Acoustical characteristics are used to classify the structural and operational conditions in underground pipes with advanced signal classification methods.

This thesis is concerned with the development and study of a pattern recognition system for siphon and sewer condition/defect analysis based on acoustic characteristics. Pattern recognition has been studied and used widely in many fields including: identification and authentication; medical diagnosis and musical modelling. Audio based classification and research has been mainly focusing on speech recognition and music retrieval, but few applications have attempted to use acoustic characteristics for underground pipe condition classification. Traditional CCTV inspection methods are relatively expensive and subjective so remote techniques have been developed to overcome this concern and increase the inspection efficiency. The acoustic environment provides a rich source of information about the internal conditions of a pipe. This thesis reports on a classification system based on measuring the direct and reflected acoustic signals and describing the energy spectrum for each condition/pipe defect. A K-nearest neighbour classifier (KNN) and Support vector machines (SVMs) classifier have been adopted to train the classification system to identify sediment and pipe surface defects by comparing the measured acoustic signals with a database containing a range of typical conditions. Laboratory generated data and field collected data were used to train the proposed system and evaluate its ability. The overall accuracy of the system recognizing blockage and structural aspects in each of the series of experiments varies between 70% and 95%.

This thesis research has attempted to address two challenging problems in winter road maintenance, namely road surface condition (RSC) estimation and forecasting. For RSC estimation, the goal of the research was to develop models to discriminate RSC classes based on continuous friction measurements (CFM) and other available data such as temperature and precipitation history. A systematic exploratory study was conducted on an extensive field data set to identify the categorical relationship between RSC and various aggregate CFM measures, such as those related to probability distribution and spatial correlation. A new multi-level model structure was designed, under which binary logistic regression models were calibrated and validated utilizing several carefully chosen aggregate measures to classify major RSC types. This model structure was found to be effective in capturing the overlapping nature of CFM ranges over different RSC types -- a problem which has not been addressed adequately in the past studies. An alternative model with support vector machine (SVM) was also developed for benchmarking the performance of the proposed logit model. It was found that the two types of models are comparative in performance, confirming the high performance of the proposed multi-level model. For road surface condition forecasting, a novel conceptual framework for short-term road surface condition forecasting is proposed, under which the short-term changing process of surface temperature, friction level and contaminant layer depths, is comprehensively explored and analyzed. This study framework is designed to consider all important conditional factors, including weather, traffic and maintenance operations. The maintenance operations, especially salting, are handled by loosening the strict Markovian assumption, i.e., a history instead of one single time interval of salting operations is considered. In this way, the variation of snow/ice melting speed caused by both residual salt amounts and salt/contaminant mixing states is incorporated in the forecasting model, which enables accurate short-term forecasting for contaminant layers. This approach practically circumvents a major limitation of previous studies, making the post-salting RSC forecasting more reliable and accurate. Under the proposed model framework, several advanced time series modelling methodologies are introduced into the analysis, which can capture the highly complex interactions between RSC measures and conditional factors simultaneously. Those methodologies, especially the univariate and multivariate ARIMA methods, are for the first time applied to the winter RSC evolution process. The forecasting errors of surface temperature, friction level and contaminant layer depths are all found to be small, implying that both the proposed study framework and the resulting solutions closely match the real-world observations. The proposed forecasting models are simple in structure, easy to interpret and mostly consistent with physical knowledge. Compared to the existing models, the proposed models provide extra flexibility for refactory, tuning and deployment. Furthermore, all the modelled RSC measures are numerical and the forecast errors are relatively small, suggesting empirical models could be an efficient alternative to physical models. With the well-designed modelling methods, the resulting empirical models as calibrated in our study can be implemented into a decision support and simulation tool with high temporal resolution and accuracy.

Gravel roads are essential for economic development as they facilitate the movement of people, transportation of goods and services, and promote cultural and social development. They typically connect sparsely populated rural areas to urban centres, providing essential access for residents and entrepreneurs. Maintaining these roads to an acceptable level of service is crucial for the efficient and safe transportation of goods and services. However, substantial maintenance investmentis required, yet resources are limited. Gravel roads are prone to dust, potholes, corrugations, rutting and loose gravel. They deteriorate faster than paved roads, and their failure development is affected by traffic action and physical, geometric and climatic factors. Thus, more condition monitoring and proper road condition assessment are necessary for dynamic maintenance planning to reach efficiency and effectiveness using objective, data-driven condition assessment methods to ensure all-year-round access. However, objective data-driven methods (DDMs) are not frequently used for gravel road condition assessment, and where they have been applied, the practical implementation is limited. Instead, visual windshield assessment and manual methods are predominant. Visual assessments are unreliable and susceptible to human judgement errors, while manual methods are time-consuming and labour-intensive. Maintenance activities are predetermined despite dynamic maintenance needs, and the planning is based on historical failure data rather than the actual road condition. This thesis establishes a data-driven approach to gravel road maintenance describing the systematic assessment of the gravel road condition and collection of the condition data to ensure efficient and effective maintenance planning. This thesis uses a design research methodology based on a literature review, concept development, interview study and field experiments. A holistic approach is proposed for data-driven maintenance of gravel roads encompassing objective condition data collection, processing, analysing, and interpreting the findings for obtaining reliable information concerning the condition to gravel road decision support by utilising the opportunities presented by technological advancements, particularly sensor technology. Then, decision-making is primarily influenced by the objectively collected gravel road condition data rather than the evaluator’s perception or experience. The successful implementation of a data-driven approach depends on the quality of the collected data; therefore, data relevance and quality are emphasised in this thesis. The lack of data quality and relevance hinders effective data utilisation, leading to less precisionin decision-making and ineffective decisions. Furthermore, the thesis proposes a participatory data-driven approach for unpaved road condition monitoring, allowing road users to be part of the maintenance process and providing an efficient and effective alternative for collecting road condition data and accomplishing broad coverage at minimum cost. A top-down iiapproach for data-driven gravel road condition classification is proposed to achieve an objective assessment to address the lack of readily available quality and relevant condition data. The established data-driven approach to gravel road maintenance is evaluated and verified with field experiments on three gravel roads in Växjö municipality, Southern Sweden. The research findings indicate that properly implementing a data-driven approach to gravel road maintenance would ensure efficient and effective condition assessment and classification, which are a basis for a maintenance management system of gravel roads and enable road maintainers and authorities to achieve cost-effective decision-making. / Sustainable maintenance of gravel road