Civil infrastructure is the driving force behind the functioning of the society whether on buildings, bridges, factories, tunnels, or offshore petroleum installations among others. Depending on various factors such as risk, ownership, hazards, and the use to which the structures are put in, the structures have to be inspected, monitored, and maintained by certain software or programs that are acceptable by law. The timely ability of the maintenance and inspection programs are as important as their effectiveness and as such encourages the need to supplement the existing inspection procedures by continuous automated systems. The proposed research will assess the structural health of structures using an automated sensor.

In the past few years, the term structural health monitoring has gained increased use in describing a variety of systems implemented in civil infrastructures with a purpose of assisting and informing the operators the useful states of the structures. Various forms of SHM exist and have been put into practice in the past few decades. However, until recently were the computer-based systems designed to provide timely information to the operators on the safety of the continued use of the aging infrastructure (Glisic, 2007).

Enckell (2007), argues that the development of an SHM strategy has various challenges. One of these limitations is the uniqueness of every structure except for particular types of private and public structures. The result of this aspect is that there is no baseline for the qualification procedures that apply to the structures of aerospace origin. According to Aktan et al. (2001), the unique feature of SHM directs the system towards a long-term assessment of normal structural health. System reliability is another limitation that must be taken into consideration. Therefore, the cost-benefit analysis is necessary to ensure that the benefits exceed the costs of maintenance, operations, and installations (Brownjohn, 2007).

The SHM can be implemented in various ways in order to meet different motives. However, the approaches link up at certain component classes, such as the sensors, data storage and transmission, decision-making, and data mining for feature extraction. There is need to make considerations for the incorporation of the needs of SHM

The first stage will involve data acquisition that encompasses the selection of the methods of excitation, the hardware for data acquisition, storage and transmission, types of sensors, and the locations. This process will be specific to applications; therefore, economic considerations are important in the decision-making process. The next stage will be the normalization of data which is a significant step that is to be conducted since data is measured at varying conditions. The measured inputs will be used to normalise the measured responses.

Data cleansing is another process that is necessary during the SHM process. This process which follows the normalization will involve a selective choice of data for rejection or passage to the feature selection process. This process is founded on the knowledge acquired by the people of are directly involved with the acquisition of data. Where the data is collected is found to be having anomalies, it will be removed from the process of feature selection by the people who performs the inspection based on their judgment. Other procedures such as filtering and sampling may also be used in the data cleansing process. According to Chong et al. (2003), the acquisition, normalization, and cleansing of data in the SHM process should not be static but should embrace the statistical model that provides information relating to the changes that enhance the process of data acquisition.

The proposed project is expected to bring about a more robust process that improves and promotes the infrastructural development. It will also provide a resource that motivates and prepares the next generation of structural engineers to engage in hands-on research and education.