79 results about "Average filter" patented technology

The invention discloses a sparse dynamic graph convolution-based electroencephalogram signal decoding method and system. The method comprises the following steps of: acquiring a multi-channel electroencephalogram signal and preprocessing the multi-channel electroencephalogram signal; performing multi-band filtering on each channel signal, extracting statistical characteristics on each band signal, calculating a covariance matrix of a task electroencephalogram signal, constructing image electroencephalogram data by taking an electroencephalogram channel as an image node, the multi-band spliced statistical characteristics on the channel as a node feature vector, and the covariance matrix between the channels as an adjacent matrix; finally, a dynamic graph convolutional neural network model is constructed, the model constructs a graph convolutional neural network based on an autoregression moving average filter, graph electroencephalogram data is used as input, the category of electroencephalogram signals is used as output, an adjacency matrix is dynamically generated in combination with bilinear mapping, fuzzy label learning and sparse constraint are added to improve the decoding capacity of the model, and the dynamic graph convolutional neural network model is obtained. And the frequency domain response capability and robustness of the model to the graph structure are enhanced.

The invention discloses a GNSS (Global Navigation Satellite System) signal spoofing detection method, device and equipment, a storage medium and a program product. The method comprises the following steps: tracking and monitoring a plurality of GNSS satellite signals, calling a tracking loop correlator to carry out autocorrelation operation to obtain the autocorrelation power of each satellite signal, constructing the AP detection quantity of each satellite signal based on the autocorrelation power, verifying the Gaussian property of the AP detection quantity, and carrying out moving average filtering processing on the AP detection quantity conforming to Gaussian distribution to obtain the AP detection quantity of each satellite signal. The method comprises the following steps: acquiring Gaussian distribution characteristic information of a GNSS satellite signal, constructing an AP-MA detection quantity, determining a detection threshold according to the Gaussian distribution characteristic information, detecting the AP-MA detection quantity based on the detection threshold, and judging whether the GNSS satellite signal has deception jamming or not; the AP detection quantity is constructed based on the self-correlation power to carry out signal spoofing detection, so that the detection range and the detection precision are effectively improved, and the timeliness and the stability of spoofing detection are ensured under the condition of not increasing additional equipment and algorithm complexity.

The invention discloses a method for estimating the state of charge of a series battery pack, which comprises the following specific steps of: firstly, constructing a battery pack equivalent circuit model based on online acquired battery parameters and series circuit characteristics, carrying out standardization processing on the terminal voltage Uti and the internal resistance R0i of each battery monomer, and carrying out Euclidean distance analysis to obtain the state of charge of the series battery pack; identifying the battery with the maximum difference as a representative battery monomer, then constructing a spatial state equation, and performing SOC estimation by adopting a self-adaptive extended Kalman filter with residual drive, thereby obtaining a battery pack state-of-charge base value SOCb; meanwhile, after abnormality judgment and effective data screening are carried out on battery monomer data collected offline, the voltage difference feature delta Uti and an estimated historical residual sequence eh are fused to form joint input, a CNN-GRU-SE hybrid neural network optimized by a KOA algorithm is used for estimating a battery pack charge state compensation value delta SOCb, and after processing is carried out through a moving average filter, the battery pack charge state compensation value delta SOCb is calculated. And superposing with the SOCb to obtain an estimated value SOCr of the state of charge of the series battery pack.

The invention provides a method for adjusting a variable-speed pumped storage unit under a working condition of a water turbine, which comprises the following steps of: arranging a multi-source sensor array in a flow channel to collect parameters such as water head pressure, rotating speed fluctuation and active power, generating operation state data through space-time alignment and self-adaptive weighted fusion, and triggering re-calibration when a threshold value is exceeded; an efficiency optimization index is calculated, fluctuation is smoothed through moving average filtering, water head fluctuation is predicted, and early warning is conducted when the water head deviates from the optimal working condition; according to the efficiency index and the water head amplitude variation factor, a maintenance / early warning / emergency adjustment grade is divided, and a guide vane instruction is generated during high deviation; determining unit importance, evaluating resource requirements by using a multi-objective optimization algorithm, and dynamically monitoring deviation; and optimizing a rotating speed regulation scheme by adopting a self-adaptive hill climbing algorithm, evaluating an iterative optimization regulation path, and triggering parameter re-calibration when the deviation exceeds the limit. The operation efficiency, the adjusting precision and the stability of the variable-speed pumped storage unit under the working condition of the water turbine can be improved, and the energy consumption and the instability risk are reduced.

The invention relates to the field of railway vehicle fastener tension monitoring, in particular to a railway intelligent fastener based on delta F judgment and burr suppression, and aims to improve the monitoring precision of the railway intelligent fastener. Comprising a tension sensor and a central processing unit, the central processing unit comprises a state recognition module and a self-adaptive filtering module, and the state recognition module is connected with the tension sensor and the self-adaptive filtering module. The state recognition module collects a tension signal output by the tension sensor at a fixed period as a sampling value, calculates a difference value between the sampling value at the current moment and the sampling value at the previous moment, and sends the tension signal to the tension sensor when the difference value is larger than a first set threshold value and smaller than or equal to the first set threshold value. And respectively judging whether the railway intelligent fastener is in an installation state or an operation state. And the adaptive filtering module receives a state judgment result, and performs smoothing processing on the tension signal by adopting an exponential weighted moving average filtering algorithm and a moving average filtering algorithm respectively in an installation state and an operation state.

The application discloses a kind of control method, device and equipment and storage medium of dense shelf running state, the method includes: the current data sequence of dense shelf in running process is collected;The current data sequence includes multiple current sampling point data;Current sampling point data in the current data sequence is carried out average filtering processing, and target current data sequence is obtained;The target current data sequence includes multiple current average filtering data;In the target current data sequence, continuous multiple current average filtering data is selected, linear fitting is carried out, and linear fitting slope is obtained;In the case where the linear fitting slope is greater than or equal to preset threshold, the dense shelf is controlled to stop running.The technical scheme provided by the application can improve the accuracy of the judgment of the dense shelf running process to a certain extent.

The invention relates to the technical field of agricultural informatization and intelligent management, in particular to a selenium-rich bio-organic fertilizer research and development and demonstration and popularization full-process management system, which comprises a raw material digital filing module, a raw material fingerprint feature vector generation module and a selenium-rich bio-organic fertilizer research and development and demonstration and popularization module, and is characterized in that the raw material digital filing module is used for executing a moving average filtering algorithm to clean data; the market demand reverse analysis module is used for extracting, calculating and generating an environment demand constraint matrix representing market differentiation demands based on a preset element circulation rule; the research and development and production scheduling intelligent decision-making module is used for starting an evolutionary resolving model, mapping raw material fingerprints to an environment constraint matrix and outputting a dynamic production management instruction list; the production execution supervision module is used for distributing an instruction to the terminal and monitoring process execution data in real time; the full-life-cycle closed-loop optimization module is used for obtaining feedback data calculation deviation and generating correction factors to update model parameters; the method solves the contradiction between the heterogeneity of the non-standard biomass raw materials and the precise nutritional requirements of functional agricultural products.

The application provides a battery system SOC estimation method, comprising the following steps: S1, obtaining historical data for the same type of battery system, and pre-processing the data set; S2, dividing into different data subsets according to different states of the battery system, and respectively constructing features, and dividing training and test data; S3, constructing an SOC estimation model based on an XGBoost algorithm for the data subsets under different states of the battery system; and S4, collecting real-time monitoring data of the battery system, and pre-processing the data; the SOC estimation method based on data driving multi-algorithm fusion under different states of the battery system can accurately estimate the SOC value of the battery system, frequent calibration is not needed, there is no error accumulation effect, a smoothing filter strategy fusing a recursive average filter and a first-order lag filter is proposed, the SOC can be efficiently and smoothly controlled, and SOC jump can be avoided.

The invention discloses a long-time filtering control method and device for analog quantity signals, and relates to the technical field of signal processing, and the method comprises the steps: constructing a circular buffer structure with the length of N as a historical data queue, and storing sampling values according to a PLC scanning period; based on the queue, calculating a filtering output value by adopting a weighted recursive average filtering algorithm; calculating a mean value and a standard deviation of the queue data in real time; comparing the current sampling value with a dynamic threshold range determined based on the mean value and the standard deviation, and if the current sampling value exceeds the dynamic threshold range, determining an abnormal value; when an abnormal value occurs, the value is discarded, the queue is not updated, and a filtering value of the last period is output as a current result, the defect that a traditional PLC filtering method is difficult to process long-time signal abnormity is effectively overcome through the circular queue with the adjustable time window and by fusing dynamic weighted filtering and a self-adaptive abnormity cleaning mechanism, and the filtering accuracy is improved. And the anti-interference capability and the reliability of the industrial control system are obviously improved.

This invention relates to the field of coordinated control of energy storage in new energy collection stations, and particularly to a coordinated control method for reactive power compensation of energy storage in new energy collection stations based on impedance reshaping. Based on the acquired three-phase AC signal, an analytical signal representation is obtained. Based on the analytical signal representation, a complex spectrum is obtained, and the impedance frequency response is determined. After processing with an exponentially weighted cumulative average filter, the actual impedance is obtained. Combined with the target impedance determined by the target impedance response model, the impedance error is determined. Based on the impedance error, a frequency-sensitive adjustment driving function is determined, and a new energy collection station adjustment residual loss function is constructed. The optimal complex impedance weighted path scheduling matrix is ​​determined. Simultaneously, a frequency segmentation objective function mechanism and a suppression function are introduced to construct a global optimization objective function, obtaining the optimal virtual impedance configuration. This solves the technical problems of resonance and stability issues, as well as reactive power response conflicts and low control efficiency caused by independent control strategies and a lack of coordinated adjustment.

The application provides a frequency standard measurement method, device, computer equipment and storage medium, the method comprises: frequency source output measurement signal is carried out frequency division processing, obtains low frequency pulse signal; using high-precision time interval counter to low frequency pulse signal is carried out delay measurement and time interval counting, and is output in the form of time stamp; by setting a sliding window, using sliding average algorithm to time stamp is carried out sliding average filtering processing, all time stamps are carried out sliding difference to obtain time difference, time difference is grouped according to order and is taken average in group to obtain average time difference; by increasing the length of the sliding window, the number of samples is increased to reduce the statistical error; using average time difference, calculate frequency measurement value, relative frequency deviation and allan variance. The method of the application increases the sliding window, and the frequency measurement result obtained by the algorithm of grouping and averaging the time difference has higher measurement precision and stability.

The present invention discloses an improved Doppler signal processing method and system, belonging to the field of Doppler signal processing technology, comprising the following steps: Step S1, signal acquisition and preprocessing: acquiring the original Doppler signal and performing a sliding average filter; Step S2, time-frequency analysis: using a Hamming window function, an improved wavelet threshold denoising method, and combining a short-time Fourier transform to perform time-domain analysis on the filtered Doppler signal to obtain a motion spectrum; Step S3, feature extraction: using a Hilbert transform to calculate the true envelope and combining a peak-finding function based on envelope analysis to traverse the data in the motion spectrum to extract peak points; Step S4, judgment output: screening the peak points that meet the peak height threshold condition and outputting the peak points and their position coordinates. The present invention achieves better signal extraction effect and visual speed measurement, effectively realizes signal separation and extraction, and significantly improves the accuracy and reliability of signal processing.

The present invention relates to an image processing method based on morphology and non-linear Poisson equation, which includes: fitting an intensity differential fitting function of the contours on both sides of the input image according to gray-scale morphological erosion and dilation operations, and defining an energy function containing the image contour line; obtaining a new energy function according to the level set function and taking the derivative to obtain a gradient descent flow equation; decomposing the data term therein and introducing a non-linear Poisson equation for representation; constructing a canonical function for non-linearly stretching the value range of the data term function; continuously updating the level set function, and after regularization and neighborhood average filtering processing, obtaining the final level set function; outputting the same and the image segmentation result; adopting mathematical morphology to increase the anti-noise ability, effectively eliminating the influence of noise on image segmentation, reducing the amount of computation and the image segmentation time; constructing a non-linear Poisson equation to weaken disturbances such as non-uniformity, introducing a level set model to complete image segmentation, and increasing the accuracy of image segmentation; constructing a canonical function to improve the robustness.

The invention discloses a robust wind speed prediction method, system and device and a medium, and the method comprises the steps: screening a wind power plant according to the relevance, and obtaining a screened wind power plant cluster data set; performing de-noising processing on the data by applying weighted average filtering to obtain preprocessed wind power plant cluster wind speed data; filling missing data values through a multi-dimensional average algorithm to obtain historical data of the wind power plant cluster; the method comprises the following steps: combining wind speed data of each wind power plant to construct a multi-dimensional sequence to obtain a wind power cluster data input set; and learning and calculating the input set through a deep extreme learning machine to obtain a final wind speed prediction result. The accuracy of the final prediction result and the efficiency of the overall prediction algorithm are effectively improved.

The invention relates to the technical field of unbalanced power grid voltage phase detection and harmonic suppression, and provides a phase locking method suitable for an unbalanced power grid condition. The objective of the invention is to solve the problems of instability of a phase-locked loop, increase of harmonic content of output current of an inverter and reduction of dynamic response performance caused by unbalanced power grid voltage. According to the main technical scheme, the method comprises the steps that the three-phase voltage Vabc of a point of common coupling PCC is converted into an alpha component and a beta component under a two-phase static coordinate system through a coordinate conversion unit of the three-phase voltage; two mutually orthogonal signals are generated through a second-order generalized integrator SOGI; orthogonal signals output by the SOGI are input into a decoupling network through Park transformation, a positive sequence voltage component and a negative sequence voltage component are separated out, and then smoothing processing is carried out through a first-order low-pass filter; an improved moving average filter is adopted for dynamic correction, and a phase locking angle is generated; the phase locking angle is adjusted through a proportional-integral controller and an integral element 1 / s, and a synchronizing signal is output to control the output current of the grid-connected inverter.

The invention relates to a glass flow measuring method and device and a medium, and the method comprises the steps: after each piece of glass is cut, recording the cutting duration of the glass as transverse cutting beat data, and transmitting and storing the transverse cutting beat data to subsequent stations step by step along with the glass flowing through each station; when the glass reaches a final weighing station and the plate weight accords with a preset threshold value, real-time flow data is calculated based on the transecting rhythm and the plate weight stored in the station, and hidden abnormal interference such as unfilled corners is eliminated through an improved median average filtering algorithm; meanwhile, setting a flow updating timer and an overtime threshold value, if no new data is obtained in an overtime state, reusing a historical effective value and marking an overtime state, and switching to an abnormal updating mode to directly output real-time flow after continuous overtime reaches the threshold value; and after normal data is continuously recovered, the filtering mode is automatically switched back. According to the method, the real-time performance and the precision of the flow data are remarkably improved through transverse cutting beat dynamic synchronization, multi-stage data cleaning and an abnormal self-adaptive strategy.

The present application relates to a kind of fA grade weak current signal software filtering method, electronic equipment and storage medium, filtering method includes the following steps: setting sampling parameter, calculate sampling point number preset target value;Start AD data acquisition, when sampling point number reaches preset target value, trigger data processing software interrupt, and carry out first-stage filtering processing;Call back secondary filtering processing function, carry out secondary filtering processing, obtain filtered voltage value, first-stage filtering uses arithmetic average filtering algorithm, secondary filtering uses recursive average filtering algorithm.The present application, by arithmetic average filtering algorithm superimposed recursive average filtering algorithm of two-stage software filtering algorithm can be sequentially effectively filtered out periodic and aperiodic interference in weak current signal, realize the effective extraction of system thermal noise in micro-current signal and filter out, and to the greatest extent, retain signal dispersion, make the fitting curve after filtering and actual curve further coincide, effectively improve measurement accuracy.

The invention discloses a road van plateau whole vehicle transient calibration development method which comprises the following steps: S101, detecting the altitude in real time, and triggering a plateau mode; s102, an accelerator signal is input into an acceleration manager after being subjected to Kalman filtering; s103, generating a target torque in combination with the intention of the driver and the vehicle dynamics constraint; s104, the anti-shake module performs moving average filtering on the torque instruction; and S105, the MPC controller dynamically adjusts the fuel injection pulse width and the ignition timing, and smooth torque output is achieved. Steering wheel turning angle data are introduced into an accelerator filtering decision for the first time, and mistaken acceleration under the steering working condition is avoided; the balance performance and efficiency are calibrated through high load and low load, the high load preferentially keeps power, and the low load preferentially saves oil.

The invention relates to the technical field of power electronics, in particular to a diesel generator test system control method based on a moving average filter, and the method comprises the steps: collecting an output voltage instantaneous value of a diesel generator in real time, and obtaining a voltage sampling sequence; inputting the voltage sampling sequence into a pre-constructed moving average filter; performing moving average processing on the input voltage sampling sequence through a moving average filter to obtain an output signal; generating a current command signal based on an output signal of the moving average filter; and according to the current instruction signal, driving the diesel generator test system to simulate a load with a specific power factor through current closed-loop control, and carrying out load simulation test on the diesel generator. The moving average filter is directly used for generating a current instruction of the test system, and the lag angle of the current instruction is linearly adjusted by adjusting the point number of the filter through the linear phase-frequency characteristic of the filter, so that the accurate and convenient control of the simulation load power factor of the diesel generator test system is realized.

The application provides a dynamic zero point correction and gravity compensation method of a six-dimensional force sensor, which comprises the following steps: 1, determining a pose change matrix of a robot end coordinate system relative to a base coordinate system M 0 T1; 2, determining a coordinate transformation relationship between an end tool and a robot base coordinate; 3, determining force components of end tool gravity in three directions of a sensor coordinate system XYZ; 4, determining a gravity compensation value, and performing zero point correction and compensation error. The application can compensate the force of the end tool gravity on the sensor; after data processing by using an average filtering algorithm, zero point correction can be performed, so that the influence of external interference factors, operation errors and the like can be reduced; the application is suitable for gravity compensation and zero point correction under various postures and motion states of a robot, and is suitable for various types of mechanical arms, end tools and six-dimensional force sensors; and the application is suitable for zero point correction and gravity compensation in a static state and in a robot motion process.

The invention relates to the technical field of automatic control, in particular to an automatic leveling control method for an aerial work platform, which comprises the following steps of: acquiring angle data through a tilt angle sensor, performing moving average filtering and noise reduction, calculating an angle change rate, constructing a gradient threshold value through a sliding window, outputting leveling parameters in a grading manner, and calculating a real-time angle by adopting a PID (Proportion Integration Differentiation) control algorithm. And dynamically adjusting proportional integral, performing fuzzy control on displacement of the amplitude-limiting landing leg, judging a main arm and an azimuth angle, outputting a safety instruction, matching a pressure curve with an opening curve, and triggering attenuation at a low matching degree until locking. According to the method, a dynamic gradient threshold value is constructed through sliding window statistics, leveling parameters and the inclination angle rate are matched, PID control cooperation coefficient self-matching adjustment is started and stopped, response and precision are balanced, main arm and rotation angle multi-dimensional constraint is achieved, a safety boundary is set through fuzzy amplitude limiting, leveling and stability are optimized, hydraulic frequency motion is reduced, and load and disturbance robustness is enhanced; and energy consumption and impact are reduced.

The invention provides a method and system for improving the detection resolution of a digital closed-loop accelerometer. The method comprises the steps that a pendulous reed, a first amplifier, an integrator, a second amplifier, an ADC chip, a digital signal processor STM32, a DAC chip, a third amplifier and a torquer are sequentially connected; a median value average filtering algorithm is added in a digital signal processor STM32 to preprocess data collected by an ADC chip, a data point collected earliest in a queue is removed every time one ADC datum is collected, then the maximum value and the minimum value of N data including new data are removed, and the maximum value and the minimum value of the N data including the new data are removed; and calculating an arithmetic mean value of the N-2 data to obtain a final acquisition result. The integrator is used for integrating the system error, and the acceleration detection resolution is improved by inversely resolving the current through the voltage. According to the technical scheme, the technical problem that the resolution of a digital accelerometer in the prior art is limited by ADC and DAC devices and is low is solved.

The invention discloses a zero point measuring device of a Coriolis flowmeter and a zero point error compensation method. The device comprises a constant-temperature water tank, a heat preservation tank, a heater, an iron support, electric control ball valves, a Coriolis flow meter, a pipeline supporting frame, a variable-diameter clamping sleeve and an upper computer, and the zero point measurement and error compensation principle is that the upper computer issues a command to control opening and closing of the upstream electric control ball valve and the downstream electric control ball valve in a time-sharing mode, and after it is ensured that pipeline fluid is in a static state, the pipeline fluid is subjected to zero point measurement and error compensation. At the moment, the instantaneous flow collected by the flow meter is a zero value, N zero values are continuously collected according to the set sampling frequency f, the zero values are arranged in an ascending order through a rapid sorting algorithm, then zero correction is conducted through a median value average filtering algorithm, and therefore the compensated zero value Q0 of the Coriolis flow meter is obtained; and zero error compensation is carried out on the instantaneous flow Q1 and the accumulated flow Qm in the T time period. According to the method, the zero point of the Coriolis flowmeter is measured and the zero point error is corrected in a pure software mode, manual participation is not needed, and the zero point measurement efficiency and the flow measurement precision are improved.

The invention provides an image enhancement method and system based on guided filtering, and the method comprises the steps: carrying out the line caching of an input image p in each filtering window, and forming the convolution of nn; calculating a mean value in the convolution kernel and a mean value of squares, and calculating a corresponding variance; calculating a filter coefficient sum based on the variance and a preset weighting coefficient; respectively carrying out average filtering processing on the sums of the plurality of filtering windows to obtain sums; and performing guided filtering processing on the input image p according to the filtering coefficient mean value and the filtering coefficient mean value. According to the invention, guided filtering enhancement processing is carried out on the input image on the SOC chip based on the line cache, and the problem of large noise in image display and image preprocessing in the image processing field is solved.

A training method of an artificial intelligence model for optimizing operation variables of a circulating fluidized bed boiler is disclosed. The method may comprise the steps of: using an exponential moving average (EMA) filter and a time series decomposition method to preprocess sensing data of a circulating fluidized bed boiler; using the preprocessed sensing data so as to train a reinforcement learning algorithm; and using the learned reinforcement learning algorithm so as to output a recommended operation variable of the circulating fluidized bed boiler. The time series decomposition method can include a seasonal and trend decomposition using loess (STL) decomposition method. The step of preprocessing the sensing data can include a step of using the EMA filter to smooth the sensing data during a soot-blowing time of the circulating fluidized bed boiler.

The invention relates to the technical field of green building power supply management, and discloses a green building management system based on intelligent power supply, which comprises a data acquisition module, a preprocessing module, a correlation analysis module and a power supply management module, according to the invention, filtering cleaning, abnormity correction and normalization processing are carried out on environment and power utilization data through a moving average filtering algorithm, a 3 sigma principle and the like, so that the data accuracy and reliability are improved; a correlation coefficient model is used for analyzing the correlation between power consumption and the environment, and multi-level power supply priorities are divided according to correlation coefficients and environment threshold values, so that on-demand power supply is realized; when the power supply amount is dynamically adjusted, basic power consumption is calculated in combination with historical data and a real-time environment, distribution is performed according to priorities, and optimization is constrained according to the total power supply capacity, so that excessive or insufficient power supply is avoided, the energy efficiency is improved, and the energy consumption is reduced; the energy waste can be reduced, the operation cost and carbon emission are reduced, the operation of equipment in an extreme environment is ensured, and an efficient scheme is provided for intelligence and low carbon of green buildings.

The invention belongs to the technical field of face living body detection, and provides a face living body detection method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the average filtering and residual processing of an original image, and obtaining an accumulated noise feature and an average filtering image; determining residual features of the original image according to the average filtering image, performing spatial conversion on the original image to obtain I channel features and Q channel features, and fusing the accumulated noise features, the residual features of the original image, the I channel features and the Q channel features to obtain fused features; performing classification training on the fusion features by adopting MLP-Mixer to obtain a face living body detection model; and the target face image is detected through the face in-vivo detection model to obtain a face in-vivo detection result, and through the technical scheme of the invention, the accuracy of face detection is improved, and the detection cost is reduced.

The invention discloses a gas sensor high and low temperature acquisition method based on pulse heating and belongs to the technical field of gas detection. According to the method, an ADC sampling time sequence is controlled by setting a start-stop identifier, and an effective acquisition window is established in a pulse high-level stage by adopting a'front delay and rear advance 'strategy aiming at a high-temperature sensitive sensor; a strategy of'delay before and after the premise 'is adopted for the low-temperature sensitive sensor, a sampling interval is constructed in a pulse low-level stage, and time-sharing accurate control of the high-temperature sensor and the low-temperature sensor is achieved. In combination with a weighted recursive average filtering algorithm, the data continuity and smoothness are improved while original signal features are reserved by increasing weight coefficients. According to the method, pulse waveform position information is combined with a variable time window, accurate interception of effective gas sensitive signals is realized through an interrupt trigger system, and filtering processing is matched, so that the effective information capture rate of the sensor is improved, and meanwhile, the signal acquisition accuracy is ensured; the method is particularly suitable for the field of VOCs detection.

The invention provides an industrial equipment fault prediction method and device, relates to the technical field of fault analysis, and solves the technical problem of insufficient fault prediction accuracy in the prior art. The method specifically comprises the following steps: acquiring equipment data; the equipment data comprises first data and second data; performing noise filtering on the third data through a moving average filtering algorithm; performing feature extraction on the third data after noise filtering to obtain equipment feature data; calculating a correlation coefficient of the equipment feature data and the equipment fault tag, and selecting and removing non-correlation features based on a threshold value; principal component analysis is carried out on the equipment feature data after the non-relevant features are removed, and low-dimensional equipment feature data are obtained; and inputting the low-dimensional equipment feature data into the dual-channel model for fault classification and fault prediction. The method is used for industrial equipment fault prediction.

The application provides a bedding structure rock finite element model reconstruction method based on a core digital image, and belongs to the technical field of digital cores and comprises the following steps: S1: acquiring a gray image of a rock sample; S2: calculating and analyzing the horizontal mean value of a region to obtain a longitudinal gray distribution curve; S3: applying a sliding average filter and a smoothing filter to obtain a smoothed gray curve; S4: performing first-order differentiation on the smoothed gray curve, taking positions with an absolute difference value greater than a threshold value as initial strip boundary candidates, and determining the start and end pixels, the width and the average gray of each strip; S5: mapping each clustering label interval to a physical interval based on FEM grid partition; and S6: constructing a sample finite element model to generate a reconstructed finite element model with real partition information. The application can directly utilize a photo in combination with gray profile analysis, efficiently identify and extract macroscopic structure characteristics of rock, and realize efficient and low-cost reconstruction of a bedding structure rock finite element model.