Search

With the rapid development of artificial intelligence, the application of this new technology to music generation has attracted more attention and achieved gratifying results. This study proposes a method for combining the transformer deep-learning model with generative adversarial networks (GANs) to explore a more competitive music generation algorithm. The idea of text generation in natural language processing (NLP) was used for reference, and a unique loss function was designed for the model. The training process solves the problem of a nondifferentiable gradient in generating music. Compared with the problem that LSTM cannot deal with long sequence music, the model based on transformer and GANs can extract the relationship in the notes of long sequence music samples and learn the rules of music composition well. At the same time, the optimized transformer and GANs model has obvious advantages in the complexity of the system and the accuracy of generating notes. [ABSTRACT FROM AUTHOR]

Fast nondominated sorting genetic algorithm II (NSGA-II) is a classical method for multiobjective optimization problems and has exhibited outstanding performance in many practical engineering problems. However, the tournament selection strategy used for the reproduction in NSGA-II may generate a large amount of repetitive individuals, resulting in the decrease of population diversity. To alleviate this issue, Lévy distribution, which is famous for excellent search ability in the cuckoo search algorithm, is incorporated into NSGA-II. To verify the proposed algorithm, this paper employs three different test sets, including ZDT, DTLZ, and MaF test suits. Experimental results demonstrate that the proposed algorithm is more promising compared with the state-of-the-art algorithms. Parameter sensitivity analysis further confirms the robustness of the proposed algorithm. In addition, a two-objective network topology optimization model is then used to further verify the proposed algorithm. The practical comparison results demonstrate that the proposed algorithm is more effective in dealing with practical engineering optimization problems. [ABSTRACT FROM AUTHOR]

In this article, an adaptive integral sliding mode control scheme is addressed for switched non-linear systems in the presence of model uncertainties and external disturbances. The control law includes two parts: a slide mode controller for the reduced model of the plant and a compensation controller to deal with the non-linear systems with parameter uncertainties. The adaptive updated laws have been derived from the switched multiple Lyapunov function method, also an admissible switching signal with average dwell-time technique is given. The simplicity of the proposed control scheme facilitates its implementation and the overall control scheme guarantees the global asymptotic stability in the Lyapunov sense such that the sliding surface of the control system is well reached. Simulation results are presented to demonstrate the effectiveness and the feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

Taking the SPI optical fiber laser as an example, we introduce the pulse output mode of operation. VC is used to control the STC12C5A60S2 chip to generate PWM wave with adjustable frequency (500Hz ~ 200kHz) and duty cycle to control the fiber laser. At the same time, VC is used to change the laser power through the RS232. The test result shows that this control system can control the laser rapidily and stablily and it meets the needs of industrial production. [ABSTRACT FROM AUTHOR]

In this article, a DSP2812 SPWM piecewise synchronous modulation system model is built in the Simulink platform with the use of Simulink modules in MATLAB(2010b). It completes the auto generation of DSP code with the use of Real-Time Workshop. It realizes the moduler programming in MATLAB environment. The experiment shows that the automatically generated program runs smoothly in TMS320F2812 development board and the result is correct. It proves this method can improve efficiency of DSP development and it has a certain practical value. [ABSTRACT FROM AUTHOR]

A DSP2812 real-time rendering of motor speed curve program based on MATLAB (2010b) is introduced in this paper. This design exchanges real-time data between a host computer and a DSP target device by calling the functions that MATLAB Embedded IDE Link provide, and it uses MATLAB GUI to develop a software to perform some functions including connecting with the DSP target device, building the project file, loading the program file, drawing the speed waveform and so on. The design has worked well on the SEED-DEC2812, as the same time, the curve of motor speed has been shown in MATLAB (2010b). [ABSTRACT FROM AUTHOR]

The design is based on PMSM servo system, TI company's TMS320F2812 chip and VC ++ 6.0. The upper control software and the PC interface is given by using VC ++ 6.0 for three-phase permanent synchronous servo motor. The motor speed, steering and rotation angle can be controlled accurately by using computer interface to realize the load locating. The servo system of PC + DSP has some superiorities such as simpleness and stabilzation of serial communication, wide range of speed regulation, strong extensibility. [ABSTRACT FROM AUTHOR]

Because of the high-input impedance, fast switch speed and heat stabilization, IGBT has been widely used in motor-control, inverter, UPS and other systems. With the increase power of IGBT, the performance of related driver circuit should be improved. In this paper, a entire IGBT driver based on the IED020112FTA coming from Infineon has been designed. And after experiment, the driver circuit is proved to be good performance. [ABSTRACT FROM AUTHOR]

We introduce the communication system between WeinView touch-screen and counter, analyze MODBUS protocol, study the asynchronous serial communication between touch-screen and counter based on MODBUS protocol. We use the touch-screen as PC and the counter as next crew and use MODBUS RTU protocol data transmission format in communication system. The communication between touch-screen and one or multiple counters is achieved and a distributed control system is formed. [ABSTRACT FROM AUTHOR]

Based on the SAMSUNG's $3C2440a microprocessor and Windows CE 6.0 operating system, this test analyzed the principle of PWM driver, described the system characteristics and kernel customization process of WinCE, in addition, designed the single-pump's distribution applications with the MFC Smart Device application, achieving the precise injection and distribution of liquid. [ABSTRACT FROM AUTHOR]

The accuracy of energy measurement is affected by the homonymous-ends directly. The defect rate of homonymous ends due to error operation can't meet the requirements during the actual production. A homonymous-ends tester for one kind of current transformer is designed and implemented based on Lenz law. The testing principles and the influence on the current transformers is analyzed. The effect of use and the implementation are also introduced in this paper. This homonymous-ends tester with high testing accuracy is reliable in its performance and easy to operate in long term use. [ABSTRACT FROM AUTHOR]

Main process and realizing method of image processing in the correction of chip components were discussed. After using several techniques, we processed the original image, the method named pixel segmentation was mainly discussed about getting the feature points. Then we fitted these points into a line with the least squares method. The angle of this line was confirmed that it could be an equivalent of the angle that the chip component deflected. [ABSTRACT FROM AUTHOR]

We took the double rear wheel drive robot as an object and mainly studied its movement structural model. The robot way recognition and the track simulation was completed with MATLAB. We used the improvement PID algorithm to control the robot and enabled the robot a better movement. [ABSTRACT FROM AUTHOR]

The design of an intelligent electronic ruler for garment is based on MSP430 microcontroller. It can measure the garment dimensions, store and transmit the measurement data using optical encoder technology, liquid crystal display technology, the external EEPROM data storage technology, as well as the USB communication technology. [ABSTRACT FROM AUTHOR]

For Certain applications, in this paper, studied a constant temperature control system of microwave oven on the base of analyzing the principle and method of microwave power regulation, desiyned the overall schematic diagram and the hardware structure diagram of the system. [ABSTRACT FROM AUTHOR]

The purpose of this golf trainer is to provide a design for the linesmen that with the mini instrument they can play golf at an indoor place. With the data from the pressure sensor during the process of waving and striking, the quality of this act can be calculated. Finally, the result will be output by the LCD or linking PC. The outcome proves that the design can reflect the transferring of body gravity center and get relevant data. [ABSTRACT FROM AUTHOR]

This thesis mainly study the application of the fuzzy neural network based on the genetic algorithm to the position control system of some type of surface mounting machine. The structure of the fuzzy neural network, the optimization process of the network structure and the membership function by the genetic algorithm are detailed to introduce by a instance. By the simulation results it is explicitly shown the excellent performance of the fuzzy neural network and the powerful advantage of the genetic algorithm in the multi-objective optimization. [ABSTRACT FROM AUTHOR]

Propese a real-time workflow time modeling and verification method based on timed automata. First, trans-form timed workflow digrams to timed automata model, and then verify the time constrains via using the mechanism of timed automata. [ABSTRACT FROM AUTHOR]

Big flux laser particle counter and auto scan worktable was used to realize leak detection of high efficiency filter in this paper. Particles gathered by laser particle counter and the location of high efficiency filter were corresponded by MSP430F149 to realize find leak accurately. The error of the system was below 0.05mm. [ABSTRACT FROM AUTHOR]

this paper introduced a project design of TPMS,The main content is about the system's makeup, working principles ,the hardware Structure diagram, and the program flow chart. [ABSTRACT FROM AUTHOR]

Computational photography has been striving to capture the spectral information of the dynamic world in the last few decades. However, due to the curse of dimensionality between the 3D spectral images and the 2D imaging sensors, light-blocking components, e.g., bandpass filters or coded apertures, have to be used in spectral imaging systems to project the 3D signal into 2D measurements selectively. Accordingly, computational reconstruction is integrated to recover the underlying 3D signal. Thus, these systems suffer from low light efficiency and high computational burden, both of which cannot afford dynamic spectral imaging. In this paper, we propose a novel snapshot spectral imaging system that can dynamically capture the spectral images. The system is composed of a lens array, a notch filter array, and a monochrome camera in principle. Incoming light beams from the scene are spatially multiplexed by the lens array, spectrally mixed by the notch filter array, and captured by the monochrome camera. The two distinct characteristics, i.e., spatial multiplexing and spectral mixing, guarantee the advantages of low computational burden and high light efficiency, respectively. We further build a prototype system according to the imaging principles. The system can record two kinds of images in a single snapshot: bandstop multispectral images and a panchromatic image, which are used jointly to recover the bandpass multispectral images at few computational costs. Moreover, the proposed system is friendly with spectral super-resolution, for which we develop a theoretical demonstration. Both simulations and experiments are conducted to verify the effectiveness of the proposed system.

Compressive hyperspectral imaging (CHI) has attracted widespread attention due to its advantage of snapshot by encoding the 3D spectral image into a 2D measurement. The bottleneck of CHI for the real application now lies in the limited reconstruction quality, for which one of the fundamental reason is the inaccurate modeling of the measurement noise. Our key observation is that in practical scenarios, the measurement is inevitably contaminated with a positive offset (i.e., noise mean) due to the unideal imaging conditions (e.g. stray light and dark current), resulting in serious degradations of the reconstruction quality. In this paper, we propose to model the real noise with non-zero mean that generalizes the traditional zero mean noise to faithfully characterizing the optical imaging principle, and then introduce a novel reconstruction method with a goal to boost the reconstruction quality. During the reconstruction, the noise mean is estimated gradually to its convergence by measuring the deviation of the intermediate reconstruction result from the system measurement. We demonstrate the superior performance of our method by experiments on synthetic data and real capture data with a hardware prototype.