Expert System

A Real-time Expert System Environment for on-line
Operational Control and Decision Support Applications

RTXPS is a real-time expert system environment designed for on-line dynamic decision support, mission critical command, control and communication tasks such as

  • Complex operational control and assessment tasks, real-time process control and non-linear dynamic, distributed optimization (SCADA), such as cascading reservoir and irrigation system management,
  • Real-time air quality assessment and management, including CEMS and PEMS;
  • Emergency management for technological and environmental hazards, including early warning for events such as floods, toxic or oil spills, land slides, dust storms, etc. including the coordination of first response, recovery, restoration and clean-up operations;
  • Technical/academic teaching and training applications.

RTXPS can be configured to implement any checklist, questionnaire or operating manual based procedure or protocol. It offers context sensitive support functions based on Artificial Intelligence technology, that can handle the most demanding dynamic situations in distributed client-server environments, with several parallel action threads. RTXPS provides extensive support and assistance to the operator, and keeps complete real-time logs for quality control, but also machine learning and CBR tools. The dynamic KnowledgeBase of RTXPS is open to asynchronous signals from any number of processes or sensors.

Setting and querying of timers or the pending of ACTIONS provide additional features for real-time control. ACTIONS triggered by RTXPS include any arbitrary complex local or remote function or model, and the inference engine can also use a backward chainging subsystem.   For a summary description, see:   /MANUALS/RTXPS/summary.html

RTXPS is based on a time-aware forward chaining inference engine, that processes context sensitive Production Rules that manage the dynamic problem knowledge base and trigger ACTIONS. An independent Watchdog process ensures mission critical reliability, and can run an independent instance for real-time AQ/QC. ACTIONS are communicated to the operator in hypertext format, and can automatically trigger a wide range of functions including data entry and display, an embedded backward-chaining expert system, and complex simulation and optimisation modeling and GIS applications.

Support of extensive documentation, logging, reporting and external communication functions such as automatic compilation and sending of e-mail or fax messages as well as the automatic generation and update of web pages for public information access are important features of the system. RTXPS can run as an "embedded process", but also in an interactive (web based) interface under direct user control.

RTXPS can also link to on-line monitoring and data acquisition systems that can provide real-time intelligence and feed-back from the field; this can be used not only to update the problem context dynamically, but also for the re-calibration of dynamic forecasting models.

RTXPS uses a simple near-natural language syntax for its Rules, ACTIONS and Descriptors, the variables that the Rules operate on. An intuitive SCRIPT language supports the efficient development of the Knowledge Base for a new application.
On-line Manuals  

Application Examples

  • RTXPS drives COR (Computer Operated River) a real-time water resources (irrigation) management system;
  • RTXPS monitors and controls real-time (continuous) forecasting systems for urban and industrial air quality, including natural dust;
  • RTXPS is the core DSS component of RiskWare, a decision support system for technological risk management, risk assessment and risk training.
  • RTXPS in an extended implementation is the basis of our CourseWare training system, developed in the A-TEAM advanced technical training system. The framework can also be used to guide users through other complex tasks such as the EIAxpert system for screening level EIA.
  • RTXPS has been implemented as the overall framework for SIGRIC, the Sistema di Gestione Rischio Chimico for the Provincial Authorities of Pisa in the Regione Toscana, Italy.
  • RTXPS is also the core DSS component of HITERM, High-Performance Computing for Technological Risk Management, an Esprit HPCN project with case study applications in Italy, Portugal, and Switzerland.
Various editors support the man-machine dialog and data acquisition for the inference engine RTXPS controls a range of dynamic simulation models that feed their results into the expert system Real-time (5 day forecasts) air quality assessment and management, public information.

© Copyright 1995-2019 by:   ESS   Environmental Software and Services GmbH AUSTRIA | print page