Neural control of fast nonlinear systems--application to a turbocharged SI engine with VCT.

Today, (engine) downsizing using turbocharging appears as a major way in reducing fuel consumption and pollutant emissions of spark ignition (SI) engines. In this context, an efficient control of the air actuators [throttle, turbo wastegate, and variable camshaft timing (VCT)] is needed for engine torque control. This paper proposes a nonlinear model-based control scheme which combines separate, but coordinated, control modules. Theses modules are based on different control strategies: internal model control (IMC), model predictive control (MPC), and optimal control. It is shown how neural models can be used at different levels and included in the control modules to replace physical models, which are too complex to be online embedded, or to estimate nonmeasured variables. The results obtained from two different test benches show the real-time applicability and good control performance of the proposed methods.     

反病毒引擎可扩展框架的研究与实现*

针对当前反病毒软件中引擎对特征码数据库过分依赖和各功能模块间耦合度大的问题。提出了一个可扩展的引擎框架,利用智能特征码和分解复合检测活动的方法实现了功能与数据的解耦合,应用控制反转的思想将功能模块之间控制耦合转换为接口耦合。该引擎框架不仅解决当前反病毒引擎缺乏可扩展性的问题,而且能方便地应用到嵌入式安全设备的设计中。原型系统验证了设计方案和核心算法的有效性,实验结果表明具有较好的检测性能。     

A review on control system architecture of a SI engine management system

Engine management systems (EMS) has become an essential component of a spark ignition (SI) engine in order to achieve high performance; low fuel consumption and low exhaust emissions. An engine management system (EMS) is a mixed-signal embedded system interacting with the engine through number of sensors and actuators. In addition, it includes an engine control algorithm in the control unit. The control strategies in EMS are intended for air-to-fuel ratio control, ignition control, electronic throttle control, idle speed control, etc. Hence, the control system architecture of an EMS consists of many sub-control modules in its structural design to provide an effective output from the engine. Superior output from the engine is attained by the effective design and implementation of the control system in EMS. The design of an engine control system is a very challenging task because of the complexity of the functions involved. This paper consolidates an overview of the vital developments within the SI engine control system strategies and reviews about some of the basic control modules in the engine management system.     

Spatial to kinematically determined structural transformations

To understand the building design process and to help designers involved, the idea of a research engine has been developed: In this engine cyclic transformations take place between spatial and structural building designs. With this engine, a design process can be studied closely and subjected to improvement, and designers can be supported. To develop the engine, in this paper a part of it is studied, namely the transformation from spatial to structural design, which can be divided into four sub transformations: (1) from spatial design to structural topology; (2) from structural topology to mechanical model; (3) from mechanical model to finite element model; (4) from finite element model to design recommendations. For the first sub transformation, two different techniques are presented: Spatial–Structural Transformation Rules and Element Selection. For the second sub transformation, also two techniques are presented: Element Approach and System Approach. Where possible, data models in EXPRESS and process models in IDEF0 are used. For the third and fourth sub transformation, new procedures have been developed using data models in EXPRESS. To test the data and process models for all four sub transformations, a simplified two-storey building, derived from a real six-storey apartment building, is used as case study. It can be concluded that the developed sub transformations function well, related to their application in the research engine, and that their development raises new research questions that have to be solved in the near future.     

Rendering fireworks displays

A particle system technique to model, render, and animate realistic fireworks displays is presented. The attributes of the fireworks display that the particle system models are color, brightness, shape, trial, size, particle dynamics, blinking, mousing, star effect, spinning, and elasticity. A rendering engine that consists of various modules which individually handle a particular property of the particle is described     

Neural modelling and control of a Diesel engine with pollution constraints

The paper describes a neural approach for modelling and control of a turbocharged Diesel engine. A neural model, whose structure is mainly based on some physical equations describing the engine behaviour, is built for the rotation speed and the exhaust gas opacity. The model is composed of three interconnected neural submodels, each of them constituting a nonlinear multi-input single-output error model. The structural identification and the parameter estimation from data gathered on a real engine are described. The neural direct model is then used to determine a neural controller of the engine, in a specialized training scheme minimising a multivariable criterion. Simulations show the effect of the pollution constraint weighting on a trajectory tracking of the engine speed. Neural networks, which are flexible and parsimonious nonlinear black-box models, with universal approximation capabilities, can accurately describe or control complex nonlinear systems, with little a priori theoretical knowledge. The presented work extends optimal neuro-control to the multivariable case and shows the flexibility of neural optimisers. Considering the preliminary results, it appears that neural networks can be used as embedded models for engine control, to satisfy the more and more restricting pollutant emission legislation. Particularly, they are able to model nonlinear dynamics and outperform during transients the control schemes based on static mappings.     

Model integration and the role of data

Model integration is becoming increasingly important as our impacts on the environment become more severe and the systems we analyze become more complex. There are numerous attempts to make different models work in concert. However model integration usually treats models as software components only, ignoring the evolving nature of models and their constant modification and re-calibration to better represent reality. As a result, the changes that used to impact only contained models of subsystems, now propagate throughout the integrated system, across multiple model components. This makes it harder to keep the overall complexity under control and, in a way, defeats the purpose of modularity, where efficiency is supposed to be gained from independent development of modules. We argue that data that are available for module calibration can serve as an intermediate linkage tool, sitting between modules and providing a module-independent baseline, which is then adjusted when scenarios are to be run. In this case, it is not the model output that is directed into the next model. Rather, model output is presented as a variation around the baseline trajectory, and it is this variation that is then fed into the next module down the chain. The Chesapeake Bay Program suite of models is used to illustrate these problems and the possible remedy.     

Robust air/fuel ratio control with adaptive DRNN model and AD tuning

Current production engines use look-up table and proportional and integral (PI) feedback control to regulate air/fuel ratio (AFR), which is time-consuming for calibration and is not robust to engine parameter uncertainty and time varying dynamics. This paper investigates engine modelling with the diagonal recurrent neural network (DRNN) and such a model-based predictive control for AFR. The DRNN model is made adaptive on-line to deal with engine time varying dynamics, so that the robustness in control performance is greatly enhanced. The developed strategy is evaluated on a well-known engine benchmark, a simulated mean value engine model (MVEM). The simulation results are also compared with the PI control.     

Composing domain-specific physical models with general-purpose software modules in embedded control software

A considerable portion of software systems today are adopted in the embedded control domain. Embedded control software deals with controlling a physical system, and as such models of physical characteristics become part of the embedded control software. In current practices, usually general-purpose languages (GPL), such as C/C++ are used for embedded systems development. Although a GPL is suitable for expressing general-purpose computation, it falls short in expressing the models of physical characteristics as desired. This reduces not only the readability of the code but also hampers reuse due to the lack of dedicated abstractions and composition operators. Moreover, domain-specific static and dynamic checks may not be applied effectively. There exist domain-specific modeling languages (DSML) and tools to specify models of physical characteristics. Although they are commonly used for simulation and documentation of physical systems, they are often not used to implement embedded control software. This is due to the fact that these DSMLs are not suitable to express the general-purpose computation and they cannot be easily composed with other software modules that are implemented in GPL. This paper presents a novel approach to combine a DSML to model physical characteristics and a GPL to implement general-purpose computation. The composition filters model is used to compose models specified in the DSML with modules specified in the GPL at the abstraction level of both languages. As such, this approach combines the benefits of using a DSML to model physical characteristics with the freedom of a GPL to implement general-purpose computation. The approach is illustrated using two industrial case studies from the printing systems domain.     

Implementation of Network Intrusion Detection System Based on Density-based Outliers Mining

The paper puts forward a new method of densitybased anomaly data mining, the method is used to design the engine of network intrusion detection system (NIDS), thus a new NIDS is constructed based on the engine. The NIDS can find new unknown intrusion behaviors, which are used to updated the intrusion rule-base, based on which intrusion detections can be carried out online by the BM pattern match algorithm. Finally all modules of the NIDS are described by formalized language.     

Fault Prediction Modeling for Software Quality Estimation: Comparing Commonly Used Techniques

High-assurance and complex mission-critical software systems are heavily dependent on reliability of their underlying software applications. An early software fault prediction is a proven technique in achieving high software reliability. Prediction models based on software metrics can predict number of faults in software modules. Timely predictions of such models can be used to direct cost-effective quality enhancement efforts to modules that are likely to have a high number of faults. We evaluate the predictive performance of six commonly used fault prediction techniques: CART-LS (least squares), CART-LAD (least absolute deviation), S-PLUS, multiple linear regression, artificial neural networks, and case-based reasoning. The case study consists of software metrics collected over four releases of a very large telecommunications system. Performance metrics, average absolute and average relative errors, are utilized to gauge the accuracy of different prediction models. Models were built using both, original software metrics (RAW) and their principle components (PCA). Two-way ANOVA randomized-complete block design models with two blocking variables are designed with average absolute and average relative errors as response variables. System release and the model type (RAW or PCA) form the blocking variables and the prediction technique is treated as a factor. Using multiple-pairwise comparisons, the performance order of prediction models is determined. We observe that for both average absolute and average relative errors, the CART-LAD model performs the best while the S-PLUS model is ranked sixth.     

基于密度的异常挖掘智能网络入侵检测系统设计与实现

论文提出了基于密度的异常挖掘新方法,并将其应用于入侵检测系统引擎设计中,构建了相应的网络入侵检测系统。该系统通过挖掘异常数据的高效性,可及时发现新的未知入侵行为,用以更新入侵规则库。基于该规则库,系统采用BM模式匹配算法进行实时入侵检测。论文运用形式化语言对入侵检测系统各子模块进行结构化分析与描述。     

Implementation of Network Intrusion Detection System Based on Density-based Outliers Mining

1 Introduction There are m any kinds of network intrusion detec- tion techniques,but which can be divided into two cata- logs generally: one is rule-based, and the other is anom aly-based. The form er is one which detects intru- sion behaviors according t…     

Fast neural networks for diesel engine control design

Advanced engine control systems require accurate dynamic models of the combustion process, which are substantially nonlinear. This contribution presents the application of fast neural net models for engine control design purposes. After briefly introducing a special local linear radial basis function network (LOLIMOT) the process of building adequate dynamic engine models is discussed in detail. These neuro-models are then integrated into an upper-level emission optimization tool which calculates a cost function for exhaust versus consumption/torque and determines optimal engine settings. A DSP-based process computer system allows a fast application of the optimization tool at the engine test stand.     

SPASS: a generic process-oriented crop model with versatile windows interfaces

Crop simulation models are now widely used in agronomy. A highly modular structure has been developed for crop growth simulation models based on the essential processes that are common to various plant species. This generic process-oriented modular structure was implemented in the SPASS (Soil-Plant-Atmosphere System Simulation) model using Microsoft Visual C/C++ under Windows. SPASS is composed of six parts: (i) data management, (ii) memory allocation/initialization, (iii) Modules for crop, soil and microclimate processes, (iv) model configuration and simulation, (v) graphic/table display and (vi) model knowledge integration. The model can be easily configured using the Windows interface by choosing various combinations of process modules developed based on different model approaches. Up to 30 graphic and 5 table MDI (Multiple Document Interface) child windows can be opened during or after the simulation run. Each child window can be resized freely on the screen for the convenience of data analysis. The model theory can be easily viewed using the online theory book. The SPASS model structure facilitates comparison of different model approaches, transfer of improvements between models, development of multi-crop models and modification of process modules for new applications.     

Cerebellar Microcomplexes and the Modulation of Motor Pattern Generators

The cerebellum provides a paradigm for motor control in which adaptive circuitry modulates control systems rather than being embedded within the motor control circuitry itself. We exemplify this by a model of the role of cerebellum in adaptation to the effects of wearing prism glasses on throwing at a target. The cerebellum is viewed as a set of modules (cerebellar microcomplexes), each of which can be added to a control system to improve smooth coordinated movement, with improvements continuing and improving over time. Moreover, context information can be injected into a module which enables it to change modes. We close with a brief discussion of the implications of work on cerebellar modeling, noting that cerebellar modules can be linked to coordinate different control systems.     

Comparative analysis of artificial neural networks and dynamic models as virtual sensors

This paper presents a comparison of predictive models for the estimation of engine power and tailpipe emissions for a 4 kW gasoline scooter. This study forms a benchmark toward establishing an online emissions control and monitoring system to bring the emissions to within specific limits. Three emissions predictive models were investigated in this study; direct and series artificial neural network (ANN) models and a MATLAB dynamic model. The direct models takes variables lambda, throttle position, engine and vehicle speed to predict the engine power and the emissions CO, CO₂ and HC. The series model first takes the mentioned input to predict the engine power and consequently using the engine power as the fifth input to predict the emissions. For the ANN models, two multilayered networks were compared and analyzed; the backpropagation (BP) and optimization layer-by-layer (OLL) algorithms. The predictive accuracy for each algorithm were compared and it was found that the OLL network is the most accurate with a maximum mean relative error (MRE) of 1.78% and 1.38% for the direct and series predictive model respectively. Comparative results showed that the series neural network model gives the most accurate predictions, with MRE of 0.63% and 0.47% for the engine power and emissions respectively. The series neural network model can be seen as generic virtual power and emissions sensors, substituting costly and cumbersome hardware. Simple obtainable process parameters together with the series neural network will contribute immensely in control and tuning of emissions for real-time vehicular applications.     

Sampled-data theory applied to the modelling and control analysis of compression ignition engines—Part I†

Proposals for the use of electronic speed governing of diesel engines used for driving alternators has led to a re-examination of the dynamic behaviour of the engine for control purposes. If maximum advantage to the plant performance is to be achieved from using more complex and expensive governing devices, then better models of individual components in the power system for simulation and control studies may be necessary. This paper describes an investigation performed to model the engine in terms of a discrete system. The frequency domain properties of the model (for various numbers of cylinders) are examined and compared with the model usually assumed, as well as with the frequency response of an actual engine. A companion paper will extend this work using 2-transform techniques.     

Modeling and online parameter estimation of intake manifold in gasoline engines using sliding mode observer

Model based control of automotive engines for fuel economy and pollution minimization depends on accuracy of models used. A number of mathematical models of automotive engine processes are available for this purpose but critical model parameters are difficult to obtain and generalize. This paper presents a novel method of online estimation of discharge coefficient of throttle body at the intake manifold of gasoline engines. The discharge coefficient is taken to be a varying parameter. Air mass flow across the throttle body is a critical variable in maintaining a closer to stoichiometric air fuel ratio; which is necessary to minimize the pollution contents in exhaust gases. The estimation method is based on sliding mode technique. A classical first Sliding mode observer is designed to estimate intake manifold pressure and the model uncertainty arising from the uncertain and time varying discharge coefficient is compensated by the discontinuity/switching signal of sliding mode observer. This discontinuity is used to compute coefficient of discharge as a time varying signal. The discharge coefficient is used to tune/correct the intake manifold model to engine measurements. The resulting model shows a very good agreement with engine measurements in steady as well s transient state. The stability of the observer is shown by Lyapunov direct method and the validity of the online estimation is successfully demonstrated by experimental results. OBD-II (On Board Diagnostic revision II) based sensor data acquisition from the ECU (Electronic Control Unit) of a production model vehicle is used. The devised algorithm is simple enough to be designed and implemented in a production environment. The online estimation of parameter can also be used for engine fault diagnosis work.     

一个基于情感的自主非玩家角色模型

提出了一个新颖的基于情感的非玩家角色模型，此类非玩家角色有人造躯体，生活在虚拟的游戏场景中，并且具有自主行为。模型将情感系统、注意聚焦、意图以及表现系统集成在一起。模拟了人类的遗忘和情绪波动特性，以期使得游戏中的非玩家角色更接近于玩家角色或者真实玩家。为了表达情感和认知固有的不确定性，模型中用到了模糊表达。系统采用Model-View-Controller(MVC)的设计模式来实现，该模式把人工智能从游戏引擎中独立出来，采用接口和组件的思想来实现人工智能。