This research predicts residual solvent (α), which is a key component of the performance assessment for a sprayed/chip seal. Solvent evaporation from the bituminous binder film of a sprayed seal is too complex and poorly understood to develop a model in a traditional way. In this study, conventional equations for α were assessed that showed prediction inefficiency (R 2 value as low as 0.82) under different experimental conditions. Accordingly, gene expression programming (GEP), an emerging branch in artificial intelligence, was utilised to resolve these difficulties by developing empirical models for α. The data required for model development was obtained from extensive laboratory tests conducted on bitumen-solvent binder films in this research. Model evaluation results showed an excellent degree of correspondence between predictions and experimental results (R 2 = 0.94). This is the first study to model a key component of sprayed seal performance using GEP. The model is recommended for pre-design purposes or as a tool to determine residual solvent in a sprayed seal when laboratory testing is not feasible, thereby saving time and expenditure.

Dr Kwesi Sagoe-Crentsil is an experienced researcher and team leader who has demonstrated excellent leadership in positioning his team and CSIRO Geopolymer research. He is the Deputy Director of Operations of the ARC Nanocomm Hub. Professor Wenhui Duan is the Director of the ARC Nanocomm Hub and an inspiring leader in the field of nanoscience-based construction materials. He has developed an innovative engagement model to motivate public researchers to connect with industry. He is the driving force behind ground-breaking work that delivers significant economic benefit in construction materials, green structures, and infrastructure asset management. A new empirical diffusion model for solvents in sprayed seals based on evaporation measurements Prediction of solvent diffusion and evaporation rate in the initial days after construction of a sprayed seal is of special concern for pavement performance assessment. It is still a major challenge as solvent evaporation is a very complicated process. In this study, laboratory tests were conducted on bitumen-solvent binder films, under different experimental conditions and varying solvent properties. A solution of Fick's diffusion equation was then used to calculate solvent diffusion coefficient (D) values for the initial 7 days. While a strong correlation was found between D and solvent viscosity as well as D and solvent distillation range, no relationship was found between D and solvent aniline point nor aromatic content. These findings were utilized in developing a multiple linear regression (MLR) diffusion model for the initial 7 days of evaporation. The evaluation of the model indicated close agreement between the predictions and experimental values (R 2 = 0.95). The model enables road agencies to predict solvent diffusion and residual solvent for the early life of a sprayed seal without needing to conduct extensive experiments thereby saving time and labour cost. Accurate prediction of residual solvent via the developed model will further ensure long-term performance of sprayed seals.

No abstract