Keywords: bridge rating, durability, load-carrying capability, expert system, fuzzy reasoning, machine learning, multi-layer neural network.

The authors have for some time been developing an expert system, which can be used to evaluate the performance of existing concrete bridges on the basis of knowledge and experience acquired from domain experts. The proposed expert system is called the concrete Bridge Rating EXpert system (BREX). The objective of the expert system is to evaluate the present performance of target bridge members in terms of factors such as load-carrying capability and durability. The input data for rating a concrete bridge are technical specifications of the target bridge, environmental conditions, traffic volume, and other information that can be obtained through simple visual inspection. In the present study, load-carrying capability is defined as the aspect of bridge performance that is based on the load-carrying capacity of a bridge member, and durability is defined as the ability of a bridge member to resist material deterioration and is based on the rate of material deterioration of the member. These two aspects of bridge performance are applied as indices for considering the necessity of performing maintenance on deteriorated bridges. Specifically, load-carrying capability is applied as an index for estimating the necessity of strengthening, and durability is applied as an index for estimating the necessity of repair.

In the expert system, the bridge performance is evaluated according to a diagnostic process, which is modelled on the inference mechanism used by domain experts for rating bridges. In a previous study, the authors used the Fuzzy Structural Modelling (FSM) method[1] to create the diagnostic process of durability and load- carrying capability for main girders and slabs. Each process is expressed by a hierarchical structure and has some judgment items. These judgment items are evaluated by about 90 input data items, such as technical specifications, traffic volume, and results of visual inspection. The ultimate goal of this process is "durability" or "load-carrying capability." The hierarchical structure expresses the relationship between judgment items and input data, such as inspection data and technical specification data, or between judgment items. In practice, these relationships are expressed by "If-then" rules with fuzzy sets, namely, fuzzy rules. Consequently, the fuzzy inference of the expert system is drawn from these rules. Naturally, these rules could be written directly into a computer in a computer language. In this study, however, these rules are implemented in a computer after a set of the rules relating judgment items and input data or relating judgment items is transformed to a Multi-layer neural network. In other words, Multi-layer neural networks identify a diagnostic process[2,3]. The system constructed from the network can easily refine the knowledge base; that is, fuzzy rules, by use of a machine learning method. More specifically, the system refines the knowledge base by applying the Back-Propagation method. The structural characteristic of multi- layer neural network enables the introduction of Back-Propagation method as a machine learning method to the system. Therefore, since the network is capable of performing fuzzy inference and machine learning, the system can be called a Neuro- Fuzzy expert system. Generally, although a neural network is a powerful machine learning tool, the inference process of a neural network becomes a "black box," which renders the representation of knowledge in the form of rules impossible. However, the multi-layer neural network proposed in the present study contributes to prevent an inference process and knowledge base from becoming a black box. As described in our paper, the effectiveness of the neural network and machine learning method was verified by comparison of the diagnostic results of bridge experts and those of the proposed system.

1

Tazaki, E. and Amagasa, M., "Structural Modeling in a Class of Systems Using Fuzzy Sets Theory," International Journal for Fuzzy Sets and Systems, Vol.2, No. 1, pp.1-17, (1979). doi:10.1016/0165-0114(79)90018-6

2

Miyamoto, A., Kawamura, K., Nakamura, H. and Yamamoto, H., "Development of concrete bridge rating expert system by using hierarchical neural networks," JACE, 644(VI-46), pp.67-86, (2000) (in Japanese).

3

Okada, H., Watanabe, N., Kawamura, A. and Asakawa, K., "Initializing Multi-layer Neural Networks with Fuzzy Logic," Proc, of IJCNN-Baltimore, 1, pp.239-244, (1992).

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £78 +P&P)