6073 results about "Biological system" patented technology

A spatial omics multi-modal fusion method under a single cell level comprises the following steps: extracting spatial morphological characteristics of differential expression genes and cell nucleuses from spatial transcriptome data, single cell sequencing data and histological images, and realizing field adaptation among different platforms by using a conditional variation auto-encoder. And based on a probability inference model, fusing spatial transcriptome expression, unicellular omics and morphological characteristics, and jointly inferring the type and gene expression level of each cell. A spatial cell network is constructed through a graph attention mechanism, and spatial diffusion and recognition of cell types in a full slice range are realized. In combination with a multi-omics enhancement module, undetected gene and protein expression is completed based on expression similarity, and prediction consistency is improved through spatial correction. According to the method, high-resolution reconstruction of single-cell multi-omics information in a three-dimensional space is realized, the information coverage and spatial resolution of spatial omics data are improved, and an efficient and low-cost solution is provided for spatial biology and precise medical research.

The invention discloses an abnormal monitoring method and system for immune cell culture. The method comprises the following steps: collecting cell physical state parameters, culture environment parameters and metabolic biochemical indexes in a culture system in real time; performing motility rate threshold judgment and morphological analysis based on the cell physical state parameters to generate a first abnormal signal; performing dynamic trend analysis on the metabolism biochemical indexes to generate a second abnormal signal; performing grade association on the culture environment parameters, the first abnormal signal and the second abnormal signal, and outputting a monitoring abnormal grade; and performing grading response construction according to the monitoring abnormity grade to obtain an abnormity monitoring report. According to the method, the pollution diffusion risk and the functional cell failure misjudgment rate can be reduced.

The invention discloses an acid-resistant plate dark crack defect detection method and system, and relates to the technical field of acid-resistant plate defect detection.The detection method comprises the steps that multiple sets of multi-mode detection data in an acid-resistant plate detection scene are obtained, and the multiple sets of multi-mode detection data comprise polarized light appearance image data and micro-strain vibration data; and respectively extracting an appearance discriminant value, an ultrasonic discriminant value, a stress discriminant value and a micro-strain discriminant value from the modal data based on the improved twinborn attention network. According to the acid-resistant plate dark crack defect detection method and system, four-mode data of polarized light appearance, multi-frequency ultrasonic, flexible stress and micro-strain vibration are synchronously obtained through a multi-mode intelligent acquisition module: the polarized light appearance data captures surface shallow cracks, and the multi-frequency ultrasonic data penetrates through a plate body to identify deep cracks; the problem of missing detection of a traditional single mode is complementarily solved; in the analysis link, through a multi-modal attention and reinforcement learning fusion weight model, the weight of each discriminant value can be dynamically adjusted according to the environmental change, and the misjudgment of the fixed weight is avoided.

The invention discloses a poultry behavior abnormity real-time monitoring system based on multi-modal image fusion, particularly relates to the technical field of intelligent breeding behavior recognition, and is used for solving the problem of poor behavior monitoring accuracy under feather shielding. The method comprises the following steps: firstly, through combined perception of a visible light image and an infrared image, extracting a claw track interruption point and an anus temperature gradient direction, and realizing analysis of a motion state of a sheltered area; then, in combination with the heat conduction delay characteristic and the group movement direction, the flexion and extension angle of the covered leg joint is inverted, and a complete gait sequence is generated; thirdly, multi-source features such as gaits, temperature differences and body postures are fused, and a dynamic deviation model of the individuals relative to the mass center of the group is constructed; and finally, generating a stress behavior threshold curve according to the ground temperature and the ammonia gas concentration, outputting an abnormal behavior type and confidence, and realizing intelligent distinguishing of mechanical obstacles and adaptive behaviors.

The present invention provides assays and assay systems for use in spatially encoded biological assays. The invention provides an assay system comprising an assay capable of high levels of multiplexing where reagents are provided to a biological sample in defined spatial patterns; instrumentation capable of controlled delivery of reagents according to the spatial patterns; and a decoding scheme providing a readout that is digital in nature.

The invention provides a Bi-BDO fermentation pH dissolved oxygen dynamic optimization method based on an online Raman spectrum, belongs to the technical field of biological fermentation process control, and aims to solve the problems of unstable process and low efficiency caused by fermentation control lag and incapability of sensing the real metabolic state of cells in the prior art. The method comprises the following steps: acquiring the concentrations of a target product BDO and key byproducts such as acetic acid and ethanol in the fermentation liquor in real time through an online Raman spectrum; according to the method, a metabolic stress index is originally proposed and constructed, the index is obtained by performing weighted operation on the instantaneous generation rate of the by-product and the target product, and the index is used for quantitatively characterizing the intrinsic metabolic stress level of the cells in real time. The control strategy of maintaining the metabolic stress index in the preset optimal stable interval is taken as a core control strategy, the conversion from passive response to active prediction in the fermentation process is realized, and the yield, the stability and the batch repeatability of Bi-BDO production are remarkably improved.

The invention discloses a traditional Chinese medicine internal medicine deficiency syndrome conditioning effect evaluation method and system based on a wearable device, and relates to the technical field of traditional Chinese medicine clinical informationization, and the method comprises the following steps: S1, building an electrode skin complex impedance time-frequency fingerprint, executing full-band sweep frequency perturbation, collecting complex impedance data in a continuous monitoring period, and carrying out the detection of the complex impedance time-frequency fingerprint; extracting resonance peak group and sideband coupling path information, and generating a self-excitation risk spectrum as a response reconstruction reference; and S2, performing anti-fact playback based on the self-excitation risk spectrum, replaying the conductance response in a non-resonance interval, comparing a stripping environment drift signal with contact pressure noise through the risk spectrum, and extracting purified anchor point data as an interface feature calibration reference. Abnormal signal recognition and positioning are achieved through complex impedance time-frequency fingerprints, self-excitation risk spectrums, anti-fact playback and micro-capacitance imaging, interference field regulation and control and self-adaptive impedance control are combined, the accuracy and stability of traditional Chinese medicine deficiency syndrome conditioning evaluation are improved, and the method has the high anti-interference capacity and the intelligent characteristic.

The invention relates to the technical field of model analysis, in particular to an imaging flow cytometry cell detection method based on an improved model. The method comprises the following steps: introducing a cell sample to be detected into an imaging flow cytometry system integrated with a micro-fluidic chip for continuous image acquisition to generate an initial cell image sequence; an automatic digital focusing algorithm is applied to the initial cell image sequence, and a cell image frame set with the optimal focal plane is screened out; inputting the cell image frame set into a preset PA-YOLO improved model for multi-dimensional extraction and fusion, and generating a multi-scale cell characteristic spectrum; carrying out refined feature learning and cell target positioning and classification on the multi-scale cell feature spectrum, and outputting a cell detection result; and carrying out validity verification on the cell detection result, and carrying out comparative analysis in combination with an imaging flow cytometry system to generate a cell detection report. According to the method, the imaging quality and the detection accuracy of cell images with different depths can be remarkably improved.

The invention discloses an unsteady flow field dimension reduction and prediction method fusing physical modeling and deep learning, and belongs to the technical field of computer-aided fluid mechanics analysis. According to the method, firstly, a modal coefficient reflecting global dynamics is extracted from an unsteady flow field by using a DMD, and meanwhile, low-dimensional feature representation of a potential space is learned from a flow field snapshot through CVAE; the two types of features have complementarity in physical and statistical meanings, and the complex dynamic evolution law of the unsteady flow field is more effectively represented through the low-dimensional features constructed in a combined mode. On the basis, an LSTM model is used for carrying out time sequence modeling on the joint features, and high-precision prediction of future evolution of the flow field is achieved. The hybrid modeling method provided by the invention improves the dimensionality reduction efficiency and prediction precision of a high-dimensional nonlinear unsteady flow field while keeping physical consistency, and is suitable for intelligent simulation and rapid prediction tasks in a complex flow scene.

The invention discloses a water source chlorophyll a concentration prediction model design method based on machine learning. The method comprises the following steps: acquiring chlorophyll a concentration data in a to-be-predicted region for a continuous period of time; carrying out data preprocessing on the chlorophyll a concentration data, and filtering high-frequency noise by adopting wavelet transform preprocessing; constructing a concentration prediction model, carrying out data preprocessing on chlorophyll a concentration data, and filtering high-frequency noise by adopting wavelet transform preprocessing; constructing different concentration prediction models, and inputting the processed chlorophyll a concentration data and physicochemical parameters into the prediction models to obtain a chlorophyll a concentration data prediction result; and comparing prediction results of different prediction models, and determining the prediction model. According to the prediction model design method, the WT-GRU model is adopted to preprocess the data through wavelet transform, the wavelet transform effectively extracts key time scale characteristics through signal decomposition, and the accuracy of chlorophyll a concentration prediction is remarkably improved.

The invention provides an intelligent evaluation method and system for the antibacterial effect of a water matrix standard substance, and relates to the technical field of intelligent evaluation, and the method comprises the following steps: preparing a bacterial suspension in a logarithmic phase and checking turbidity; preparing a water matrix standard substance and a control solvent, and obtaining a baseline parameter set; setting inoculum size and incubation conditions, determining the antibacterial efficiency in parallel, and performing image segmentation correction on sticky colonies to obtain an original observation set; establishing a deviation transfer relationship, correcting the original data, and forming an endpoint quantization set; and the bacteriostatic validity is output through evidence fusion, and a supplementary experiment is carried out on a critical condition. According to the method, the accuracy and reliability of bacteriostatic effect evaluation of the water matrix standard substance are improved.

The invention provides a multi-source fusion spectrum cross-domain high-precision prediction method and system based on transfer learning. The method comprises the following steps: S1, acquiring spectrograms collected by a spectral imaging device under multiple wavelengths; s2, extracting various types of features from the spectrogram; s3, training a fusion model to obtain a trained fusion model; and S4, inputting a to-be-predicted spectrum into the trained fusion model, and outputting a result. According to the invention, 10 <-4 > nm-level wavelength prediction can be achieved in a common industrial camera system, and the level of a scientific research-level grating spectrometer (0.001-0.002 nm) can be reached / exceeded; on a narrow-band, middle-band and wide-band multi-scene cross-domain data set, the mean absolute error (MAE) can be reduced from the nanoscale to the magnitude of 10 <-4 > nm, and excellent robustness is kept under the conditions of noise, feature deficiency and few samples.

The invention belongs to the field of bioinformatics, and relates to an improved integrated deep learning cell communication ligand-receptor interaction prediction method. The method comprises the following steps: firstly, carrying out extraction and dimensionality reduction on biological sequence features of a ligand and a receptor, and constructing multi-modal feature input; secondly, constructing an improved deep neural network branch, introducing a batch normalization layer and a Leaky ReLU activation function, solving the problems of gradient disappearance and neuronal necrosis, and improving regularization strength to prevent overfitting; meanwhile, an enhanced heterogeneous graph auto-encoder branch is constructed, the graph embedding dimension is remarkably expanded to improve the feature capacity, and full convergence of the model is ensured by increasing training rounds; thirdly, fusing the improved deep network with the prediction probability of a heterogeneous graph auto-encoder by adopting a weighted integration strategy; and finally, outputting a potential interaction relationship based on the fusion probability. By optimizing the architecture and the strategy, the prediction accuracy and robustness are remarkably improved, and a reliable tool is provided for analyzing a complex cell communication network.

A non-invasive liquid integrity monitoring system using dielectric fingerprinting and machine learning to detect and identify contamination in sealed containers is described. The system may employ externally-mounted sensors that measure dielectric properties through electromagnetic interrogation, comparing measurements against baseline signatures to detect deviations indicating contamination, tampering, or degradation. Industry-specific ML models enable identification of specific contaminants with confidence, providing alerts without breaching container integrity.

The invention discloses a spectrum aliasing decoupling and concentration inversion method under the cross influence of multi-source environmental factors, belongs to the field of industrial process control and environment monitoring, and constructs an environment-spectrum collaborative fusion decoupling model for concentration prediction. The method specifically comprises the following steps: respectively collecting absorption spectrum signals of specified mixed gas at different temperatures, pressures and known concentrations, meanwhile, collecting environmental parameter data, constructing a multi-source data set, and carrying out denoising, dimension reduction and preprocessing on the multi-source data set; constructing a self-supervised feature extraction network for adaptive modulation of environmental parameters to realize deep fusion of spectrum and environmental information; the feature expression capability and generalization performance of the self-supervised feature extraction network are improved by using a self-supervised learning mechanism; and constructing a BPBO-GRNN self-adaptive concentration inversion optimization model for realizing inversion of mixed gas concentration and self-adaptive optimization of model parameters. According to the invention, high-precision concentration inversion and stable detection of the aliasing gas can be realized.

The invention relates to a construction method of a multi-class lipid retention time general prediction model and a prediction system. The method comprises the following steps: by taking experimental retention time tRE of a lipid compound in a training set as a dependent variable and characteristic structure parameters of the lipid compound as an independent variable, carrying out quantitative processing on the independent variable and then carrying out regression modeling analysis, the characteristic structure parameters comprise the total carbon number c and the total carbon-carbon double bond number d of a fatty acyl chain, an ether chain, an alkenyl ether chain or / and a sphingosine skeleton, the types of skeletons contained in the lipid compound and the number of corresponding skeletons, and the types of characteristic groups and residues in the lipid compound and the number of corresponding residues; carrying out numerical quantization on parameters according to the number of skeletons, characteristic groups or residues of the corresponding types; the QSRR general prediction model of the retention time of the multi-class lipid compounds is obtained by adopting regression modeling, a more accurate MRM data acquisition window can be set for the lipid compounds, and the sensitivity, stability and coverage can be improved.

The invention discloses a machine learning assisted polyethylene reaction performance prediction model training method, prediction method and device. The method comprises the following steps: acquiring a training set; screening feature items used for model training; obtaining a gradient boosting regression model for catalytic activity, a gradient boosting regression model for molecular weight and a gradient boosting regression model for molecular weight distribution; extracting feature items for model training from the data of the training set so as to obtain feature vectors; and respectively inputting the feature vectors into each model so as to train each model, thereby respectively obtaining hyper-parameters of the trained gradient-boosted regression model for catalytic activity, hyper-parameters of the trained gradient-boosted regression model for molecular weight and hyper-parameters of the trained gradient-boosted regression model for molecular weight distribution. According to the method, a model relationship between input characteristics and polymerization results (including catalytic activity, molecular weight, molecular weight distribution and the like) is established through training set learning.

The invention discloses a reaction site prediction method and device based on chemical and physical prior driving, and the method comprises the steps: extracting set features through the multi-modal input of a fusion molecular map, an SMILES sequence and a three-dimensional conformation; generating atomic embedding by using a message passing neural network, and calculating a mixed feature fusing a topological path and a three-dimensional distance; combining the key type weight to construct a graph position code of chemical environment correction; injecting the mixed distance and the charge difference into a Transform attention mechanism, and explicitly modeling an inter-atomic long-range electron effect; a model is jointly trained through double tasks of comparative learning and mask prediction, the comparative learning adopts a directional negative sample to enhance generalization, and mask prediction synchronously recovers an atom type and a charge transfer matrix; and finally, injecting quantum chemistry priori constraint attention weights such as a Fuzzy well function, outputting an atomic-scale reaction activity probability, generating a thermodynamic diagram, and realizing high-precision and interpretable active site labeling. According to the method, the drug design and reaction mechanism analysis efficiency can be remarkably improved.

The invention discloses a self-energy-supply multi-mode sensing electronic skin based on ionic gel heterojunction array integration and a preparation method and application of the self-energy-supply multi-mode sensing electronic skin. The electronic skin adopts a multi-layer composite structure design and comprises an electrode array layer, a silver paste connecting layer, a nano material doped ionic gel array layer and a pure ionic gel continuous layer, and passive self-energized work is realized through a space ion migration effect at a heterogeneous gel interface. The method is characterized in that the design of a multi-layer flexible composite structure is adopted, space-time coded light, temperature, pressure and humidity four-mode stimulation can be synchronously converted into electroneurographic signals, and a collaborative identification strategy of response intensity dynamic range and synaptic learning / delay time difference is utilized; and high-precision decoupling of the multi-source signals is realized in combination with a classification decision tree algorithm. The electronic skin has the characteristics of flexibility, deformation, environment self-repairing and bionic synapse, and geometrical characteristics of a reconfigurable target source are fused through time-space domain multi-modal data.

The invention provides a sample pretreatment automation method for flow cytometry, and belongs to the technical field of sample pretreatment for flow cytometry. A biological sample to be detected is collected and placed in a collection tube containing an EDTA-K2 anticoagulant for pretreatment; an automatic pipetting system is used for carrying out incubation reaction on an anticoagulant whole blood sample and an intelligent matching fluorescence labeling antibody mixed solution, and a double-layer game optimization verification system is used for verifying the rationality of an antibody adding proportion and reaction condition parameters; carrying out fluorescence characteristic readability index prediction on the incubated cell suspension by adopting an intelligent dilution parameter regulator model, dynamically adjusting hemolysis parameters and suspension conditions, and adding 1 * hemolysin working solution by using an automatic liquid adding device to carry out hemolysis treatment so as to finish pretreatment; the technical problems that in the pretreatment process of flow cytometry detection samples, parameters are often based on artificial experience, and the reproducibility and standardization degree of detection results are insufficient are solved.

The invention relates to the technical field of artificial intelligence, and provides a quantum-enhanced multi-scale network intrusion detection method, which comprises the following steps: calculating a covariance matrix for an original traffic feature matrix, and obtaining a feature value and a feature vector through feature decomposition, mapping each sample xi to a quantum Hilbert space to generate an enhanced feature matrix, executing complex field transformation on the enhanced feature matrix to generate an entangled feature tensor, and realizing dynamic feature enhancement through a multi-head attention mechanism based on a quantum probability amplitude; performing space-time attention calculation and gating fusion on the feature tensor after dynamic feature enhancement to obtain a space-time fusion feature; converting the space-time fusion features into a time sequence form, extracting behavior features through a multi-scale convolution branch, and fusing the behavior features to obtain a three-dimensional feature tensor; and calculating a mean value of the three-dimensional feature tensor in a sequence dimension, generating a two-dimensional feature matrix, and performing classification prediction, uncertainty quantification and threat grading evaluation based on a classification network, an uncertainty network and a threat grading network.

The invention provides a method and system for predicting the utilization rate of feed amino acid in multiple stages of laying hens, and relates to the field of bioinformatics, and the method comprises the following steps: obtaining chemical component measured values of feed raw material samples in different growth stages of the laying hens and in-vivo measured values of standard ileum amino acid digestibility; performing predictive factor screening according to the chemical component measured value and the standard ileum amino acid digestibility in-vivo measured value to obtain a predictive factor combination; constructing a prediction model according to the prediction factor combination to obtain a candidate prediction equation; optimizing according to the candidate prediction equation, and screening to obtain an optimized equation; performing model verification according to the optimization equation to obtain a target prediction model; and performing digestibility prediction according to the target prediction model to obtain a predicted standard ileum amino acid digestibility value. According to the method, the standard ileum amino acid digestibility is accurately predicted based on in-vitro detection data, and the limitation of a traditional in-vivo determination method is effectively overcome.

The invention relates to the technical field of material testing, and particularly discloses an intelligent quality detection method and system for a micro-mineral bio-organic fertilizer, local thermal excitation is applied to a fertilizer sample through a micro-area thermal pulse excitation device, a gas release kinetic curve and a spectrum change track are synchronously collected, and a gas spectrum coupling data cube is constructed; performing differential transformation and modal decomposition on the time sequence feature set, extracting transient response feature vectors and generating an activity response distribution diagram; establishing component-activity correlation analysis, and decoupling biological metabolic activity and matrix background interference through feature separation and a comparative learning strategy to obtain a dynamic metabolic fingerprint; constructing a multi-dimensional feature space by using the dynamic metabolic fingerprints and the apparent characteristic parameters, and performing information aggregation and feature reconstruction by using a graph convolutional network to generate a comprehensive quality index; and finally, realizing quality grade judgment based on a quality characteristic pyramid structure, and establishing a dynamic early warning mechanism by analyzing time sequence evolution characteristics of the activity response distribution diagram.

The invention relates to an improved YOLOv8 small target detection method based on SENet, and the method comprises the steps: introducing semantic dilution loss, and measuring the dilution degree of small target features in a channel; a suppression reverse weight is generated through an SENet structure, and background redundancy is suppressed while a high response area is reserved; a C2f structure of YOLOv8 is fused, and decoupling characteristics are transmitted in cross-layer connection; in the Neck feature pyramid, a SENet response migration relation is constructed; calculating a weight deviation value, and judging whether the small target response has spatial deviation or not; position balance loss is introduced, and feature repositioning is carried out on a small target area with overlarge center-of-gravity drift; designing a channel response consistency measurement index, and measuring the SE response consistency of the small target between different epochs; sENet channel output is extracted from the image, and the variance of target area channel response distribution is counted; a channel with high variability is weakened or suppressed from a current image detection path, a detection head is introduced into a channel gating mechanism, a stable channel is adaptively selected to participate in prediction, and the small target feature representation capability is significantly enhanced.

The invention relates to the technical field of image analysis, and discloses an end-to-end visual tactile perception method and system based on a morphology-force field analysis model, a terminal and a storage medium, and the method comprises the steps: employing a morphology reconstruction module to achieve the analysis of a micron-order contact surface, employing a force field analysis model to achieve the precise analysis of a force field in each direction, and taking the two results as a data set, inputting and mapping the image into contact morphology, normal and shear force distribution through an end-to-end network, integrating the high efficiency of data driving and the reliability of physical consistency, and finally introducing partial differential equation residual error sum into a loss function to carry out optimization. And the morphology and the force field meet the set physical consistency on the whole. According to the method, micron-sized morphology analysis and multi-axial force synchronous estimation are realized, the real-time robust performance under a high-frequency dynamic task is realized, the cost of tactile perception is reduced, and meanwhile, the accuracy of a tactile perception result is improved.

The invention discloses a poisoning defense method based on characteristic difference analysis and model layer purification. The method comprises the following steps: S1, constructing a poisoning classification model according to an electromagnetic signal sample; adversarial disturbance is introduced, cross entropy loss of disturbed samples is calculated and sorted, and a threshold value is set to distinguish clean samples from poisoned samples; s2, after the poisoning samples are separated out, the poisoning score of each layer of the model is calculated through quantification, and the higher the score is, the stronger the influence of the back door neurons of the layer on the poisoning samples is; s3, generating a pseudo-poisoning sample based on an inversion trigger, analyzing the feature distribution difference between the pseudo-poisoning sample and a clean sample, aligning a feature space and purifying a model layer by optimizing an objective function, and enhancing the distinguishing ability of the model to the sample; s4, repeating the step S3 until the model classification precision converges, and storing the optimal network parameters; and the classification precision of the model on a normal sample and the attack success rate on a poisoning sample before and after defense are evaluated. According to the method, the robustness and the safety of the model are improved, and the method has relatively high universality.

The invention discloses a protein palmitoyl transferase prediction method and system based on a multi-branch deep convolutional neural network, and belongs to the technical field of bioinformatics and artificial intelligence. The method comprises the following steps: S1, obtaining a to-be-detected protein sequence; s2, inputting the protein sequence into a pre-trained iPalmT model; and S3, judging whether the target protein is palmitoyl transferase or not according to a model output result. The iPalmT model comprises a coding module, two paths of parallel convolution branches, a feature fusion module and a classification module; and after the convolution layers of each convolution branch are stacked, an SE module is arranged and is used for channel weighting and feature re-calibration. The model extracts multi-level sequence features through convolution kernels of different scales, realizes high-precision prediction through feature fusion and a residual structure, can automatically learn multi-scale features from large-scale data, realizes end-to-end palmitoyl transferase recognition, and has high accuracy and good universality.

The invention discloses an intelligent SPR noise data removal method based on a generative adversarial network, and the method comprises the following steps: S1, collecting a response signal for preprocessing, and outputting noise data; s2, inputting the noise data into an auto-encoder to obtain a sparse latent variable; s3, performing weighted combination on the sparse latent variable features, and outputting spectrum enhancement features; s4, inputting the spectrum enhancement characteristics into a diffusion model, and outputting an SPR signal sequence; s5, inputting the SPR signal sequence into the generative adversarial network, and outputting a pseudo-truth enhanced SPR signal; s6, inputting the pseudo-truth enhanced SPR signal into a decomposition and reconstruction module to obtain a reconstructed SPR signal; s7, comparing the reconstructed SPR signal with an original labeling signal, and outputting an optimized model parameter; and S8, carrying out SPR detection on the optimized model parameters, and outputting an intelligent denoising SPR response curve. According to the invention, intelligent removal of SPR noise data is realized.

The invention discloses a radar wave measurement method and system for the liquid level of a storage tank, and relates to the technical field of liquid level measurement. The radar wave measurement method for the liquid level of the storage tank comprises the following steps: acquiring radar echo signal data of the storage tank in a set measurement period, and preprocessing the radar echo signal data; based on a pre-trained liquid level identification deep learning model, performing prediction analysis on the radar echo signal data to obtain a liquid level feature set of the storage tank; and acquiring liquid level control parameters of the storage tank, analyzing liquid level control driving indexes of the storage tank in combination with the corresponding liquid level feature set, and controlling the start-stop state of a water pump of the storage tank based on the liquid level control driving indexes. Multi-dimensional modeling is carried out on radar echo signal data in a continuous time period, the limitation that a traditional liquid level measurement method depends on echo signals at a single moment to carry out height judgment is broken through, and the method is particularly suitable for industrial liquid level monitoring requirements with high disturbance and high precision requirements.

The invention relates to the technical field of Brassica rapa polysaccharide detection, and discloses a quantitative detection method of Brassica rapa polysaccharide based on near infrared spectroscopy. The method comprises the following steps: acquiring near infrared spectrum data of a brassica rapa sample, and dividing detection stages by combining spectral characteristics to obtain a plurality of detection stage identifiers; performing differential mapping on the spectrum load spectrum according to the identifier to obtain an optical parameter set of each stage; constructing a staged near infrared spectrum quantitative model by using the set; performing importance weighting on the original spectral data according to the identifier to generate optimized spectral data; and extracting polysaccharide related characteristics from the optimized spectral data through a staged model, and outputting a predicted value of the content of the Brassica rapa polysaccharide. According to the method, through stage division, differential mapping and data weighting, the spectral data utilization rate and the model suitability are improved, a targeted technical path is provided for quantitative detection of Brassica rapa polysaccharide, and the method can be used for quality control of Brassica rapa related products.