The thesis delves into the area of troubleshooting procedures, an interesting areafor industry. Many products in industry tend to be complex, which in turn makestroubleshooting procedures trickier. A fast and efficient repair process is oftendesired, since customers want the product to be repaired as fast as possible. The purpose of a troubleshooting procedure is to find a fault in a broken product,and to choose proper repair actions in a workshop. Such a procedure can besimplified by diagnosis tools, for example software programs that make faultconclusions based on fault codes. These tools can make such conclusions withthe help of algorithms, i.e. fault tracing algorithms. Before a product release, it is hard to specify all faults and connections in the system.New unknown fault cases are likely to arise after release, and somehow thisneed to be taken into account in the troubleshooting scenario. The troubleshootingprocedure can be made more robust, if new data could be easily incorporatedin the current structure. This work seek to answer how new data can be incorporatedin trouble shooting procedures. A good and reliable fault tracing algorithm is essential in the process of findingfaults and repair actions, which is the reason behind the focus of this thesis. Thepresented problem asks how a fault can be identified from fault codes and symptoms,in order to recommend suitable repair actions. Therefore, the problem isdivided into two parts, finding the fault and recommending repair actions. Inthe first part, three candidate algorithms for finding the faults are investigated,namely Bayesian networks, neural networks, and a method called matrix correlationinspired from latent semantic indexing. The investigation is done by trainingeach algorithm with data, and evaluating the results. The second part consists ofone method proposal for repair action recommendations and one example. Thetheoretical investigation is based on the Servo unit steering (SUS), which residein the IPS system of Volvo Penta. The primary contribution of the thesis is the evaluation of three different algorithmsand a proposal of one strategy to recommend suitable repair actions.In this study Bayesian networks are found to conform well with the desired attributes,which in turn lead to the conclusion that Bayesian networks is well suited for this problem.