Condition Assessment Method Research Articles

Unsupervised deep learning method for bridge condition assessment based on intra-and inter-class probabilistic correlations of quasi-static responses

Data-driven methods for structural condition assessment have been extensively investigated using deep learning (DL). However, studies on quasi-static response data-based structural health diagnoses are relatively insufficient. The difficulty is that quasi-static response data contain coupled effects of structural parameters and external loads. Considering that the correlation between quasi-static responses subjected to identical external loads is only a function of structural parameters and independent from the external loads, the correlation can therefore be employed as an indicator of the structural condition. This study proposes a condition assessment approach for cable-stayed bridges based on correlation modeling between the deflection of girders and tension in cables. The correlation is modeled by an unsupervised DL network comprising two variational autoencoders (AE) and two generative adversarial networks (GANs). The input and output are marginal probability density functions (PDFs). The DL network is trained as the reconstruction and translation processes to model the intra-class and inter-class correlations. Assumptions of shared latent space and cycle consistency are taken to ensure mutual modeling capacity. The Wasserstein distance between the predicted and ground-truth PDFs of tension in cables is used as an indicator of the structural condition. Using probabilistic correlation of quasi-static responses only requires the PDF of external loads to be identical and does not need the external loads to be precisely identical at any moment, thus relieving time-synchronization restrictions for different sensors. The results show that the predicted PDFs agree well with the ground-truth values under normal conditions. Furthermore, the Wasserstein distance is sensitive to damage and shows noticeable variations when the damage of the stay cable occurs.

Integration and Comparison Methods for Multitemporal Image-Based 2D Annotations in Linked 3D Building Documentation

Data acquisition systems and methods to capture high-resolution images or reconstruct 3D point clouds of existing structures are an effective way to document their as-is condition. These methods enable a detailed analysis of building surfaces, providing precise 3D representations. However, for the condition assessment and documentation, damages are mainly annotated in 2D representations, such as images, orthophotos, or technical drawings, which do not allow for the application of a 3D workflow or automated comparisons of multitemporal datasets. In the available software for building heritage data management and analysis, a wide range of annotation and evaluation functions are available, but they also lack integrated post-processing methods and systematic workflows. The article presents novel methods developed to facilitate such automated 3D workflows and validates them on a small historic church building in Thuringia, Germany. Post-processing steps using photogrammetric 3D reconstruction data along with imagery were implemented, which show the possibilities of integrating 2D annotations into 3D documentations. Further, the application of voxel-based methods on the dataset enables the evaluation of geometrical changes of multitemporal annotations in different states and the assignment to elements of scans or building models. The proposed workflow also highlights the potential of these methods for condition assessment and planning of restoration work, as well as the possibility to represent the analysis results in standardised building model formats.

Transformer evaluation strategy based on improved machine learning

A transformer state assessment method based on an improved extreme learning machine is proposed in this paper, which introduces an adaptive evolution algorithm into the extreme learning machine. This method is used in the evaluation model to evaluate the state of the transformer. The algorithm is trained and tested through sample sets. Furthermore, the test results are analyzed to prove the feasibility of the proposed control strategy.

Condition Assessment of the Cable Trench Based on an Intelligent Inspection Robot

Accurate evaluation of the cable trench condition is the key to realizing its intelligent operation and maintenance, and the intelligent cable trench inspection robot is a reliable information acquisition method for the condition assessment of cable trench. According to task requirements and site’s environment, an intelligent inspection robot is designed. The crawler-type motion mechanism is determined based on the demand for sizes and obstacle-surmounting. Cartographer SLAM technology is used to map the underground cable trench environment, and a path planning method combined with the improved A∗ algorithm and dynamic window method (DWA) is presented. Multiple sensors are equipped on this robot, and various kinds of information are obtained. Based on the information obtained, a condition assessment method of an underground cable trench is proposed. An extension neural network model is constructed to assess air quality. Channel capacity and ground flatness are calculated to evaluate the internal structure of the cable trench. The water depth and water surface area are comprehensively used to evaluate the hazard of water accumulation. The evaluation results are used to realize the linkage control of the cable trench’s operation and maintenance. A field test shows that the intelligent inspection robot can reliably obtain seven kinds of information from the underground cable trench, and the proposed condition evaluation method can assess the condition of the cable trench and provide four kinds of suggestions for potential hazards.

Empirical techniques for assessing rock mass condition

The relevance of the work is due to the existence of a large number of empirical methods for predicting the condition of a rock mass and the need to apply them at the design and operational stage of mining enterprises to minimize costs during construction and future maintenance. Research objective is to analyze and compare existing empirical methods for determining the strength and deformation properties of rock mass. Methods of research include the analysis, systematization and synthesis of existing empirical methods of rock mass condition assessment and their applicability to real-world sites. Recommendations for further application of empirical rock mass assessment methods in real-world conditions are determined by generalization of theory and practice, research results and analytical calculations based on the assessment of fracture formation in rock masses. Results. The main empirical methods such as Deere's method (RQD) of structural failure evaluation, the method relating strain rate to RMR rating system and the method relating strain rate to geomechanical classification of rock mass Q were found and chosen for comparison. Several types of rocks such as limestone, diorite, granite, basalt, tuff, andesite in different geotechnical conditions are chosen for comparison of the methods. Comparison of different empirical methods of rock mass condition assessment is carried out. Evaluations of each method are given. Ways of application of empirical research methods are recommended. It is concluded that it is necessary to apply several methods in order to get a more accurate picture of the rock mass condition. Recommendations for the initial assessment of the state of rocks are given. Conclusions. There are a large number of empirical methods of rock mass condition estimation. The results obtained by some methods for some types of rocks under different mining and geological conditions are very different from each other, this is due to the fact that the considered methods were created on the basis of different sources. It is necessary to take into account the stresses acting in the rock mass, which also influence the results obtained.

Cost-effective assessment of in-service asphalt pavement condition based on Random Forests and regression analysis

The condition assessment of in-service asphalt pavement plays a key role in pavement maintenance and rehabilitation. Driven by historical data, the Random Forests algorithm with the Gini importance measurement was employed to identify and extract key detection indicators from the pavement assessment standards. On top of that, a cost-effective method for pavement condition assessment based on the key detection indicators was proposed by decreasing unnecessary data dimensions. A comparison between the proposed method and the traditional method has been made to verify the feasibility of pavement condition assessment. The results show that the pavement assessment results based on the proposed method matched well with those based on the traditional method, which achieved a more than 90% consistency of overall assessment results in validation samples. Hence, they demonstrated that the proposed method utilized fewer pavement detection indicators to reduce the burden of data collection and improve the cost-effectiveness of pavement condition assessment tasks. In the future, it will be a promising alternative to assist pavement maintenance and rehabilitation.

An Innovative Condition Assessment Method for Wastewater Treatment Facilities to Promote Long-Term Sustainability in Management and Operations

Conventionally, the success of a wastewater treatment plant is evaluated by the quantity of chemical oxygen demand (COD), dissolved organic matter (BOD), total suspended solids (TSS), and other consequences of wastewater treatment that are removed during the treatment process and thereafter. Environmental engineers consider a number of parameters at the plant's discharge, including pH, NH4-N, NTotal, fecal coliform, and others. The traditional approach to performance assessment fails because it does not directly compare the effluent's distribution of these characteristics throughout the output stage of the process to the standards or specification limits issued by the Central Pollution Control Board (CPCB). To fill this knowledge gap, we propose and implement the probability-based Process Capability Indices (PCIs) and Multi - variate Process Flow Indices (MPCIs) in this research. These indices measure the effectiveness of a wastewater treatment process by contrasting the observed results with the predicted ones. PCIs have been widely used as a baseline against which manufacturing processes may be evaluated and tweaked to increase efficiency. The focus of this effort is on PCIs and MPCIs from the standpoint of environmental engineers, with the hope that their use would grow. Using capacity indicators accurately measures the effectiveness of the process of wastewater treatment, which is essential for reducing pollution and permitting the reuse of treated water. This study provides an analysis of the treating wastewater process's capacity by applying appropriate capability indices, using additional information acquired from case studies via literature research. Findings suggest that appropriate capacity indices may allow for more precise assessments of sewage treatment system performance than are presently possible.

High-Voltage Cable Condition Assessment Method Based on Multi-Source Data Analysis

In view of the problem that the weight value given by the previous state evaluation method is fixed and single and cannot analyze the influence of the weight vector deviation on the evaluation result, a method based on the weight space Markov chain and Monte Carlo method (Markov chains Monte Carlo, MCMC) is proposed. The sampling method is used for evaluating the condition of high-voltage cables. The weight vector set obtained by MCMC sampling and the comprehensive degradation degree of the high-voltage cable sample are weighted and summed then compared in pairs to obtain the comprehensive degradation degree result. The status probability value and overall priority ranking probability of the object to be evaluated are obtained based on probability statistics, and the order of maintenance is determined according to the status probability value and the ranking result. It is realized that the cable line that needs to be identified in the follow-up defect is clarified according to the evaluation result. This is helpful for operational and maintenance personnel to more accurately implement the maintenance plan for the cable and improve the operational and maintenance efficiency.

A Characterization Method for Pavement Structural Condition Assessment Based on the Distribution Parameter of the Vehicle Vibration Signal

A pavement structural survey plays a vital role in road maintenance and management. This study was intended to explore the feasibility of a non-stop pavement structure assessment method by analyzing the vibration data from a vehicle sensor. In this study, three falling weight deflectometer (FWD) tests and four vehicle vibration tests were conducted on five pavement structures. The FWD test results show that the continuously reinforced composite pavement has a higher structural stiffness than the semi-rigid base asphalt pavement. According to the statistical distribution of vehicle acceleration, a distribution parameter, the peak probability density (PPD), was proposed. The correlation coefficient (−0.722) of the center deflection (D1) and PPD indicates a strong correlation between the two variables. Therefore, PPD is strongly correlated with pavement structural stiffness. This study proposed a novel characterization method for pavement structural conditions based on the distribution parameter of the vehicle vibration signal.

A data‐driven approach to state assessment of the converter valve based on oversampling and Shapley additive explanations

The utilization of data-driven artificial intelligence technology for ultra-high voltage converter valve state assessment can improve efficiency and accuracy, but there are still problems such as imbalance of raw data and poor model interpretability. This paper aims to propose a new type of ultra-high voltage converter valve state assessment method to solve these problems. An oversampling method that considers characteristic boundary information is proposed, which can retain and enhance the boundary information of minority samples. The balanced data are imported into categorical boosting to realize offline training and online evaluation of converter valve state assessment. An interpretability analysis framework of the converter valve state assessment model based on the Shapley additive explanations is proposed, which can explain the operation logic of the model and find the key factors that affect the assessment results. The calculation example shows that the evaluation accuracy of this method can reach up to 98.5%, and the running speed is faster than the conventional method. The results can provide guidance for the maintenance and repair of UHV converter valves.

Development of Strategies for Analysing the Factors which Influence the Organization of Routine Railway Track Maintenance

It is critical for railway transport management to be able to predict the condition of any railway track that operates in a challenging environment, including high tonnage, magnitude of traffic flow, an increased governed speed, and harsh climate — factors that combine to reduce the life cycle of track superstructure components. The condition of railway track cannot be predicted until after the factors affecting all track elements and their interrelationships have been identified. It is therefore essential to identify the factors that have a bearing impact on the management of routine track maintenance and track work processes. This article discusses the formulation of strategies for reviewing existing methods for track condition assessment followed by assignment of track works and efforts to identify factors that may not have been recognized in previous planning. The studies used both statistical and analytical methods.

A Bootstrapping Solution for Effective Interpretation of Transformer Winding Frequency Response

The current interpretation procedure for the transformer frequency response analysis (FRA) is practically based on either subjective visual inspection or an observed value of a statistical indicator (SIn) programed in commercial software. However, both solutions are unable to provide very detailed information on transformer conditions in the industry. The former approach highly depends on the experience of the technical personnel, while the latter suffers from uncertainties of SIn-based decision boundaries for classification. This study has specifically focused and introduced a new comprehensive FRA data interpretation and classification method. Evaluation of the proposed technique is performed by emulation of winding short-circuit faults in transformers via a parallel connected rheostat. The method is able to categorize the operational mode of the transformer into the normal, suspicious, and critical classes based on the cumulative effect of 12 frequently used SIns and then provide a confidence level (CL) associated with classification to support operators for making a precise decision. Bootstrap sampling technique is introduced for the first time in FRA data evaluation to simulate the effect of many experiments <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in silico</i> and overcome the difficulty of limited available measured data. Particularly, in a novel approach, a large set of SIn-specific decision boundaries is established by bootstrap sampling of the real experimentally obtained boundaries. In addition, a new transformer condition assessment method that employs the cumulative effect of individual SIns is developed and examined. Classification results and the CLs in FRA evaluation have a substantial practical significance and will support on-site utility managers or engineers for further diagnosis and maintenance.

Critical evaluation of NDT for rapid condition assessment of existing RC buildings: A case study

There is an urgent need for rapid and reliable condition assessment of existing reinforced concrete (RC) buildings as a basis for structural safety evaluation, especially in developing countries in seismic regions such as Turkey. Traditionally, RC structures are evaluated by taking core samples from a limited number of structural elements for concrete strength and performing spot checks for the steel reinforcement by removing the concrete cover. In-situ concrete strength is determined through compression testing of core samples. Through spot checks, conformance of the existing reinforcement with the structural drawings is evaluated and a reinforcement realization factor is calculated for use in the analyses. Even though these conventional methods are relatively more accurate and reliable for condition assessment of existing RC structures, they are destructive, involved, time taking, slow and expensive. Non-destructive testing (NDT) methods are proposed as a solution to this problem. Using NDT methods in conjunction with a relatively small number of core tests potentially allows for more rapid yet still reliable condition assessment of existing structures. In this paper, a critical evaluation of rapid and reliable condition assessment methods is made through investigations on an 18-story residential RC building as a case study. Investigation results show that using NDT helps achieve time and cost savings while allowing for reliable condition assessment of existing buildings, and promises further savings through continued research and development in this area.

Simultaneous Identification of Bridge Structural Damage and Moving Loads Using the Explicit Form of Newmark-β Method: Numerical and Experimental Studies

Bridge infrastructures are always subjected to degradation because of aging, their environment, and excess loading. Now it has become a worldwide concern that a large proportion of bridge infrastructures require significant maintenance. This compels the engineering community to develop a robust method for condition assessment of the bridge structures. Here, the simultaneous identification of moving loads and structural damage based on the explicit form of the Newmark-β method is proposed. Although there is an extensive attempt to identify moving loads with known structural parameters, or vice versa, their simultaneous identification considering the road roughness has not been studied enough. Furthermore, most of the existing time domain methods are developed for structures under non-moving loads and are commonly formulated by state-space method, thus suffering from the errors of discretization and sampling ratio. This research is believed to be among the few studies on condition assessment of bridge structures under moving vehicles considering factors such as sensor placement, sampling frequency, damage type, measurement noise, vehicle speed, and road surface roughness with numerical and experimental verifications. Results indicate that the method is able to detect damage with at least three sensors, and is not sensitive to sensors location, vehicle speed and road roughness level. Current limitations of the study as well as prospective research developments are discussed in the conclusion.

A Decision-Making Model for Self-Driving Vehicles Based on Overtaking Frequency

The driving state of a self-driving vehicle represents an important component in the self-driving decision system. To ensure the safe and efficient driving state of a self-driving vehicle, the driving state of the self-driving vehicle needs to be evaluated quantitatively. In this paper, a driving state assessment method for the decision system of self-driving vehicles is proposed. First, a self-driving vehicle and surrounding vehicles are compared in terms of the overtaking frequency (OTF), and an OTF-based driving state evaluation algorithm is proposed considering the future driving efficiency. Next, a decision model based on the deep deterministic policy gradient (DDPG) algorithm and the proposed method is designed, and the driving state assessment method is integrated with the existing time-to-collision (TTC) and minimum safe distance. In addition, the reward function and multiple driving scenarios are designed so that the most efficient driving strategy at the current moment can be determined by optimal search under the condition of ensuring safety. Finally, the proposed decision model is verified by simulations in four three-lane highway scenarios. The simulation results show that the proposed decision model that integrates the self-driving vehicle driving state assessment method can help self-driving vehicles to drive safely and to maintain good maneuverability.

Condition Assessment of Subsurface Drained Areas and Investigation of their Operational Efficiency by Field Inspection and Remote Sensing Methods

Abstract The extreme weather events highlight the need to develop action concepts to maintain agricultural production security in the future. Hydrological extremes can occur within a year in the form of surplus water (i.e. inland excess water), water scarcity or even drought. These adverse effects are influenced, inhibited and also facilitated by human activity. Previously, complex amelioration interventions, including subsurface drainage, aimed to improve the productivity of agricultural areas with unfavourable water management properties. The current efficiency of the subsurface drain networks in the regulation of groundwater level or soil moisture content can be questioned from several aspects. After the end of the socialist era (after 1990s), lack of maintenance and operation tasks have become typical, and are still a problem today in Hungary. Unfortunately, there is no exact national cadastre on the tile drained areas, and data is only available to a limited extent in the original amelioration plan documentations. In the present study, we aimed to reveal the possibilities of delineating the subsurface drained areas, and to develop a new method of condition assessment. Three tile drained study sites were selected on the Great Hungarian Plain in Central Europe. Our field investigations revealed the typical problems of the drained areas: (1) excessive vegetation of the receiving channels; (2) inadequate condition of the receiving main channel bed; (3) soil compaction in multiple layers above the drainage network; and (4) poor condition of outlets of the drain pipes. The developed methodology enabled us to evaluate the soil and the surface/subsurface water of the tile drained areas, and the technical condition of the drains. The necessary action plans or treatments were also outlined to replace the unused drain networks into use. Based on the scientific literature, we also sketched the target conditions and technological solutions that are required for the installation of new drains. The organization of the derived data into a GIS database could serve as a basis for the development of a cadastre of the tile drained areas based on a regional approach.

Time-dependent robustness-based condition assessment of RC bridges subjected to corrosion

At present, the main methods of bridge condition assessment are reliability analysis and analytic hierarchy process method. Robustness, as a measure of the structural ability to maintain the performance after the occurrence of variations, can provide a different perspective based more on the structural property itself. Although robustness has been mainly used in structural design optimization against progressive collapse and extreme events, it can also be used in assessing the condition of bridges with material deterioration. In this paper, a time-varying robustness index model is proposed to quantify the condition of the reinforced concrete bridge girder under corrosion. In this model, the robustness index represents the average performance of the concrete girder in the remaining life. The method is exemplified through a case study of an existing reinforced concrete bridge girder. Combining with the current specification, the robustness index is compared with the reliability analysis results of the girder in the case study. The result shows that when the reliability index drops below the target reliability index, the robustness index descends to Grade 5 specified in the Code for Maintenance of Highway Bridge and Culvers (JTG H11-2004). Both results indicate that the safety of the girder cannot satisfy demand.

A method for evaluating and upgrading systems with parallel structures with forced redundancy

The objects of the study are parallel-structure machine systems with redundancy associated with safety assurance of continuous material flow. The problem concerns systems in which the supply of materials takes place continuously (24 hours a day), and the system of operated machines must ensure the receipt and movement of the material at a strictly defined time and in the desired quantity. It is a system where the presence of a failure poses a threat to human life and environmental degradation. This paper presents a method for system condition assessment and upgrading for maintaining proper operation under conditions of continuous operation. A database of information about the current parameters of the system components (measurements, monitoring) is necessary for condition assessment. The method also uses lean techniques (including TPM). System evaluation and selection criteria for a suitable structure in terms of further operation were proposed. Exemplification was performed for an underground mine drainage system. As a part of the identification, selected parameters of the system components were measured, and their characteristics (motors, pumps, pipelines) were developed. The results of the analysis and the values of the adopted criteria were compared to the indicators for new pump sets. A two-option system upgrade was proposed, in addition to machine operating schedules, maintenance periods, and overhaul cycles.

A health condition assessment method of wind turbine generator system based on multiple turbines cooperation

To improve the reliability and optimize the maintenance strategy of a large-scale wind farm, a health condition assessment method of wind turbine generator system (WTGS) based on multiple turbines cooperation is presented in this paper. First, a health condition assessment framework is established by analyzing the existing monitoring characteristics of SCADA system. Second, to quantify the health condition of a WTGS, the concept of synthetic degradation factor is introduced and calculated using variable weight of assessment indices. Third, in order to acquire the health level of a WTGS effectively, based on the idea of multiple turbines cooperation, the health condition assessment model is proposed by utilizing the moving average method and quantile algorithm. Finally, by using SCADA monitoring data of a wind farm with 33 × 1.5 MW WTGSs including temperature, pressure, vibration, and so on; the processes of condition assessment are performed, and the effectiveness is also compared to a traditional assessment method with the fixed threshold. The results show that the condition assessment that utilizes the proposed method can acquire the change of health conditions and has a better coherence with real health conditions.

Operational state assessment of cross-linked polyethylene power cable on the basis of an optimized cloud matter-element theory

Polyethylene power cables are likely to encounter high failure rates due to adverse operation conditions. In order to ensure a safe and reliable operation of the Polyethylene power cables, a state assessment approach should be conducted to evaluate the actual operation state of the Polyethylene power cables and determine the maintenance schedule. Several techniques which are used to preempt cable failure and schedule efficient maintenance in the past work have been reviewed, each of which is found with limitation. Taking a 10 kV – Polyethylene power cable as an example and considering the uncertainty of cloud model as well as the qualitative characteristics of matter-element theory, a cable operation state assessment method based on improved cloud matter-element theory with optimal entropy was proposed. Firstly, aiming at the randomness and fuzziness of operation condition level boundary, cloud matter-element theory was proposed to construct the index system of state evaluation. Secondly, based on a comprehensive consideration on the characteristics of clarity and fuzziness of grade division, the optimized cloud entropy calculation method suitable for fuzzy indices is proposed, and the traditional extension cloud theory is improved. Finally, according to the cloud matter-element model correlation degree assessment matrix and comprehensive weight, the operation condition grade of Polyethylene power cable is comprehensively evaluated. The method could effectively deal with the uncertainties in the state assessment according to the changes of the power cable operation condition, and the assessment results were more objective and reasonable. The proposed method in this paper conquers the drawbacks of the past work and can effectively deal with the uncertainty factors in transformer state assessment. The evaluation results are closer to the real state of the equipment and have wider application scenarios.