A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Development of hybrid optimisation method for Artificial Intelligence based bridge deterioration model — Feasibility study
Abstract Bridge Management Systems (BMSs) are a common tool for bridge management to extend the life cycle of bridge networks. However, the reliability of current BMS outcomes is doubtful. This is because: (1) Overall Condition Rating (OCR) method cannot represent individual bridge elements’ condition and is unable to represent condition ratings of bridge elements in lower Condition States and due to (2) insufficient historical bridge records available. A long-term Performance Bridge (LTPB), i.e. deterioration, model is the most crucial component and decides level of reliability of long-term bridge needs. Recent development of an AI-based bridge deterioration model was undertaken to minimise these shortcomings. However, this model is computationally costly due to the process of Neural Network, generating a large data output. To improve the neural network process, optimisation is required. The hybrid optimisation method is proposed in this paper to filter out feasible condition ratings as input for long-term prediction modelling.
Highlights ► A comparison of bridge deteriorations, one with optimisation and the other without. ► The optimisation is a hybrid method of case-based reasoning and genetic algorithm. ► The outcome provided sufficient data that proved the optimisation was effective.
Development of hybrid optimisation method for Artificial Intelligence based bridge deterioration model — Feasibility study
Abstract Bridge Management Systems (BMSs) are a common tool for bridge management to extend the life cycle of bridge networks. However, the reliability of current BMS outcomes is doubtful. This is because: (1) Overall Condition Rating (OCR) method cannot represent individual bridge elements’ condition and is unable to represent condition ratings of bridge elements in lower Condition States and due to (2) insufficient historical bridge records available. A long-term Performance Bridge (LTPB), i.e. deterioration, model is the most crucial component and decides level of reliability of long-term bridge needs. Recent development of an AI-based bridge deterioration model was undertaken to minimise these shortcomings. However, this model is computationally costly due to the process of Neural Network, generating a large data output. To improve the neural network process, optimisation is required. The hybrid optimisation method is proposed in this paper to filter out feasible condition ratings as input for long-term prediction modelling.
Highlights ► A comparison of bridge deteriorations, one with optimisation and the other without. ► The optimisation is a hybrid method of case-based reasoning and genetic algorithm. ► The outcome provided sufficient data that proved the optimisation was effective.
Development of hybrid optimisation method for Artificial Intelligence based bridge deterioration model — Feasibility study
Callow, Daniel (author) / Lee, Jaeho (author) / Blumenstein, Michael (author) / Guan, Hong (author) / Loo, Yew-Chaye (author)
Automation in Construction ; 31 ; 83-91
2012-11-07
9 pages
Article (Journal)
Electronic Resource
English
AI , Artificial Intelligence , ANN , Artificial Neural Network , BMS , Bridge Management System , BPM , Backward Prediction Model , CBR , Case-based Reasoning , CS , Condition State , GA , Genetic Algorithm , lr , learning rate , LTPB , Long-term Performance Bridge , mc , momentum coefficient , MLP , Multi-layer Perceptron , MR&R , Maintenance, Repair and Rehabilitation , NNFIR , Neural Network Finite Impulse Response , OCR , Overall Condition Rating , TDNN , Time Delay Neural Network , Bridge Management System (BMS) , Long-term Performance Bridge (LTPB) , Artificial Neural Network (ANN) , Optimisation , Case-based Reasoning (CBR) , Genetic Algorithm (GA)
| British Library Online Contents | 2013
| British Library Conference Proceedings | 2012