Expert Systems with Applications 39 (2012) 8204–8211

Contents lists available at SciVerse ScienceDirect

Expert Systems with Applications

journal homepage: www.elsevier .com/locate /eswa

A knowledge-based decision support system for shipboard damage control

F. Calabrese c, A. Corallo b, A. Margherita b,⇑, A.A. Zizzari a

a Centro Cultura Innovativa d’Impresa, University of Salento, Campus Ecotekne, Via Monteroni s.n., 73100 Lecce, Italyb Department of Innovation Engineering, University of Salento, Campus Ecotekne, Via Monteroni s.n., 73100 Lecce, Italyc Apphia s.r.l., via Clementina Carrelli n. 26, 73100 Lecce, Italy

a r t i c l e i n f o a b s t r a c t

Keywords:Damage control systemDecision support systemExpert systemKill cardKnowledge-based systemShipboard management

0957-4174/$ - see front matter � 2012 Elsevier Ltd. Adoi:10.1016/j.eswa.2012.01.146

⇑ Corresponding author. Address: University of Saltion Engineering, c/o Euro-Mediterranean Incubator, Croni s.n., 73100 Lecce, Italy. Tel.: +39 0832 297922; f

E-mail address: alessandro.margherita@unisalento

The operational complexity of modern ships requires the use of advanced applications, called damagecontrol systems (DCSs), able to assist crew members in the effective handling of dangerous events andaccidents. In this article we describe the development of a knowledge-based decision support system(KDSS) integrated within a DCS designed for a national navy. The KDSS uses a hybrid design and runtimeknowledge model to assist damage control operators through a kill card function which supports damageidentification, action scheduling and system reconfiguration. We report a fire fighting scenario as illustra-tive application and discuss a preliminary evaluation of benefits allowed by the system in terms of criticalperformance measures. Our work can support further research aimed to apply expert systems to improveshipboard security and suggest similar applications in other contexts where situational awareness anddamage management are crucial.

� 2012 Elsevier Ltd. All rights reserved.

1. Introduction various types of damage situations, based on the collection and

Navy ships have been traditionally manned with a large crewinvolved in the manual control of onboard systems. The reductionof through-life costs of vessels is today a priority and there is aninterest towards reducing crew without affecting damage controlcapabilities or jeopardizing the ability of ships to complete theirmissions (Cosby & Lamontagne, 2006). Beside efficiency pressures,factors like the increased complexity of modern vessels, therequirements for easy maintainability and more sophisticatedoperational demands generate a need for intelligent functionalitiesand leading-edge technologies (Bøgh & Severinsen, 2009) whichcan assist human decisions and actions onboard.

In this endeavor, one relevant area is related to the manage-ment of events which may lead to shipboard damage and crewdanger. These events require rapid actions, also without on-sitehuman intervention, to prevent serious injuries to personnel ordamages to vital ship systems. Whereas damage control has beentraditionally a manual and manpower-intensive function, the auto-mation of emergency management operations is today driven bycomplex technology architectures called damage control systems(DCSs) and related progresses in human-system integration, whichgets increasing attention in ship design (Runnerstrom, 2003). ADCS is an information-retrieval and equipment-control system thatgives ship personnel the ability to detect, analyze, and handle

ll rights reserved.

ento, Department of Innova-ampus Ecotekne, Via Monte-

ax: +39 0832 297927..it (A. Margherita).

processing of vast quantities of shipboard information.In the navy context, a damage control system (DCS) is aimed to

assure the timely and informed application of men and equipmentin scenarios such as fire or flooding, violation of the ship closurestate, threats to essential equipments, ventilation close down,and atomic/biological/chemical issues. DCSs are also relevant foremergency training and damage instructor assistance purposes(Bulitko & Wilkins, 1999; Peters, Bratt, Clark, Pon-Barry, & Schul,2004). The noteworthiness of these systems is proven by the num-ber of leading market players (e.g. ABB, L3, Northrop Grumman,Rockwell, and Siemens) involved in the design and developmentof innovative solutions for damage control.

The assistance to damage control operators, with recommenda-tions for counteractions and reconfigurations, requires a highlystructured approach to problem identification and action planning.The field of expert and decision support systems can thus provide arelevant contribution to design more performing DCSs. However,the study of expert systems and DSS in navy contexts has mostlyfocused on the design process whereas a very limited number ofcontributions have addressed the implementation of integratedsystems to ensure the safety and operational stability of modernships.

In this paper, we show the development of a knowledge-baseddecision support system (KDSS) which has been integrated withinthe DCS designed for the operating needs of a national navy. Westart from the analysis of the typical damage control process andidentify a model of knowledge acquisition and reuse in damagemanagement scenarios. The model is implemented through thedevelopment of a kill card function providing an interactive

F. Calabrese et al. / Expert Systems with Applications 39 (2012) 8204–8211 8205

interface and a shared decision and action platform for damagecontrol personnel onboard. The tool provides a graphical informa-tion-retrieval and equipment-control dashboard that gives damagecrew the ability to handle various types of damage controlsituations.

The remainder of the paper is structured as follows: Section 2reviews existing literature on damage control and DSS applicationsin the navy context; Section 3 introduces the research require-ments and describes the overall architectural design; Section 4illustrates the KDSS developed; Section 5 presents an illustrativeapplication related to a fire-fighting scenario and proposes a preli-minary evaluation of quali-quantitative benefits; Section 6 con-cludes the paper and draws avenues for future research.

2. Damage control and DSS

The concept of damage control is not limited to the navy indus-try. In fact, it is largely used in the field of medicine, surgery, andinjury prevention as well as in project management, politics, med-ia, and industrial production. In general, the term is used to de-scribe the process of identifying, monitoring and dealing withany problem that may jeopardize a given system or endeavor.

A first area in which information and decision support systemshave been developed for damage control purposes is the field ofdynamic emergency response and resource intervention(Minciardi, Sacile, & Trasforini, 2007; Turoff, Murray, de Walle, &Yao, 2003). The use of expert systems and virtual reality to supportdecision making in emergency management situations has beenalso studied (Beroggi, Waisel, & Wallace, 1995; Caro, 1992). Othercontributions have investigated the use of computer-based sys-tems to support human improvisation in extreme events(Mendonca, 2007) and the inter/intra-organizational communica-tion and coordination in emergency response (Kanno & Furuta,2006). As a specific area of application, the response logistics toroadway network incident (Zografos, Androutsopoulos, & Vasilakis,2002) has been studied. Besides emergencies, damage manage-ment has represented an area of interest for expert systems andneural networks in manufacturing and engineering contexts, witha focus on structural damage detection and assessment (Barai &Pandey, 2000; Jiang, Zhang, & Zhang, 2011; Mehrjoo, Khaji,Moharrami, & Bahreininejad, 2008; Ubeyli & Ubeyli, 2009).

Despite the relevance of the topic and the applicability of deci-sion support and expert system principles, few contributions haveinstead focused on the development of intelligent systems for ship-board damage control. An effective damage control system (DCS)needs a systemic approach to realize key functions such as providesupport to control personnel to make informed and real-time deci-sions, enhance total ship, coordinated, real-time control of menand equipment at the scene of damage, and allow changeover fromremote-automated to local-manual control in case of emergency(Geer, 1988).

In the area of intelligent applications for shipboard damagecontrol, an expert system was created to support the cognitive pro-cesses involved in ship piloting and collision avoidance (Grabowski& Wallace, 1993). With a more specific focus on damage manage-ment, a rule-based expert system based on information from navydamage control tactics, procedures, doctrine, and experts waspresented (Tate, 1996). A fuzzy distributed expert system was builtto assist command and control activities (Simoes-Marques & Pires,2003) and a virtual environment has been developed to supportemergency planning decisions by considering what could occurwhen fluids disseminate through ship compartments, such as flood-ing, fire, or contamination (Varela & Guedes Soares, 2007). Finally,an expert system was developed for ship auxiliary machinerytroubleshooting (Cebi, Celik, Kahraman, & Deha Er, 2009).

The design and development of expert and decision supportsystems in ship contexts has been mostly focused on the designprocess (Park & Storch, 2002). Different contributions have ad-dressed the aided design of ship systems automation (Arendt,2004; Arendt & van Uden, 2011; Kowalski, Arendt, Meler-Kapcia,& Zielnski, 2001; Kowalski, Meler-Kapcia, Zielinski, & Drewka,2005), the support of the conceptual design stage based on knowl-edge engineering (Lee, 1999; Lee & Lee, 1999), and the analysis ofdesign problems and assessment of trade-offs between perfor-mance and cost (Chou & Benjamin, 1992). Two specific studieshave developed an expert system to support compartment designof a crude oil tanker (Lee & Lee, 1997) and a DSS for vessel fleetscheduling (Fagerholt, 2004).

All these studies can provide a larger background to define therequirements for ship design, building and management, with thepurpose to extend the research on decision support systems ap-plied for ship personnel security and control of casualties to shipsystems.

3. Overview of the DCS

The development of our KDSS was framed within a collaborativeproject with Avio SpA. This a leading company operating both in theaerospace propulsion (participates in military programs such as theF-35 JSF and civil partnerships with General Electric, Pratt &Whitney, and Rolls Royce) and in the marine industry for theprovision of control, automation and propulsion systems and com-ponents (e.g. turbine control, lubrication and fuel systems). Thecompany is a Marine System Supplier (MSS) of General Electric.

In the last years, Avio has worked in the development of innova-tive damage control systems (DCSs) for national navies. The DCS is asupervisor system embedded in the Integrated Platform Manage-ment System (IPMS), which is a distributed hardware architectureused for real-time monitoring of the ship propulsion, mechanical,electrical, auxiliary and damage control systems. Monitored com-ponents include gearboxes, pitch propellers, power generation sets,power distribution switchboards, electrical distribution centers,fire pumps, systems for heating, ventilation, air conditioning,chilled water, and so forth.

In practice, the IPMS controls all the onboard equipment,excluding weapons/sensors (for military ships) and the ship’s com-munication and navigation equipment. The general IPMS architec-ture comprises Multi-Function Consoles (MFCs) and Remote TerminalUnits (RTUs). MFCs are mostly laptops and workstations providingthe human–machine interface for the operators at various ship-board locations whereas RTUs are used for data acquisition andcontrol and they are connected to sensors and actuators (e.g. FDS– fire detection sensors, pumps, fans). The IPMS is endowed with aruntime application allowing to monitor the whole ship from eachMFC.

Whereas the IPMS represents the hardware backbone for dam-age control operations, the DCS is the software platform configuredwithin the IPMS with functions such as monitoring of ship subsys-tems, longitudinal, planar and isometric views, Tiled LayeredGraphics (TLGs) approach (for automatic de-cluttering and displayof complex information), casualty management, support to man-age emergency states, event log and report, and compartmentmonitoring.

These functionalities are integrated into four modules: (1) Dam-age Control Management System (DCMS), which enables to auto-matically acquire all the relevant ship safety and other dataneeded to handle damages, display data to the operator in an opti-mized way, handle alarms, and rapidly share/communicate theinformation between the different MFCs; (2) On Board Stability Soft-ware (OBSS), to obtain and visualize ship stability data (e.g. tanks

Fig. 1. IPMS hardware architecture and main DCS interface.

8206 F. Calabrese et al. / Expert Systems with Applications 39 (2012) 8204–8211

level, flooding sensors, water tight doors status, etc.) and calculatethe stability parameters; (3) Closed Circuit TV (CCTV), which acti-vates cameras to monitor real-time the compartments of the ship;and (4) Decision Support System (DSS), to assist the damage controlofficer in case of critical events by indicating the most suitable pro-cedures to handle the specific situation.

The four modules are organized within an interactive interfacewhich allows the operator to access each function starting from amain window and navigating within the system by means ofguided paths and hyperlinks. Fig. 1 shows the architecture of theIPMS and the basic interface of the DCS. The red arrow indicatesthat the DCS interface can be accessed from every damage controlterminal (the RTU) onboard.

To develop the KDSS, we first studied the decision/action pro-cess of the damage control operator onboard. We have then iden-tified the information flows at the basis of decisions ad actions anddeveloped the four core components of the DSS (Bonczek,Holsapple, & Whinston, 1981), i.e. the knowledge system (sourcesof data and information), the language system (input format), thepresentation system (interface and layout) and the problem-processing system (software engine). Next section describes theoutput of our work.

Fig. 2. Decision and action flow

4. KDSS for shipboard damage control

Damage and emergency management efforts onboard are coor-dinated by a damage control officer (DCO), which is usually sup-ported by a damage control assistant (DCA) and a team in chargeof maintaining situational awareness and taking actions to preventinjury to personnel, damage to ship systems, or loss of the ship aswell.

The KDSS developed has a direct impact on the decision makingprocess and actions of these actors. A generic decision making flowincludes the recognition of the problem, the listing of objectives,the perception of environment and constraints, the listing of op-tions, the decision analysis and the action plan (Arbel & Tong,1982). In the damage control perspective, these steps are specifi-cally translated in a flow including five key steps (Fig. 2).

The monitoring of ship systems through the damage controlplatform allows the operator to acquire situational awareness ofdamage (step one) and identify where the damage is located andwhich is its extent (step two). Next, the operator can start a setof preliminary actions aimed to contain and control the effects ofdamage (step three) and activate the damage control systemsand crew to eliminate the causes of emergency and prevent further

of damage control operator.

F. Calabrese et al. / Expert Systems with Applications 39 (2012) 8204–8211 8207

issues (step four). Finally, the operator reconfigures the navy andcontrol systems after that the problem has been completely solved(step five). Throughout the five steps, the operator takes criticaldecisions related with what to do, what to do first, how to undertakeactions, and in which order undertake actions.

In order to streamline the decision flow and the execution of ac-tions, we identified four major requirements to drive the design ofthe KDSS:

(1) monitor all damage control status and operations at anytime and from each control position onboard;

(2) support damage control operations by acquiring all ship’sand security relevant data;

(3) allow efficient presentations of information to the damagecontrol operator;

(4) provide decision aids, actions, procedural checklists andalarms when handling emergency situations.

A KDSS is a special system for decision support which is able torecommend actions based on specialized problem-solving exper-tise stored as facts, rules, procedures, or in similar structures. Wefirst designed the knowledge model underlying the system. Basicknowledge to support the decisions and actions of the damage con-trol crew derives from two main sources: (1) design time knowl-edge sources, which include the ship and damage control dataavailable at the design of the system; and (2) run time knowledge,including damage control data received ‘‘in process’’ through thedamage control equipments.

Design time knowledge was obtained from the ship structureand engineering data (e.g. ship layout and dimensions of compart-ments), navy/ship rules (e.g. operating and security managementprocedures) and damage control officer (e.g. engineering expertise,design suggestions, insights). Run time knowledge is implementedin the system through damage system information (e.g. fire andflooding sensors connected with the RTUs) and shared communi-cations among the damage control operators onboard (e.g. sepa-rated actions which have to be consolidated into a uniquedamage checklist).

Fig. 3. Model of the knowledge-based D

Concerning the problem processing level of the KDSS, theknowledge sources are integrated within the kill card, i.e. an infor-mation and operation support dashboard which groups logically allthe information related to the ship equipment and security sys-tems, provides predefined automatic control sequences to respondto specific casualty conditions, and allows the operator to rapidly(knowing and) executing the correct actions at the moment. Sincea damage generally originates in one specific compartment of theship (and then it can propagate to other compartments), each com-partment is associated to a dedicated kill card. We have thus devel-oped a total of about 300 cards, which is the average number ofcompartments for a large vessel.

We implemented the KDSS as a Microsoft Windows Environ-ment developed in Visual Studio 2008. We used C# as program-ming language as it presents the power of C++ and the slicknessof Visual Basic. Besides, the language supports the introductionof XML comments which can turn into documentation. The com-ments are placed into XML format and can then be used as docu-mentation which can include example code, parameters, andreferences to other topics. Fig. 3 shows the overall model of ourKDSS.

We developed the kill card function with two main compo-nents, i.e. the editor and the viewer. The editor allows to create anew card (with a preview function), modify or delete an existingcard from the kill card database if/when basic requirements relatedto ship structure, rules and operating procedures should change(i.e. the design time knowledge sources). The viewer allows to openand visualize an existing kill card generated through the editor. Inorder to retrieve a card, the operator has three options: (1) use aplan or isometric view of the ship to click on the description of acompartment; (2) choose a card from a purposeful kill card areaby using a database tree structure (which describes the wholeship); (3) use a search function based on compartment names. Inthe viewer function, the damage control operator can also sharethe action list, i.e. score when response actions (e.g. in case of fire)have been started and/or completed and transmit this informationto every MFC onboard. Finally, it is possible to reset changes byusing a clear function and control the dynamic buttons of devices

SS for shipboard damage control.

Fig. 4. Kill card structure.

8208 F. Calabrese et al. / Expert Systems with Applications 39 (2012) 8204–8211

through a device window. All the information contained in everykill card and all the changes made on them are stored in a databaseusing a XML file whose name corresponds to the ship compartmentname (e.g. wardroom, engine room).

The general format of a kill card (the ‘‘template’’) is an emptyformat structured in text fields and buttons (allowing to operatevarious devices) and it includes three sections or areas:

(1) compartment identification area, showing critical informa-tion such as ship general data and compartment location;

(2) summary area, with information related to ship and com-partment sensors;

(3) detail area, including several tables with information relatedto ventilation control, danger hazards, fire fighting installa-tions, actions, compartment views and video clips, and sta-tus of devices.

The damage control operator can visualize actions from a pre-defined list and ‘‘check off’’ (see Fig. 4) when these actions havebeen successfully completed. The system also allows to link killcards of different compartments when the effects of damage prop-agate into different ship rooms. In this way, it is possible to use thesensors and devices available in more compartments, identify pri-ority areas, execute shared actions, and so forth.

The basic structure and content of a kill card template can bemodified through a purposeful configurator. The editor, viewerand configurator components are operationalized by a softwareapplication available in every MFC of the ship, allowing damage

control operators to be always in possess of the information perti-nent to the emergency situation managed at the moment.

The kill card ‘‘uses’’ the design information (such as compart-ments layout and dimensions, ship security management proce-dures, and damage control officer insights) and run timeknowledge (like system status, status of actuators and sharedinformation on actions taken by different operators), to provide ex-pert assistance to the damage control crew. The kill card is themain element of the user interface and it allows a dynamic situa-tional awareness of damage, damage localization and extent, preli-minary counteractions, damage control systems and crewactivation and reconfiguration. The KDSS suggests therefore tothe damage control operator what to do, what to do first, how toundertake actions, and in which order undertake actions in the differ-ent emergency situations which may happen onboard.

Next section shows an illustrative scenario of fire fighting inwhich the system can provide its support to damage control oper-ations. A preliminary evaluation of benefits achieved is alsodescribed.

5. Illustrative scenario and evaluation of benefits

We describe hereafter an illustrative scenario in which a fireemergency onboard requires rapid actions to avoid serious injuriesto personnel or damages to vital ship systems. In this case, thedamage control crew is involved in the following sequence ofsteps:

F. Calabrese et al. / Expert Systems with Applications 39 (2012) 8204–8211 8209

(1) acquire awareness about a fire happened onboard;(2) identify where fire is located and which is its extent;(3) start a set of preliminary actions aimed to contain and con-

trol the effects of fire;(4) activate damage control systems and crew to eliminate

causes of fire and prevent further damages;(5) reconfigure and restore the ship and damage control sys-

tems after fire.

The five steps are supported by the integrated functionalities al-lowed by the IPMS and the DCS of the ship. In particular, the KDSSdeveloped has a direct impact on steps 3 and 4. In the first step, thesensors installed in the compartment concerned with the firetransmit an alarm or warning message which is visible in the sum-mary area of the kill card interface. The operator can thus immedi-ately become aware of the emergency.

In step two, the system allows the operator to visualize whichcompartment is concerned and which is the seriousness of dam-age. These analyses are supported by different visualization op-tions of the compartment and the use of a zoom feature and redsigns on the interface (in Fig. 5 a red box in the ship layout indi-cates the compartment where fire has started). Besides, devicesand sensors acquire quantitative measures (e.g. temperature, pres-sure, CO2 level, etc.) which are sent to the system for real-timedamage evaluation.

After that, the operator can start a set of preliminary actions (step3) aimed to contain and control the effects of fire. At this purpose,the operator access the kill card database to retrieve the specific killcard of the compartment concerned with the fire. In fact, this killcard will indicate the list of actions suggested by the KDSS (on thebasis of the knowledge model underlying the system) to resolvethe problem. An example of action list in case of fire is the following:(1) close ventilation; (2) preserve watertight integrity; (3) maintainvital systems; (4) isolate, prevent, extinguish, combat and removethe effects of fire; (5) facilitate the care of personnel casualties;and (6) make rapid repairs to the ship’s structure and equipment.

The operator can then activate the damage control systems andcrew (step 4) to prevent further damage and limit current issues.

Fig. 5. Kill card windows in t

For example, the operator can monitor the status of devices andcontrol remotely pumps and fans which are present at the firescene. Then, he/she can assemble the damage control task forceand execute the secondary action plan with the purpose to com-pletely extinguish the fire.

When the alarm status is over, the operator can then reconfig-ure and restore the ship and damage control systems. Throughthe remote control functionalities of the KDSS, the sensors and de-vices, as well as all the action lists turned on can be reset and madeready in case of a new emergency.

The fire fighting case, along with other damage managementscenarios, was created to test the behavior of the crew and the sys-tem through the damage management process. To validate theKDSS, we used indeed a combination of technical, empirical andsubjective methods (Adelman, 1992; Borenstein, 1998; Papamichail& French, 2005). We realized a technical validation by cross-check-ing the information retrieval and visualization output obtainedfrom different damage control stations onboard, with a specificattention to the consistency of data obtained and knowledgesources used. In particular, we ascertained that all the MFCs onboard show the same data to the different damage controloperators.

We obtained empirical validation through simulations aimed toverify the correct functioning of the tool and measure its perfor-mance as enhancer of the decision making and action process. Acombination of outcome and process criteria is in fact highly rele-vant for DSS evaluation (Phillips-Wren, Hahn, & Forgionne, 2004).Empirical validation was strictly linked with the subjective assess-ment obtained with user confirmation about the benefits/utilityand usability of the tool. At this purpose, we interviewed the shipdamage officer and operators to understand if the system meetsthe needs of users and how well the interface was designed.

We have also measured the benefits allowed by the DSS on thebasis of four critical metrics and four qualitative indicators. Metricsmostly refer to the impact in terms of user and damage controlprocess performance and include: (1) awareness time, i.e. the aver-age time needed by the damage control operator to acquire situa-tion awareness after that a damage event happens; (2) action time,

he fire fighting scenario.

Table 1Indicators and benefits allowed by the KDSS.

Indicator Without KDSS With KDSS

Awareness time 15 min 1 minAction time 45 min 15 minCrew need 5 Operators 2 OperatorsAction cost 112,5$ 15$Navigability Not allowed Hypertexts and function treesMultimediality Not allowed Audio/videoInformation

sharingDocs, phone, meetings MFCs

Interoperability Not allowed Integrated DCS

8210 F. Calabrese et al. / Expert Systems with Applications 39 (2012) 8204–8211

i.e. the average time needed to activate the key procedures to solvethe problem or reduce the damage; (3) crew need, i.e. the averagenumber of total crew members required to act throughout thewhole damage handling process; (4) action cost, i.e. the averagecost for the complete end-to-end decision and action procedure.

Qualitative indicators refer to system features in terms of: (1)navigability, i.e. the direct and fast access to single functions ofthe tool; (2) multimediality, i.e. the possibility to integrate differentforms of information visualization and human–system interactiontools; (3) information sharing, i.e. the availability of the same dam-age information and actions status at the different control posi-tions onboard; and (4) interoperability, i.e. the integration ofdifferent software applications with effects which are immediatelyimplemented within the different tools.

Table 1 reports a comparison of indicators in the ‘‘withoutKDSS’’ and ‘‘with KDSS’’ scenarios. ‘‘Without KDSS’’ values are aver-age measures reported by navy personnel involved in damagecontrol operations whereas after-implementation values (‘‘withKDSS’’) derive from a preliminary estimation based on simulationsand managerial/operator validation at the utilization site.

The situational awareness time is about 15 min without the sys-tem. In fact, a visible damage or problem in a ship system or com-partment activates the internal crew communication processthrough which the warning message is received by the damagecontrol operator. The use of kill cards connected with sensorsand cameras allows to reduce such time to few seconds (and lessthan 1 min) needed by the operator to visualize the automaticwarning message on the screen (with an improvement of about93%). The damage action time can be decreased from 45 to about15 min (improvement of 67%), as the operator can now immedi-ately start a set of corrective actions directly from the remote ter-minal unit and there is no need to be physically present at thedamage site. The KDSS provides the operator with a kill card whichsynthesizes all the information and knowledge critical to success-fully handle the problem. Naturally, damage action time representsa very critical measure for the safety of personnel and the survivalof vital ship systems.

Concerning crew need, five persons are needed on average in thedamage control staff to handle the situation from end to end. In thewith-KDSS scenario, only two persons (60% decrease) are requiredto use the interface and support the overall damage recognitionand recovery action process. As a consequence of reduction in ac-tion time and crew need, the total action cost related with theemployment of specialized crew (materials, resources consump-tion and other costs are thus left out in this calculation) can benow reduced from 112,5$ to about 15$, with a reduction of about87% (we made an assumption of 30$ for the average hour cost of adamage crew member). Moreover, the automation of routine ac-tions allows to further improve the performance of damage controloperations since the overall efficiency of operations is increasedand damage personnel can be involved in value added activitiesconnected with damage control or other tasks related with ship-board management.

Concerning qualitative benefits, navigability, multimediality,information sharing and interoperability are new features allowedby the KDSS and the integrated damage control platform. Naviga-bility of the tool is supported by the use of hyperlinks and functionnavigation trees. The system allows some multimedia featureswith audio and video signals directly coming from ship compart-ments. Information sharing, which was based on exchange of doc-uments, physical meetings and phone calls, is now supported bythe direct communication among the Multi-Function Consoles(MFCs) on board. Finally, the system also supports interoperabilityas the IPMS, the modules of the DCS and the KDSS are fully inte-grated and can be customized based on user needs andrequirements.

6. Conclusions

The identification and management of events that may lead toshipboard damage and crew danger are interesting areas of appli-cation for expert and decision support methods and tools. Na-tional navies around the world are in fact turning to enhancedand distributed damage control systems to achieve higher levelof security and operational efficiency through effective informa-tion sharing, fast problem identification and action planning andautomation.

In this paper, we have presented a knowledge based DSS whichuses design time and run time knowledge sources to streamlinethe decision making process and sequence of actions required tothe damage control operator in case of emergency. The system re-duces situational awareness time, action time, crew need and over-all action cost. The KDSS also allows full navigability of damagecontrol information, the use of multimedia tools for damage mon-itoring, the interoperability with other DCS applications, and amore effective information sharing. The dedicated displays on-board enable the operators to immediately identify the emergencyand initiate corrective actions. The ship-wide data network allowsseveral dispersed damage stations to retrieve coherent informationand thereby effectuate a coordinated and effective action, resultingin reduced damage control response time, enhanced consistency ofactions, and reduced manning.

The use of the application developed could be enlarged to othercontexts (e.g. building sites, nuclear and other energy productionsites) where the monitoring of risky events in different compart-ments or operation areas requires advanced control and decision/action support technologies. In such cases, the KDSS can be of valueto increase the situational awareness of damage crew membersand enhance data consistency through the use of automatized con-trol devices for the remote identification of risks.

Next research will be addressed to extend the application of theDSS for training purposes, and in particular for on-the-job trainingof damage crew members. The onboard training system of the shipcould be indeed used to simulate events in normal ship operationas well as in degraded conditions using the same interface. A sec-ond area of development is represented by the adoption of en-hanced reality and 3D technologies and functionalities within thesystem. This could further enhance the situational awareness ofoperators and their ability to promptly identify and assess theproblem, resulting in faster and more effective actions.

Acknowledgments

The authors are grateful to the persons at Avio SpA who havecollaborated in the design and implementation activities. A partic-ular acknowledgment goes to Marco Rosso for his support in the fi-nal revision of the article.

F. Calabrese et al. / Expert Systems with Applications 39 (2012) 8204–8211 8211

References

Adelman, L. (1992). Evaluating decision support and expert systems. New York, NY:Wiley.

Arbel, A., & Tong, R. (1982). On the generation of alternatives in decision analysisproblems. Journal of the Operational Research Society, 33, 377–387.

Arendt, R. (2004). The application of an expert system for simulation investigationsin the aided design of ship power systems automation. Expert Systems withApplications, 27(3), 493–499.

Arendt, R., & van Uden, E. (2011). A decision-making module for aiding ship systemautomation design: A knowledge-based approach. Expert Systems withApplications, 38(1), 410–416.

Barai, S. V., & Pandey, P. C. (2000). Integration of damage assessment paradigms ofsteel bridges on a blackboard architecture. Expert Systems with Applications,19(3), 193–207.

Beroggi, G. E. G., Waisel, L., & Wallace, W. A. (1995). Employing virtual realitytechnology to support decision making in emergency management. SafetyScience, 20(1), 79–88.

Bøgh, S. A., & Severinsen, T. (2009). Damage management control system on theDanish navy ships. In Proceedings of the 14th international ship control systemssymposium (SCSS). Ottawa, Canada.

Bonczek, R. H., Holsapple, C., & Whinston, A. B. (1981). Foundations of decisionsupport systems. New York, NY: Academic Press.

Borenstein, D. (1998). Towards a practical method to validate decision supportsystems. Decision Support Systems, 23(3), 227–239.

Bulitko, V. V. & Wilkins, D. C. (1999). Automated instructor assistant for shipdamage control. In Proceedings of the 16th national conference on artificialintelligence. Orlando, FL: American Association for Artificial Intelligence.

Caro, D. H. J. (1992). Expert support systems in an emergency managementenvironment – An evaluative framework. Educational and Training TechnologyInternational, 29(2), 132–142.

Cebi, S., Celik, M., Kahraman, C., & Deha Er, I. (2009). An expert system towardssolving ship auxiliary machinery troubleshooting: SHIPAMTSOLVER. ExpertSystems with Applications, 36(3), 7219–7227.

Chou, Y.-C., & Benjamin, C. O. (1992). AI-based decisions support system for navalship design. Naval Engineers Journal, 104(3), 156–164.

Cosby, L., & Lamontagne, Y. (2006). Critical assessment of damage control systemtechnologies. Defence R&D Canada Report.

Fagerholt, K. (2004). A computer-based decision support system for vessel fleetscheduling – Experience and future research. Decision Support Systems, 37(1),35–47.

Geer, D. (1988). Advanced damage control systems. Naval Engineers Journal, 100(3),143–153.

Grabowski, M., & Wallace, W. A. (1993). An expert system for maritime pilots: Itsdesign and assessment using gaming. Management Science, 39(12), 1506–1520.

Jiang, S.-F., Zhang, C.-M., & Zhang, S. (2011). Two-stage structural damage detectionusing fuzzy neural networks and data fusion techniques. Expert Systems withApplications, 38(1), 511–519.

Kanno, T., & Furuta, K. (2006). Modeling and simulation of inter-and intra-organizational communication and coordination in emergency response.International Journal of Emergency Management, 3(2–3), 149–167.

Kowalski, Z., Arendt, R., Meler-Kapcia, M., & Zielnski, S. (2001). An expert system foraided design of ship systems automation. Expert Systems with Applications,20(3), 261–266.

Kowalski, Z., Meler-Kapcia, M., Zielinski, S., & Drewka, M. (2005). CBR methodologyapplication in an expert system for aided design ship’s engine roomautomation. Expert Systems with Applications, 29(2), 256–263.

Lee, D.-K. (1999). Hybrid system approach to optimum design of a ship. ArtificialIntelligence for Engineering Design, Analysis and Manufacturing: AIEDAM, 13(1), 1–11.

Lee, K.-H., & Lee, K.-Y. (1997). Knowledge-based nonmonotonic reasoning process inship compartment design system. Expert Systems with Applications, 13(2),145–154.

Lee, D., & Lee, K.-H. (1999). An approach to case-based system for conceptual shipdesign assistant. Expert Systems with Applications, 16(2), 97–104.

Mehrjoo, M., Khaji, N., Moharrami, H., & Bahreininejad, A. (2008). Damage detectionof truss bridge joints using artificial neural networks. Expert Systems withApplications, 35(3), 1122–1131.

Mendonca, D. (2007). Decision support for improvisation in response to extremeevents: Learning from the response to the 2001 world trade center attack.Decision Support Systems, 43(3), 952–967.

Minciardi, R., Sacile, R., & Trasforini, R. (2007). A decision support system forresource intervention in real-time emergency management. InternationalJournal of Emergency Management, 4(1), 59–71.

Papamichail, K. N., & French, S. (2005). Design and evaluation of an intelligentdecision support system for nuclear emergencies. Decision Support Systems,41(1), 84–111.

Park, J.-H., & Storch, R. L. (2002). Overview of ship-design expert systems. ExpertSystems, 19(3), 136–141.

Peters, S., Bratt, E. O., Clark, B., Pon-Barry, H., Schul, K. (2004). Intelligent systems fortraining damage control assistants. In Interservice/industry training, simulation,and education conference (I/ITSEC).

Phillips-Wren, G. E., Hahn, E. D., & Forgionne, G. A. (2004). A multiple-criteriaframework for evaluation of decision support systems. Omega-InternationalJournal of Management Science, 32(4), 323–332.

Runnerstrom, E. (2003). Human systems integration and shipboard damage control.Naval Engineers Journal, 115(4), 71–80.

Simoes-Marques, M. J., & Pires, F. J. (2003). SINGRAR – A fuzzy distributed expertsystem to assist command and control activities in naval environment.European Journal of Operational Research, 145(2), 343–362.

Tate, D. L. (1996). Development of a tactical decision aid for shipboard damage control.NRL, Report NRL/FR/5580-96-9837.

Turoff, M., Murray, C., de Walle, B. V., & Yao, X. (2003). The design of a dynamicemergency response management information system (DERMIS). Journal ofInformation Technology Theory and Application, 5(4) [article 3].

Ubeyli, E. D., & Ubeyli, M. (2009). Estimation of radiation damage at the structuralmaterials of a hybrid reactor by probabilistic neural networks. Expert Systemswith Applications, 36(3), 5184–5189.

Varela, J. M., & Guedes Soares, C. (2007). A virtual environment for decision supportin ship damage control. IEEE Computer Graphics and Applications, 27(4), 58–69.

Zografos, K. G., Androutsopoulos, K. N., & Vasilakis, G. M. (2002). A real-timedecision support system for roadway network incident response logistics.Transportation Research, 10(1), 1–18.