The paper is devoted to applied methods for finding the global extremum in high-dimensional combinatorial problems. It is stated that the solution of these problems, for example, in the case of automated design decisi...
详细信息
This article presents an integrated design of intelligent decision support systems (DSSs) for industrial risk management. The need for this class of systems has been necessitated by resilience building and threat resp...
详细信息
ISBN:
(纸本)9781665476874
This article presents an integrated design of intelligent decision support systems (DSSs) for industrial risk management. The need for this class of systems has been necessitated by resilience building and threat response planning problems faced by complex industrial installations in energy and mining sectors. The proposed DSS software architecture is AI-based and applies causal and anticipatory networks, multi-criteria analysis, information fusion and knowledge engineering techniques. The use of AI-tools follows the AI-alignment paradigm, where AI evolution provides clues regarding the most suitable techniques to solve anticipated industrial safety problems in different time scales. We propose a general scheme of industrial risk management which includes threats, sensors, information flows, and decision-making models. This scheme is complemented by the risk optimization module, which selects the actions and actuators to implement them. Signals received from sensors are fused and confronted with threat management scenarios contained in the knowledge base. The recommendations concerning prevention, protection, and threat mitigation measures are generated by the DSS and conveyed to human decision makers for approval. Selected actions can also be autonomously initiated. Previous activity assessments result on an improved configuration of sensors and actuators, as well as more effective first responder actions. Threat and risk management modules of the DSS are linked by a sequential machine learning procedure, so that the results of prior decisions can be used to learn managerial preferences and parameters of risk mitigating scenarios.
Due to the advancements in technology, the demand for electric power keeps on increasing, which further leads to voltage stability problems. Another undesirable effect is an increase in the transmission line losses in...
详细信息
The proceedings contain 47 papers. The special focus in this conference is on Principles and Practice of Multi-Agent systems. The topics include: Assume-Guarantee Verification of Strategic Ability;sample complexi...
ISBN:
(纸本)9783031212024
The proceedings contain 47 papers. The special focus in this conference is on Principles and Practice of Multi-Agent systems. The topics include: Assume-Guarantee Verification of Strategic Ability;sample complexity of Learning Multi-value Opinions in Social Networks;a Hybrid Model of Traffic Assignment and control for Autonomous Vehicles;MTIRL: Multi-trainer Interactive Reinforcement Learning System;action Languages Based Actual Causality in Decision Making Contexts;goal-Oriented Coordination with Cumulative Goals;Optimal Parameter Selection Using Explainable AI for Time-Series Anomaly Detection;does Order Simultaneity Affect the Data Mining Task in Financial Markets? – Effect Analysis of Order Simultaneity Using Artificial Market;fine-Grained Prediction and control of Covid-19 Pandemic in a City: Application to Post-Initial Stages;explanation-Based Negotiation Protocol for Nutrition Virtual Coaching;preference Aggregation Mechanisms for a Tourism-Oriented Bayesian Recommender;weaponizing Actions in Multi-Agent Reinforcement Learning: Theoretical and Empirical Study on Security and Robustness;learning to Classify Logical Formulas Based on Their Semantic Similarity;time Series Predictive Models for Opponent Behavior modeling in Bilateral Negotiations;An MCTS-Based Algorithm to Solve Sequential CFGs on Valuation Structures;the FastMap Pipeline for Facility Location problems;an Axiomatic Approach to Formalized Responsibility Ascription;task Selection Algorithm for Multi-Agent Pickup and Delivery with Time Synchronization;dynamic Continuous Distributed Constraint Optimization problems;DITURIA: A Framework for Decision Coordination Among Multiple Agents;cooperative Driving at Intersections Through Agent-Based Argumentation;evaluating Adaptive and Non-adaptive Strategies for Selecting and Orienting Influencer Agents for Effective Flock control;a Proportional Pricing Mechanism for Ridesharing Services with Meeting Points;privacy-Aware Explanations for Team Formation;a New
The paper illustrates the process of generating synthetic data used to develop a computer vision industrial control system, based on the simulation of an industrial belt conveyor. The result of this study represents t...
详细信息
The proceedings contain 45 papers. The topics discussed include: research on mobile robot localization algorithm based on multi-sensor fusion;decision trees based multi-factor remote technical diagnostics of car retar...
ISBN:
(纸本)9781510664845
The proceedings contain 45 papers. The topics discussed include: research on mobile robot localization algorithm based on multi-sensor fusion;decision trees based multi-factor remote technical diagnostics of car retarders;decision trees based multi-factor remote technical diagnostics of car retarders;the construction of expert systems based on the theory of fuzzy sets as a trend in modern science and education;development of an adaptive control system for the quality parameter in the lack of information;point cloud analysis in a production quality guarantor computer vision system;using mathematical statistics to optimize the process of crossovers using data center infrastructure management;simulation modeling photovoltaic modules;machine learning techniques combination for selective and hierarchical analysis of psycho diagnostic data;rationalization of neural network training parameters on WWII poster classification example;and development of software and hardware complex for control and access management based on face recognition algorithms and neural networks.
Conventional programming of explicit control code is unsuitable for flexible and collaborative production systems. A model-based approach, which focuses on defining capabilities of a system, instead of specifying how ...
详细信息
In the study of any objects and devices, the first step is the construction of the geometric structure, which is divided into finite elements with large number of nodes. Such model with millions of degrees of freedom ...
详细信息
Facing the urgent need to mitigate anthropogenic climate change, reducing emissions from the combustion of natural gas has become imperative. This is particularly challenging in the steel or cement industry, where hig...
详细信息
ISBN:
(纸本)9780791887899
Facing the urgent need to mitigate anthropogenic climate change, reducing emissions from the combustion of natural gas has become imperative. This is particularly challenging in the steel or cement industry, where high-temperature heat is essential. A promising solution is substituting natural gas with biogas or hydrogen. The typically highly decentralized gas production presents a transportation challenge due to the high costs of pipeline networks. In this paper, we propose a novel Mixed Integer Linear Programming (MILP) formulation to minimize the investment costs of pipeline networks. The pipeline network is modeled dendritically, allowing the efficient connection of multiple production plants and feed points. The topology of the network and the discrete pipe diameters are optimized simultaneously. A significant novelty is the use of a boolean matrix-vector multiplication in our formulation, allowing the usually non-linear formulation to be formulated linearly without loss of information. This enables hitherto unsolvable problems to be solved using highly efficient MILP solvers. The method is demonstrated using a case study with 37 biogas plants and seven feed points in Austria. The optimization results are the topology of the network and the pipe diameters at minimum specific costs of 3.24e/(MWh). The results further highlight the economic efficiency of individual clusters, enabling decision-makers to implement step-by-step network expansion. The proposed method represents a novel contribution to optimizing the construction of gas transport infrastructure for biogas, offering potential applications in the broader context of renewable energy integration.
Cloud-network integration(CNI) is an inevitable choice to enhance the supply capacity of industrial Internet. In traditional industrial controlsystems, there are problems such as insufficient depth of perception, ins...
详细信息
暂无评论