211 results about "Sample entropy" patented technology

The invention discloses a gear fault diagnosis method based on the SVD decomposition and noise reduction and correlation EEMD entropy features. The method includes utilizing an acceleration vibration sensor to acquire experimental platform gear vibration signals including four types of faults, namely gear normality, gear tooth breaking, gear tooth missing and gear wearing; performing noise reduction on the signals, of four gear states, containing simulated strong noise background of Gaussian white noise by the SVD decomposition method with correlation analysis and noise ratio optimization; decomposing the four types of noises by the EEMD method after noise reduction, and selecting valid IMF components according to correlative coefficients; performing sample entropy calculation on the valid IMF components, and establishing feature vectors composed of the IMF samples; identifying the four different types of gear faults through a PNN neural network. The method is effective and is capable of recognizing the gear fault types on the strong-noise background effectively.

The invention provides an opening-closing fault diagnosis method for an air circuit breaker based on vibration signals, wherein an acceleration sensor is used to collect machine body vibration signals generated during opening-closing courses of the air circuit breaker. The method comprises the steps that firstly, the acceleration sensor is used to collect the machine body vibration signals generated during opening-closing actions of the air circuit breaker and transform the vibration signals into digital signals, so that initial vibration signals are obtained; secondly, an improved wavelet packet threshold de-noising algorithm is used to process the collected vibration signals; thirdly, a complementary ensemble-average empirical mode decomposition algorithm is used to extract intrinsic mode function components from the de-noising vibration signals; fourthly, the quantity Z of the intrinsic mode function components is determined; fifthly, the intrinsic mode function components of the first Z orders are selected and extracted as sample entropies of a characteristic quantity; sixthly, binary tree multi-classifiers based on a relevance vector machine are established; and seventhly, the binary tree multi-classifiers based on the relevance vector machine obtained at the sixth step are used to establish a fault recognition model of the air circuit breaker.

The invention discloses a high-voltage circuit breaker mechanical state monitoring and fault diagnosis method. The method comprises the following steps of 1) according to the historical fault data statistics result of high-voltage circuit breakers, carrying out an artificial fault simulation experiment on some common high-voltage circuit breakers to obtain fault data; 2) analyzing the fault current data, and extracting the current data characteristic quantity of each mechanism fault to be used as one of state diagnosis classification basis; 3) analyzing a fault vibration signal, adopting wavelet packet decomposition and sample entropy for processing high-frequency and low-frequency components to obtain corresponding wavelet packet relative energy and sample entropy respectively to be usedas vibration signal characteristic quantities; and 4) performing dimensionality reduction on the vibration signal characteristic quantities through principal component analysis to be used as one of state diagnosis classification basis, and carrying out state diagnosis on the circuit breaker by a support vector machine. By adoption of the method, the multi-dimensional information of the fault statecan be effectively utilized, so that the development of multi-parameter multi-dimensional mapping fault diagnosis of the circuit breaker can be promoted.

The invention discloses a centrifugal pump fault diagnosis method based on complete ensemble empirical mode decomposition and random forest. The method comprises the following steps: (1) decomposing a centrifugal pump vibrating signal obtained by a sensor into a series of IMF categories by utilizing CEEMD; (2) taking the sample entropy of the IMF categories as characteristic vector of the signal; and (3) carrying out fault diagnosis by taking the characteristic vector obtained by the CEEMD-sample entropy as input of a random forest classifier. According to the invention, the CEEMD and the sample entropy are used for characteristic extraction of the centrifugal pump vibrating signal, on one hand, the phenomena of modal aliasing and end effect occurring in EMD decomposition are avoided as far as possible; and on the other hand, characteristic extraction is relatively convenient and simple, calculated amount is small, and the characteristic extraction is not sensitive to data length and noise, thus being high in applicability. According to the invention, the random forest classifier is used for fault mode identification of the centrifugal pump, thus avoiding the phenomenon of overfitting caused by the fact that conventional classifiers depend too much on training samples, and improving the classification accuracy as far as possible.

The invention discloses a fatigue brain electrical characteristic research method based on different experiment difficulties. Mental fatigue is a gradual and cumulative phenomenon, and generally shows weakening of physiological activities of the human body. Fatigue brain electricity under different states is induced by setting two groups of Stroop experiments with different difficulties, and characteristic analysis is carried out on brain electrical signals in a waking state and in a fatigue state in the two groups of experiments by using wavelet packet decomposition and a sample entropy algorithm. Experimental results show that the relative energy of alpha waves and theta waves is increased from the waking state to the fatigue state, the relative energy of beta waves is obviously reduced (P<0.05), the ratio (P<0.05) of parameters alpha/beta and (alpha+theta)/beta is gradually increased along with deepening of fatigue, and sample entropy values of encephalic regions are in decreasing tendency; compared with the experiment group with high difficulty, parameter changes in low-difficulty tasks are more obvious, and therefore the parameters alpha/beta and (alpha+theta)/beta can serve as potential indicators for measuring mental fatigue and meanwhile can verify that proper increase of experiment difficulty can prevent generation of metal fatigue to a certain extent.

We disclose a system, an apparatus, and a method for high frequency temperature monitoring and analysis. According to a disclosed embodiment the system comprises: (a) a wireless temperature acquisition and logging device especially designed for multi-day, high-frequency, and high-resolution temperature sampling; and (b) an analysis system implemented in a digital computer with one or more processors in order to analyze and characterize said temperature using a plurality of methods including complexity analysis techniques such as Lempel-Ziv complexity, Approximate Entropy, Sample Entropy, Multiscale Entropy, and Detrended Fluctuation Analysis; and other statistical time-series analysis techniques. According to one embodiment the temperature monitoring system is designed to capture the dynamic aspects of temperature in order to enable researchers and clinicians to study temperature regulation, thermal physiology, and clinical thermometry.

The invention provides a method for recognizing and separating magnetotelluric signal and noise. Firstly, a magnetotelluric signal collected in a strong electromagnetic interference environment is equidistantly segmented, by optimizing inherent time-scale decomposition, each magnetotelluric signal segment is subjected to adaptive decomposition to obtain a rotational component, and a sample entropyand a fuzzy entropy of the rotational component are extracted. Then, the sample entropy and the fuzzy entropy are taken as joint feature parameters to carry out fuzzy C-means clustering, according tothe feature parameters and a clustering method, a measured magnetotelluric signal sequence is divided into two kinds including a useful signal and a strong interference signal. Finally, only a magnetotelluric signal segment which is recognized as the strong interference signal is subjected to noise suppression processing by using a wavelet threshold, and a reconstructed magnetotelluric signal isobtained after superposition. The method has high reliability.

The invention relates to a new energy power system optimal dispatching method based on sample entropy, belonging to the field of new energy power system optimal dispatching in power system. At first,that invention predicts the output according to the new energy source, the wind pow and the photovoltaic power; New energy forms net load with traditional load. Secondly, the characteristics of the payload series are analyzed, and the sub-series are divided to calculate the entropy of the corresponding samples. Finally, the complexity of the payload subsequence is evaluated based on sample entropy, and the power role is adjusted according to the sample entropy reflecting the complexity. The traditional power supply can track the fluctuation of the payload flexibly. As to that problem of grid connection of new energy source in the electric power system, the invention propose that the net load is formed by the high proportion of new energy sources and the traditional load, and the phenomenonof abandoning wind and light is avoided; According to the fluctuation degree of the payload curve, the output state and interval of the thermal power unit are adjusted to minimize the fluctuation ofthe thermal power unit and maximize the renewable energy utilization efficiency and system economic benefits.

The invention discloses a cyberspace security situation real-time detection method. The method comprises the following steps: original characteristic extraction that original network data packet characteristics are obtained from a network, multi-scale entropy calculations that sample entropy of an original data packet characteristic sequence is calculated at different time scales, detector training that a mature immunization detector is trained and generated by utilizing a sample entropy characteristic vector and a negative-selection algorithm at the different time scales, network threat security detection that a network sample is detected by utilizing the trained mature immunization detector at the different time scales, cyberspace security situation calculations that cyberspace security situations at the different time scales and different network layers, and situation visualization that the cyberspace security situations are expressed by different colors of curve charts at different time and the different network layers. The time scales considered in the method is relatively comprehensive, the fusion level is high, a situation assessment result is relatively accurate, a complex characteristics of a network behavior can be described, and the whole process of a network threat behavior can be carved in a fine-grained manner.

The invention provides an N400 evoked potential lie detection method based on sample entropy. The method comprises the following steps of extracting and synchronously amplifying electroencephalogram, collecting the electroencephalogram, receiving and synchronously storing the electroencephalogram, preprocessing the electroencephalogram, conducting superposition averaging on the electroencephalogram, extracting an electroencephalogram sample entropy feature value, conducting state judgment on whether a lie is told or not, measuring the complexity of the N400 induced electroencephalogram on the basis of the sample entropy, reflecting nonlinear features of the electroencephalogram, finding a feature threshold value for distinguishing whether a lie is told or not through statistical analysis of data, comparing the threshold value with an absolute value of the entropy gradient of probe stimulus and indifferent stimulus ERP electroencephalogram data samples, and judging whether a lie is told or not. The defects existing when lie testing judgment is performed by means of evoked potential waveform geometric properties in the prior art are overcome, so that the method has the advantage that the stable lie recognition accuracy can be effectively ensured.

A method of creating an anesthetic consciousness index with an artificial neural network includes, obtaining physiological signals, including electroencephalographic signals and eye movement signals, from subjects during a physiological signal monitoring process; filtering noise out of the physiological signals by empirical mode decomposition (EMD); calculating sample entropy values of the noise-removed physiological signals; obtaining sample entropy value sets of the physiological signals; repeating the aforesaid steps to effectuate measurement, noise-filtering, and sample entropy value calculation of the subjects' physiological signals and thus obtain a sample entropy value set; and applying an artificial neural network in conducting regression analysis of the sample entropy value set and a set of levels of consciousness measured with a physiological signal monitor during the physiological signal monitoring process, thereby creating the anesthetic consciousness index model for evaluating the level of consciousness of an anesthetized patient during the physiological signal monitoring process.

The invention discloses a method for diagnosing mechanical states of a distribution switch on the basis of empirical mode decomposition (EMD) sample entropy and fuzzy c-means clustering (FCM). The method comprises the following steps that a piezoelectric accelerometer is mounted near to a main shaft of a switch operating mechanism, and the vibration signals of the distribution switch of different mechanical states at the off and on moments are collected through a data acquisition card and a waveform display storage platform; EMD time frequency decomposition is carried out on the collected vibration signals to obtain the limited number of intrinsic mode components of different frequency and unequal bandwidths and residual error components; the sample entropies of intrinsic mode functions (IMFs) of all orders of the vibration signals of different mechanical states are calculated, and a sample entropy array is formed as the characteristic quantity of the mechanical states of the distribution switch; the sample entropy array is used as the input of the FCM, and the mechanical states of the distribution switch are diagnosed through a fuzzy clustering method.

The present invention discloses a brain electrical emotion identification method for extracting features based on the empirical wavelet transformation. The brain electrical emotion identification method comprises the steps of according to the coherence between the brain electrical emotion data peripheral physiological signals and the brain electrical signal channels, selecting the brain electricalchannels having the highest coherence degrees as the feature extraction channels; extracting the brain electrical emotion features based on the empirical wavelet transformation, and obtaining a series of intrinsic mode functions after the empirical wavelet transformation decomposition; calculating the sample entropy of each intrinsic mode function, and constructing the feature vectors based on the sample entropy values to form a feature vector set; dividing the brain electrical emotion data into a plurality of types according to the two dimensions of arousal and titer, and using a support vector machine to identify the brain electrical emotion. The method of the present invention considers the non-linear features and the non-stationary features of the data in a brain electrical emotion data set simultaneously, thereby guaranteeing the classification precision, accuracy and execution speed of the method.

The embodiment of the invention discloses a PCA-BP-based emotion recognition method and system. The method comprises the steps that a first emotional sound spectrum feature vector of training audio isobtained by blending a first acoustic feature vector and a first sample entropy feature of the training audio; a PCA algorithm is adopted for conducting dimensionality reduction on the emotional sound spectrum feature vector, and a second emotional sound spectrum feature vector is obtained; the second emotional sound spectrum feature vectors of the training audio corresponding to various emotionsare input into a preset BP neural network model separately for training, and sound spectrum feature vector emotion models corresponding to various emotions are obtained; a second acoustic feature vector and a second sample entropy feature of to-be-detected audio are blended to obtain a third emotional sound spectrum feature vector of the to-be-detected audio, the third emotional sound spectrum feature vector is compared with all the acoustic feature vector emotion models, the emotion model matching degree is calculated, and the acoustic feature vector emotion model corresponding to the maximum emotion model matching degree is output. The technical problems that the current voice emotion recognition process is complex, the implement difficulty is high, the accuracy is low, and the efficiency is low are solved.

The invention provides a method and device for evaluating the coma degree. The method comprises: electroencephalogram data of a patient is acquired; the electroencephalogram data is pretreated, and purified electroencephalogram signals are obtained; according to the purified electroencephalogram signals, the coma degree of the patient is evaluated. According to the method, the coma degree of the patient is automatically evaluated according to the purified electroencephalogram signals of the coma patient, manual intervention in the evaluating process of the coma degree is lowered, the influence of subjective factors of medical personnel on the evaluating process is avoided, man-made erroneous judgment is avoided, the evaluating error is reduced, and the evaluating accuracy is improved. Sample entropy is applied to evaluation of the coma degree, the sample entropy corresponding to the purified electroencephalogram signals is calculated, according to a threshold value range of the sample entropy, the coma degree is evaluated, quantification evaluation of the coma degree is achieved, and the evaluation efficiency is greatly improved. Meanwhile, according to the purified electroencephalogram signals, prognosis judgment is automatically conducted, the sample entropy is applied to the prognosis judgment of the coma patient, and the efficiency and accuracy of the prognosis judgment are improved.

The invention discloses an electrocerebral non-linear dual-measure feature extraction and fusion processing method, and relates to the field of electrocerebral signals. The method comprises the following steps: acquiring an electrocerebral signal; performing data preprocessing on the electrocerebral signal; extracting an LZC (Leucocyte Zinc Content) complexity feature from preprocessed data; extracting a sample entropy feature, and performing feature analysis on the LZC complexity feature and the sample entropy feature; establishing a classification model with an SVM (Support Vector Machine) classifier by jointly taking the LZC value of the electrocerebral signal and a sample entropy value which are remarkably different as a feature parameter in order to classify and identify people in different psychological states. By adopting the method for classifying and identifying the electrocerebral signals of people in different psychological states, higher classifying accuracy can be achieved, and an objective evaluation index can be provided for the partition of people in different psychological states.

A portable stimulating, awaking and evaluating system for disturbance of consciousness comprises an EEG acquisition device, a signal preprocessing device which is connected with the EEG acquisition device and used for extracting an independent source component from a first EEG using an independent component analysis algorithm, a digital filter device which is connected with a signal preprocessing device and used for carrying out digital filter process on a second EEG using an empirical mode decomposition algorithm so as to extract an effective third EEG, a feature extracting device which is connected with the digital filter device and used for extracting frequency spectrum features, the sample entropy and the approximation entropy, a classification and a recognition device which is connected with the feature extracting device and used for classifying and recognizing disturbance of consciousness using a support vector machine according to the spectrum features, the sample entropy and the approximation entropy, and an output device which is used for outputting a stimulating signal through a stimulator. The portable stimulating, awaking and evaluating system for disturbance of consciousness is simple in structure and good in portability, and the portable stimulating, awaking and evaluating system for disturbance of consciousness can be used for families and communities using stimulation therapy on disturbance of consciousness.