duminică, 28 septembrie 2014



Safety at the workplace is one of the essential concerns of every worker, supervisor and enterprise manager. Our research was focused towards improving safety at the workplace through a better safety knowledge management. We have designed a safety knowledge management system (SaKnoMaS) which includes a safety knowledge map that will disseminate the resources towards the main components of the workplace system. The obtained  results are spectacular in a sense of way. Our prototype solution  improves safety and health at workplace with more than 30% through a better safety knowledge management.

Keywords: Safety knowledge management, safety knowledge map, risk reduction


Safety at the workplace is one of the essential concerns of every worker, supervisor and enterprise manager. However, safety understanding and implementation is very different. Safety, from the worker’s point of view is different from managerial safety image. Also, an external observer could have a very different safety image than the inside one. This difference of opinions is not necessarily bad. But when it  interferes with  an optimal safety assurance there could be problems.
In risk prevention knowledge is essential[1]. Simple information is not good enough. Knowledge in order to perform optimally and safely is a need. This knowledge must:

  • Show what to do;
  • Show how to do;
  • Show why to do so;
  • Safety culture;
  • Safety motivation;
  • Specific tasks;
  • Acquirement of knowledge- through elicitation tools like Acquire;
  • Internal representation of knowledge- there was sought a solution to optimize the old representation through knowledge rules; representation through knowledge rules is optimal  generally; an object oriented approach was considered as the best solution for optimization from this point on- so , the internal representation of knowledge was performed in the shape of knowledge objects.
  • Tailoring the knowledge in order to perform optimally for the safety domain- general knowledge could be a bit not prepared to solve specific safety problems. So , there is a need for safety knowledge that will allow the efficient solving of specific problems;
  • Storage of knowledge resources for further usage; the ideal storage solution was found in the form of knowledge seeds; knowledge seeds are roots of knowledge bases that can be further developed interactivelly through the users contribution; the next figure presents this solution;
  • Knowledge dissemination; we considered that the whole workplace could be used as a safety knowledge disseminator, partly through clasical means (posters, etc.) partly through ambiental friendly knowledge systems. In this respect we have developed portable disseminators, based on devices like PDA’s or Pocket PC’s.
  • If there is any need for supplemental knowledge;
  • What kind of knowledge is needed;
  • If the knowledge management process is performed;
  • If the knowledge management process is optimal or could be improved;
Not know
1.Do you have sufficient knowledge in order to avoid risks at workpace ?

Specific risks at workplace:
2.Do you have necessary and sufficient knowledge in order to perform the current activities ?

Current activities being performed:
3.Do you have the necessary and sufficient knowledge in order to perform usual activities ?

Usual activities being performed:
4.Do you have sufficient knowledge in order to use the existing workplace tools and devices ?

Most usual workplace tools and devices:
5.Do you have the necessary knowledge in order to perform maintenance activities ?

Current maintenance activities:
6.Do you have the necessary knowledge in order to perform first help and emergency activities ?

First help and emergency activities:
Not know
1.Do you have the necessary knowledge in order to perform current supervisory activities ?

Current supervisory activities:
2.Do you have the necessary knowledge in order to perform current workplace management activities ?

Current workplace management activities:
  • Acquirement of new knowledge- 22% of the intervieved persons have no such knowledge;
  • Improvement of the existing knowledge- 30% of the intervieved persons had just summary maintenance knowledge.
  • Development of new knowledge;
  • A safety knowledge assessment system;
  • A safety knowledge acquirement and processing system;
  • A safety knowledge dissemination system;

Knowledge could be the difference between a severe accident and 100% safety. Knowledge could also be the difference between loss and an optimal functioning of the enterprise.
Why knowledge ? Because knowledge could be seen as the cheapest safety resource. Knowledge is plenty through the trial and error everyday work experiences.
But knowledge is also a very expensive thing. Specific domain knowledge is invaluable. In order to acquire knowledge, to process it optimally (to tailor it according with the specific enterprise needs), to store it (in order to use it lately) or re-use it  and more important to disseminate knowledge among those who need it a knowledge management system is required.
Our research started with this fact, proved through numberless incidents and accidents occurred in Romania and caused by insufficient or improper allocated knowledge.
Through the usage of specific knowledge engineering methods and techniques correlated with safety mastering  procedures it could be defined and developed a better safety knowledge management.
Knowledge management is performed through assessment, prevention and risk reduction, as could be seen in the next figure.

Figure 1 Knowledge management and resource allocation

All those activities must be performed through resource allocation. Resource allocation is the central point of safety management and also of safety knowledge management. Resources allocated optimally could avoid economic loss, incidents and accident minimizing also the costs of prevention.
Knowledge could also improve safety attitudes, as shown in the next figure.
Some very important improvements could be obtained through mediated safety knowledge management from characteristics like:

Figure 2 Knowledge management and the improvement of human operator safety attitudes

So, the management of the knowledge resource could play a central part in the prevention game[2].
Knowledge resource is relatively cheap[3], at hand, easy to acquire and process. Used optimally it could be a definite asset in avoiding occupational incidents and accidents.
Unifying the safety vision in order to assure an united safety image for all the players at the workplace could also be obtained through knowledge management.
So, taking into account all these aspects and our previous research towards the safety knowledge engineering, we decided to start a research project focused on safety knowledge management.
Our research was focused towards improving safety at the workplace through a better safety knowledge management. This management, based on the knowledge engineering concept, could assure a unified safety vision, beneficial for everyone implied in the process.


In order to be able to process knowledge, there must be used techniques and methods connected with knowledge engineering[4].
Methods specific to knowledge engineering are used along the whole life cycle of  knowledge management. The next image presents the most significant aspects of knowledge management through knowledge engineering techniques, starting with safety knowledge acquirement and ending with knowledge dissemination.

Figure 3 Steps in knowledge management through 
knowledge engineering

Generally, expert tools were used in order to :

Figure 4 Knowledge storage structure

We have started our research with the goal to find the safety knowledge needs at  some specific workplaces. We have asked questions like : is there enough knowledge in order to perform safely a certain task ? Has the manager/supervisor of the workplace/worker the appropriate knowledge to do this or that ?
From these questions we have developed a knowledge management checklist which is used as a front for our Safety Knowledge Management System (SaKnoMaS).
The general SaKnoMaS schema is presented in the next figure.

Figure 5 SaKnoMaS general structure

It could be seen that the first step towards the management of safety knowledge at the workplace is represented by the assessment of the existent safety knowledge. This assessment is performed in order to know:
This knowledge assessment is performed on a threefolded structure:
·         On the first level the knowledge assessment is performed at the floor level of the enterprise, asking the workers;
·         On the second level, the knowledge assessment process is performed at the supervisor level- this level will give an image from the point of view of qualified workers;
·         On the third level, the knowledge assessment process is performed at the management level; this management level is the view from the top

Our system maps knowledge on the desired targets, as could be seen in the figure below.

Figure 6 SaKnoMaS and USKF

Our system is also a three leveled system.
On the first level there is the safety knowledge assessment system[5]. This system performs assessment on existing safety knowledge and establishes the need for supplemental safety knowledge and also the knowledge cathegories needed.
On the second level there is the processment and storage system- composed as stated before by a network of interactively developable knowledge bases.
On the third level there is the knowledge dissemination system [6]that allows the optimal dissemination of knowledge through tose implied in the work process.
All these systems are controlled by a control system.
Two examples from our knowledge assessment are presented below.


The developed prototype for the safety knowledge assessment component of the system was applied for 300 enterprises in the construction and  electric domains, in order to catch and analyse the knowledge needs.The checklists were modified in order to use a 1(most unfavourable) to 6(most favorable) scale of assessment. This scale is more precise than a yes-no one.
We think that some results are interesting from the need of knowledge point of view.Some of these most interesting results are presented graphically below.

a)Knowledge regarding existing risks at the workplace
This is one of the most important things in order to assure safety at workplace- to know what are the risks that are specifically acting there.

  Figure 7 Risk knowledge

As shown in figure a percent of 48% of the intervieved specialists have not the necessary knowledge in order to optimally identify and assess risks at the workplace.
Here, the usage of  SaKnoMaS is a primordial necessity with an essential need of a massive risk knowledge import from authorised sources.This import could be performed from risk assessment qualified sources.

b)Assessment of safety knowledge regarding current activities

Current activities are performed everyday and are the main work being done at the workplace. Current activities are important because about 75% of the incidents and accidents at workplace are occuring in current activities.
Current activities could be efficiently supported by knowledge.

Figure 8 Current activities knowledge

From this figure it could be seen that about 28%  percent of the intervieved workers had just a mediocre knowledge regarding the safety in current task that they perform. In this case SaKnoMaS could act as a knowledge improver and knowledge developer through the betterment of dissemination procedures.
SaKnoMaS could update the existing knowledge through new knowledge sources. Also, it could assure necessary hyperlinks to external knowledge sources.
SaKnoMaS could also consolidate knowledge in order to inprint this knowledge in the worker’s mind.
c)Assessment of  safety knowledge regarding maintenance

Figure 9 Maintenance knowledge needs

Here SaKnoMaS could help towards:
As stated before we have developed our system modularly, taking into account the need to:
·         Assess knowledge;
·         Acquire and process knowledge;
·         Disseminate knowledge; the system is conceived in order to run on IBM-PC and also on pocket devices like tablets or mobiles.
 An image of the SaKnoMaS running on a mobile  is presented in the figure below.

Figure 10 SaKnoMaS running on a Pocket PC


Knowledge is an essential asset in risk prevention and safety assurance at workplaces. Knowledge could be tailored in order to focus on specific problems at workplace.
Knowledge management could be a usefull instrument in managing this resource, assuring the necessary knowledge in the right place at the right time.
This paper present some highlights from a research developed inside the Romanian National Research Institute for Occupational Safety in the period 2001-2005.
This research was targeted towards the development of a efficient safety knowledge management system. This system is a need for every enterprise in order to optimise its safety state.
Till now there was developed a prototype containing three distinct systems:
The research continues towards the full development of this system.

[1] G.Arnold,R.Roane,Safety,Health and Environmental Management- a practitioner’s guide, International Risk Management Institute, 1998
[2] D.Petersen, Techniques of Safety Management (A systems Approach),Goshen NY,Alloray Inc, 1989
[3] I.Masaaki,Kaizen,Ney York Random House Buisness Division, 1986
[4] T.Kletz,Lessons from Disasters, Institute of Chemical Engineers
[5] T.Ferry,Safety and health management planning, New York,N.Y.Times Book 1982
[6] R.C.Grote,Bringing about a system change, Performance System Corporation, Dallas, 1989

sâmbătă, 27 septembrie 2014



Expert systems are intended to solve problems in difficult, unstructured domains, where knowledge guides the expert reasoning.
The paper presents an expert based approach to the problem of risk assessment at various work places, underlying the advantages in using expert system methods and techniques to deal with risk identification and evaluation.

Classic risk assessment

At the work place we should consider in the risk assessment process, the man-machine system with its four components, the human operator, the task, the machine and the working environment. An efficient risk assessment must study all these components and also their interaction that results in the activity being done at the work place.
However, the majority of risk assessment systems are centered on the machine. There are some reasons for that approach, considering the great subjectivity of human risk assessment. The programs that are implementing these methods could be called classical programs, having a pre-defined algorithm to perform the risk assessment. This classic, machine-centered approach is not very suitable in many cases, especially where the man generated accidents are prevailing.

Expert systems and their applications to risk assessment

What is an expert system?

Expert systems are programs that offer advice or solve problems by reasoning with volumes of knowledge highly specific to a particular domain. The activity of designing and implementing expert systems is known as knowledge engineering.
A general structure of an expert system is presented in the following figure.

Figure 1 General schema of an expert system

Why an expert approach?

Risk assessment is a very important process, regarding the safety and health of many workers. A well done risk assessment process could lead to significant improvements not only just to the work conditions but also to the efficiency of the work.
Considering the core of the risk assessment process at the work place, it is mainly an expert job. The human expert identifies specific risks, is giving them severity and probability weight and is proposing measures to reduce risks at ALARP levels or simply eliminate them. Risk assessment is not a repetitive process; the work place conditions are unique. So, indifferent of how performing are classic assessment programs, indifferent of the complexity of the implemented assessment method (Hazop, FMEA,FMECA, or other such like) they could not perform expert tasks regarding risk assessment but just the repetitive and monotonous part of the process.

What could an expert system do regarding risk assessment?

Having established that risk assessment is mainly an expert approach we could see the expert system as an integrator and also as an assistant to the human assessor .The expert system could:
-analyze and logically validate the results obtained by running machine centered assessment methods;
-interpret the obtained results considering the global picture of the work place being assessed;
-perform an objective assessment for the human component at the work place;
-generate risk models and use these models to predict risk development for short and medium prognosis;
-integrate all these pieces in a single view and use this view to develop prevention plans so to reduce risks at ALARP levels or just eliminate them ; the next figure presents a general schemata of a risk assessment expert system.

Figure 2 General schema of an expert risk assessment system

Expert elements in risk assessment

Machine risk assessment

There are many programs that perform more or less efficiently machine risk assessment, using a variety of assessment methods centered on the machine component
The classic assessment methods are centered mainly on the machine, giving little importance to the external risk sources[1]. But, in many situations, the external risk sources (such as environment conditions, task design, and task execution) are triggers to incidents and accidents. So, for the correct image of risks at the work place, there must be analyzed all the chained components of the man-machine system. Classical programs are not doing this-an expert system may perform this analysis.
Also, the expert system may quantify the obtained results into significant cases that would simplify further similar assessments:
-by using the obtained results as a case oriented knowledge source and simply cross-check these results against the real situation, instead of performing again all the assessment process which can be very time consuming;
-by working as an example for similar assessments;
The expert system could work assisted by the human specialist to develop such cases and put those cases into a specific case base. For example, results for similar work places must be somehow similar; giving a similarity check-list for a specific machine, such a check-list could be quickly cross-checked against the real situation and established if the case and the real situation are perfectly matching, partially matching or if there are singularity points that must be analyzed separately.
Also, having the risk assessment results, the expert system could develop and run scenarios that will predict risk trends over a period of time, considering various degree of intervention towards preventing risk effects. These scenarios could be very efficient in developing and prioritizing prevention measures.
Using its learning mechanism the expert system could also improve the machine risk assessment process, mainly in his primary parts, establishing the data that will be collected and processed.
To sumarize, in the machine risk assessment process, the expert system can action as an assistant to the human specialist and also as an improver of the assessment results and as a predictor of risk trends.

Human operator assessment 

The problem of human operator assessment from the risk point of view is a crucial one. Most of the occupational accidents have as their principal cause human operator failures and mistakes.[2].The principal problem with the risk assessment methods regarding human operator is their subjectivity degree combined also with the environment and task influence. A checklist results will be influenced by the operator’s self-perception, stress and so on. In establishing a decent and objective human risk assessment a very important role can be played by corporate specific memories regarding the human operator (mode of behaviour, incidents, accidents, capacity to work alone/to work inside a team, etc.).For a specific operator, these memories could be invaluable-generally, an operator that performs badly a task and is not corrected will be performing in the same way, till an incident is happening. Defining best work procedures and checking up the real activity against these procedures could be another objective assessment factor.[3].
Based on expert system techniques, it is possible to define, inside expert assessment system behaviour models (based on best work procedures and also on normal work condition and physiologic paramethers) and follow the real situation by cross-checking the actual behaviour of human operators against these models. The over-passing of model defined thresholds could be alarm signals and could lead to the stop of machines and of the whole process, so that the human operator will not be hurt.
The human operator assessment may be modeled by belief networks that will define, regarding the human operator, believed relations (uncertain, stochastic, and imprecise) between sets of risk relevant variables to build patterns toward the birth and development of human operator related risks.
Belief updating may be done for each new assessment, by:
-new cases;
-mistake-the learning from trial and errors;
-new beliefs;
The expert system may infere new beliefs from the already existing knowledge and also may check the beliefs against the real situation.

An expert approach to risk assessment

An integrated expert approach to the risk assessment problem will be developed around the expert system methods for solving specific problems. It will use a goal-oriented strategy, choosing a goal (to exactly and correctly identify the risks at work place and to establish the optimum prevention plan for the risks being identified) and attempting to achieve it.
It is difficult to think of a universal expert system[4] that will be able to assess every risk in every industrial domain, regardless of the specific activities, machinery and so on.
A better approach would be, in this aspect, to imagine a dual expert system, with an external knowledge base, containing risk assessment methods and also significant cases and an internal, corporate specific knowledge base, which will contain the internal knowledge required to perform an efficient risk assessment.
This internal knowledge base (IKB) will be based on corporate knowledge and will act partly like a corporate safety memory[5] . IKB will be a guide for the external risk auditing system, having captured and updated inside the significant aspects that deserve study. It will also preserve safety events inside the corporation and will be a source of lessons for safety specialists[6] in learning from the past mistakes and improving safety at the work place.
A possible design for such a base is shown in the next figure.

Figure 3-Possible design for Corporate Internal Knowledge Base

Generally, the risk assessment problem could be interpreted as a search problem[7] in which a solution must be found in a state space pool.
This search may be optimized using heuristic evaluation functions H(x)[8].How does a heuristic evaluation function work? By asigning to each significant risk state x an estimate of the minimum cost to reach the goal state-in our case the definition of the subsequent risk. With such a function available, all we have to do in order to obtain efficient risk identification will be to sort the found risk list according to H(x).H(x) is only an estimator. To make it a predictor it must be done to search exhaustively the state space. The risk identifying performance varies directly with the accuracy of the heuristic evaluation function. So, if

 H(x) =d   [1] 

where d is the true remaining distance to the nearest risk identification for all the risk states x, then, the search is optimal[9]. If 

H(x) =1/d [2]

 the search will always find the goal node last, after exploring the entire state space. The perfect heuristic function, which will lead to perfect balance between the assessment costs (g (x) and assessment results H (x), could be defined using the following equation

H(x) =H’(x) for all risk state spaces x [3

We could also define a cost-results function

 f(x) =g(x) +H(x) [4]

The optimal path to the risk identification, called P, must be perfect regarding the balance assessment costs/assessment results. So, we could write

H’ (P) =0   [5]

 and also
 f (P) = g (P) +0 [6]

and the estimate of P costs turns out to be perfect-the real cost


As presented before, expert approach could improve the risk assessment for the machine and  lead to an objective and efficient assessment regarding the human operator, giving also a global risk view  for the work place,.It takes  into account also the task and the working environment.
In risk assessment, the expert approach could give:
-a reality approach evaluation, considering the corporate internal memories of past events and also the expert internal capability of the corporation being assessed;
-optimum prevention solutions, arranged in order of their efficiency;
-a efficient and optimized assessment;
-reduced assessment costs, time and resources;
There are also some problems. Expert based assessment using cases as an assessment base may lead to misjudgements in case of singularities existence. Also, expert based assessment needs expert knowledge which, in some situations may be very expensive.
We have realized some progress towards the development of efficient expert tools for risk assessment, some of our results being presented at various international scientific congresses. One primary research direction was the development of tools for human operator assessment from the risk/safety point of view.[10]  [11].We hope that in the future, with a consistent international co-operation, to be able to launch an expert system for risk assessment as soon as 2015.


[1] Siu N.-Risk assessment for dynamic systems-an owerview-in Reliability Engineering and System Safety 60, pg.153-164,1994
[2] Rasmussen J.-Major accident prevention:what is the basic research issue ? in Safety and Reliability (eds:Lydersen and others),Balkema,Rotterdam, pg.739-740,1998
[3] Reason J.-Human error,Cambridge University Press, 1990
[4] „A new duty to investigate accidents”,HSE Consultative document CD 169
[5] T.A.Kletz-Accident investigation-missed opportunities-keynote paper at the Hazards XVI-Analysing the past, planning the future symposium, Manchester, 2001,pg.1-12
[6] Dr.J.Bond-A Janus approach to safety--keynote paper at the Hazards XVI-Analysing the past, planning the future symposium, Manchester, 2001,pg.13-23
[7] K.Pearl-Heuristics:Intelligence search strategies for computer problem solving, Bantam, 1997
[8] J.Nilsson Problem solving methods in AI, McMillan Books, 1996
[9] Benjamin R.jr.,Dinamics of job evaluation,in Management Review nr.42,pg.190-194,April 1993
[10] Ph.D.Stefan Kovacs and others-Human operator assessment-basis for a safe work place in the process industry, Hazards XVI Proceedings, Symposium series no.148,ISBN 85295-441-7, pg.819-832.
[11] Ph.D.Stefan Kovacs-Expert systems in risk assessment, SafeCon Proceedings, Athens, 2000