L. Enrique Sucar

MICAI 2000: Advances in Artificial Intelligence

Unique Fixpoint Induction, UFI, is a chief inference rule to prove the equivalence of recursive processes in CCS [7]. It plays a major role in the equational approach to verification. This approach is of special interest as it offers theoretical advantages in the analysis of systems that communicate values, have infinite state space or show parameterised behaviour. The use of UFI, however, has been neglected, because automating theorem proving in this context is an extremely difficult task. The key problem with guiding the use of this rule is that we need to know fully the state space of the processes under consideration. Unfortunately, this is not always possible, because these processes may contain recursive symbols, parameters, and so on. We introduce a method to automate the use of UFI. The method uses middle-out reasoning and, so, is able to apply the rule even without elaborating the details of the application. The method introduces variables to represent those bits of the processes’ state space that, at application time, were not known, hence, changing from equation verification to equation solving. Adding this method to the equation plan developed by Monroy, Bundy and Green [8], we have implemented an automated verification planner. This planner increases the number of verification problems that can be dealt with fully automatically, thus improving upon the current degree of automation in the field.

A Probabilistic Model for Information and Sensor Validation

This paper develops a new theory and model for information and sensor validation. The model represents relationships between variables using Bayesian networks and utilizes probabilistic propagation to estimate the expected values of variables. If the estimated value of a variable differs from the actual value, an apparent fault is detected. The fault is only apparent since it may be that the estimated value is itself based on faulty data. The theory extends our understanding of when it is possible to isolate real faults from potential faults and supports the development of an algorithm that is capable of isolating real faults without deferring the problem to the use of expert provided domain-specific rules. To enable practical adoption for real-time processes, an any time version of the algorithm is developed, that, unlike most other algorithms, is capable of returning improving assessments of the validity of the sensors as it accumulates more evidence with time. The developed model is tested by applying it to the validation of temperature sensors during the start-up phase of a gas turbine when conditions are not stable; a problem that is known to be challenging. The paper concludes with a discussion of the practical applicability and scalability of the model.

Tool-Wear monitoring based on continuous hidden markov models

In this work we propose to monitor the cutting tool-wear condition in a CNC-machining center by using continuous Hidden Markov Models (HMM). A database was built with the vibration signals obtained during the machining process. The workpiece used in the milling process was aluminum 6061. Cutting tests were performed on a Huron milling machine equipped with a Sinumerik 840D open CNC. We trained/tested the HMM under 18 different operating conditions. We identified three key transitions in the signals. First, the cutting tool touches the workpiece. Second, a stable waveform is observed when the tool is in contact with the workpiece. Third, the tool finishes the milling process. Considering these transitions, we use a five-state HMM for modeling the process. The HMMs are created by preprocessing the waveforms, followed by training step using Baum-Welch algorithm. In the recognition process, the signal waveform is also preprocessed, then the trained HMM are used for decoding. Early experimental results validate our proposal in exploiting speech recognition frameworks in monitoring machining centers. The classifier was capable of detecting the cutting tool condition within large variations of spindle speed and feed rate, and accuracy of 84.19%.

SADEP—a fuzzy diagnostic system shell-an application to fossil power plant operation

Abstract Artificial Intelligence applications in large-scale industry, such as fossil fuel power plants, require the ability to manage uncertainty and time. In these domains, the knowledge about the process comes from experts experience and it is generally expressed in a vague-fuzzy way using ill-defined linguistic terms. In this paper, we present a fuzzy expert system shell to assist an operator of fossil power plants. The fuzzy expert system shell, called SADEP, is based.on a new methodology for dealing with uncertainty and time called Fuzzy Temporal Network (FTN). The FTN generates a formal and systematic structure used to model the temporal evolution of a process under uncertainty. The inference mechanism for a FIN consists in the calculation of the possibility degree of the real time occurrence of the events using the fuzzy compositional rule Sup-min. A FTN can be used to recognize the significance of events and state variables with respect to current plant conditions and predict the future propagation of disturbances. SADEP was validated with the diagnosis of two detailed disturbances of a fossil power plant: a power load increment in the drum level and a water condenser pump failure. The evaluations performed in this work indicate that SADEP can potentially improve plant availability through early diagnosis of disturbances that could lead to plant shutdown.

A semi-open learning environment for virtual laboratories

Open learning environments often involve simulation where learners can experiment with different aspects and parameters of a given phenomenon to observe the effects of these changes. These are desirable in virtual laboratories. However, an important limitation of open learning environments is the effectiveness for learning, because it strongly depends on the learner ability to explore adequately. We have developed a semi-open learning environment for a virtual robotics laboratory based on simulation, to learn through free exploration, but with specific performance criteria that guide the learning process. We proposed a generic architecture for this environment, in which the key element is an intelligent tutoring system coupled to a virtual laboratory. The tutor module combines the performance and exploration behaviour of a student in several experiments, to decide the best way to guide his/her. We present an evaluation with an initial group of 20 students. The results show how this semi-open leraning environment can help to accelerate and improve the learning process.

Project oriented learning for basic robotics using virtual laboratories and intelligent tutors

We have developed a course for teaching basic robotics, at the undergraduate level, with several new didactical and technical contributions, aimed at helping the students learn in a more effective way. The guiding thread for the course is based on the Project Oriented Learning didactic strategy which promotes interdisciplinary integration, capacity of analysis and synthesis, true teamwork, leadership, and knowledge sharing. The course integrates three developments. Firstly, we have developed a virtual laboratory based on a 3-D simulation, which lets students explore the first concepts in the course: mechanical design, sensors, and control, before they start building a physical robot. Secondly, an intelligent tutoring system guides the students during their interactions with the virtual lab. Finally, the students form teams to build a small mobile robot for a competition. We present the results from several years of teaching this course, as well as an evaluation of how the virtual laboratory and the tutor can help accelerate and improve the learning process

A Probabilistic Relational Student Model for Virtual Laboratories

We have developed a novel student model based on probabilistic relational models (PRMs). This model combines the advantages of Bayesian networks and object-oriented systems. It facilitates knowledge acquisition and makes it easier to apply the model for different domains. The model is oriented towards virtual laboratories, in which a student interacts by doing experiments in a simulated or remote environment. It represents the students knowledge at different levels of granularity, combining the performance and exploration behavior in several experiments, to decide the best way to guide the student in the next experiments. Based on this model, we have developed tutors for virtual laboratories in different domains. An evaluation of with a group of students, show a significant improvement in learning when a tutor based on the PRM model is incorporated to a virtual robotics lab.

A Virtual Laboratory for Mobile Robotics

Abstract We are developing a virtual robotics laboratory as a complementary tool for learning basic robotics, in particular for mobile robots. The laboratory includes both types, remote and simulated, and can be used to perform and observe the results of simple experiments with different mobile robots. It is based on a generic architecture, which provides a framework for developing virtual laboratories. An intelligent tutor is integrated to the virtual lab, which serves to improve the learning process of the students using the lab. We describe a prototype for the remote and simulated labs, and present some initial experiments in remote robot programming.

A multifunctional knowledge-based system for engineering

Abstract Knowledge-based systems are normally designed to perform a single task (e.g. diagnosis) for which they are competent, but their knowledge base is rarely used for other tasks, even when they are very similar and in the same application domain. An alternative approach is to build a knowledge core that has the basic knowledge for a certain domain, on top of which different tasks could be built. In this paper, a multifunctional knowledge-based system for engineering domains, called MF-KBS , is described. MF-KBS has (i) a library of engineering components, such as pumps, valves, tanks, etc. associated with mathematical models at different abstraction levels, (ii) several reasoning mechanisms for these models, and (iii) knowledge operators capable of performing different tasks with the reasoning mechanisms, such as diagnosis, problem solving, tutoring, etc. Particular applications are built by joining components, producing a global model via composition, and selecting one or more of the knowledge operators. Experiments in a subsystem of an electric power plant with different knowledge operators are described.