Saber Darmoul

Fault detection, diagnosis and recovery using Artificial Immune Systems: A review

Abstract Biological immunity is a natural system that protects a host organism against disease causing elements threatening its normal functioning. It offers many interesting features that inspired the design of Artificial Immune Systems (AIS) to solve several kinds of engineering problems. As a manufacturing system can be assimilated to a host organism, while process anomalies (e.g. faults, errors and failures) can be considered as disease causing elements, biological immunity is particularly inspiring approaches for fault detection, diagnosis and recovery (FDDR). Although many interesting works and different adaptations were suggested, we are not aware of any recent survey that would aim at reviewing works, synthesizing modeling approaches and reporting on results in this field. This paper provides a recent survey and an analysis framework to fill in this gap. After a first part overviewing FDDR needs and requirements, we introduce biological immunity and highlight the main concepts and mechanisms that are particularly relevant to FDDR problems. The numerous works analyzed distinguish three categories of AIS: one-signal (for positive and negative selection) based approaches, two-signal (for danger and NK) based approaches and immune network based approaches. We suggest a possible architecture for FDDR systems, and organize the immune system concepts, components and mechanisms in such a way to show how they are applied for each of the detection, diagnosis and recovery tasks. Our analysis allows an overview of current technical and methodical developments in this field and foresight of future research perspectives.

Scheduling Using Artificial Immune System Metaphors: A Review

Artificial immune systems (AIS) are relatively young emerging techniques, which explore, derive and apply different biologically inspired immune mechanisms, aimed at computational problem solving. Although several researchers have already attempted to adapt such metaphors to production and service scheduling problems, we are not aware of any literature review reporting the use of AIS for scheduling problems. This review of existing scheduling AIS applications shows that the published studies are related to several types of problems: single machine, hybrid and no wait flow shops, job shops, parallel processors. Task allocation and sequencing problems are also addressed in single or multi-objective optimization. After a first part introducing the main principles of artificial immune systems, we summarize how AIS paradigms are used and adapted in existing works to tackle scheduling problems. A discussion is then presented and, finally, several opened research directions are drawn

Handling disruptions in manufacturing systems: An immune perspective

One of the major issues in the monitoring and control of manufacturing systems is to determine how to effectively deal with unexpected disruptions (e.g. material unavailability, resource failures, unavailability of operators, rush orders, etc.). Existing approaches and tools offer few concepts that are specific enough and sufficiently generic to help in handling a broad variety of such unexpected events. The biological immune system potentially offers interesting features to face the threats (bacteria, viruses, cancers, etc.) that may harm an organism. This research aims to investigate this potential for the monitoring and control of manufacturing systems at the occurrence of disruptions. Based on analogies that we point out, we suggest a framework to help with the design of software tools that are more able to assist decision makers in dealing with various types of disruptions occurring in a manufacturing system. A first prototype implementation, developed using a multi agent approach, contributes to show the feasibility and the interest of this immune based framework.

Artificial immunity to control disturbances in public transportation systems: Concepts, mechanisms and a prototype implementation of a knowledge based decision support system

In public transportation, the occurrence of unpredictable disturbances (e.g. accidents, delays, traffic congestion, etc.) may affect the expected execution of preset organization and pre-established timetables of transportation resources (buses, trains, metros, trams, etc.). Affected timetables may become useless, or at least deviate from expected behavior and/or performance. Unfortunately, existing literature suffers limitations with respect to the development of decision support approaches and tools that are able to help decision makers in monitoring and controlling public transportation systems, particularly at the occurrence of disturbances. Existing works are still limited with respect to dealing with several types of disturbances, and suggesting reactive decisions at execution time in such a way to maintain the performance of pre-established timetables and provide users with high quality of services (in terms of punctuality, frequency of programmed shuttles, etc.). In this paper, we show that biological immunity can provide useful principles and mechanisms that are pertinent for the management of disturbances in public transportation systems. We highlight these principles and mechanisms, associate them with application components and fully document them. To show their feasibility, we develop a prototype artificial immune system able to assist decision makers in performing several disturbance management functions, such as detection of disturbances, construction of reaction strategies, supervised learning and memory of previous experiences with disturbances. Through experimental validation, we show that immune concepts and mechanisms can yield to the design and implementation of knowledge based decision support tools that are able to deal with different kinds of disturbances, and to assist decision makers through the disturbance management process.

Using immune designed ontologies to monitor disruptions in manufacturing systems

We rely on biological immunity to suggest a knowledge-based approach.Immunity provides concepts and mechanisms to model, represent and deal with disruptions and risks.We implement the knowledge-based approach using ontologies and a multi-agent system.We consider a case study from the steel industry.We show how the approach detects a machine failure, identifies inventory, production and quality risks, and suggests reaction decisions. Manufacturing systems are subject to several kinds of disruptions and risks, which may break the continuity of workflows, disturb pre-set organization, and prevent the production system from reaching its expected levels of performance. Several approaches were proposed to deal with manufacturing system disruptions and risks. Unfortunately, most of them focus more on explaining the causes of the disruption/risk, rather than on determining disruption/risk effects on workflows, pre-set organization and expected performance. Existing approaches usually operate off-line, thus missing current and accurate data about plant activities and changing conditions. Most of them do not offer concepts that allow the design of computerized tools dedicated to disruption/risk monitoring and control. In this paper, we rely on biological immunity to guide the design of a knowledge-based approach, and to use it to monitor disruptions and risks in manufacturing systems. The suggested approach involves functions specifically dedicated to deal with a variety of disruptions and risks, such as detection, identification of consequences and reaction to disruptions. This architecture is intended to be embedded within industrial information and decision support systems, such as ERP (ź Enterprise Resource Planning ź) and MES (ź Manufacturing Execution System ź). A prototype implementation using ontologies and multi-agent systems shows the relevance of the suggested approach in monitoring disruptions and risks. A simplified example from the steel industry illustrates the kind of support that can be provided to decision makers.

Development of a virtual manufacturing assembly simulation system

Assembly operations are a key component of modern manufacturing systems. Designing, planning, and conducting assembly operations represent an important part of the cost of a product. Virtual reality provides an efficient and cost-effective solution to manufacturing design, planning, and prototyping. Still there are certain issues (such as data translation, integration of various hardware and software systems, and real-time collision detection) faced while applying this advanced technology to the assembly domain. For example, existing works focus on using virtual reality systems and environments mainly to design new products and to plan for assembly. Little focus has been given to develop virtual reality environments that contribute to train operators on assembly operations and to bridge the gap between design and implementation/execution of assembly. Therefore, the research work presented in this article focuses on developing a fully functional virtual manufacturing assembly simulation system that solves the issues related to virtual reality environments. The proposed system uses a virtual environment to create an interactive workbench that can be used for evaluating assembly decisions and training assembly operations. It is a comprehensive system that provides visual, auditory, tactile, as well as force feedback. The system works successfully even with large components.

Using ontologies to capture and structure knowledge about disruptions in manufacturing systems: An immune driven approach

Artificial immune systems have recently been identified as a promising approach to assist decision makers in managing occurrences of unexpected disruptions in manufacturing systems. However, the design of such systems requires capturing and structuring knowledge related to disruptions. Such knowledge consists of manufacturing system specificities, control principles, disruption features, etc. Based on biological immune concepts, we design a generic ontology framework to capture this knowledge. This framework can be used as an initial basis to incorporate more specific disruption knowledge models in specific domain applications. An ontology implementation is proposed using the OWL language and Protégé ontology editor.

Reconfiguring Manufacturing Systems using an Analytic Hierarchy Process with strategic and operational indicators

In Reconfigurable Manufacturing Systems (RMS), decision makers often have to select one configuration among a set of available alternatives to meet new, unexpected and unpredictable changes disturbing production. A lot of research has been dedicated to evaluate configuration selection decisions using operational indicators based on performance. Unfortunately, the use of such indicators only may be relatively restrictive and can lead to choose an inefficient configuration. There is a need to include strategic indicators, which reflect both the capacity of the system to evolve and the real operating conditions of the workshop. In this paper, we consider both strategic and operational indicators when evaluating the reconfiguration decisions. We suggest a multi-criteria decision-making approach based on an Analytic Hierarchy Process (AHP) to assist decision makers in the selection process. Simulation results are provided to show the effectiveness of our approach.

A survey of simulation platforms for the assessment of public transport control systems

In public transportation, simulation provides capabilities of investigation of complex interactions between the components of the transportation system, including infrastructure, vehicles, passengers and intelligent transportation system. Although many simulation platforms (either commercial or open source) exist to test, validate and evaluate the performance of control systems, the development of platforms that integrate specific requirements of public transport systems still requires much investigation and effort. This paper reviews the main features of traditionally used simulation platforms. A comparative analysis is provided based on different criteria related to infrastructure, vehicles or the ability to implement and test intelligent and distributed control architectures. Several research directions are also pointed out and discussed.

An Immune Based Ontology Implementation of Hazard and Operability Analysis in Production Systems

In production systems, HAZOP is an example of such approaches that were suggested to identify, analyze, assess and control industrial risks. Unfortunately, HAZOP is not supported by methodological guidelines to implement it. Also, HAZOP does not rely on core concepts that allow the design of computerized toolkits that could be integrated within enterprise information systems to store and reuse knowledge stemming from the implementation of HAZOP projects. In this paper, we suggest an artificial immune based methodology to assist experts in implementing HAZOP projects. Through a case study, we show how immune concepts can provide both methodological guidance and computerized support in order to backbone expert efforts, and to capture risk related knowledge generated through each step of a HAZOP study.