一种用于异步电机效率优化的混合搜索方法

针对异步电机效率优化问题,提出了一种混合搜索方法。该方法起始于模糊自适应搜索,然后切换至黄金分割法以获取确定收敛速度。这样的搜索步骤能够降低转矩波动,避免在最优点附近发生振荡。利用一个包含铁损和机械损耗的异步电机模型,对该方法进行了矢量控制下的性能验证。仿真结果验证了该方法的有效性。

基于模糊推理水下作业系统运动控制研究

水下作业系统是运动学冗余系统,本文将模糊推理方法融入基于任务优先运动学控制算法,对系统载体与机械手进行协调运动分配,同时对系统多个任务进行优化。通过带有3自由度水下机械手的水下作业系统进行算例仿真研究,说明运动控制算法的有效性。

自适应模糊PID控制在AUV控制中的应用

自治潜水器(AUV,Autonomous Underwater Vehicle)是非线性、强耦合、大惯性的多输入多输出系统,又由于受到海流、传感器、执行机构等不确定性的影响,对AUV控制器的鲁棒性能提出了更高的要求。本文针对我国正在研制开发的长航程自治潜水器的特性及其对航行控制的要求,将PID控制与模糊控制的简便性、灵活性以及鲁棒性结合起来,为AUV设计了可在线修改PID参数的自适应模糊PID控制器,仿真结果证明了该种控制方法不但提高了AUV系统的动态特性,而且可在参数摄动和外界扰动时获得较好的控制性能。

基于模糊神经网络的多移动机器人自学习协调系统

研究多移动机器人的运动规划问题．针对机器人模型未知或不精确以及环境的动态变化，提出一种自学习模糊控制器（ＦＬＣ）来进行准确的速度跟踪．首先通过神经网络的学习训练构造ＦＬＣ，再由再励学习算法来在线调节ＦＬＣ的输出，以校正机器人运动状态，实现安全协调避撞

油气勘探风险评价与决策技术研究

PetroChina and other national petroleum incorporations need rigorous procedures and practical methods in risk evaluation and exploration decision at home and abroad to safeguard their international exploration practice in exploration licence bidding, finding appropriate ratio of risk sharing with partners, as well as avoiding high risk projects and other key exploration activities. However, due to historical reasons, we are only at the beginning of a full study and methodology development in exploration risk evaluation and decision. No rigorous procedure and practical methods are available in our exercises of international exploration. Completely adopting foreign procedure, methods and tools by our national incorporations are not practical because of the differences of the current economic and management systems in China. The objective of this study is to establish a risk evaluation and decision system with independent intellectual property right in oil and gas exploration so that a smooth transition from our current practice into international norm can take place. The system developed in this dissertation includes the following four components: 1. A set of quantitative criteria for risk evaluation is derived on the basis of an anatomy of the parameters from thirty calibration regions national wide as well as the characteristics and the geological factors controlling oil and gas occurrence in the major petroleum-bearing basins in China, which provides the technical support for the risk quantification in oil and gas exploration. 2. Through analysis of existing methodology, procedure and methods of exploration risk evaluation considering spatial information are proposed. The method, utilizing Mahalanobis Distance (MD) and fuzzy logic for data and information integration, provides probabilistic models on the basis of MD and fuzzy logic classification criteria, thus quantifying the exploration risk using Bayesian theory. A projection of the geological risk into spatial domain provides a probability map of oil and gas occurrence in the area under study. The application of this method to the Nanpu Sag shows that this method not only correctly predicted the oil and gas occurrence in the areas where Beibu and Laoyemiao oil fields are found in the northwest of the onshore area, but also predicted Laopu south, Nanpu south and Hatuo potential areas in the offshore part where exploration maturity was very low. The prediction of the potential areas are subsequently confirmed by 17 exploration wells in the offshore area with 81% success, indicating this method is very effective for exploration risk visualization and reduction. 3. On the basis of “Methods and parameters of economic evaluation for petroleum exploration and development projects in China”, a ”pyramid” method for sensitivity analysis was developed, which meets not only the need for exploration target evaluation and exploration decision at home, but also allows a transition from our current practice to international norm in exploration decision. This provides the foundation for the development of a software product “Exploration economic evaluation and decision system of PetroChina” (EDSys). 4. To solve problem in methodology of exploration decision, effort was made on the method of project portfolio management. A drilling decision method was developed employing the concept of geologically risked net present value. This method overcame the dilemma of handling simultaneously both geological risk and portfolio uncertainty, thus casting light into the application of modern portfolio theory to the evaluation of high risk petroleum exploration projects.

Fast Learning VIEWNET Architectures for Recognizing 3-D Objects from Multiple 2-D Views

The recognition of 3-D objects from sequences of their 2-D views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNET incorporates a preprocessor that generates a compressed but 2-D invariant representation of an image, a supervised incremental learning system that classifies the preprocessed representations into 2-D view categories whose outputs arc combined into 3-D invariant object categories, and a working memory that makes a 3-D object prediction by accumulating evidence from 3-D object category nodes as multiple 2-D views are experienced. The simplest VIEWNET achieves high recognition scores without the need to explicitly code the temporal order of 2-D views in working memory. Working memories are also discussed that save memory resources by implicitly coding temporal order in terms of the relative activity of 2-D view category nodes, rather than as explicit 2-D view transitions. Variants of the VIEWNET architecture may also be used for scene understanding by using a preprocessor and classifier that can determine both What objects are in a scene and Where they are located. The present VIEWNET preprocessor includes the CORT-X 2 filter, which discounts the illuminant, regularizes and completes figural boundaries, and suppresses image noise. This boundary segmentation is rendered invariant under 2-D translation, rotation, and dilation by use of a log-polar transform. The invariant spectra undergo Gaussian coarse coding to further reduce noise and 3-D foreshortening effects, and to increase generalization. These compressed codes are input into the classifier, a supervised learning system based on the fuzzy ARTMAP algorithm. Fuzzy ARTMAP learns 2-D view categories that are invariant under 2-D image translation, rotation, and dilation as well as 3-D image transformations that do not cause a predictive error. Evidence from sequence of 2-D view categories converges at 3-D object nodes that generate a response invariant under changes of 2-D view. These 3-D object nodes input to a working memory that accumulates evidence over time to improve object recognition. ln the simplest working memory, each occurrence (nonoccurrence) of a 2-D view category increases (decreases) the corresponding node's activity in working memory. The maximally active node is used to predict the 3-D object. Recognition is studied with noisy and clean image using slow and fast learning. Slow learning at the fuzzy ARTMAP map field is adapted to learn the conditional probability of the 3-D object given the selected 2-D view category. VIEWNET is demonstrated on an MIT Lincoln Laboratory database of l28x128 2-D views of aircraft with and without additive noise. A recognition rate of up to 90% is achieved with one 2-D view and of up to 98.5% correct with three 2-D views. The properties of 2-D view and 3-D object category nodes are compared with those of cells in monkey inferotemporal cortex.

Universal power quality manager with a new control scheme

A new universal power quality manager is proposed. The proposal treats a number of power quality problems simultaneously. The universal manager comprises a combined series and shunt three-phase PWM controlled converters sharing a common DC link. A control scheme based on fuzzy logic is introduced and the general features of the design and operation processes are outlined. The performance of two configurations of the proposed power quality manager are compared in terms of a recently formulated unified power quality index. The validity and integrity of the proposed system is proved through computer simulated experiments

Multiple Input Governor Control for a Diesel Generating Set

The paper presents a multiple input single output fuzzy logic governor algorithm that can be used to improve the transient response of a diesel generating set, when supplying an islanded load. The proposed governor uses the traditional speed input in addition to voltage and power factor to modify the fuelling requirements during various load disturbances. The use of fuzzy logic control allows the use of PID type structures that can provide variable gain strategies to account for non-linearities in the system. Fuzzy logic also provides a means of processing other input information by linguistic reasoning and a logical control output to aid the governor action during transient disturbance. The test results were obtained using a 50 kVA naturally aspirated diesel generator testing facility. Both real and reactive load tests were conducted. The complex load test results demonstrate that, by using additional inputs to the governor algorithm, enhanced generator transient speed recovery response can be obtained.

Behaviours in video

With a significant increment of the number of digital cameras used for various purposes, there is a demanding call for advanced video analysis techniques that can be used to systematically interpret and understand the semantics of video contents, which have been recorded in security surveillance, intelligent transportation, health care, video retrieving and summarization. Understanding and interpreting human behaviours based on video analysis have observed competitive challenges due to non-rigid human motion, self and mutual occlusions, and changes of lighting conditions. To solve these problems, advanced image and signal processing technologies such as neural network, fuzzy logic, probabilistic estimation theory and statistical learning have been overwhelmingly investigated.

Energy monitoring and quality control of a single screw extruder

Polymer extrusion, in which a polymer is melted and conveyed to a mould or die, forms the basis of most polymer processing techniques. Extruders frequently run at non-optimised conditions and can account for 15–20% of overall process energy losses. In times of increasing energy efficiency such losses are a major concern for the industry. Product quality, which depends on the homogeneity and stability of the melt flow which in turn depends on melt temperature and screw speed, is also an issue of concern of processors. Gear pumps can be used to improve the stability of the production line, but the cost is usually high. Likewise it is possible to introduce energy meters but they also add to the capital cost of the machine. Advanced control incorporating soft sensing capabilities offers opportunities to this industry to improve both quality and energy efficiency. Due to strong correlations between the critical variables, such as the melt temperature and melt pressure, traditional decentralized PID (Proportional–Integral–Derivative) control is incapable of handling such processes if stricter product specifications are imposed or the material is changed from one batch to another. In this paper, new real-time energy monitoring methods have been introduced without the need to install power meters or develop data-driven models. The effects of process settings on energy efficiency and melt quality are then studied based on developed monitoring methods. Process variables include barrel heating temperature, water cooling temperature, and screw speed. Finally, a fuzzy logic controller is developed for a single screw extruder to achieve high melt quality. The resultant performance of the developed controller has shown it to be a satisfactory alternative to the expensive gear pump. Energy efficiency of the extruder can further be achieved by optimising the temperature settings. Experimental results from open-loop control and fuzzy control on a Killion 25 mm single screw extruder are presented to confirm the efficacy of the proposed approach.

A computational intelligent approach to multi-factor analysis of violent crime information systems

Various scientific studies have explored the causes of violent behaviour from different perspectives, with psychological tests, in particular, applied to the analysis of crime factors. The relationship between bi-factors has also been extensively studied including the link between age and crime. In reality, many factors interact to contribute to criminal behaviour and as such there is a need to have a greater level of insight into its complex nature. In this article we analyse violent crime information systems containing data on psychological, environmental and genetic factors. Our approach combines elements of rough set theory with fuzzy logic and particle swarm optimisation to yield an algorithm and methodology that can effectively extract multi-knowledge from information systems. The experimental results show that our approach outperforms alternative genetic algorithm and dynamic reduct-based techniques for reduct identification and has the added advantage of identifying multiple reducts and hence multi-knowledge (rules). Identified rules are consistent with classical statistical analysis of violent crime data and also reveal new insights into the interaction between several factors. As such, the results are helpful in improving our understanding of the factors contributing to violent crime and in highlighting the existence of hidden and intangible relationships between crime factors.

Secagem convectiva de produtos alimentares: otimização e controlo

O presente trabalho tem como objetivo analisar a cinética de secagem do bacalhau salgado verde (Gadus morhua) em secador convectivo. É apresentada a análise da composição físico-química dos bacalhaus utilizados nos ensaios experimentais, bem como o estudo das isotermas de sorção do produto, através de experiências e modelação matemática. Dos modelos usados para o ajuste das isotermas de sorção do bacalhau salgado verde, o que melhor se adaptou aos resultados experimentais foi o modelo de GAB Modificado, com coeficientes de correlação variando entre 0,992 e 0,998. Para o controlo do processo de secagem (nomeadamente os parâmetros temperatura, humidade relativa e velocidade do ar) foi utilizada lógica difusa, através do desenvolvimento de controladores difusos para o humidificador, desumidificador, resistências de aquecimento e ventilador. A modelação do processo de secagem foi realizada através de redes neuronais artificiais (RNA), modelo semi-empírico de Page e modelo difusivo de Fick. A comparação entre dados experimentais e simulados, para cada modelo, apresentou os seguintes erros: entre 1,43 e 11,58 para o modelo de Page, 0,34 e 4,59 para o modelo de Fick e entre 1,13 e 6,99 para a RNA, com médias de 4,38, 1,67 e 2,93 respectivamente. O modelo obtido pelas redes neuronais artificiais foi submetido a um algoritmo de otimização, a fim de buscar os parâmetros ideais de secagem, de forma a minimizar o tempo do processo e maximizar a perda de água do bacalhau. Os parâmetros ótimos obtidos para o processo de secagem, após otimização realizada, para obter-se uma humidade adimensional final de 0,65 foram: tempo de 68,6h, temperatura de 21,45°C, humidade relativa de 51,6% e velocidade de 1,5m/s. Foram também determinados os custos de secagem para as diferentes condições operacionais na instalação experimental. Os consumos por hora de secagem variaram entre 1,15 kWh e 2,87kWh, com uma média de 1,94kWh.