Design of a fault-tolerant decision-making system for biomedical applications

This paper describes the design of a fault-tolerant classification system for medical applications. The design process follows the systems engineering methodology: in the agreement phase, we make the case for fault tolerance in diagnosis systems for biomedical applications. The argument extends the idea that machine diagnosis systems mimic the functionality of human decision-making, but in many cases they do not achieve the fault tolerance of the human brain. After making the case for fault tolerance, both requirements and specification for the fault-tolerant system are introduced before the implementation is discussed. The system is tested with fault and use cases to build up trust in the implemented system. This structured approach aided in the realisation of the fault-tolerant classification system. During the specification phase, we produced a formal model that enabled us to discuss what fault tolerance, reliability and safety mean for this particular classification system. Furthermore, such a formal basis for discussion is extremely useful during the initial stages of the design, because it helps to avoid big mistakes caused by a lack of overview later on in the project. During the implementation, we practiced component reuse by incorporating a reliable classification block, which was developed during a previous project, into the current design. Using a well-structured approach and practicing component reuse we follow best practice for both research and industry projects, which enabled us to realise the fault-tolerant classification system on time and within budget. This system can serve in a wide range of future health care systems.     

A diagnostic expert system

The introduction of new technologies in the field of electronics has influenced the development of technical equipment over the last few years. The progressive miniaturization of integrated circuits makes possible an expansion of the spectrum of functions offered by this equipment. This also applies to medical technology. These more complex units call for new methods of fault detection and diagnosis. In addition to analytical redundancy, tools developed by the artificial intelligence research community, such as expert systems, are becoming more and more important for fault diagnosis. On the basis of a realized diagnosis expert system the possibilities as well as the limits of such system are discussed. Also, possible future developments of artificial intelligence, like machine learning, are considered.     

Reconfigurable control system design for fault diagnosis and accommodation

The growing demand in system reliability and survivability under failures has urged ever-increasing research effort on the development of fault diagnosis and accommodation. In this paper, the on-line fault tolerant control problem for dynamic systems under unanticipated failures is investigated from a realistic point of view without any specific assumption on the type of system dynamical structure or failure scenarios. The sufficient conditions for system on-line stability under catastrophic failures have been derived using the discrete-time Lyapunov stability theory. Based upon the existing control theory and the modern computational intelligence techniques, an on-line fault accommodation control strategy is proposed to deal with the desired trajectory-tracking problems for systems suffering from various unknown and unanticipated catastrophic component failures. Theoretical analysis indicates that the control problem of interest can be solved on-line without a complete realization of the unknown failure dynamics provided an on-line estimator satisfies certain conditions. Through the on-line estimator, effective control signals to accommodate the dynamic failures can be computed using only the partially available information of the faults. Several on-line simulation studies have been presented to demonstrate the effectiveness of the proposed strategy. To investigate the feasibility of using the developed technique for unanticipated fault accommodation in hardware under the real-time environment, an on-line fault tolerant control test bed has been constructed to validate the proposed technology. Both on-line simulations and the real-time experiment show encouraging results and promising futures of on-line real-time fault tolerant control based solely upon insufficient information of the system dynamics and the failure dynamics.     

Adaptive control for mimo uncertain nonlinear systems using recurrent wavelet neural network

Recurrent wavelet neural network (RWNN) has the advantages such as fast learning property, good generalization capability and information storing ability. With these advantages, this paper proposes an RWNN-based adaptive control (RBAC) system for multi-input multi-output (MIMO) uncertain nonlinear systems. The RBAC system is composed of a neural controller and a bounding compensator. The neural controller uses an RWNN to online mimic an ideal controller, and the bounding compensator can provide smooth and chattering-free stability compensation. From the Lyapunov stability analysis, it is shown that all signals in the closed-loop RBAC system are uniformly ultimately bounded. Finally, the proposed RBAC system is applied to the MIMO uncertain nonlinear systems such as a mass-spring-damper mechanical system and a two-link robotic manipulator system. Simulation results verify that the proposed RBAC system can achieve favorable tracking performance with desired robustness without any chattering phenomenon in the control effort.     

Motion control of musculoskeletal systems with redundancy

Motion control of musculoskeletal systems for functional electrical stimulation (FES) is a challenging problem due to the inherent complexity of the systems. These include being highly nonlinear, strongly coupled, time-varying, time-delayed, and redundant. The redundancy in particular makes it difficult to find an inverse model of the system for control purposes. We have developed a control system for multiple input multiple output (MIMO) redundant musculoskeletal systems with little prior information. The proposed method separates the steady-state properties from the dynamic properties. The dynamic control uses a steady-state inverse model and is implemented with both a PID controller for disturbance rejection and an artificial neural network (ANN) feedforward controller for fast trajectory tracking. A mechanism to control the sum of the muscle excitation levels is also included. To test the performance of the proposed control system, a two degree of freedom ankle–subtalar joint model with eight muscles was used. The simulation results show that separation of steady-state and dynamic control allow small output tracking errors for different reference trajectories such as pseudo-step, sinusoidal and filtered random signals. The proposed control method also demonstrated robustness against system parameter and controller parameter variations. A possible application of this control algorithm is FES control using multiple contact cuff electrodes where mathematical modeling is not feasible and the redundancy makes the control of dynamic movement difficult.     

Advances in functional electrical stimulation (FES)

This review discusses the advancements that are needed to enhance the effects of electrical stimulation for restoring or assisting movement in humans with an injury/disease of the central nervous system. A complex model of the effects of electrical stimulation of peripheral systems is presented. The model indicates that both the motor and sensory systems are activated by electrical stimulation. We propose that a hierarchical hybrid controller may be suitable for functional electrical stimulation (FES) because this type of controller acts as a structural mimetic of its biological counterpart. Specific attention is given to the neural systems at the periphery with respect to the required electrodes and stimulators. Furthermore, we note that FES with surface electrodes is preferred for the therapy, although there is a definite advantage associated with implantable technology for life-long use. The last section of the review discusses the potential need to combine FES and robotic systems to provide assistance in some cases.     

A Fault Diagnosis Methodology for Gear Pump Based on EEMD and Bayesian Network

This paper proposes a fault diagnosis methodology for a gear pump based on the ensemble empirical mode decomposition (EEMD) method and the Bayesian network. Essentially, the presented scheme is a multi-source information fusion based methodology. Compared with the conventional fault diagnosis with only EEMD, the proposed method is able to take advantage of all useful information besides sensor signals. The presented diagnostic Bayesian network consists of a fault layer, a fault feature layer and a multi-source information layer. Vibration signals from sensor measurement are decomposed by the EEMD method and the energy of intrinsic mode functions (IMFs) are calculated as fault features. These features are added into the fault feature layer in the Bayesian network. The other sources of useful information are added to the information layer. The generalized three-layer Bayesian network can be developed by fully incorporating faults and fault symptoms as well as other useful information such as naked eye inspection and maintenance records. Therefore, diagnostic accuracy and capacity can be improved. The proposed methodology is applied to the fault diagnosis of a gear pump and the structure and parameters of the Bayesian network is established. Compared with artificial neural network and support vector machine classification algorithms, the proposed model has the best diagnostic performance when sensor data is used only. A case study has demonstrated that some information from human observation or system repair records is very helpful to the fault diagnosis. It is effective and efficient in diagnosing faults based on uncertain, incomplete information.     

Control of functional electrical stimulation with extended physiological proprioception

The use of functional electrical stimulation (FES) of muscle for paraplegic locomotion, or grasp augmentation in tetraplegia, is limited by the variability in muscle response to stimulation as a result of several external and internal factors. Previous approaches to this problem have used position-servo controllers, which have been shown to function satisfactorily in the laboratory. However, such systems will fail should obstacles be encountered or should the stimulation hardware develop a fault. To prevent such potentially dangerous failures some form of sensory feedback is required. This paper describes the first application of a technique known as extended physiological proprioception (EPP) to the control of FES to compensate for muscle response variability and provide proprioceptive feedback via the appropriate sensory pathways. In the experimental system described, a paraplegic subject controlled the extension of his paralysed knee by shoulder protraction. A Bowden cable linked the two joints, and a dynamometer in this cable was used to derive the control signal for a computer-controlled stimulator which delivered surface stimulation to the quadriceps muscle group. Modelling and parameter identification were performed by analysis of the step response, and the controller was designed from consideration of the root locus. The advantages of the system, in terms of improved proprioceptive feedback and reduced limb-positioning error were assessed in a test of joint positioning accuracy with vision occluded. The EPP system showed improvements over both open and closed-loop position-servo controllers.     

Multiple-Objective Scheduling for the Hierarchical Control of Flexible Manufacturing Systems

This paper presents a hierarchical approach to scheduling flexible manufacturing systems (FMSs) that pursues multiple performance objectives and considers the process flexibility of incorporating alternative process plans and resources for the required operations. The scheduling problem is solved at two levels: the shop level and the manufacturing system level. The shop level controller employs a combined priority index developed in this research to rank shop production orders in meeting multiple scheduling objectives. To overcome dimensional complexity and keep a low level of work-in-process inventory, the shop controller first selects up to three production orders with the highest ranking as candidates and generates all possible release sequences for them, with or without multitasking. These sequences are conveyed to the manufacturing system controller, who then performs detailed scheduling of the machines in the FMS using a fixed priority heuristic for routing parts of multiple types while considering alternative process plans and resources for the operations. The FMS controller provides feedback to the shop controller with a set of suggested detailed schedules and projected order completion times. On receiving these results, the shop controller further evaluates each candidate schedule using a multiple-objective function and selects the best schedule for execution. This allows multiple performance objectives of an FMS to be achieved by the integrated hierarchical scheduling approach.     

Fault Diagnosis for the Heat Exchanger of the Aircraft Environmental Control System Based on the Strong Tracking Filter

The aircraft environmental control system (ECS) is a critical aircraft system, which provides the appropriate environmental conditions to ensure the safe transport of air passengers and equipment. The functionality and reliability of ECS have received increasing attention in recent years. The heat exchanger is a particularly significant component of the ECS, because its failure decreases the system’s efficiency, which can lead to catastrophic consequences. Fault diagnosis of the heat exchanger is necessary to prevent risks. However, two problems hinder the implementation of the heat exchanger fault diagnosis in practice. First, the actual measured parameter of the heat exchanger cannot effectively reflect the fault occurrence, whereas the heat exchanger faults are usually depicted by utilizing the corresponding fault-related state parameters that cannot be measured directly. Second, both the traditional Extended Kalman Filter (EKF) and the EKF-based Double Model Filter have certain disadvantages, such as sensitivity to modeling errors and difficulties in selection of initialization values. To solve the aforementioned problems, this paper presents a fault-related parameter adaptive estimation method based on strong tracking filter (STF) and Modified Bayes classification algorithm for fault detection and failure mode classification of the heat exchanger, respectively. Heat exchanger fault simulation is conducted to generate fault data, through which the proposed methods are validated. The results demonstrate that the proposed methods are capable of providing accurate, stable, and rapid fault diagnosis of the heat exchanger.     

Machine learning in quantitative histopathology

The role of expert systems functioning as process controllers in learning image understanding systems is discussed. Numeric learning systems already have found a number of applications in cytologic and histopathologic diagnosis. Depending on the required capabilities, systems of increasing complexity are needed. Expert systems to guide scene segmentation in histopathologic imagery require model-based reasoning. Diagnostic image interpretation with learning capability demands a full model of the human expert's competence, including a considerable variety of knowledge representation schemes and inference strategies, coordinated by a meta-process controller.     

Design of a neurofuzzy controller with simplified architecture

This work presents the design of a neurofuzzy controller with simplified architecture that minimizes the processing time used in several stages associated with systems and processes modelling. The basic procedures of fuzzification and defuzzification are very simplified, whereas the inference procedures are computed in a direct way. The simplified architecture has allowed a fast and easy configuration of the neurofuzzy controller, as consequence, the control rules that define the control actions are obtained automatically. To validate the proposed approach, this neurofuzzy system is used in an industrial application for fluid flow control.     

Evolving experience-dependent robust behaviour in embodied agents

In this work, based on behavioural and dynamical evidence, a study of simulated agents with the capacity to change feedback from their bodies to accomplish a one-legged walking task is proposed to understand the emergence of coupled dynamics for robust behaviour. Agents evolve with evolutionary-defined biases that modify incoming body signals (sensory offsets). Analyses on whether these agents show further dependence to their environmental coupled dynamics than others with no feedback control is described in this article. The ability to sustain behaviours is tested during lifetime experiments with mutational and sensory perturbations after evolution. Using dynamical systems analysis, this work identifies conditions for the emergence of dynamical mechanisms that remain functional despite sensory perturbations. Results indicate that evolved agents with evolvable sensory offset depends not only on where in neural space the state of the neural system operates, but also on the transients to which the inner-system was being driven by sensory signals from its interactions with the environment, controller, and agent body. Experimental evidence here leads discussions on a dynamical systems perspective on behavioural robustness that goes beyond attractors of controller phase space.     

Adaptive Controller for Dynamic Power and Performance Management in the Virtualized Computing Systems

Power and performance management problem in large scale computing systems like data centers has attracted a lot of interests from both enterprises and academic researchers as power saving has become more and more important in many fields. Because of the multiple objectives, multiple influential factors and hierarchical structure in the system, the problem is indeed complex and hard. In this paper, the problem will be investigated in a virtualized computing system. Specifically, it is formulated as a power optimization problem with some constraints on performance. Then, the adaptive controller based on least-square self-tuning regulator(LS-STR) is designed to track performance in the first step; and the resource solved by the controller is allocated in order to minimize the power consumption as the second step. Some simulations are designed to test the effectiveness of this method and to compare it with some other controllers. The simulation results show that the adaptive controller is generally effective: it is applicable for different performance metrics, for different workloads, and for single and multiple workloads; it can track the performance requirement effectively and save the power consumption significantly.     

Design of methanol Feed control in Pichia pastoris fermentations based upon a growth model

The methylotrophic yeast Pichia pastoris is an effective system for recombinant protein productions that utilizes methanol as an inducer, and also as carbon and energy source for a Mut(+) (methanol utilization plus) strain. Pichia fermentation is conducted in a fed-batch mode to obtain a high cell density for a high productivity. An accurate methanol control is required in the methanol fed-batch phase (induction phase) in the fermentation. A simple "on-off" control strategy is inadequate for precise control of methanol concentrations in the fermentor. In this paper we employed a PID (proportional, integral and derivative) control system for the methanol concentration control and designed the PID controller settings on the basis of a Pichia growth model. The closed-loop system was built with four components: PID controller, methanol feed pump, fermentation process, and methanol sensor. First, modeling and transfer functions for all components were derived, followed by frequency response analysis, a powerful method for calculating the optimal PID parameters K(c) (controller gain), tau(I) (controller integral time constant), and tau(D) (controller derivative time constant). Bode stability criteria were used to develop the stability diagram for evaluating the designed settings during the entire methanol fed-batch phase. Fermentations were conducted using four Pichia strains, each expressing a different protein, to verify the control performance with optimal PID settings. The results showed that the methanol concentration matched the set point very well with only small overshoot when the set point was switched, which indicated that a very good control performance was achieved. The method developed in this paper is robust and can serve as a framework for the design of other PID feedback control systems in biological processes.     

Advanced Fault Diagnosis Methods in Molecular Networks

Analysis of the failure of cell signaling networks is an important topic in systems biology and has applications in target discovery and drug development. In this paper, some advanced methods for fault diagnosis in signaling networks are developed and then applied to a caspase network and an SHP2 network. The goal is to understand how, and to what extent, the dysfunction of molecules in a network contributes to the failure of the entire network. Network dysfunction (failure) is defined as failure to produce the expected outputs in response to the input signals. Vulnerability level of a molecule is defined as the probability of the network failure, when the molecule is dysfunctional. In this study, a method to calculate the vulnerability level of single molecules for different combinations of input signals is developed. Furthermore, a more complex yet biologically meaningful method for calculating the multi-fault vulnerability levels is suggested, in which two or more molecules are simultaneously dysfunctional. Finally, a method is developed for fault diagnosis of networks based on a ternary logic model, which considers three activity levels for a molecule instead of the previously published binary logic model, and provides equations for the vulnerabilities of molecules in a ternary framework. Multi-fault analysis shows that the pairs of molecules with high vulnerability typically include a highly vulnerable molecule identified by the single fault analysis. The ternary fault analysis for the caspase network shows that predictions obtained using the more complex ternary model are about the same as the predictions of the simpler binary approach. This study suggests that by increasing the number of activity levels the complexity of the model grows; however, the predictive power of the ternary model does not appear to be increased proportionally.     

Implementing multilevel dynamic scheduling for a highly flexible 5-rail high throughput screening system

As automation solves the bottleneck involved in drug screening, new bottlenecks present themselves. Some of these bottlenecks include sample management, hit picking and confirmation, and reagents lost as a result of incomplete runs. To keep up with the demands of a large HTS department, scientists spend a disproportionate amount of time simply feeding these systems with samples and reagents. Automating the sample management functions directly on the screening systems would solve this problem. With the use of online data analysis, an integrated sample store permits automated hit picking and confirmation. In addition to these issues, other bottlenecks are often caused by instrument malfunctions. A single lost run can now mean a loss of hundreds of plates and the reagents associated with their testing. A system was designed to include four assaying systems that are fed by an automated online sample repository system. Redundancy between the assaying systems allows for an extra level of error handling in case of a malfunction. The control of such a system requires a sophisticated scheduler/controller software package capable of coordinating the interaction between multiple systems and reacting to changes in the robotic environment in realtime. This paper discusses the design of the system as well as the requirements and selection of an appropriate scheduler/controller package.     

Design and Implementation of a Flexible Manufacturing Control System Using Neural Network

Design and implementation of a sequential controller based on the concept of artificial neural networks for a flexible manufacturing system are presented. The recurrent neural network (RNN) type is used for such a purpose. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than depending on experience and trial and error techniques. The proposed controller is also more flexible because it is not limited by the restrictions of the finite state automata theory. Adequate guidelines of how to construct an RNN-based sequential controller are presented. These guidelines are applied to different case studies. The proposed controller is tested by simulations and real-time experiments. These tests prove the successfulness of the proposed controller performances. Theoretical as well as experimental results are presented and discussed indicating that the proposed design procedure using Elman's RNN can be effective in designing a sequential controller for event-based type manufacturing systems. In addition, the simulation results assure the effectiveness of the proposed controller to outperform the effect of noisy inputs.