Use of the lognormal distribution for the coefficients of friction and wear

To predict the reliability of a system, an engineer might allocate a distribution to each input. This raises a question: how to select the correct distribution? Siddall put forward an evolutionary approach that was intended to utilise both the understanding of the engineer and available data. However, this method requires a subjective initial distribution based on the engineer's understanding of the variable or parameter. If the engineer's understanding is limited, the initial distribution will be misrepresentative of the actual distribution, and application of the method will likely fail. To provide some assistance, the coefficients of friction and wear are considered here. Basic tribology theory, dimensional issues and the central limit theorem are used to argue that the distribution for each of the coefficients will typically be like a lognormal distribution. Empirical evidence from other sources is cited to lend support to this argument. It is concluded that the distributions for the coefficients of friction and wear would typically be lognormal in nature. It is therefore recommended that the engineer, without data or evidence to suggest differently, should allocate a lognormal distribution to the coefficients of friction and wear.