52 results about "Wavelet filtering" patented technology

The invention relates to the technical field of information processing, in particular to a mine microseism positioning control system and method.The mine microseism positioning control method comprises the steps that microseism signals are synchronously collected through a geophone, an accelerometer, an acoustic emission sensor and an optical fiber sensor, and data timestamps are aligned based on a GPS / Beidou clock; blind source separation is carried out on the signals after wavelet filtering, independent seismic source components are extracted, multi-sensor features are fused through a graph neural network, and a space-time joint feature matrix is constructed; classifying micro-seismic event types by using a ResNet-LSTM hybrid model, generating a seismic source coordinate initial solution based on deep reinforcement learning, and iteratively converging to an optimal solution through a particle swarm optimization algorithm; and mapping a positioning result to a three-dimensional geological grid model, simulating an energy diffusion path, triggering a three-level alarm according to the event energy density, and automatically pushing an emergency instruction to a mine safety management system. Therefore, the problem of low precision of the existing mine microseism positioning control system is solved.

The invention relates to the technical field of relay protection loop detection, and discloses a relay protection loop fault detection method and system, comprising data acquisition, data processing, feature extraction, fault diagnosis and early warning and alarming. Multi-dimensional state data of current, voltage, temperature and vibration are collected in real time, wavelet filtering, mean or median filtering and normalization preprocessing are performed, comprehensive characteristic parameters are extracted in combination with time domain and frequency domain analysis and wavelet packet decomposition, a fault is accurately diagnosed and positioned through a fault diagnosis model, early warning and alarming are achieved based on graded thresholds, and the fault diagnosis accuracy is improved. The fault key information is synchronously transmitted to the operation and maintenance terminal, database storage and display terminal display are matched, the problems of poor real-time performance, one-sided feature extraction, no graded early warning and the like of traditional detection are effectively solved, the fault detection efficiency, the diagnosis accuracy and the operation and maintenance response speed are greatly improved, the operation risk of a power system is remarkably reduced, and the safety and stability of the power system are guaranteed.

The invention discloses a Mini LED lamp panel needle mark defect detection method and system, and the method comprises the following steps: S1, carrying out the preprocessing of a Mini LED lamp panel surface image, suppressing high-frequency noise, and enhancing the defect features; s2, extracting defect features by adopting a self-adaptive convolution adjacency analysis method: S21, dynamically adjusting the shape and size of a convolution kernel through a deformable self-adaptive convolution kernel, and matching the local form of the needle mark defect; and S22, carrying out correlation analysis on the pixel points and neighborhoods thereof, and eliminating isolated noise interference. According to the method, defect forms are dynamically matched through the self-adaptive convolution kernel, isolated noise is eliminated through adjacency analysis, defects of different sizes are covered through multi-scale fusion, wavelet filtering and a parallel computing architecture are combined, the detection precision and the anti-jamming capability are remarkably improved, stable recognition of the tiny needle marks in the complex environment is achieved, meanwhile, high-speed real-time processing is guaranteed, and the detection accuracy and the anti-jamming capability are improved. The method is suitable for diversified industrial scenes and material requirements, reduces the false detection and omission ratio, and promotes the intelligent upgrading of precision manufacturing quality inspection.

The invention relates to the technical field of power distribution network fault detection, and provides a neutral point small current grounding power distribution network single-phase grounding fault section positioning method based on a space-time diagram wavelet neural network. The method comprises the following steps: constructing a training data set covering multiple types of single-phase earth fault scenes, and carrying out time sequence electrical quantity sampling; data preprocessing is completed through operations such as data cleaning and missing completion; constructing a spatial-temporal feature extraction module fusing a graph wavelet neural network and a gating circulation unit network, and carrying out spatial-temporal joint modeling on node voltage and current time sequence information; and outputting a node-level fault positioning probability through a full connection layer and a Softmax classifier. According to the method, the response capability of the model to topological disturbance is enhanced through frequency domain wavelet filtering, the information transmission efficiency is improved in combination with a residual mechanism, the fault section identification precision under the conditions of sparse observation data and weak electrical disturbance characteristics is effectively improved, and the method is suitable for a small current grounding fault positioning task in a complex operation environment of a power distribution network.

The invention provides a hot rolled steel strip surface defect detection method based on target detection, and aims to solve the problems of difficulty in multi-scale small target recognition, insufficient feature fusion and complex background interference in hot rolled steel strip surface defect detection. Extracting multi-scale defect features by using wavelet convolution through decomposition, convolution and reconstruction processes; multi-scale features are adaptively fused based on channels and space attention through a dynamic feature fusion module (DFF); a dynamic hyperbolic tangent function (DyT) is used to replace a normalization layer to dynamically adjust the input range and compress extreme values to reduce the amount of calculation. The method has the effects of high detection average precision (mAP), low missing report rate and remarkably reduced calculation complexity, effectively improves the efficiency and reliability of identifying the surface defects of the hot rolled steel strip in a complex industrial environment, and is suitable for intelligent steel manufacturing quality control.

The invention discloses an energy efficiency optimization regulation and control method and system combined with energy consumption data analysis, and relates to the technical field of energy efficiency optimization regulation and control. By combining energy consumption data analysis and a support vector machine model, the relation between equipment and regional energy consumption is accurately captured, the future energy efficiency change trend is predicted, global optimization is performed by using a particle swarm optimization algorithm, parameters such as the use duration, the load rate and the power of the equipment are adjusted in real time, energy efficiency management is optimized, and the precision and the flexibility are improved; compared with a traditional static regulation and control method, the energy efficiency requirements under different working conditions can be dynamically responded; the energy consumption data is collected in real time, wavelet filtering and normalization processing are carried out, data accuracy and consistency are ensured, resource waste and operation cost are reduced through particle swarm optimization, and energy consumption and operation cost are reduced; and the PID controller is combined to perform smooth control on the scheduling process, so that the problem of instability of the system is avoided.

The present invention relates to the field of wind turbine monitoring technology, and specifically to a monitoring method, device, equipment and medium for a wind turbine pitch system. The method comprises: collecting image data of the wind turbine pitch system; grayscale processing the image data based on an adaptive grayscale algorithm adjusted by parameters; filtering the grayscale image data using median filtering, Gaussian filtering and wavelet filtering to obtain filtered image data; edge detection and feature and feature point recognition of the filtered image data, wherein the feature point recognition adopts SIFT and SURF fusion algorithms; based on the recognized feature points, the angle of the wind turbine pitch system is calculated according to a geometric relationship algorithm, or, based on the recognized features, the angle of the wind turbine pitch system is calculated according to a template matching algorithm. This method overcomes many drawbacks of traditional sensor monitoring methods, and can timely and accurately grasp the operating status of the pitch system, effectively reducing the probability of wind turbine shutdown due to pitch system failure.

The invention relates to the field of deformation monitoring, in particular to an image deformation monitoring method, device and equipment and a program product. The method comprises the steps that matching errors are remarkably reduced by combining a Zhang's calibration method with epipolar correction, and the signal-to-noise ratio and the contrast ratio of an image are enhanced through median + wavelet filtering and histogram equalization processing. Through multi-scale census transformation and weighted Hamming distance calculation, local and global information can be effectively combined, and the robustness of a cost matrix is enhanced; according to the eight-path aggregation optimization method based on dynamic planning, the precision and the calculation efficiency of parallax calculation are further improved. According to the full-image displacement calculation method based on SIFT feature guidance, the problem of displacement propagation error accumulation is solved through sub-region matching and Gaussian Newton iterative optimization, the displacement measurement precision of a low-texture region is remarkably improved, and good robustness and accuracy are achieved in a complex scene.

The invention discloses a cone motion test data processing method based on parallel calculation and harmonic wavelet filtering, and the method comprises the steps: collecting an original voltage signal matrix measured by a wind tunnel force measurement six-component balance through a data collection system when a test model carries out the cone motion in a cone motion wind tunnel test; a principal coefficient matrix and a secondary coefficient matrix are constructed by using a six-component balance formula matrix, and a parallel resolving matrix is constructed by using the principal coefficient matrix and an original voltage signal matrix; iteratively solving a time-domain balance load matrix at each moment in the conical motion wind tunnel test based on the original voltage signal matrix, the principal coefficient matrix, the secondary coefficient matrix and the parallel solution matrix; the method comprises the following steps: determining the center frequency of a harmonic wavelet according to the prior information of a conical motion wind tunnel test, constructing a generalized harmonic wavelet, constructing a comb filter in a frequency domain based on the generalized harmonic wavelet, filtering a frequency domain balance load matrix by using the constructed comb filter, and then converting the frequency domain balance load matrix into a time domain, thereby completing the extraction and reconstruction of load data.

The invention belongs to the technical field of inertial navigation, and provides an inertial instrument anti-disturbance alignment method based on sliding window wavelet filtering to solve the problems that measurement information cannot be fully utilized, an alignment result cannot be globally optimal and is seriously influenced by sudden change interference in an existing alignment method. The anti-disturbance alignment method comprises the following steps: extracting a speed error of an inertial instrument; based on a sliding window wavelet filtering method, carrying out noise reduction processing on system noise of the inertial instrument; and carrying out anti-disturbance self-alignment on the inertial instrument according to the speed error and the noise-reduced output data of the inertial instrument. According to the method, the output data of the inertial instrument can be subjected to noise reduction processing, the holding time of the alignment precision of the inertial measurement unit is prolonged, the dispersion of a convergence value is reduced, and the navigation precision is improved.

The application discloses a kind of traffic image segmentation control method and system, it is related to image processing field, wherein the method comprises: the camera of interactive target vehicle is obtained first traffic image;According to wavelet filtering algorithm, first traffic image is carried out denoising processing, and second traffic image is obtained;Based on the second traffic image, ORB feature recognition is carried out, and ORB feature recognition result is obtained;Based on the ORB feature recognition result, clustering is carried out, and ORB feature clustering result is obtained;Based on the ORB feature clustering result, the second traffic image is carried out background isolation, and third traffic image is obtained, and, third traffic image has ORB feature mark;Traffic image segmentation channel is built;Based on the ORB feature mark, according to the traffic image segmentation channel, third traffic image is carried out segmentation control, and target traffic image segmentation result is obtained.The technical problem that present technique is low in accuracy for traffic image segmentation is solved.

The invention relates to the technical field of electrocardiosignal quality evaluation, and discloses an electrocardiosignal quality evaluation method based on an unsupervised cascade adaptive network, which comprises the following steps: S1, preprocessing an obtained original electrocardiosignal: removing power frequency interference through adaptive notch filtering, removing high-frequency myoelectricity noise through soft threshold wavelet filtering, and obtaining a pre-processed electrocardiosignal; keeping a potential pathological characteristic waveform in a filtering process to obtain a preprocessed electrocardiosignal; s2, unsupervised multi-modal feature extraction: an unsupervised feature extraction network is constructed based on an auto-encoder; a normal electrocardiosignal distribution rule is automatically learned through an auto-encoder, so that the dependence on labeling resources of professional doctors is reduced; meanwhile, by means of a two-stage self-adaptive evaluation network, significant noise is filtered first, then pathological signals and noise are accurately distinguished, it is effectively avoided that abnormal waveforms caused by diseases such as myocardial infarction and atrial fibrillation are misjudged as noise, the retention rate of the pathological signals is remarkably increased, and more complete effective data support is provided for clinical diagnosis.

The invention discloses a GPS (Global Positioning System) and inertial navigation fused high-precision navigation method, aiming at the problems that a GPS signal is easily shielded and interfered and an inertial navigation error is accumulated along with time, high-precision navigation is realized through data preprocessing, a self-adaptive fusion algorithm, GPS signal interruption processing and fusion result optimization. In the data preprocessing, multi-path effect detection and correction are performed on GPS data, and zero offset error compensation is performed on inertial navigation data; the adaptive fusion algorithm constructs a model based on a fuzzy logic system, and updates a fusion weight in real time; when a GPS signal is interrupted, map matching is adopted to assist navigation, and the prediction model is utilized to compensate an inertial navigation error; and a fusion result is subjected to wavelet filtering and smoothing processing, and the accuracy is ensured by using consistency check. The method can effectively overcome the limitation of independent use of GPS and inertial navigation, realizes high-precision, continuous and reliable navigation in a complex environment, and improves the adaptability and stability of a navigation system.

The invention provides an easily-confused emotion recognition method based on multi-path feature extraction and gating fusion. The method can be applied to scenes such as human-computer interaction, emotion calculation and psychological health auxiliary diagnosis. According to the method, a feature path is constructed for each group of emotions aiming at three groups of easily-confused emotions of happiness-angry, fear-surprising and sadness-neutral, each path adopts different wavelet parameter sets to generate a multi-scale wavelet filtering kernel, and multi-path time-frequency features are extracted from the same voice signal. And inputting each path output into a gating attention mechanism module, calculating a path weight and performing weighted summation to obtain a fusion feature for easily confused emotion discrimination, and inputting the fusion feature into a classifier to output an emotion category. According to the method, a wavelet filtering kernel group emphasizing different emotion categories is constructed, a multi-path feature extraction structure is generated, and fusion is performed by using a gating mechanism, so that the model can realize easy-to-confusion emotion recognition according to feature contributions of different paths, and the easy-to-confusion emotion recognition accuracy of the model is improved.

The invention belongs to the field of power distribution network governance, and relates to a power distribution network harmonic optimization method and system based on electrochemical energy storage, and the method comprises the steps: collecting initial harmonic data, and carrying out the preprocessing of the initial harmonic data, and obtaining the processed harmonic data; the harmonic data comprises power grid current, energy storage system parameters, PCS power and power grid voltage; the preprocessing comprises wavelet filtering processing and direct current component filtering processing on the initial harmonic data in sequence; based on the processed harmonic data, calculating to obtain a fundamental wave parameter; the fundamental wave parameters comprise fundamental wave active power, fundamental wave reactive power and fundamental wave apparent power; based on the fundamental wave parameter, calculating to obtain a fundamental wave component, and based on the fundamental wave component, determining a compensation current target value; the fundamental component comprises a fundamental active component, a fundamental reactive component and a harmonic component; based on the compensation current target value, a control instruction is generated through cooperation of model predictive control and rapid repetitive control; and the overall power quality and operation reliability of the power distribution network are improved.

The present invention discloses a radar communication modulation recognition method based on hierarchical classification, comprising the following steps: S1, acquiring modulation signal data; S2, normalizing the modulation signal data; S3, performing wavelet filtering on the normalized data; S4, performing feature extraction on the filtered data; S5, using the extracted features as input to a support vector machine, and constructing a hierarchical modulation recognition classifier based on the support vector machine. The present invention utilizes wavelet filtering to reduce the impact of the noise environment on the characteristics of the received signal, and employs time domain statistical features to mitigate frequency bias problems caused by carrier frequency estimation deviations. By hierarchically classifying the signal through a support vector machine trained with corresponding features, the accuracy and stability of signal recognition are improved, and good robustness can be achieved under noise and frequency bias conditions.

The invention relates to the technical field of injection molding machine mold locking return-to-zero control, and discloses an injection molding machine mold locking return-to-zero control system and method. Meanwhile, temperature sensors are arranged on the pull rod, the movable template and the guide rail, and thermal expansion amount of each component is calculated and dynamically compensated in real time; calculating the wear compensation amount based on the accumulated number of cycles of the guide rail; fusing the position of the encoder, temperature compensation and wear compensation to obtain a real position; when approaching a mechanical zero point, monitoring a zero point sensor signal which is subjected to wavelet filtering and self-adaptive threshold processing; and finally, the driving mechanism moves to the zero point in a closed loop mode and automatically stops within the error controllable range.

The application discloses a small drilling rig multi-model drilling speed prediction method and equipment based on stratum lithology classification, considers the important factor of stratum lithology reflecting the drilling environment of the small drilling rig in the role of the drilling speed prediction, introduces stratum lithology information, establishes drilling speed prediction models of multiple lithologies, and is divided into three stages, in the first stage, according to actual engineering application experience, data is screened and resampled, then, the data is processed through wavelet filtering and normalization; in the second stage, three typical lithologies are selected from drilling data, and real-time drilling data is used for lithology classification; in the third stage, the lithology classification result of the second stage is used, drilling data of classification is introduced into the drilling speed model of the corresponding lithology for prediction, a good foundation is laid for intelligent control research in the drilling process of the small drilling rig, the problem that a single drilling speed model has low adaptability to different stratum lithologies is solved, and drilling speed prediction precision is improved.

The invention relates to the technical field of radiation detection, in particular to radiation monitoring equipment and a signal processing method, device and equipment based on combination of wavelet filtering and differential filtering, and the signal processing method based on combination of wavelet filtering and differential filtering comprises the following steps: acquiring a signal to be processed; preprocessing the signal to obtain a processed signal; and processing the processed signal by combining a wavelet filtering algorithm with a delay differential filtering algorithm to obtain a pulse signal peak value. According to the signal processing method based on combination of wavelet filtering and differential filtering, the obtained signal is preprocessed, and then the processed signal is processed by combining a wavelet filtering algorithm and a delay differential filtering algorithm to obtain a pulse signal peak value, so that the signal filtering precision is improved; the technical problem that an existing signal processing filtering mode is low in filtering precision is solved.

The invention discloses a cornea thickness meter and a cornea thickness measuring method, and relates to the technical field of cornea thickness meters, the cornea thickness meter comprises a lower base, an upper base, a thickness meter, a face limiting frame, a transverse adjusting assembly and a face adjusting assembly; an optical transmitting module, an optical receiving module, an ultrasonic auxiliary module and a data processing module are arranged in the thickness meter, a physical positioning mark is formed through high-frequency ultrasonic waves to determine an optical measurement area, and cornea stimulation and measurement deviation are avoided; the transverse and face adjusting assemblies are matched with a distance sensor to achieve automatic and accurate adjustment of the head position of a tester, and in addition, the data processing module is combined with wavelet filtering, an FFT algorithm and a curvature correction formula to achieve real-time processing of multi-channel signals and accurate calculation of the thickness; the problems of measurement deviation and data processing delay caused by low manual adjustment precision and irregular cornea surface of a traditional thickness gauge are effectively solved, and the cornea thickness gauge has the advantages of operation convenience, measurement accuracy and data management convenience.

The invention relates to the technical field of crossing of artificial intelligence and tobacco processing, discloses a cut tobacco feeding moisture regulation and control method and system based on LightGBM, and aims to solve the problems of moisture signal distortion and low regulation and control precision caused by dust interference. The method comprises the following steps: acquiring dust concentration and noise-containing moisture signals of a production line in real time; dynamically generating an optimal wavelet filtering parameter through a nonlinear mapping model based on the dust concentration; performing adaptive wavelet filtering on the moisture signal to reconstruct a pure signal; inputting the pure signal into a pre-trained LightGBM model to predict a moisture value; and generating a regulation and control instruction according to the deviation between the predicted value and the target value to realize closed-loop control. The system comprises a working condition sensing module, a signal acquisition module, a filtering parameter dynamic generation module, an adaptive filtering module, a moisture prediction module and a regulation and control instruction generation module. Through decoupling integration of dynamic filtering and an existing LightGBM model, on the premise that an original model is not changed, the moisture regulation and control precision and the response speed are remarkably improved, and the engineering transformation cost is reduced.

The invention provides an intelligent tire lateral force estimation method and system based on an improved iTransform network, and the method is realized through the following steps: S1, carrying out the acceleration signal collection of a tire, and obtaining the three-axis acceleration data; s2, performing IEEEEMDAN-permutation entropy-wavelet filtering noise reduction on the x-axis acceleration signal and the y-axis acceleration signal, and performing 200Hz low-pass filtering on the z-axis acceleration signal; s3, identifying starting and ending feature points of the z-axis acceleration signal based on an adaptive threshold method, and segmenting three-axis acceleration data; s4, constructing a hybrid network model, and replacing a linear mapping layer and a regression prediction layer in an iTransform model by using a KAN network; and S5, predicting the lateral force of the tire by using the trained model. According to the method, by combining the advantages of the iTransform in time sequence modeling and the KAN in nonlinear representation, the precision and stability of tire lateral force estimation are remarkably improved, and the method is suitable for vehicle dynamics analysis and control scenes and has great significance in improving the maneuverability and safety of vehicle driving.

The invention provides a target detection-based weld infrared thermal imaging image defect detection method. The target detection-based weld infrared thermal imaging image defect detection method comprises the following steps of: selecting an optimal filtering algorithm (Gaussian / median / mean / wavelet filtering) through peak signal-to-noise ratio comparison to pre-process an image; an improved YOLO-AttCrossW model is constructed, a backbone network of the improved YOLO-AttCrossW model fuses high and low dimension features by adopting a cross auxiliary connection module, a neck network is embedded into a deformable channel attention module to realize sampling position adaptive offset, and a detection head applies a dynamic weighting loss function; during training, efficiency and precision are calculated through lightweight convolution and hyper-parameter fine tuning balance. Multi-scale features are fused by means of the spanning auxiliary connection module, the detection confidence of the tiny pores is greatly improved, and the detection confidence is obviously improved compared with original YOLOv5s; the deformable channel attention module can dynamically track the defect contour, and even if interference such as splashing and oxide skin exists, a high average precision mean value can still be kept. And by dynamically adjusting the confidence coefficient weight of the background complex region, the occurrence of false detection conditions is remarkably reduced.

The invention discloses a method for accurately calculating passive discharge time, and the method comprises the steps: S1, carrying out the wavelet filtering processing, obtaining a time sequence tk and a voltage sequence vk of a passive discharge curve of a passive discharge resistor collected by an oscilloscope, carrying out the wavelet filtering of the voltage sequence vk, and obtaining a voltage sequence vfk after the wavelet filtering; s2, determining a passive discharge starting point, and obtaining a time point tstart corresponding to the starting point; s3, determining a passive discharge termination point and a time point tend corresponding to the termination point; and S4, calculating the passive discharge time. According to the method for accurately calculating the passive discharge time, the defects that in the prior art, manual point taking errors are large, and the accuracy of actually measured passive discharge time cannot be guaranteed are overcome.

The present invention relates to the technical field of power system electricity consumption monitoring and analysis, and discloses a load identification method based on power signal similarity clustering. A collector or a special transformer terminal deployed at the user side incoming line is used to perform denoising on the collected voltage and current waveform data using a wavelet filtering algorithm. Time domain features, frequency domain features and time-frequency domain features are extracted from the pre-processed voltage and current waveform data respectively, and a measurement method combining Euclidean distance and cosine similarity is used. The present invention uses the characteristic similarity of voltage and current waveforms to perform non-invasive electrical equipment identification, which is deployed on a collector or a special transformer terminal to realize energy consumption structure analysis on the user side. With the energy consumption structure analysis, users can clearly know the energy consumption status and usage patterns of each electrical equipment, thereby formulating a more scientific and reasonable electricity consumption plan, avoiding the use of high-energy-consuming equipment during peak hours, reducing unnecessary electricity waste, and thus significantly reducing electricity costs.

The invention provides an actor-commentator training method and system based on Hamiltonian error wavelet filtering, and relates to the technical field of artificial intelligence and automatic control. The invention aims to solve the problems of slow training and low precision caused by noise contained in Hamiltonian-Jacobi-Bellman approximation errors. The method comprises the following steps: calculating an approximate error signal of a Hamiltonian-Jacobi-Bellman equation; filtering the signal and extracting main components for training; updating parameters of the actor network and the commentator network based on the filtered error signals; the invention further discloses a corresponding system. By filtering the core error signal updated by the driving network, the training mechanism is improved, and the loss function is smoother, so that the convergence speed is accelerated, and the control precision and robustness are improved.

The invention relates to the technical field of multi-source acoustic signal separation, in particular to a multi-source acoustic signal separation method based on Doppler wavelet filtering, and the method comprises the following steps: 1, collecting a trackside mixed acoustic signal: arranging a single microphone at a vertical distance d from a track, and collecting a mixed acoustic signal s (t) containing at least two sound sources; 2, calculating pseudo time-frequency distribution: performing improved Doppler wavelet transform (IDT) on s (t) to obtain pseudo time-frequency distribution FTFD: t0 is a time center, f0 is a characteristic frequency, and D (tau) is a dynamic distance between a sound source and a microphone; 3, sound source parameters are extracted, wherein time centers t01, t02,..., t0n and corresponding characteristic frequencies f0j of all sound sources are extracted from FTFD; and step 4, constructing a Doppler wavelet filter: aiming at the target sound source i. The invention provides a multi-source signal separation technology based on pseudo time-frequency distribution and Doppler wavelet filtering, can realize rail-side multi-source acoustic signal separation, and has a better application prospect in wayside acoustic fault diagnosis.

The invention provides a non-contact blood pressure prediction method in a natural state based on a multi-level model, which comprises the following steps: sequentially performing face recognition, region of interest selection, color signal extraction, signal enhancement, abrupt change noise removal and wavelet filtering on each frame of picture to obtain a filtered IPPG signal; carrying out expansion and label classification on the data set; constructing a residual bidirectional long-short-term memory network, wherein the network comprises a convolutional neural sub-network, a residual sub-network and a bidirectional long-short-term memory sub-network; inputting the data set with the label into the network, and training the network by using a callback function to obtain the trained network; inputting a one-dimensional signal obtained through image processing into the trained network so as to predict the blood pressure value of the human body; according to the distance and the attitude angle, the blood pressure value is corrected through a Kalman filtering algorithm, and the corrected blood pressure value is obtained. In this way, the situation of overfitting can be avoided, the method is suitable for more real scenes, and the accuracy of the predicted blood pressure value is high.

The present invention relates to the technical field of data processing, and particularly to a method and system for monitoring the operating state of devices based on the Internet of Things. The method includes the steps of: obtaining the oxygen concentration time series and temperature time series of the device; obtaining a plurality of preset local ranges of the oxygen concentration data at each moment in the oxygen concentration time series, calculating the noise performance degree of the oxygen concentration data, calculating the corrected noise performance degree of the oxygen concentration data according to the noise performance degree, and setting the decomposition level in the wavelet filtering algorithm by using the corrected noise performance degree to implement denoising processing to assist in monitoring the operating state of the device. Thus, efficient and accurate denoising processing is achieved through an adaptive decomposition level.

The application relates to the technical field of artificial intelligence and tobacco processing, and discloses a tobacco cut filler moisture control method and system based on LightGBM, which aims to solve the problems of distorted moisture signal and low control precision caused by dust interference. The method comprises the following steps: acquiring the dust concentration of a production line and a moisture signal with noise in real time; generating optimal wavelet filtering parameters through a nonlinear mapping model based on the dust concentration; performing adaptive wavelet filtering on the moisture signal to reconstruct a pure signal; inputting the pure signal into a pre-trained LightGBM model to predict the moisture value; generating a control instruction according to the deviation between the predicted value and a target value to realize closed-loop control. The system comprises six modules, namely, working condition sensing, signal acquisition, dynamic filtering parameter generation, adaptive filtering, moisture prediction and control instruction generation. The application realizes decoupling integration of dynamic filtering and the existing LightGBM model, significantly improves the moisture control precision and response speed without changing the original model, and reduces the engineering transformation cost.