the power transmission and transformation equipment is collected and standardized for preprocessing. Then, feature extraction is performed on the preprocessed data to obtain feature data of the power transmission and transformation equipment. A pre-trained least squares support vector machine model is used to obtain the equipment operating status prediction result. Next, the equipment operating status prediction result is converted into a state confidence score. The state confidence scores are then fused using an improved D-S evidence theory method based on Euclidean distance to obtain a comprehensive confidence score for the equipment operating status. Finally, based on the comprehensive confidence score, an exponentially weighted moving average algorithm is used to construct a dynamic threshold for graded early warning of the power transmission and transformation equipment. This invention solves the technical problem that simple models cannot cope with the nonlinear correlation of multiple parameters in power transmission and transformation, and accurately adapts to the actual operation and maintenance needs of multi-parameter collaborative monitoring of power transmission and transformation systems.

This invention relates to the field of data deduplication technology, and discloses a method and system for deduplicating redundant information based on data feature recognition. The method includes: acquiring terminal feature data of the target object; analyzing the correlation between features based on the preprocessed terminal feature data; generating a correlation contribution degree representing the correlation between features; this scheme can retain the nonlinear correlation between features through the correlation contribution degree; adaptively distinguishing the degree of redundancy through the generated feature correlation redundancy set; further fusing the same-direction locking value and the stripping binding coefficient to obtain the redundancy confidence degree; thereby eliminating common environmental interference; and finally obtaining the deduplicated feature set through natural segmentation points and reverse feature pairs. Compared with existing linear dimensionality reduction methods such as PCA, this scheme completely preserves the local structure and high-order correlation information in high-dimensional sparse data, which can reduce the missed and false judgment rates and improve the deduplication accuracy of smart home Wi-Fi router terminal feature data.

The invention relates to the technical field of atomizer control, in particular to an intelligent atomization control method and system for an atomizer, and the method comprises the steps: obtaining parameters of an equivalent model of a piezoelectric transducer; analyzing parameter fluctuation characteristics of the piezoelectric transducer under different external conditions according to parameters of the equivalent model; constructing an overall equivalent circuit of the atomizer, wherein the overall equivalent circuit comprises an LC filter and a piezoelectric transducer at the output end of an inverter; applying one or more pulse voltages to the overall equivalent circuit to trigger a transient phenomenon, measuring a transient current in the circuit, and determining the overall resonant frequency; based on the nonlinear correlation between the whole resonant frequency and the mechanical resonant frequency of the piezoelectric transducer, fitting related data by using a curve fitting algorithm; and according to the result of the curve fitting algorithm, calculating and tracking the mechanical resonant frequency of the piezoelectric transducer, and applying the tracked mechanical resonant frequency to the atomization system. The problems of slow tracking and low efficiency caused by fluctuation of the resonant frequency of the piezoelectric transducer in an existing atomization system due to external conditions can be solved.

The present invention relates to a control method and system of a front-end conveying device for soil leaching remediation. The method includes: acquiring device monitoring status data, which encompasses soil weight, feeder rate, and conveyor belt speed, along with an image of the soil to be remediated from the conveying device; obtaining the soil remediation boundary region based on the image of the soil to be remediated; performing non-linear correlation mapping learning on the conveyor belt speed according to the soil weight parameters to obtain weight-conveying speed correlation data; conducting multi-level cooperative response neural network learning on the conveyor belt speed and the feeder's feeding rate based on the weight-conveying speed correlation data to generate cooperative response data for the conveying device; acquiring a monitoring image of the front-end conveying device; and deriving 3D component structure data from these images. This approach enables precise feeding control of the conveying device.