Self-Organizing Map Neural Architectures Based on Limit Cycle Attractors

Recent efforts to develop large-scale neural architectures have paid relatively little attention to the use of self-organizing maps (SOMs). Part of the reason is that most conventional SOMs use a static encoding representation: Each input is typically represented by the fixed activation of a single node in the map layer. This not only carries information in an inefficient and unreliable way that impedes building robust multi-SOM neural architectures, but it is also inconsistent with rhythmic oscillations in biological neural networks. Here I develop and study an alternative encoding scheme that instead uses limit cycle attractors of multi-focal activity patterns to represent input patterns/sequences. Such a fundamental change in representation raises several questions: Can this be done effectively and reliably? If so, will map formation still occur? What properties would limit cycle SOMs exhibit? Could multiple such SOMs interact effectively? Could robust architectures based on such SOMs be built for practical applications? The principal results of examining these questions are as follows. First, conditions are established for limit cycle attractors to emerge in a SOM through self-organization when encoding both static and temporal sequence inputs. It is found that under appropriate conditions a set of learned limit cycles are stable, unique, and preserve input relationships. In spite of the continually changing activity in a limit cycle SOM, map formation continues to occur reliably. Next, associations between limit cycles in different SOMs are learned. It is shown that limit cycles in one SOM can be successfully retrieved by another SOM’s limit cycle activity. Control timings can be set quite arbitrarily during both training and activation. Importantly, the learned associations generalize to new inputs that have never been seen during training. Finally, a complete neural architecture based on multiple limit cycle SOMs is presented for robotic arm control. This architecture combines open-loop and closed-loop methods to achieve high accuracy and fast movements through smooth trajectories. The architecture is robust in that disrupting or damaging the system in a variety of ways does not completely destroy the system. I conclude that limit cycle SOMs have great potentials for use in constructing robust neural architectures.

Microfabricated elastomer tactile sensors for robotic fingertip systems

Tactile sensing is an important aspect of robotic systems, and enables safe, dexterous robot-environment interaction. The design and implementation of tactile sensors on robots has been a topic of research over the past 30 years, and current challenges include mechanically flexible “sensing skins”, high dynamic range (DR) sensing (i.e.: high force range and fine force resolution), multi-axis sensing, and integration between the sensors and robot. This dissertation focuses on addressing some of these challenges through a novel manufacturing process that incorporates conductive and dielectric elastomers in a reusable, multilength-scale mold, and new sensor designs for multi-axis sensing that improve force range without sacrificing resolution. A single taxel was integrated into a 1 degree of freedom robotic gripper for closed-loop slip detection. Manufacturing involved casting a composite silicone rubber, polydimethylsiloxane (PDMS) filled with conductive particles such as carbon nanotubes, into a mold to produce microscale flexible features on the order of 10s of microns. Molds were produced via microfabrication of silicon wafers, but were limited in sensing area and were costly. An improved technique was developed that produced molds of acrylic using a computer numerical controlled (CNC) milling machine. This maintained the ability to produce microscale features, and increased the sensing area while reducing costs. New sensing skins had features as small as 20 microns over an area as large as a human hand. Sensor architectures capable of sensing both shear and normal force sensing with high dynamic range were produced. Using this architecture, two sensing modalities were developed: a capacitive approach and a contact resistive approach. The capacitive approach demonstrated better dynamic range, while the contact resistive approach used simpler circuitry. Using the contact resistive approach, normal force range and resolution were 8,000 mN and 1,000 mN, respectively, and shear force range and resolution were 450 mN and 100 mN, respectively. Using the capacitive approach, normal force range and resolution were 10,000 mN and 100 mN, respectively, and shear force range and resolution were 1,500 mN and 50 mN, respectively.

Effects of Drive Speed Modulation on Dynamics of Slender Rotating Structures

Slender rotating structures are used in many mechanical systems. These structures can suffer from undesired vibrations that can affect the components and safety of a system. Furthermore, since some these structures can operate in a harsh environment, installation and operation of sensors that are needed for closed-loop and collocated control schemes may not be feasible. Hence, the need for an open-loop non-collocated scheme for control of the dynamics of these structures. In this work, the effects of drive speed modulation on the dynamics of slender rotating structures are studied. Slender rotating structures are a type of mechanical rotating structures, whose length to diameter ratio is large. For these structures, the torsion mode natural frequencies can be low. In particular, for isotropic structures, the first few torsion mode frequencies can be of the same order as the first few bending mode frequencies. These situations can be conducive for energy transfer amongst bending and torsion modes. Scenarios with torsional vibrations experienced by rotating structures with continuous rotor-stator contact occur in many rotating mechanical systems. Drill strings used in the oil and gas industry are an example of rotating structures whose torsional vibrations can be deleterious to the components of the drilling system. As a novel approach to mitigate undesired vibrations, the effects of adding a sinusoidal excitation to the rotation speed of a drill string are studied. A portion of the drill string located within a borewell is considered and this rotating structure has been modeled as an extended Jeffcott rotor and a sinusoidal excitation has been added to the drive speed of the rotor. After constructing a three-degree-of-freedom model to capture lateral and torsional motions, the equations of motions are reduced to a single differential equation governing torsional vibrations during continuous stator contact. An approximate solution has been obtained by making use of the Method of Direct Partition of Motions with the governing torsional equation of motion. The results showed that for a rotor undergoing forward or backward whirling, the addition of sinusoidal excitation to the drive speed can cause an increase in the equivalent torsional stiffness, smooth the discontinuous friction force at contact, and reduce the regions of negative slope in the friction coefficient variation with respect to speed. Experiments with a scaled drill string apparatus have also been conducted and the experimental results show good agreement with the numerical results obtained from the developed models. These findings suggest that the extended Jeffcott rotordynamics model can be useful for studies of rotor dynamics in situations with continuous rotor-stator contact. Furthermore, the results obtained suggest that the drive speed modulation scheme can have value for attenuating drill-string vibrations.

Holistic Design In High-Speed Optical Interconnects

Integrated circuit scaling has enabled a huge growth in processing capability, which necessitates a corresponding increase in inter-chip communication bandwidth. As bandwidth requirements for chip-to-chip interconnection scale, deficiencies of electrical channels become more apparent. Optical links present a viable alternative due to their low frequency-dependent loss and higher bandwidth density in the form of wavelength division multiplexing. As integrated photonics and bonding technologies are maturing, commercialization of hybrid-integrated optical links are becoming a reality. Increasing silicon integration leads to better performance in optical links but necessitates a corresponding co-design strategy in both electronics and photonics. In this light, holistic design of high-speed optical links with an in-depth understanding of photonics and state-of-the-art electronics brings their performance to unprecedented levels. This thesis presents developments in high-speed optical links by co-designing and co-integrating the primary elements of an optical link: receiver, transmitter, and clocking.

In the first part of this thesis a 3D-integrated CMOS/Silicon-photonic receiver will be presented. The electronic chip features a novel design that employs a low-bandwidth TIA front-end, double-sampling and equalization through dynamic offset modulation. Measured results show -14.9dBm of sensitivity and energy efficiency of 170fJ/b at 25Gb/s. The same receiver front-end is also used to implement source-synchronous 4-channel WDM-based parallel optical receiver. Quadrature ILO-based clocking is employed for synchronization and a novel frequency-tracking method that exploits the dynamics of IL in a quadrature ring oscillator to increase the effective locking range. An adaptive body-biasing circuit is designed to maintain the per-bit-energy consumption constant across wide data-rates. The prototype measurements indicate a record-low power consumption of 153fJ/b at 32Gb/s. The receiver sensitivity is measured to be -8.8dBm at 32Gb/s.

Next, on the optical transmitter side, three new techniques will be presented. First one is a differential ring modulator that breaks the optical bandwidth/quality factor trade-off known to limit the speed of high-Q ring modulators. This structure maintains a constant energy in the ring to avoid pattern-dependent power droop. As a first proof of concept, a prototype has been fabricated and measured up to 10Gb/s. The second technique is thermal stabilization of micro-ring resonator modulators through direct measurement of temperature using a monolithic PTAT temperature sensor. The measured temperature is used in a feedback loop to adjust the thermal tuner of the ring. A prototype is fabricated and a closed-loop feedback system is demonstrated to operate at 20Gb/s in the presence of temperature fluctuations. The third technique is a switched-capacitor based pre-emphasis technique designed to extend the inherently low bandwidth of carrier injection micro-ring modulators. A measured prototype of the optical transmitter achieves energy efficiency of 342fJ/bit at 10Gb/s and the wavelength stabilization circuit based on the monolithic PTAT sensor consumes 0.29mW.

Lastly, a first-order frequency synthesizer that is suitable for high-speed on-chip clock generation will be discussed. The proposed design features an architecture combining an LC quadrature VCO, two sample-and-holds, a PI, digital coarse-tuning, and rotational frequency detection for fine-tuning. In addition to an electrical reference clock, as an extra feature, the prototype chip is capable of receiving a low jitter optical reference clock generated by a high-repetition-rate mode-locked laser. The output clock at 8GHz has an integrated RMS jitter of 490fs, peak-to-peak periodic jitter of 2.06ps, and total RMS jitter of 680fs. The reference spurs are measured to be –64.3dB below the carrier frequency. At 8GHz the system consumes 2.49mW from a 1V supply.

MILITARY VEHICLE OPTIMIZATION AND CONTROL

It is remarkable that there are no deployed military hybrid vehicles since battlefield fuel is approximately 100 times the cost of civilian fuel. In the commercial marketplace, where fuel prices are much lower, electric hybrid vehicles have become increasingly common due to their increased fuel efficiency and the associated operating cost benefit. An absence of military hybrid vehicles is not due to a lack of investment in research and development, but rather because applying hybrid vehicle architectures to a military application has unique challenges. These challenges include inconsistent duty cycles for propulsion requirements and the absence of methods to look at vehicle energy in a holistic sense. This dissertation provides a remedy to these challenges by presenting a method to quantify the benefits of a military hybrid vehicle by regarding that vehicle as a microgrid. This innovative concept allowed for the creation of an expandable multiple input numerical optimization method that was implemented for both real-time control and system design optimization. An example of each of these implementations was presented. Optimization in the loop using this new method was compared to a traditional closed loop control system and proved to be more fuel efficient. System design optimization using this method successfully illustrated battery size optimization by iterating through various electric duty cycles. By utilizing this new multiple input numerical optimization method, a holistic view of duty cycle synthesis, vehicle energy use, and vehicle design optimization can be achieved.

MODELING OF TRANSFER PATH FOR DETERMINATION OF COMBUSTION AND NOISE METRICS ON DIESEL ENGINES

Determination of combustion metrics for a diesel engine has the potential of providing feedback for closed-loop combustion phasing control to meet current and upcoming emission and fuel consumption regulations. This thesis focused on the estimation of combustion metrics including start of combustion (SOC), crank angle location of 50% cumulative heat release (CA50), peak pressure crank angle location (PPCL), and peak pressure amplitude (PPA), peak apparent heat release rate crank angle location (PACL), mean absolute pressure error (MAPE), and peak apparent heat release rate amplitude (PAA). In-cylinder pressure has been used in the laboratory as the primary mechanism for characterization of combustion rates and more recently in-cylinder pressure has been used in series production vehicles for feedback control. However, the intrusive measurement with the in-cylinder pressure sensor is expensive and requires special mounting process and engine structure modification. As an alternative method, this work investigated block mounted accelerometers to estimate combustion metrics in a 9L I6 diesel engine. So the transfer path between the accelerometer signal and the in-cylinder pressure signal needs to be modeled. Depending on the transfer path, the in-cylinder pressure signal and the combustion metrics can be accurately estimated - recovered from accelerometer signals. The method and applicability for determining the transfer path is critical in utilizing an accelerometer(s) for feedback. Single-input single-output (SISO) frequency response function (FRF) is the most common transfer path model; however, it is shown here to have low robustness for varying engine operating conditions. This thesis examines mechanisms to improve the robustness of FRF for combustion metrics estimation. First, an adaptation process based on the particle swarm optimization algorithm was developed and added to the single-input single-output model. Second, a multiple-input single-output (MISO) FRF model coupled with principal component analysis and an offset compensation process was investigated and applied. Improvement of the FRF robustness was achieved based on these two approaches. Furthermore a neural network as a nonlinear model of the transfer path between the accelerometer signal and the apparent heat release rate was also investigated. Transfer path between the acoustical emissions and the in-cylinder pressure signal was also investigated in this dissertation on a high pressure common rail (HPCR) 1.9L TDI diesel engine. The acoustical emissions are an important factor in the powertrain development process. In this part of the research a transfer path was developed between the two and then used to predict the engine noise level with the measured in-cylinder pressure as the input. Three methods for transfer path modeling were applied and the method based on the cepstral smoothing technique led to the most accurate results with averaged estimation errors of 2 dBA and a root mean square error of 1.5dBA. Finally, a linear model for engine noise level estimation was proposed with the in-cylinder pressure signal and the engine speed as components.

REALIZATION OF A DC MICROGRID USING A HAMILTONIAN BASED CONTROLS SOLUTION

Future power grids are envisioned to be serviced by heterogeneous arrangements of renewable energy sources. Due to their stochastic nature, energy storage distribution and management are pivotal in realizing microgrids serviced heavily by renewable energy assets. Identifying the required response characteristics to meet the operational requirements of a power grid are of great importance and must be illuminated in order to discern optimal hardware topologies. Hamiltonian Surface Shaping and Power Flow Control (HSSPFC) presents the tools to identify such characteristics. By using energy storage as actuation within the closed loop controller, the response requirements may be identified while providing a decoupled controller solution. A DC microgrid servicing a fixed RC load through source and bus level storage managed by HSSPFC was realized in hardware. A procedure was developed to calibrate the DC microgrid architecture of this work to the reduced order model used by the HSSPFC law. Storage requirements were examined through simulation and experimental testing. Bandwidth contributions between feed forward and PI components of the HSSPFC law are illuminated and suggest the need for well-known system losses to prevent the need for additional overhead in storage allocations. The following work outlines the steps taken in realizing a DC microgrid and presents design considerations for system calibration and storage requirements per the closed loop controls for future DC microgrids.

Analisi multi-obiettivo in ottica lean-green della reverse logistics dei veicoli a fine vita (ELV)

La gestione del fine vita dei prodotti è un argomento di interesse attuale per le aziende; sempre più spesso l’imprese non possono più esimersi dall’implementare un efficiente sistema di Reverse Logistics. Per rispondere efficacemente a queste nuove esigenze diventa fondamentale ampliare i tradizionali sistemi logistici verso tutte quelle attività svolte all’interno della Reverse Logitics. Una gestione efficace ed efficiente dell’intera supply chain è un aspetto di primaria importanza per un’azienda ed incide notevolmente sulla sua competitività; proprio per perseguire questo obiettivo, sempre più aziende promuovono politiche di gestione delle supply chain sia Lean che Green. L’obiettivo di questo lavoro, nato dalle esigenze descritte sopra, è quello di applicare un modello innovativo che consideri sia politiche di gestione Lean, che dualmente politiche Green, alla gestione di una supply chain del settore automotive, comprendente anche le attività di gestione dei veicoli fuori uso (ELV). Si è analizzato per prima cosa i principi base e gli strumenti utilizzati per l’applicazione della Lean Production e del Green supply chain management e in seguito si è analizzato le caratteristiche distintive della Reverse Logistics e in particolare delle reti che trattano i veicoli a fine vita. L’obiettivo finale dello studio è quello di elaborare e implementare, tramite l’utilizzo del software AMPL, un modello di ottimizzazione multi-obiettivo (MOP- Multi Objective Optimization) Lean e Green a una Reverse Supply Chain dei veicoli a fine vita. I risultati ottenuti evidenziano che è possibile raggiungere un ottimo compromesso tra le due logiche. E' stata effettuata anche una valutazione economica dei risultati ottenuti, che ha evidenziato come il trade-off scelto rappresenti anche uno degli scenari con minor costi.

Robotic Sensing and Manipulation of Deformable Linear Objects with Learning-based methods

Nowadays robotic applications are widespread and most of the manipulation tasks are efficiently solved. However, Deformable-Objects (DOs) still represent a huge limitation for robots. The main difficulty in DOs manipulation is dealing with the shape and dynamics uncertainties, which prevents the use of model-based approaches (since they are excessively computationally complex) and makes sensory data difficult to interpret. This thesis reports the research activities aimed to address some applications in robotic manipulation and sensing of Deformable-Linear-Objects (DLOs), with particular focus to electric wires. In all the works, a significant effort was made in the study of an effective strategy for analyzing sensory signals with various machine learning algorithms. In the former part of the document, the main focus concerns the wire terminals, i.e. detection, grasping, and insertion. First, a pipeline that integrates vision and tactile sensing is developed, then further improvements are proposed for each module. A novel procedure is proposed to gather and label massive amounts of training images for object detection with minimal human intervention. Together with this strategy, we extend a generic object detector based on Convolutional-Neural-Networks for orientation prediction. The insertion task is also extended by developing a closed-loop control capable to guide the insertion of a longer and curved segment of wire through a hole, where the contact forces are estimated by means of a Recurrent-Neural-Network. In the latter part of the thesis, the interest shifts to the DLO shape. Robotic reshaping of a DLO is addressed by means of a sequence of pick-and-place primitives, while a decision making process driven by visual data learns the optimal grasping locations exploiting Deep Q-learning and finds the best releasing point. The success of the solution leverages on a reliable interpretation of the DLO shape. For this reason, further developments are made on the visual segmentation.

Distributed non-cooperative robust economic predictive control for dynamically coupled linear systems.

In this thesis, a tube-based Distributed Economic Predictive Control (DEPC) scheme is presented for a group of dynamically coupled linear subsystems. These subsystems are components of a large scale system and control inputs are computed based on optimizing a local economic objective. Each subsystem is interacting with its neighbors by sending its future reference trajectory, at each sampling time. It solves a local optimization problem in parallel, based on the received future reference trajectories of the other subsystems. To ensure recursive feasibility and a performance bound, each subsystem is constrained to not deviate too much from its communicated reference trajectory. This difference between the plan trajectory and the communicated one is interpreted as a disturbance on the local level. Then, to ensure the satisfaction of both state and input constraints, they are tightened by considering explicitly the effect of these local disturbances. The proposed approach averages over all possible disturbances, handles tightened state and input constraints, while satisfies the compatibility constraints to guarantee that the actual trajectory lies within a certain bound in the neighborhood of the reference one. Each subsystem is optimizing a local arbitrary economic objective function in parallel while considering a local terminal constraint to guarantee recursive feasibility. In this framework, economic performance guarantees for a tube-based distributed predictive control (DPC) scheme are developed rigorously. It is presented that the closed-loop nominal subsystem has a robust average performance bound locally which is no worse than that of a local robust steady state. Since a robust algorithm is applying on the states of the real (with disturbances) subsystems, this bound can be interpreted as an average performance result for the real closed-loop system. To this end, we present our outcomes on local and global performance, illustrated by a numerical example.

Laser cladding and its potential to reduce particulate matter emissions from the automotive and locomotive sector

Laser Cladding (LC) is an emerging technology which is used both for coating applications as well as near-net shape fabrication. Despite its significant advantages, such as low dilution and metallurgical bond with the substrate, it still faces issues such as process control and repeatability, which restricts the extension to its applications. The following thesis evaluates the LC technology and tests its potential to be applied to reduce particulate matter emissions from the automotive and locomotive sector. The evaluation of LC technology was carried out for the deposition of multi-layer and multi-track coatings. 316L stainless steel coatings were deposited to study the minimisation of geometric distortions in thin-walled samples. Laser power, as well as scan strategy, were the main variables to achieve this goal. The use of constant power, reduction at successive layers, a control loop control system, and two different scan strategies were studied. The closed-loop control system was found to be practical only when coupled with the correct scan strategy for the deposition of thin walls. Three overlapped layers of aluminium bronze were deposited onto a structural steel pipe for multitrack coatings. The effect of laser power, scan speed and hatch distance on the final geometry of coating were studied independently, and a combined parameter was established to effectively control each geometrical characteristic (clad width, clad height and percentage of dilution). LC was then applied to coat commercial GCI brake discs with tool steel. The optical micrography showed that even with preheating, the cracks that originated from the substrate towards the coating were still present. The commercial brake discs emitted airborne particles whose concentration and size depended on the test conditions used for simulation in the laboratory. The contact of LC cladded wheel with rail emitted significantly less ultra-fine particles while maintaining the acceptable values of coefficient of friction.

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.

Fuzzy linguistic controllers applied to decouple control loop effects

A fuzzy linguistic controller has been developed and implemented with the aim to cope with interactions between control loops due to coupling effects. To access the performance of the proposed approach several experiments have also been conducted using the classical PID controllers in the control loops. A mixing process has been used as test bed of all controllers experimented and the corresponding dynamic model has been derived. The successful results achieved with the fuzzy linguistic controllers suggests that they can be an alternative to classical controllers when in the presence of process plants where automatic control as to cope with coupling effects between control loops. © 2014 IEEE.

The closed-string 3-loop amplitude and S-duality

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

The surface accessibility of the glycine receptor M2-M3 loop is increased in the channel open state

Mutations in the extracellular M2-M3 loop of the glycine receptor (GlyR) alpha1 subunit have been shown previously to affect channel gating. In this study, the substituted cysteine accessibility method was used to investigate whether a structural rearrangement of the M2-M3 loop accompanies GlyR activation. All residues from R271C to V277C were covalently modified by both positively charged methanethiosulfonate ethyltrimethylammonium (MTSET) and negatively charged methanethiosulfonate ethylsulfonate (MTSES), implying that these residues form an irregular surface loop. The MTSET modification rate of all residues from R271C to K276C was faster in the glycine-bound state than in the unliganded state. MTSES modification of A272C, L274C, and V277C was also faster in the glycine-bound state. These results demonstrate that the surface accessibility of the M2-M3 loop is increased as the channel transitions from the closed to the open state, implying that either the loop itself or an overlying domain moves during channel activation.