Point-wise confidence interval estimation by neural networks: A comparative study based on automotive engine calibration.

In developing neural network techniques for real world applications it is still very rare to see estimates of confidence placed on the neural network predictions. This is a major deficiency, especially in safety-critical systems. In this paper we explore three distinct methods of producing point-wise confidence intervals using neural networks. We compare and contrast Bayesian, Gaussian Process and Predictive error bars evaluated on real data. The problem domain is concerned with the calibration of a real automotive engine management system for both air-fuel ratio determination and on-line ignition timing. This problem requires real-time control and is a good candidate for exploring the use of confidence predictions due to its safety-critical nature.

Tuotetiedon hallinta, Case: moottorinohjausjärjestelmä

Tuotetiedonhallinnan tavoitteena on tuotteeseen liittyvien tietojen hallinta koko tuotteen elinkaaren ajan. Teollisen liiketoiminnan uudet suuntaukset ovat lisänneet tarvetta tuotetietojen hallinnan tehostamiseen. Tehokkaalla tuotetietojen hallinnalla voidaan saada välittömiä ja välillisiä parannuksia liiketoimintaan, joten se on merkittävä tekijä liiketoiminnan kilpailukyvyn ylläpitämisessä. Työssä on esitelty tuotetiedon hallintajärjestelmien tyypillisiä perustoiminnallisuuksia ja niiden soveltamista yrityksen eri toiminnoissa. Lisäksi on kuvailtu tuotetiedon hallintajärjestelmän käyttöönottoprojektia, joka on sekä tietojärjestelmäprojekti että liiketoimintaprosessien kehittämishanke. Käyttöönoton lähtökohtana on yrityksen toimintaprosessien tunteminen ja tarvittaessa kehittäminen. Työn soveltavassa osassa on kuvattu kohdeyrityksen elektroniseen moottorinohjausjärjestelmään liittyvien tuotetietojen hallinnan nykytilaa ja pohdittu tuotetiedon hallintajärjestelmän mahdollisuuksia sen kehittämiseksi.

Optimierung von Betriebsstrategien für elektrifizierte Antriebskonzepte

Im Rahmen dieser Arbeit wird eine gemeinsame Optimierung der Hybrid-Betriebsstrategie und des Verhaltens des Verbrennungsmotors vorgestellt. Die Übernahme von den im Steuergerät verwendeten Funktionsmodulen in die Simulationsumgebung für Fahrzeuglängsdynamik stellt eine effiziente Applikationsmöglichkeit der Originalparametrierung dar. Gleichzeitig ist es notwendig, das Verhalten des Verbrennungsmotors derart nachzubilden, dass das stationäre und das dynamische Verhalten, inklusive aller relevanten Einflussmöglichkeiten, wiedergegeben werden kann. Das entwickelte Werkzeug zur Übertragung der in Ascet definierten Steurgerätefunktionen in die Simulink-Simulationsumgebung ermöglicht nicht nur die Simulation der relevanten Funktionsmodule, sondern es erfüllt auch weitere wichtige Eigenschaften. Eine erhöhte Flexibilität bezüglich der Daten- und Funktionsstandänderungen, sowie die Parametrierbarkeit der Funktionsmodule sind Verbesserungen die an dieser Stelle zu nennen sind. Bei der Modellierung des stationären Systemverhaltens des Verbrennungsmotors erfolgt der Einsatz von künstlichen neuronalen Netzen. Die Auswahl der optimalen Neuronenanzahl erfolgt durch die Betrachtung des SSE für die Trainings- und die Verifikationsdaten. Falls notwendig, wird zur Sicherstellung der angestrebten Modellqualität, das Interpolationsverhalten durch Hinzunahme von Gauß-Prozess-Modellen verbessert. Mit den Gauß-Prozess-Modellen werden hierbei zusätzliche Stützpunkte erzeugt und mit einer verminderten Priorität in die Modellierung eingebunden. Für die Modellierung des dynamischen Systemverhaltens werden lineare Übertragungsfunktionen verwendet. Bei der Minimierung der Abweichung zwischen dem Modellausgang und den Messergebnissen wird zusätzlich zum SSE das 2σ-Intervall der relativen Fehlerverteilung betrachtet. Die Implementierung der Steuergerätefunktionsmodule und der erstellten Steller-Sensor-Streckenmodelle in der Simulationsumgebung für Fahrzeuglängsdynamik führt zum Anstieg der Simulationszeit und einer Vergrößerung des Parameterraums. Das aus Regelungstechnik bekannte Verfahren der Gütevektoroptimierung trägt entscheidend zu einer systematischen Betrachtung und Optimierung der Zielgrößen bei. Das Ergebnis des Verfahrens ist durch das Optimum der Paretofront der einzelnen Entwurfsspezifikationen gekennzeichnet. Die steigenden Simulationszeiten benachteiligen Minimumsuchverfahren, die eine Vielzahl an Iterationen benötigen. Um die Verwendung einer Zufallsvariablen, die maßgeblich zur Steigerung der Iterationanzahl beiträgt, zu vermeiden und gleichzeitig eine Globalisierung der Suche im Parameterraum zu ermöglichen wird die entwickelte Methode DelaunaySearch eingesetzt. Im Gegensatz zu den bekannten Algorithmen, wie die Partikelschwarmoptimierung oder die evolutionären Algorithmen, setzt die neu entwickelte Methode bei der Suche nach dem Minimum einer Kostenfunktion auf eine systematische Analyse der durchgeführten Simulationsergebnisse. Mit Hilfe der bei der Analyse gewonnenen Informationen werden Bereiche mit den bestmöglichen Voraussetzungen für ein Minimum identifiziert. Somit verzichtet das iterative Verfahren bei der Bestimmung des nächsten Iterationsschrittes auf die Verwendung einer Zufallsvariable. Als Ergebnis der Berechnungen steht ein gut gewählter Startwert für eine lokale Optimierung zur Verfügung. Aufbauend auf der Simulation der Fahrzeuglängsdynamik, der Steuergerätefunktionen und der Steller-Sensor-Streckenmodelle in einer Simulationsumgebung wird die Hybrid-Betriebsstrategie gemeinsam mit der Steuerung des Verbrennungsmotors optimiert. Mit der Entwicklung und Implementierung einer neuen Funktion wird weiterhin die Verbindung zwischen der Betriebsstrategie und der Motorsteuerung erweitert. Die vorgestellten Werkzeuge ermöglichten hierbei nicht nur einen Test der neuen Funktionalitäten, sondern auch eine Abschätzung der Verbesserungspotentiale beim Verbrauch und Abgasemissionen. Insgesamt konnte eine effiziente Testumgebung für eine gemeinsame Optimierung der Betriebsstrategie und des Verbrennungsmotorverhaltens eines Hybridfahrzeugs realisiert werden.

Análise das emissões gasosas de um veículo flex funcionando com diferentes combustíveis

Efforts in research and development of new technologies to reduce emission levels of pollutant gases in the atmosphere has intensified in the last decades. In this context, it can be highlighted the modern systems of electronic engine management, new automotive catalysts and the use of renewable fuels which contributes to reduce the environmental impact. The purpose of this study was a comparative analysis of gas emissions from a automotive vehicle, operating with different fuels: natural gas, AEHC or gasoline. To execute the experimental tests, a flex vehicle was installed on a chassis dynamometer equipped with a gas analyzer and other complementary accessories according to the standard guidelines of emission and security procedures. Tests were performed according to NBR 6601 and NBR 7024, which define the urban and road driving cycle, respectively. Besides the analysis of exhaust gases in the discharge tube, before and after the catalyst, using the suction probe of the gas analyzer to simulate the vehicle in urban and road traffic, were performed tests of fuel characterization. Final results were conclusive in indicating leaded gasoline as the fuel which most contributed with pollutant emissions in atmosphere and the usual gasoline being the fuel which less contributed with pollutant emissions in atmosphere

Modelamento matemático e controle PI de uma válvula borboleta eletrônica.

Este trabalho apresenta uma investigação das propriedades dinâmicas da válvula borboleta eletrônica do sistema de admissão de ar de um motor a combustão interna. O objetivo é utilizar um modelo matemático da válvula borboleta com todos os seus parâmetros identificados para efetuar o controle da válvula e aplica-lo em ambiente real. Tendo o modelo e os parâmetros identificados, compara-se o comportamento real de uma válvula borboleta com o comportamento simulado, utilizando os mesmos sinais de entrada, de tal forma a validar o modelo desenvolvido. Utilizando o controle Proporcional Integral, foi possível mostrar a aplicabilidade da metodologia que pode ser estendida para projetos de controle mais complexos. Com o controle PI, o modelo matemático é validado e pode ser utilizado como base para projetos de controle mais complexos. O modelo aqui desenvolvido representa satisfatoriamente a dinâmica da válvula borboleta, sendo possível utilizá-lo em outros tipos de válvula borboleta.

Análise das emissões gasosas de um veículo flex funcionando com diferentes combustíveis

Efforts in research and development of new technologies to reduce emission levels of pollutant gases in the atmosphere has intensified in the last decades. In this context, it can be highlighted the modern systems of electronic engine management, new automotive catalysts and the use of renewable fuels which contributes to reduce the environmental impact. The purpose of this study was a comparative analysis of gas emissions from a automotive vehicle, operating with different fuels: natural gas, AEHC or gasoline. To execute the experimental tests, a flex vehicle was installed on a chassis dynamometer equipped with a gas analyzer and other complementary accessories according to the standard guidelines of emission and security procedures. Tests were performed according to NBR 6601 and NBR 7024, which define the urban and road driving cycle, respectively. Besides the analysis of exhaust gases in the discharge tube, before and after the catalyst, using the suction probe of the gas analyzer to simulate the vehicle in urban and road traffic, were performed tests of fuel characterization. Final results were conclusive in indicating leaded gasoline as the fuel which most contributed with pollutant emissions in atmosphere and the usual gasoline being the fuel which less contributed with pollutant emissions in atmosphere

Development and testing of methodologies for the control and diagnosis of innovative combustion systems

In pursuit of aligning with the European Union's ambitious target of achieving a carbon-neutral economy by 2050, researchers, vehicle manufacturers, and original equipment manufacturers have been at the forefront of exploring cutting-edge technologies for internal combustion engines. The introduction of these technologies has significantly increased the effort required to calibrate the models implemented in the engine control units. Consequently the development of tools that reduce costs and the time required during the experimental phases, has become imperative. Additionally, to comply with ever-stricter limits on 〖"CO" 〗_"2" emissions, it is crucial to develop advanced control systems that enhance traditional engine management systems in order to reduce fuel consumption. Furthermore, the introduction of new homologation cycles, such as the real driving emissions cycle, compels manufacturers to bridge the gap between engine operation in laboratory tests and real-world conditions. Within this context, this thesis showcases the performance and cost benefits achievable through the implementation of an auto-adaptive closed-loop control system, leveraging in-cylinder pressure sensors in a heavy-duty diesel engine designed for mining applications. Additionally, the thesis explores the promising prospect of real-time self-adaptive machine learning models, particularly neural networks, to develop an automatic system, using in-cylinder pressure sensors for the precise calibration of the target combustion phase and optimal spark advance in a spark-ignition engines. To facilitate the application of these combustion process feedback-based algorithms in production applications, the thesis discusses the results obtained from the development of a cost-effective sensor for indirect cylinder pressure measurement. Finally, to ensure the quality control of the proposed affordable sensor, the thesis provides a comprehensive account of the design and validation process for a piezoelectric washer test system.

Audel's Gas engine manual : a practical treatise relating to the theory and management of gas, gasoline and oil engines, including chapters on producer gas plants, marine motors and automobile engines.

Mode of access: Internet.

The steam engine indicator and its appliances. Being a comprehensive treatise for the use of constructing, erecting and operating engineers, superintendents, master mechanics, and students ... with many illustrations, rules, tables, and examples for obtaining the best results in the economical operation of all classes of steam, gas and ammonia engines ... Its correct use, management and care, derived from the author's practical and professional experience ...

Mode of access: Internet.

Locomotive engine running and management.

Mode of access: Internet.

A treatise on the steam-engine in its various applications to mines, mills, steam navigation, railways, and agriculture with theoretical investigations respecting the motive power of heat and the proper proportions of steam-engines, elaborate tables of the right dimensions of every part and practical instructions for the manufacture and management of every species of engine in actual use,

Mode of access: Internet.

Establishing a framework for dynamic risk management in 'intelligent' aero-engine control

The behaviour of control functions in safety critical software systems is typically bounded to prevent the occurrence of known system level hazards. These bounds are typically derived through safety analyses and can be implemented through the use of necessary design features. However, the unpredictability of real world problems can result in changes in the operating context that may invalidate the behavioural bounds themselves, for example, unexpected hazardous operating contexts as a result of failures or degradation. For highly complex problems it may be infeasible to determine the precise desired behavioural bounds of a function that addresses or minimises risk for hazardous operation cases prior to deployment. This paper presents an overview of the safety challenges associated with such a problem and how such problems might be addressed. A self-management framework is proposed that performs on-line risk management. The features of the framework are shown in context of employing intelligent adaptive controllers operating within complex and highly dynamic problem domains such as Gas-Turbine Aero Engine control. Safety assurance arguments enabled by the framework necessary for certification are also outlined.

An improved memory management scheme for large scale graph computing engine GraphChi

GraphChi is the first reported disk-based graph engine that can handle billion-scale graphs on a single PC efficiently. GraphChi is able to execute several advanced data mining, graph mining and machine learning algorithms on very large graphs. With the novel technique of parallel sliding windows (PSW) to load subgraph from disk to memory for vertices and edges updating, it can achieve data processing performance close to and even better than those of mainstream distributed graph engines. GraphChi mentioned that its memory is not effectively utilized with large dataset, which leads to suboptimal computation performances. In this paper we are motivated by the concepts of 'pin ' from TurboGraph and 'ghost' from GraphLab to propose a new memory utilization mode for GraphChi, which is called Part-in-memory mode, to improve the GraphChi algorithm performance. The main idea is to pin a fixed part of data inside the memory during the whole computing process. Part-in-memory mode is successfully implemented with only about 40 additional lines of code to the original GraphChi engine. Extensive experiments are performed with large real datasets (including Twitter graph with 1.4 billion edges). The preliminary results show that Part-in-memory mode memory management approach effectively reduces the GraphChi running time by up to 60% in PageRank algorithm. Interestingly it is found that a larger portion of data pinned in memory does not always lead to better performance in the case that the whole dataset cannot be fitted in memory. There exists an optimal portion of data which should be kept in the memory to achieve the best computational performance.

Quincy and Torch Lake Railroad engine house facility management and interpretive plan

The “Quincy & Torch Lake Railroad Engine House Facility Management and Interpretive Plan" was designed to serve as a guide to aid the Quincy Mine Hoist Association in their efforts to restore and interpret historic railroad resources under their stewardship. Early searches for existing management and interpretive plans demonstrated that similar plans were primarily produced by the National Park Service and were intended to guide large scale heritage sites that consist of a variety of cultural resources. This project adapts concepts found in those large scale management and interpretive site plans, to guide small scale site management, restoration, and interpretive projects. The document presents a three stage, second phase restoration process. Each stage of development is guided by a series of management and interpretive goals and objectives which were set for the engine house facility.

Distributed Energy Resources Management using Plug-in Hybrid Electric Vehicles as a Fuel-Shifting Demand Response Resource

In the smart grids context, distributed energy resources management plays an important role in the power systems’ operation. Battery electric vehicles and plug-in hybrid electric vehicles should be important resources in the future distribution networks operation. Therefore, it is important to develop adequate methodologies to schedule the electric vehicles’ charge and discharge processes, avoiding network congestions and providing ancillary services. This paper proposes the participation of plug-in hybrid electric vehicles in fuel shifting demand response programs. Two services are proposed, namely the fuel shifting and the fuel discharging. The fuel shifting program consists in replacing the electric energy by fossil fuels in plug-in hybrid electric vehicles daily trips, and the fuel discharge program consists in use of their internal combustion engine to generate electricity injecting into the network. These programs are included in an energy resources management algorithm which integrates the management of other resources. The paper presents a case study considering a 37-bus distribution network with 25 distributed generators, 1908 consumers, and 2430 plug-in vehicles. Two scenarios are tested, namely a scenario with high photovoltaic generation, and a scenario without photovoltaic generation. A sensitivity analyses is performed in order to evaluate when each energy resource is required.