To identify some special formation lithology with imbalanced logging data, a framework of Multi-layer lithology identification method is proposed. In this framewoke, some special lithology is divided into one class in...
详细信息
To identify some special formation lithology with imbalanced logging data, a framework of Multi-layer lithology identification method is proposed. In this framewoke, some special lithology is divided into one class in the first layer, and each lithology is separated in the second layer. A novel algorithm of Ada Cost2-support vector machine(AdaC2-SVM) is put forward using logging data of actual well located in Karamay for training, and the support vector machine-recursive feature elimination(SVM-RFE) is adopted to select attribute, and logging data from another well nearby is used for testing. Experiment result shows the G-mean and accuracy of our method is up to 95.3% and 94.4%, which has better performance than random forest(RF)algorithm, particle swarm optimization-support vector machine(PSO-SVM) algorithm and improved PSO-SVM(IPSO-SVM)algorithm. In the future, the proposed method have a good prospect and give a valuable result for geology research.
Sintering process is the second most energy-consuming process in steel making and the main energy consumption of the process is the combustion of carbon. Under the background of the transformation of the world’s majo...
详细信息
Sintering process is the second most energy-consuming process in steel making and the main energy consumption of the process is the combustion of carbon. Under the background of the transformation of the world’s major economies to the low carbon economy, to improve the carbon efficiency for saving energy and reducing undesired emissions is of great *** this paper, the comprehensive coke ratio(CCR) is taken as the index of the carbon efficiency. Mechanism analysis was carried out to analyze the influences of the CCR and a predictive model of the CCR based on back-propagation neural network(BPNN)is built that contains state parameters predictive model and the CCR predictive model. Then the optimization method for the CCR is formulated, which aims to minimize the CCR by optimizing the operating parameters. Finally, the method was implemented in an intelligent optimization and control system for carbon efficiency(IOCSCE) in an iron and steel plant. The running results show that the method can reduce the CCR by an average of 1.98 kg/t and effectively reduce the energy consumption of the sintering process. Thus, it can provide guidance for the operators of the sintering process and improve the carbon efficiency.
In order to study the cement hydration characteristics in the process of cement condensation, based on eddy current measuring technology and GMR (giant magnetoresistive sensor), it designed a non-contact cement-hydrat...
详细信息
In order to study the cement hydration characteristics in the process of cement condensation, based on eddy current measuring technology and GMR (giant magnetoresistive sensor), it designed a non-contact cement-hydration-characteristics measuring device. As an advanced nondestructive detection technology, Eddy current detection is convenient and non-contact. And GMR has high sensitivity and good linearity. Combining eddy current detection technology with GMR in design, it successfully gets rid of electrode polarization in traditional contact testing method, and greatly improves the accuracy of cement impedance measurement, and it effectively solves the collision problem that the excitation coil needs high frequency and the measure must have high sensitivity. The measuring device mainly includes magnetic field, GMR sensor, and STM32F427 micro-computer data acquisition system. The testing results show that the device has high precision, good repeatability.
Aiming at the problems of slow recognition,low efficiency and degree of automation in handwritten letter recognition system at present,a handwritten letter recognition system based on extreme learning machine is desig...
详细信息
Aiming at the problems of slow recognition,low efficiency and degree of automation in handwritten letter recognition system at present,a handwritten letter recognition system based on extreme learning machine is designed in this *** system is implemented by mixed programming with M ATLAB and visual studio,it can reads,normalize,binarize and extract the handwritten letter *** real-time interactive recognition of handwritten letters can be realized on the basis of training the simple pictures by using the identification model of the extreme learning machine *** experimental results show that the handwriting recognition system based on extreme learning machine designed in this paper can recognize 98.82%of handwritten letters and greatly reduce learning and testing *** with BP neural network and other recognition algorithms,its training times have been reduced by hundreds or even thousands of *** the same time,there is no manual intervention in the entire learning and testing process,which improves the automation of handwriting recognition.
The human-computer interaction technology which based on the gaze tracking system is convenient and fast. It can achieve the purpose of sight and computer interaction. Based on the relatively static head tracking syst...
详细信息
The human-computer interaction technology which based on the gaze tracking system is convenient and fast. It can achieve the purpose of sight and computer interaction. Based on the relatively static head tracking system, we make improvements for OTSU algorithm to separate the binarized pupil image and the background image completely. I wrote a function to delete a small area that gets a complete and clear binarized pupil image for the existence of small area noise clump. Finally, using the contour extraction method and the three-point circle method to complete the task of Pupil location.
This paper presents a novel single-parameter optimization method for extracting coupling matrix from either measured or electromagnetic simulated S-parameters of a narrow band coaxial-resonator filter with losses. Hav...
详细信息
This paper presents a novel single-parameter optimization method for extracting coupling matrix from either measured or electromagnetic simulated S-parameters of a narrow band coaxial-resonator filter with losses. Having had the polynomials of the S-parameters of a filter by the Cauchy method with removing phase shift, the rational polynomials can be *** the rational polynomials having been determined, a single-parameter optimization method is proposed to obtain ε and the coupling matrix with an assigned topology, which can be extracted using well established techniques. The measured Sparameters compared with the S-parameters obtained from the coupling matrix, and the attenuation factor K is easily *** loss effects will be removed after obtaining the value of the attenuation factor K. The approach is useful and can be used in computer-aided tuning of microwave filters. Example is presented to illustrate the validity of the proposed method.
This paper investigates the stability of neural networks with a time-varying *** on the good effectiveness of the augmented Lyapunov-Krasovskii functional(LKF),some useful integral vectors are summarized and used to c...
详细信息
This paper investigates the stability of neural networks with a time-varying *** on the good effectiveness of the augmented Lyapunov-Krasovskii functional(LKF),some useful integral vectors are summarized and used to construct single integral terms with augmented quadratic integrand so as to develop a novel augmented LKF *** an extended reciprocally convex matrix inequality and an auxiliary function-based inequality are utilized to estimate the derivative of the *** a result,an improved stability criterion is ***,the advantage of proposed method is demonstrated by a numerical example.
Deep drilling is a costly project and efficiency is of paramount importance. The weight on bit is one of the main operating parameters that influences the drilling efficiency and it was controlled by manual before. Bu...
详细信息
Deep drilling is a costly project and efficiency is of paramount importance. The weight on bit is one of the main operating parameters that influences the drilling efficiency and it was controlled by manual before. But after people saw the giant potential of an auto-drilling system in increasing the drilling efficiency, more and more studies on the feed back control of weight on bit have emerged. This paper mainly studied weight on bit dynamic under the variational formation based on a lumped parameter model and a self-tuning PID controller for weight on bit control. The parameters of the PID controller are tuned by using gradient descent method and RBF neural network identification.
A new method for localization of epileptic seizure onset zones(SOZs) is proposed, which uses the Shannon-entropybased complex Morlet wavelet transform to extract a satisfactory time-frequency feature of high-frequen...
详细信息
A new method for localization of epileptic seizure onset zones(SOZs) is proposed, which uses the Shannon-entropybased complex Morlet wavelet transform to extract a satisfactory time-frequency feature of high-frequency oscillations(HFOs).The singular value decomposition and the K-medoids clustering algorithm are employed to extract effective features from the redundant matrix of wavelet coefficients. A distinctive feature is to use the singular values to detect HFOs with the consideration that the singular values of HFOs are generally significantly higher than those of normal case. Based on the half-maximum method,the localization of SOZs are achieved by using the characteristics of HFOs. Comparisons show that our method provides a higher sensitivity and specificity than two existing methods do.
The microphone array speech enhancement algorithm(MASEA), the minimum mean square error algorithm for short-time logarithmic spectrum estimation based on voice activity detection(VAD-LSA-MMSE), and the Wiener filt...
详细信息
The microphone array speech enhancement algorithm(MASEA), the minimum mean square error algorithm for short-time logarithmic spectrum estimation based on voice activity detection(VAD-LSA-MMSE), and the Wiener filtering algorithm based on voice activity detection(VAD-Wiener) are currently the three most commonly used speech enhancement algorithms. Among them, the MASEA algorithm has some disadvantages such as poor noise reduction effect. VAD-LSA-MMSE algorithm has some disadvantages of relying on high SNR and introducing music noise, thereby reducing the intelligibility. The VAD-Wiener algorithm has some disadvantages such as higher SNR requirements. Aiming at the shortcomings of these three speech enhancement algorithms, based on the VAD algorithm and the MASEA algorithm, this paper proposed a new speech enhancement algorithm by combining the characteristics of Wiener filtering algorithm and LSA-MMSE algorithm. The new speech enhancement algorithm is a VAD-based microphone array speech enhancement algorithm(VAD-MASEA). VAD-MASEA is better than the other three algorithms in noise reduction, speech enhancement and voice intelligibility, and has the characteristics of adapting to a lower SNR environment. This paper used MATLAB to carry out experimental research, including the new algorithm and the three existing algorithms were simulated and compared the signal waveforms of the four algorithms. Experimental results show that the proposed VAD-MASEA algorithm overcomes the high SNR requirement and can be used in low SNR environments and obtain highly intelligible enhanced signals.
暂无评论