Model-based Expert Research Articles

A recommendation system for energy saving and user engagement in existing buildings

Ranked as the major energy-consuming sector, the building industry continuously introduces enhanced energy-management systems towards more energy efficiency. Despite technological progress, high amounts of resources are still wasted worldwide due to the wrong usage of energy systems in existing building stock. As a response, this paper proposes a recommendation system that is based on information and communication technologies and that provides building users with hands-on executable recommendations to reduce their energy consumption. Indeed, because of their lack of energy awareness and knowledge, people may need guidance in their daily usage of a building to change their energy behaviour and to save energy. For that purpose, the recommendation system analyses building operation data in real time to identify energy wastes as well as suitable energy conservation measures that shall help in saving energy. One main challenge is to provide a highly scalable solution that can be easily applied in a wider range of buildings, thus enabling resource saving at a large scale or even worldwide. For that purpose, the system relies on a model-based expert system for easy adaptation in any building regardless of its type, size and usage.

Reducing Computational Cost During Robot Navigation and Human–Robot Interaction with a Human-Inspired Reinforcement Learning Architecture

We present a new neuro-inspired reinforcement learning architecture for robot online learning and decision-making during both social and non-social scenarios. The goal is to take inspiration from the way humans dynamically and autonomously adapt their behavior according to variations in their own performance while minimizing cognitive effort. Following computational neuroscience principles, the architecture combines model-based (MB) and model-free (MF) reinforcement learning (RL). The main novelty here consists in arbitrating with a meta-controller which selects the current learning strategy according to a trade-off between efficiency and computational cost. The MB strategy, which builds a model of the long-term effects of actions and uses this model to decide through dynamic programming, enables flexible adaptation to task changes at the expense of high computation costs. The MF strategy is less flexible but also 1000 times less costly, and learns by observation of MB decisions. We test the architecture in three experiments: a navigation task in a real environment with task changes (wall configuration changes, goal location changes); a simulated object manipulation task under human teaching signals; and a simulated human–robot cooperation task to tidy up objects on a table. We show that our human-inspired strategy coordination method enables the robot to maintain an optimal performance in terms of reward and computational cost compared to an MB expert alone, which achieves the best performance but has the highest computational cost. We also show that the method makes it possible to cope with sudden changes in the environment, goal changes or changes in the behavior of the human partner during interaction tasks. The robots that performed these experiments, whether real or virtual, all used the same set of parameters, thus showing the generality of the method.

Quality Assessment of Pre-Classification Maps Generated from Spaceborne/Airborne Multi-Spectral Images by the Satellite Image Automatic Mapper™ and Atmospheric/Topographic Correction™-Spectral Classification Software Products: Part 2 — Experimental Results

This paper complies with the Quality Assurance Framework for Earth Observation (QA4EO) international guidelines to provide a metrological/statistically-based quality assessment of the Spectral Classification of surface reflectance signatures (SPECL) secondary product, implemented within the popular Atmospheric/Topographic Correction (ATCOR™) commercial software suite, and of the Satellite Image Automatic Mapper™ (SIAM™) software product, proposed to the remote sensing (RS) community in recent years. The ATCOR™-SPECL and SIAM™ physical model-based expert systems are considered of potential interest to a wide RS audience: in operating mode, they require neither user-defined parameters nor training data samples to map, in near real-time, a spaceborne/airborne multi-spectral (MS) image into a discrete and finite set of (pre-attentional first-stage) spectral-based semi-concepts (e.g., “vegetation”), whose informative content is always equal or inferior to that of target (attentional second-stage) land cover (LC) concepts (e.g., “deciduous forest”). For the sake of simplicity, this paper is split into two: Part 1—Theory and Part 2—Experimental results. The Part 1 provides the present Part 2 with an interdisciplinary terminology and a theoretical background. To comply with the principle of statistics and the QA4EO guidelines discussed in the Part 1, the present Part 2 applies an original adaptation of a novel probability sampling protocol for thematic map quality assessment to the ATCOR™-SPECL and SIAM™ pre-classification maps, generated from three spaceborne/airborne MS test images. Collected metrological/ statistically-based quality indicators (QIs) comprise: (i) an original Categorical Variable Pair Similarity Index (CVPSI), capable of estimating the degree of match between a test pre-classification map’s legend and a reference LC map’s legend that do not coincide and must be harmonized (reconciled); (ii) pixel-based Thematic (symbolic, semantic) QIs (TQIs) and (iii) polygon-based sub-symbolic (non-semantic) Spatial QIs (SQIs), where all TQIs and SQIs are provided with a degree of uncertainty in measurement. Main experimental conclusions of the present Part 2 are the following. (I) Across the three test images, the CVPSI values of the SIAM™ pre-classification maps at the intermediate and fine semantic granularities are superior to those of the ATCOR™-SPECL single-granule maps. (II) TQIs of both the ATCOR™-SPECL and the SIAM™ tend to exceed community-agreed reference standards of accuracy. (III) Across the three test images and the SIAM™’s three semantic granularities, TQIs of the SIAM™ tend to be significantly higher (in statistical terms) than the ATCOR™-SPECL’s. Stemming from the proposed experimental evidence in support to theoretical considerations, the final conclusion of this paper is that, in compliance with the QA4EO objectives, the SIAM™ software product can be considered eligible for injecting prior spectral knowledge into the pre-attentive vision first stage of a novel generation of hybrid (combined deductive and inductive) RS image understanding systems, capable of transforming large-scale multi-source multi-resolution EO image databases into operational, comprehensive and timely knowledge/information products.

Model-based expert system to automatically adapt milling forces in Pareto optimal multi-objective working points

The objective of this paper is to present an open and modular expert rule-based system in order to automatically select cutting parameters in milling operations. The knowledge base of the system presents considerations of stability, machine drives efficiency and restrictions while adaptively controlling milling forces in suitable working points. Moreover, a novel classical cost function has been conceived and constructed to Pareto-optimise cutting parameters subjected to multi-objective purposes, namely: tool-life, surface roughness, material remove rate and stability rate parameter. Different Pareto optimal front solutions can be obtained modulating the weighting factors of the cost function. Additional rules have been added in order to manually and/or automatically modulate this cost function. Furthermore, a database which relates weighting factors, cutting conditions and cost function variables is produced for learning purposes. Chatter detection and suppression system automatically feedback to the system to take into account non-modelled disturbances. Finally, since the knowledge of the system is basically obtained from mathematical models, the possibility of combining experience and knowledge from expert engineers and operators is included. In this way, best practice from mathematical modelling and expert engineers and operators is joined in one system obtaining a full, automated system combining the best of each world.As a result, the expert rule-based system selects Pareto optimal cutting conditions for a broad range of milling processes, sorting out automatically different problems such as chatter vibrations, incorporating model reference adaptive control (MRAC) of forces. This procedure is intuitive, being executed in the same way as a human expert would do and it provides the possibility to interact with expert engineers and operators in order to take into account their experience and knowledge. Finally, the expert system is designed in modular form allowing incorporating new functionalities in rule based forms to them or just adding new modules to improve the performance of the milling system.

Minimisation of the capping tendency by tableting process optimisation with the application of artificial neural networks and fuzzy models

The pharmaceutical industry is increasingly aware of the advantages of implementing a quality-by-design (QbD) principle, including process analytical technology, in drug development and manufacturing. Although the implementation of QbD into product development and manufacturing inevitably requires larger resources, both human and financial, large-scale production can be established in a more cost-effective manner and with improved efficiency and product quality. The objective of the present work was to study the influence of particle size (and indirectly, the influence of dry granulation process) and the settings of the tableting parameters on the tablet capping tendency. Artificial neural network and fuzzy models were used for modelling the effect of the particle size and the tableting machine settings on the capping coefficient. The suitability of routinely measured quantities for the prediction of tablet quality was tested. Results showed that model-based expert systems based on the contemporary routinely measured quantities can significantly improve the trial-and-error procedures; however, they cannot completely replace them. The modelling results also suggest that in cases where it is not possible to obtain sufficient number of measurements to uniquely identify the model, it is beneficial to use several modelling techniques to identify the quality of model prediction.

Generalized linear model-based expert system for estimating the cost of transportation projects

Timely effective cost management requires reliable cost estimates at every stage of project development. While underestimation of transportation costs seems to be a global trend, improving early cost prediction accuracy in estimates is difficult. This paper presents a parametric estimating technique applied to Texas highway projects using a set of project characteristics. Generalized linear models (GLM) of early quantity prediction for geometry-related work activities, namely earthwork, pavement and traffic control were developed for continuous project cost tracking. The approach of cost breakdown demonstrates the potential to separate quantity uncertainty from price uncertainty for highway construction. The benefit of this approach is to provide a platform for evolving the preliminary parametric cost estimates to a fully detailed cost management as further information becomes available as the project progresses. During project execution, managers are given opportunities to review the associated work activities and make better decisions from the developed GLM-based estimating system. Compared to typical practice of applying a gross cost per lane length during pre-project planning phase, the proposed approach with the aid of the developed expert system provides more detailed basis and efficiency for tracking the effects of changes within the project life cycle.

Model-Based Expert System for Design and Simulation of APS Coatings

This article aims at presenting an expert system to assist the design and the simulation of 2-D shapes of alumina-titania (i.e., Al2O3-13 wt.% TiO2) Atmospherically Plasma Sprayed (APS) coatings. Indeed, the expert system derives from a spray deposition mathematic model resulting from experiments. The varied processing parameters were the geometric and the kinematics parameters, mainly, such as: the relative speed gun-substrate, the spray distance, the spray angle, the relative positioning powder injector-spray gun trajectory, the number of passes and the powder feed rate. The variations of the geometry and some of the structural parameters were analyzed relatively to the aforementioned varied parameters. Thus, a large set of spray pattern parameters was designed. This set considers mostly the spray pattern geometry. All the relationships between the processing parameters and the spray pattern parameters were hence grouped in a spray deposition model. The second step of this work consisted in optimizing the robotic (i.e., spray gun) trajectory using a robotic code, which permits a realistic simulation of the spray gun speed and its inertia. Using this simulation software, a trajectory file was built. In the third step of the work, an expert system was developed by combining the spray deposition model with the trajectory. The tasks of the expert system are: (1) to assist the user in designing the coatings by selecting the processing parameters and (2) to simulate the coating shapes by integrating the gun trajectory.

Erratum to “An approach to use linguistic and model-based fuzzy expert knowledge for the analysis of MRT images”

Erratum to “An approach to use linguistic and model-based fuzzy expert knowledge for the analysis of MRT images”

Dynamic probabilistic model-based expert system for fault diagnosis

The design and implementation of a probabilistic model-based fault diagnosis expert system is described in this paper. Possible cause and effect graph (PCEG) methodology, an enhanced signed-directed graph (SDG) approach, was used for qualitative modeling. A rule-based approach is proposed to transform the Bayesian belief network into an acyclic network dynamically during the diagnosis phase to allow simple on-line probability calculation in a belief network with causality loops. A dynamic time-delay methodology is also proposed to manage the possibility of phantom alarms, which are the consequences of process time-delays. The application to a pilot scale distillation column with communication with DCS environment is presented. Two sample runs were included to demonstrate the concept of dynamic causal network modification and time-delay management.

Model-based control of Aitik bulk flotation

The Boliden Aitik concentrator in Sweden processes 2,000 t/h (2,200 stph) of low-grade copper ore. The plant consists of five grinding lines that feed four bulk-flotation banks with a scavenger-concentrate regrind mill and a column cleaner circuit with a re grind mill. The authors installed a model-based expert optimizing control system to maximize copper recovery in the bulk-flotation circuit while maintaining an appropriate copper grade in the cleaner feed. The optimizing control system uses on-line assays and calculates and implements set points for cell pulp levels, air rates and reagent-addition rates. It combines the power of a dynamic population-balance model that estimates mineral liberation in each stream, an optimizer that computes appropriate set points and a rule-based module that implements the strategy. The benefits have been evaluated over a period of three months. The model-based expert optimizing control system generates a measurable increase in copper recovery, around 0.5%, and an optimized bulk-concentrate grade. The need to maintain the optimizing control system and other practical aspects are discussed.

A model-based expert control strategy using neural networks for the coal blending process in an iron and steel plant

Two important aspects of the control of the coal blending process in the iron and steel industry are computation of the target percentage of each type of coal to be blended and the blending of the different types in the target percentages. This paper proposes an expert control strategy to compute and track the target percentages accurately. First, neural networks, mathematical models and rule models are constructed based on statistical data and empirical knowledge on the process. Then a methodology is proposed for computing the target percentages that combines the neural networks, mathematical models and rule models and uses forward chaining and model-based reasoning. Finally, the tracking control of the target percentages is carried out by a distributed PI control scheme. The expert control strategy proposed is implemented in an expert control system that contains an expert controller and a distributed controller. The results of actual runs show that the proposed expert control strategy is an effective way to control the coal blending process.

A model-based expert control system for the leaching process in zinc hydrometallurgy

One important step in zinc hydrometallurgy is the leaching process, which involves the dissolving of zinc-bearing material in dilute sulfuric acid to form a zinc sulfate solution. The key point in the control of the process is to determine the optimal pHs of the overflows of the continuous leach process and track them. This paper describes a model-based expert control system for the leaching process, which is being used in nonferrous metals smeltery. Specifically, steady-state mathematical models and rule models are first constructed based on the chemical reactions involved, the empirical knowledge of engineers and operators, and empirical data of the process. Then, a methodology is proposed for determining and tracking the optimal pHs with an expert control strategy based on a combination of mathematical models and rule models of the process. The results of actual runs show that the proposed control strategy is an effective way to control the leaching process.

A Model-Based Expert System for Determining Optimal Control Inputs in Purification Process Control

One important step in zinc hydrometallurgy is the purification process, which involves removing impurities such as copper, cadmium and cobalt from a zinc sulfate solution to obtain a satisfactory electrolyte. The key point in the control of the purification process is the determination of the optimal amounts of zinc dust, ethylxanthic acid sodium salt and copper sulfate that are added to the reaction tanks. This paper describes a methodology for determining the optimal amounts by using a model-based expert system technique. First, a static mathematical model is established based on the chemical reactions involved and experimental data on the process. Then, it is modified in accordance with the experience and knowledge of ‘expert’ personnel and with data on the process, and a rule model is established. Finally, the modified mathematical model and the rule model are combined into a model-based expert system that determines the optimal amounts. The results of an actual run show that a control system using the proposed methodology provides not only a high-purity product but also significant economic benefits.

Integrated decision support for aviation safety inspectors

This paper presents a systems viewpoint for developing an advanced decision support system for aircraft safety inspectors. Research results from a Federal Aviation Administration (FAA) sponsored project to use neural network and expert systems technology to analyze aircraft maintenance databases are summarized. One of the main objectives of this research is to define more refined “alert” indicators for national comparison purposes that can signal potential problem areas by aircraft type for safety inspector consideration. Integration aspects are addressed on two levels: (1) integration of the various technical components of the decision support system, and (2) integration of the decision support system with individual behavior, management systems and organizational structure, as well as corporate culture across both formal and informal dimensions. The paper summarizes the creation of strategic “inspection profiles” for aging aircraft and reliability curve fitting for structural components both based upon using neural network technology. Also, the potential use of a model-based expert system to facilitate field inspection diagnostics is presented. Finally, a framework for developing an intelligent decision system to support aircraft safety inspections is proposed that links expert systems, neural networks, as well as a paradigm of the decision making process typically used in unstructured situations.

Cost reduction in grinding plants through process optimization and control

The major cost in comminution is energy consumption, which can be as high as 50% of the operating cost. Improvements in plant operations have resulted in up to a 15% reduction in energy usage (kw-hr/t). These improvements have been made through the optimization of grinding efficiency and the use of expert model-based control systems. Optimization involves the determination of the levels of the critical-operating conditions that result in the most efficient breakage of ore in the mill. These optimal levels are identified through plant/laboratory test work and through computer simulation using advanced process models. Model-based expert control achieves the maximum performance from the grinding circuit by identifying the characteristics of the ore in the mill with an optimal on-line estimator. Using this information, the control system dynamically determines the operating point that will yield the optimal performance. Two industrial applications of grinding-circuit optimization and model-based control are presented to demonstrate the power of this new technology.

A method of qualitative reasoning for model-based problem solving and its application to a nuclear plant

Model-based expert systems are expected to contribute to overcoming the difficulties of conventional rule-based systems. This paper describes the modeling of mechanical systems and a method of qualitative reasoning based on causal specifications. The causal specifications represent a component's local causal properties, following the principles for reusability and composability. It contributes to providing intuitive causal ordering of complex behavior originated in the combination of components, including inter-component negative feedback. A model of a system is represented by combining a set of local component models and global knowledge derived from general properties of the physical entity. This allows for reusable knowledge which is easy to describe. Furthermore, the method has been successfully applied to a nuclear power plant. Reasoning results were unambiguous and matched those obtained by domain experts.

An algorithm for complete enumeration of the mechanisms of supraventricular tachycardias that use multiple atrioventricular, AV nodal, and/or Mahaim pathways

The EINTHOVEN system is a model-based expert system that interprets the cardiac rhythm from the electrocardiogram. It simulates the expected behavior of realistic semi-quantitative cardiac models constructed by heuristic rules to generate interpretations that include both text descriptions and event-by-event causal explanations in the form of ladder diagrams. The simulation has been limited by an inability to predict all possible behaviors of hearts with more than one reentrant circuit. We now describe an algorithm that overcomes this limitation. Its output has been validated by an independent possibility-tree analysis. Timing and storage measurements are presented for models with up to three slow atrioventricular nodal pathways, four atrioventricular pathways, and a single atriofascicular (Mahaim) pathway. This is the first report in the literature of an algorithm that enumerates all possible mechanisms for reentrant supraventricular tachycardias that use atrioventricular, atrioventricular nodal, and/or atriofascicular pathways in humans.

A Model-Based Expert System of Wheat Cultivation Management

A Model-based Expert System of Wheat Cultivation Management (MbESWCM) have been developed to simulate the expert ability of problem -solving in Wheat Cultivation Management ( WCM) and make decisions and recommendations for farmers, extension workers, and administrators. MbESWCM consisted of Data Base System (DBS), Knowledge Base System (KBS), Model Base System (MBS), Inference Engine (IE) and the Interface of Computer-User( ICU). MbESWCM takes the form of decision aids integrated with optimal cultivar choice, sowing date and density, plant population, fertilizer and water application, weeds, insects and diseases control. Also, MbESWCM could help farmers to analyze the economical effects of agronomical practices.

Intelligent operation of distribution network

The authors present an intelligent distribution control system operating in conjunction with a SCADA system with minimum supervision and interaction with a human operator. The application of a model-based expert system results in an intelligent power distribution system with learning, self organising and diagnostic capabilities. The work deviates from previous approaches in two important aspects: the use of model-based reasoning allows many different application knowledge bases (e.g. fault diagnosis, restoration, maintenance planning, etc.) to operate on the common model of the distribution network thus making it very compact and versatile, and it introduces for the first time the concept of intelligence in a power distribution system. To support modular development and simple maintenance of the expert system, the knowledge required to do the reasoning has been separated into a model of the distribution system and several knowledge bases which work on it. The frame-based object-oriented knowledge representation provides the flexibility to extend the model without adversely affecting the performance. The expert system has been tested extensively for operation with a real-time 22 kV SCADA system covering a large area of 180 substations. The expert system gives accurate fault analysis for all the fault cases and proposes the best restoration plans in less than 15 seconds. In addition, it advises the control centre operators in cases of emergency, helps them in maintenance planning and can be used as a training simulator in offline mode.

カラー時間ペトリネットを用いた電力系統故障区間判定

A correct and rapid inference is required for practical use of expert system for fault section estimation in power systems. This paper proposes a new model-based expert system for fault section estimation using colored and timed Petri nets. The Petri nets simplify the inference procedure greatly because it can represent the causalities among faults of power system components, protective actions of relays and circuit breakers. They can also represent the operating states of these protective devices explicitly, or, more precisely, whether a relay has been actuated correctly or falsely, etc. In addition, time sequence information on actuated relays and tripped circuit breakers can be handled by using the colored and timed Petri nets. Therefore, the operating states of relays and circuit breakers can be inferred more correctly. Petri nets are suited for parallel processing so well that there is a possibility of reducing the inference time considerably. In the proposed system, the inference is executed by setting the initial states in the Petri nets using the information on the actuated relays and the tripped circuit breakers and then operating the Petri nets. There have been several test cases which used a prototype system on the Macintosh computer employing Object Common Lisp, and good results have been obtained.