136 results about "Wavelet packet analysis" patented technology

The invention discloses an automatic expert comprehensive fault diagnosis system and a diagnosis method for wind turbines, which include: a data acquisition module that collects relevant data of a main control unit and a vibration signal acquisition unit and transmits it to a fault diagnosis module; a fault diagnosis module that comprehensively uses The neural network knowledge and expert system module use forward reasoning and compare the parameter fluctuation values ​​obtained in real time with the data in the fault sample knowledge base to generate fault information in real time; the fault diagnosis module passes the diagnosed fault information through the human-machine interface module for output. This invention uses the main control unit to read parameters such as instantaneous power, rotation speed, propeller angle, cabin temperature, wind speed, oil temperature, yaw status and other parameters of the wind turbine to improve the accuracy of fault diagnosis, and uses a neural network expert system based on wavelet packet analysis Carry out automatic analysis and give operation and maintenance suggestions through the expert diagnosis system.

The invention discloses a method for diagnosing bearing breakdown of a wind generating set. The method comprises the steps that vibration signals of a bearing are acquired; a wavelet packet analysis method is used for conducting three-layer decomposition on the vibration signals, soft threshold quantitative processing is conducted on high-frequency coefficients under all decomposition scales, and one-dimensional wavelet reconstruction is conducted according to the low-frequency coefficients and the high-frequency coefficients of a bottommost layer of wavelet decomposition; wavelet packet decomposition is conducted on the reconstructed vibration signals, the energy of all frequency bands on a third layer is extracted, the energy of all the frequency bands constitutes a breakdown diagnosis input vector with a breakdown feature input vector used as a BP neural network, and a three-layer BP neural network is established; a feature input vector sample of historical breakdown data is acquired and input to the three-layer BP neural network for training; a breakdown diagnosis feature vector of real-time operation data of the bearing is acquired and input to the trained BP neural network; intelligent diagnosis of bearing breakdown types is achieved. The method for diagnosing bearing breakdown of the wind generating set can be used for precisely diagnosing the bearing breakdown types and precisely positioning breakdown positions.

The invention relates to a cutter wear monitoring method based on current and acoustic emission compound signals. According to the cutter wear monitoring method, the current signal of a spindle motor and acoustic emission signals of a turning tool wear state in cutting machining are detected, processing and analyzing are conducted based on the current and acoustic emission compound signals, and then the wear state of a cutter is monitored in real time; the current signals of the cutting motor and the cutter wear state features in the acoustic emission signals are obtained in a self-adaptive mode, the abundant cutter wear state information in the current signals of the cutting motor and the acoustic emission compound signals are fully excavated, through a wavelet packet analysis method, a correlation analysis method, a principle compound analysis method and the like, the feature information reflecting the current wear state of the cutter is extracted in a self-adaptive mode, and the wear degree of the cutter is judged by analyzing the relevance between the feature information reflecting the current wear state and initial wear state features.

The invention relates to a cutter abrasion online monitoring method based on wavelet packet analysis and a radial basis function (RBF) neural network. The method comprises the steps that shear force coefficients and cutting edge force coefficients of tangential force and radial force in different cutter abrasion states are calibrated by means of an instantaneous cutting force coefficient recognition method; and by analyzing the correlation between cutting force coefficients and cutter abrasion, the coefficients are taken as cutter abrasion characteristic parameters and input into a RBF neutralnetwork model after being subjected to normalization processing. An input layer of a RBF neutral network monitoring model training process comprises cutting force characteristics, cutting vibration characteristics, the shear force coefficients and the cutting edge force coefficients after being subjected to normalization processing; and an output layer comprises the cutter rear cutter surface abrasion capacity after being subjected to normalization processing; a hidden layer comprises neurons obtained through radial basis function iterative optimization; and it is verified that the RBF neuralnetwork monitoring model has the advantages of high response speed and high recognition precision through cutter abrasion monitoring experiments.

The invention discloses a cutter damage adaptive alarm method based on a wavelet packet and a probability neural network. The method comprises the following steps of: fixing an acoustic emission sensor on a cutter bar, acquiring acoustic emission signals, performing three-layer wavelet packet analysis, selecting characteristic frequency bands and taking root mean square values thereof, normalizing the root mean square values to obtain smoothing factors and prior probability, establishing a cutter damage state probability model by using a probability neural network, determining an alarm value of the cutter abrasion state according to the model and the Pauta criterion, forming a dynamic alarm line, and performing adaptive alarm monitoring of the cutter operating state according to the dynamic alarm line. By the method, the probability distribution curve of the root mean square value related with the cutter abrasion can be found, the alarm value is determined by using a mathematical statistic method, the dynamic alarm line is formed together with the cutter abrasion state change, and missing alarm and error alarm are not caused.

The invention provides a monitoring method for blade crack of a wind driven generator. The monitoring method mainly includes setup of a piezoelectric ceramic fan crack damage health monitoring system and a fan blade crack damage assessment method. The piezoelectric ceramic fan crack damage health monitoring system mainly comprises piezoelectric ceramic pieces, a function generator and an oscilloscope. The working principle is an active surveillance technology based on a piezoelectric ceramic wave method, and the working procedures include utilizing the function generator to emit sine sweeping-frequency signals and the oscilloscope is used for real-time display and storage for received detection signals. The fan blade crack damage assessment method includes utilizing Fourier spectrum analysis to calculate two defined damage indexes based on wavelet packet analysis, successfully monitoring crack areas and performing verification through time reversal. The monitoring method is easy to operate, and the identification effect of blade crack of the wind driven generator is remarkable. The monitoring method is general, and can be applied to damage monitoring of composite materials similar to fan blades.

The drilling pump is a reciprocating piston pump, generally adopts three-cylinder single-acting mode, and is a key equipment of petroleum drilling machine and can be used for pumping drilling liquor into downhole. According to the structure of drilling pump and monitoring object the acceleration measuring points are respectively distributed on the pump head, crosshead position and every bearing seat of power end, and an eddy current sensor is mounted for monitoring phase signal, then the acceleration signal can be respectively transferred into charge amplifier, passed through interface box and inputted into computer to make processing so as to implement drilling pump condition detection and fault diagnosis.

The invention discloses a CEEMD and wavelet packet-based ultrasonic signal denoising method. The method comprises the steps of firstly performing mode decomposition on a signal by utilizing a CEEMD algorithm to obtain a series of intrinsic mode functions and a trend term; secondly performing soft threshold denoising on noise dominant modes in the intrinsic mode functions, and performing adaptive rule denoising of an unbiased risk estimate principle for signal dominant modes; and finally further denoising the signal by utilizing a fine decomposition capability of wavelet packet analysis. According to the CEEMD algorithm, two opposite white noises are added to an original signal, EMD is performed and results are averaged; the end effect and the mode aliasing problem can be effectively eliminated; and the signal is further denoised under the condition of not adding auxiliary noises through wavelet and wavelet packet decomposition. The denoising method has better performance in comparisonwith that of a conventional denoising method. The denoising method can be widely applied to the material defect signal processing.

A method for nondestructively detecting rock bolt ¿C anchoring system includes acting acoustic signal issued by stress wave generator on top portion of rock bolt, sending dynamic measuring signal reflected form rock bolt ¿C anchoring system to signal receiving unit being used to transmit said signal to microprocessor for carrying out wavelet packet analysis, carrying out intelligent processing and analyzing on signal being analyzed with wavelet packet.

The invention provides an analog circuit fault diagnosis method based on wavelet packet analysis and the Hopfield network. The method includes data obtaining, feature extraction and fault classification, wherein data obtaining includes performing data sampling for output response of an analog circuit respectively through simulation program with integrated circuit emphasis (SPICE) simulation and a data collection plate connected at a practical circuit terminal so as to obtain an ideal output response data set and an actually-measured output response data set; feature extraction includes performing wavelet packet decomposition with ideal circuit output response and actually-measured output response respectively serving as a training data set and a test data set, and leading energy values obtained by decomposed wavelet coefficient through energy calculating to form feature vectors of corresponding faults; and fault classification includes leading the feature vectors of all samples to be subjected to Hopfield coding and then submitting the coded feature vectors to the Hopfield network to achieve accurate and fast fault classification. The analog circuit fault diagnosis method is good in fault feature pretreatment effect aiming at hard faults with weak amplitude response and soft faults with large amplitude response, and the newly defined energy function and the newly defined coding rule are remarkable in influence on fault diagnosis accuracy of the analog circuit.

The invention relates to a voltage transformer on-load tap-changer mechanical fault diagnosis method of which key technical points are that a vibration detection probe is adhered to a box wall of an on-load tap-changer in a surface-mounted manner, vibration signals generated in tap-changer operation processes can be captured, the vibration signals are subjected to energy frequency band decomposition operation via wavelet packet analysis technologies, frequency spectrum characteristics of the signals can be extracted, a state characteristic vector can be formed, a characteristic vector database is formed via signal collection and storage, an Euclidean distance function is used for analyzing a changing trend of the characteristic vector, and a mechanical state of the on-load tap-changer is diagnosed and assessed. Via the voltage transformer on-load tap-changer mechanical fault diagnosis method, the vibration signals generated in the tap-changer operation processes can be captured in real time, a characteristic quantity of the vibration signals is extracted and is compared with historical data, whether a fault occurs is determined and a fault development trend is determined, overhaul cost is lowered, detection efficiency is raised, early stage mechanical faults can be found timely and effectively, and the faults can be prevented from worsening.

The invention discloses a fiber bragg grating sensing dynamic load identification method based on AR model and mahalanobis distance. The method comprises the following steps: arranging the position of a distributed fiber bragg grating sensing network; monitoring and collecting impact response dynamic signals in real time; analyzing time domains of impact response signals and determining a response spectrum characteristic frequency capable of representing impact position information; extracting wavelet-packet-analysis-based spectrum response characteristic frequency and building an AR model parameter matrix; judging similarity between the impact position signals and response signals in a sample library of the AR model parameter matrix by using mahalanobis distance, primarily determining the area of the impact load to be monitored according to three impact positions with high similarity, then accurately identifying the impact load position by using a triangular center location method. Since a fiber bragg grating demodulating system is relatively low in demodulating frequency, the impact load cannot be located by using a time difference method; compared with the conventional time domain locating method, the method is simple and reliable.

The invention relates to a knowledge base construction method oriented to fault diagnosis and fault prediction of a numerical control machine tool. The method comprises the following steps of: step 1, performing real-time monitoring on a high-grade turning center through a remote monitoring device, and obtaining multiple groups of vibration data Xj(t) representing different fault types, wherein j is the number of acquired vibration data groups, and n is a positive integer; step 2, orderly executing temporal rough wavelet packet analysis on the multiple groups of vibration data Xj(t), obtaining an energy feature vector T' as a condition attribute, and taking the fault type as a decision attribute to construct a fault knowledge primary decision table; step 3, executing discernibility matrix-based fault feature attribute reduction on the fault knowledge primary decision table to generate a rule and form a knowledge base; and step 4, taking the confidence level of the rule as an evaluation index to measure and evaluate the final rule. The method provided by the invention can provide effective guarantee for fault diagnosis and fault prediction, and can be widely used in the high-grade turning center.

The invention discloses a wood damage monitoring method based on an acoustic emission technique. The method specifically comprises the following steps: arranging an acoustic emission sensor on the surface of a wood stress concentration part; collecting weak acoustic emission signals generated by wood damages; amplifying and filtering the collected acoustic emission signals, carrying out analogue-to-digital conversion, and then transmitting the converted signal to an FIFO in an FPGA control module and buffering; uploading data to an upper computer through a wireless transmission module; carrying out wavelet noise reduction and reconstitution on the collected acoustic emission signals collected by the upper computer; positioning a wood-damage acoustic emission source by a linear positioning method, and monitoring the position of the wood-damage acoustic emission source in real time through a human-computer interaction interface designed by LABVIEW; and extracting energy characteristic values form the collected acoustic emission signals by the upper computer by virtue of a wavelet packet analysis system, constructing a corresponding training sample set, building a neural network, and predicting and analyzing the variation trend of the acoustic emission signals of wood stress damages through accumulated energy so as to deduce the positions of the wood damages.

This invention relates to continuous casting dross detection method and device based on vibration detection. On section if the end of motion arm far away the long nozzle, assemble multiple vibration sensors with different directions to collect vibration signals of different directions; form sampled signal after amplifying, filtering, sampling and A / D transform; take off-line process for the ,mass collected signals to form norm eigen vector; use effective vector quantization algorithm to train codebook corresponding to all states used as codebook KB of all casting states when recognizing on line; by wavelet analysis method, obtain eigen vector of sampled signals; through the search and calculation for code word, decide which codebook that current state belongs to and give dross information. The advantage of this invention is that it needs just to set multiple vibration sensors on motion arm and treat the signal real time, and needs no other auxiliary device.

The invention discloses a composite material damage detection method based on wavelet analysis and a BP neural network, comprising the steps as follows: preprocessing a damage signal based on wavelet packet analysis in a wavelet analysis algorithm; reconstructing a wavelet packet decomposition coefficient according to a wavelet packet analysis algorithm; using a wavelet packet to decompose the damage signal into five layers to obtain 32 frequency components; reconstructing the wavelet packet decomposition coefficient; obtaining the energy spectrum diagram of the wavelet packet based on the fact that each node coefficient represents the energy of a corresponding order; selecting the energy value of an order, which has the maximum energy value (namely, which is the most sensitive) in the energy spectrum diagram of the wavelet packet, as a damage feature vector; and extracting feature vectors of different damage levels to constitute a learning sample of the BP neural network. The composite material damage detection method is fast in convergence, and simple and effective. The BP neural network after learning and training has the ability to identify the mode of damage to a composite material, can accurately identify the damage to a composite material and the degree of damage, and can locate the damage.

The invention provides a fault diagnosis method for a gear case of an aerogenerator. The method comprises the following steps that a vibration sensor obtains a vibration signal when the gear box runs; a wavelet packet analysis method is used to carry out three-layer decomposition analysis on the collected vibration signal; empirical mode decomposition is carried out on the vibration signal after wavelet packet analysis, and a first component of the signal is extracted; characteristic values are extracted from the extracted first signal component, and serve as a characteristic value used for fault diagnosis; a characteristic vector sample of historical fault data of the gear case is obtained; a support vector machine is used to train the characteristic vector sample, and a group of highest classification accuracy is used as parameters for fault diagnosis later; real-time operation data of the gear case is obtained, and a characteristic vector is obtained; and the support vector machine is used to classify the characteristic vector, and a diagnosis result is output. According to the invention, whether the operation state of the gear box is normal can be analyzed, and a fault part can be determined in a fault state.

The invention relates to a coal rock interface analysis method based on coal mining machine perception, and is realized based on a coal rock interface analysis system based on the coal mining machine perception. The system is composed of a large-capacity data storage device, a coal mining machine electrical main controller, an intrinsically safe type vibration accelerated speed sensor and the like. In the method, through coal mining machine working parameters composed of vibration signals, voltage and current and temperature torque of coal mining machine cutting and traction motors, coal mining machine rocker arm lifting oil cylinder pressure, and traction motor speed signals, signal characteristics of coal mining machine drum cutting teeth cutting coal and rock different roofs and floors situations are analyzed, wavelet packets are used for analyzing energy features of different frequency bands of the vibration signals, probability and statistic samples are used for analyzing feature distribution of the cutting machine working parameters, a multi-sensor information fusion technology is used for comprehensive establishment of different coal rock character databases, a coal mining machine perception coal rock interface is defined through a fuzzy mathematic theory, and a coal rock interface membership degree is calculated according to the coal mining machine perception multi-sensor information, so as to be used as a coal rock interface recognition basis.

The invention discloses a primary fault diagnosis method of a converter in a wind turbine system. The method includes steps of establishing a primary fault classification principle; measuring direct current side output voltage signals of the converter in states of normal operation and fault operation, subjecting the obtained output signals to wavelet packet analysis, reconstructing a wavelet packet decomposition coefficient, extracting and calculating energy of each frequency band signal, and determining which frequency range energy of an original signal mainly concentrates on; subjecting the signals in the frequency range to wavelet power spectrum analysis, and determining fault characteristic frequencies; and analyzing and comparing the characteristic frequencies and power spectrums of the converter in the states of normal operation and various fault operations to obtain a primary fault diagnosis result of the converter. By means of characteristics of wavelet packet analysis, fault diagnosis of the converter can be simply and rapidly achieved in the aspects of energy spectrums and power spectrums, and the fault diagnosis method of the converter is capable of effectively improving safety and effectiveness of the wind turbine system.

The invention discloses a method and a device for diagnosing gear faults based on combination of a wavelet packet and spectral kurtosis. The method comprises the steps of (1) acquiring a gearbox vibration acceleration signal as a signal to be analyzed, (2) performing wavelet packet decomposition on the signal to be analyzed to obtain acceleration signals in different frequency bands, (3) calculating the spectral kurtosis values of the acceleration signals in different frequency bands by use of a spectral kurtosis method, (4) performing Fourier operation on the acceleration signal in the frequency band having the maximum spectral kurtosis value to obtain the optimal frequency band envelope spectrogram, and (5) observing whether a fault characteristic frequency is present in the envelope spectrogram, and if so, determining that the gear of the gearbox has faults, otherwise, determining that the gear of the gearbox has no fault; the device comprises an acceleration sensor, a wavelet decomposition module and a spectral kurtosis demodulation analysis module. The method for diagnosing gear faults based on combination of the wavelet packet and the spectral kurtosis is simple in diagnosis process and high in accuracy by use of the method of combined wavelet packet analysis and spectral kurtosis analysis.

The invention provides a gear failure diagnosis method based on an adaptive genetic algorithm and an SOM (Self-Organizing Map) network. The method comprises the following steps: obtaining a vibration signal of a gear, carrying out wavelet packet analysis on the vibration signal, extracting the feature vectors of the vibration signal, dividing the feature vectors into training data and test data, firstly, utilizing the training data to train the SOM network optimized by the adaptive genetic algorithm, continuously updating the weight and the threshold value of the SOM network until an error output by the SOM network meets an accuracy requirement or achieves a maximum iteration, then, adopting the trained SOM network to diagnose a fault type of the test data, and outputting a fault diagnosis result of the gear. The gear failure diagnosis method has the characteristics of being high in precision, high in reliability and the like, and can be widely applied to the field of the fault diagnosis of mechanical equipment.

The invention belongs to the technical field of human body differentiation and provides a method for extracting and differentiating human body heat source features of infrared pyroelectricity wavelet packet energy. According to the method, the purposes of detection within a 360-degree large-scale range and with a long distance and detection of a static infrared heat source are achieved and the problems that the comfort and the energy-saving performance in an intelligent air conditioner conflict and the false alarm rate in a safety supervision system is high are effectively solved. Thus, according to the technical scheme, the method for extracting and differentiating the human body heat source features of infrared pyroelectricity wavelet packet energy comprises the following steps that a single pyroelectricity infrared detector is driven by a stepping motor to rotate at a constant speed, so that detection of a static object at the long distance and within 360-degree large-scale range is achieved; the detection range is within a disc, wavelet packet analysis is conducted on a collected sample of the human body heat source and a collected sample of a non-human-body heat source, wavelet packet energy serves as a feature of a signal, 5-folding-time cross validation is conducted through a BP neural network, and therefore the human body heat source and the non-human-body heat source are differentiated. The method for extracting and differentiating the human body heat source features of infrared pyroelectricity wavelet packet energy is mainly applied to occasions of the human body differentiation technology.

The invention discloses an equipment state prediction method and system based on multi-dimensional data fusion, and the method comprises the steps: collecting and preprocessing a state monitoring signal of an equipment operation full life cycle, and carrying out noise reduction of the state monitoring signal through wavelet packet analysis; performing time domain, frequency domain and time-frequency domain feature extraction on the original state monitoring signal and the intrinsic mode component, performing feature screening by using permutation entropy and information entropy, performing unsupervised identification of equipment working conditions on the screened features, performing model training at a cloud center end; and storing to an edge end to predict the running state and the residual life of the equipment. Useful multi-dimensional data information in similar working conditions is mined by using a multi-task learning method so as to improve the regression performance of the equipment state and residual life prediction model, and a cloud-side combined system architecture is adopted to save the communication overhead and improve the calculation efficiency.

The invention discloses an active damage monitoring device for a hydraulic concrete structure. The device comprises a vibrating table (1), a waveform generator (2), a driver (3), a sensor (4), a digital filter (6), a digital collector (5), a wavelet packet analysis system (7) and a monitored hydraulic concrete structural body (8), wherein the monitored hydraulic concrete structural body (8) is arranged on the vibrating table (1); after the waveform generator (2) sends a swept-frequency signal to the driver (3), the driver (3) is excited to generate stress waves; the stress waves are propagated in the monitored hydraulic concrete structural body (8) and then are received by the sensor (4); stress wave signals sequentially pass through the digital filter (6), the digital collector (5) and the wavelet packet analysis system (7). The testing platform provided by the invention plays an important role in health monitoring of the hydraulic concrete structure and has the advantages of high accuracy, simple arrangement, low monitoring cost, high working efficiency, high engineering applicability and the like.

The invention discloses a mining drill fault intelligent identification method which mainly comprises a primary diagnosis based on signal processing and a secondary diagnosis based on hybrid intelligence. According to the primary diagnosis based on signal processing, signal processing methods such as time domain and frequency domain analysis, wavelet packet analysis and empirical mode decomposition are utilized to extract a drill fault feature, a characteristic value is obtained through calculating and doing statistics, and a drill fault is judged preliminarily. According to the secondary diagnosis based on hybrid intelligence, the feature of the primary judgment is taken as an input, a support vector machine, an expert system, a fault tree analysis are used to diagnose the drill fault, and a diagnosis result is obtained by using voting technology. According to the mining drill fault intelligent identification method, a plurality of signal processing technology and intelligent diagnosis methods are integrated, the accuracy of drill fault diagnosis can be effectively raised, the examination and repair times are reduced, and the drilling cost is reduced.

The invention discloses a method for identifying a fine crack impact signal of a metal deep drawing part. The method comprises the following steps: acquiring a fine crack acoustic emission impact signal of a metal deep drawing part by using an acoustic emission sensor, carrying out preamplification, filtering and A / D conversion pretreatment on the acquired signal, inputting the pretreated signal into a computer, analyzing the wavelet packets, reconstructing data at different wave bands after the wavelet packets are decomposed, carrying out time series analysis on the denoised acoustic emission signal by using a time series method, establishing a time series model, and finally, identifying the state of the metal deep drawing part in the computer by combining a fuzzy comprehensive judgment method with maximum membership grade principle. The invention can enhance the accuracy that characteristic parameters reflect the actual working conditions can greatly reduce the sampling number on the premise of ensuring to acquire sufficient information, has the advantages of accurate and clear frequency positioning, and is suitable for the occasions with high requirements for on-line monitoring.

The invention relates to a microgrid fault diagnosis method for optimizing an extreme learning machine based on a whale algorithm. The method comprises the steps of: S1, building a microgrid grid-connected operation simulation model comprising a wind driven generator, a photovoltaic cell and a storage battery, and collecting three-phase fault voltage signals at two ends of a line; S2, selecting adb6 wavelet as a wavelet basis, decomposing and reconstructing the three-phase fault voltage signals containing the phase A, the phase B and the phase C obtained by simulation according to a wavelet packet analysis related formula, calculating the energy entropies of the three-phase fault voltage signals to obtain a feature vector X= [x1, x2,..., x24] T containing 24 wavelet packet energy entropies, and taking the feature vector as a data sample; and S3, utilizing a whale algorithm WOA to optimize an input weight and a hidden layer threshold of an extreme learning machine ELM to establish a WOA-ELM fault diagnosis model, and substituting the data sample obtained in the S2 into the WOA-ELM model to carry out training and verification. A BP neural network, an RBF neural network and the ELM are utilized to establish the diagnosis model, the diagnosis model and the WOA-ELM model are subjected to comparative analysis, and the effectiveness and reliability of the WOA-ELM model are verified.

The invention discloses a method for monitoring a marine propulsion shafting bearing vibration failure. The method comprises the following steps: (1) creating a marine propulsion shafting vibration template library in an off-line mode; (2) synchronously collecting various monitor variables, including marine propulsion shafting bearing vibration acceleration signals, the host rotating speed, the propeller shaft rotating speed and the gearbox joining state; (3) classifying data; (4) performing time-frequency transformation on the classified vibration acceleration speed data by adopting a wavelet packet analysis method to acquire energy feature vectors on different feature frequency bands, transforming feature data of different frequency bands, and extracting the energy entropy feature vectors of the feature data to serve as to-be-matched feature vectors; (5) monitoring a failure, namely determining a specific failure type according to the similarity measure matching result; and (6) online updating the marine propulsion shafting vibration template library by utilizing the energy entropy feature vector which has no failure found in detection. The method is convenient and feasible to collect data, can be used for online monitoring and failure diagnosis, and can meet the requirement of long-term failure diagnosis and analysis.

The invention relates to a coal rock character identification method based on multiple parameters of cutting motors of a coal cutter. The coal rock character identification method is achieved by virtue of a coal rock character identification system based on the multiple parameters of the cutting motors of the coal cutter. The coal rock character identification system comprises a large-volume data storage device, an electrical main controller of the coal cutter, an intrinsically safe vibration acceleration sensor, a vibration data transmission cable, a communication data transmission wire and an onboard power supply of the coal cutter. The coal rock character identification method and the coal rock character identification system are achieved in the manners that working parameters consisting of vibration signals, the voltages, currents and temperature torques of left and right cutting motors and a traction motor of the coal cutter, the pressures of left and right rocker arm lifting oil cylinders of the coal cutter as well as speed signals of the traction motor are collected and stored, the signal features of coal and rock cut by cutting teeth of a roller of the coal cutter at different top and base plates are analyzed, the energy features of the vibration signals at different frequency bands are analyzed by virtue of a wavelet packet, the feature distribution of the working parameters of the cutting motors is analyzed by virtue of probability statistic samples, and different coal rock character databases are established by virtue of a multi-sensor information fusion technique.

The invention belongs to the technical field of human body distinguishing and discloses a human body heat source feature extracting and distinguishing method based on infrared pyroelectric information. The method aims to achieve 360-degree wide-range and remote detection and detection of static infrared heat sources and effectively solves the problems of confliction between comfort and energy saving of an intelligent air-conditioner and high false alarm rate of a safety supervision system. According to the technical scheme, the method comprises the steps that a stepping motor is adopted to drive a single pyroelectric infrared detector to rotate at a uniform speed, and then remote, 360-degree wide-range and static object detection is achieved; the detection range is a disk shape, wavelet packet analysis is conducted on collected human body heat source samples and non-human-body heat source samples, a signal wavelet entropy is taken as the features of the signal, 5-fold cross-validation is conducted by means of the BP neural network, and then human body heat resources are distinguished from non-human-body heat resources. The method is mainly applied to human body distinguishing.