Damage detection in offshore structures using neural networks

This paper discusses the damage detection in offshore jacket platforms subjected to random loads using a combined method of random decrement signature and neural networks. The random decrement technique is used to extract the free decay of the structure from its online response while the structure is in service. The free decay and its time derivative are used as input for a neural network. The output of the neural network is used as an index for damage detection. It has been shown that function N is effective in damage detection in the members of an offshore structure. Experimental studies conducted on a reduced model for a real jacket structure with geometrical scale of 1:30 are used. The applied loads were random loads. Two different load spectra were used: White noise, and Pierson-Moskowitz.     

Experimental study on a model azimuthing podded propulsor in ice

The objective of this study was to investigate the performance of a model azimuthing podded propulsor in ice-covered water. Model tests were carried out with two different depths of cut into the ice (15 and 35 mm), two different ice conditions (presawn and pack ice conditions), and four different azimuthing angles. The depth of cut is the maximum penetration depth of the propeller blade into the ice block. The 0.3-m-diameter model propeller was operated in a continuous ice milling condition. Ice loads were measured by several sensors which were installed in various positions on the model. Six one-axis pancake-style load cells on the top of the model measured the global loads and two six-component dynamometers were installed on the shaft to measure the shaft loads. One six-component dynamometer was attached to the one of the propeller blades inside the hub to measure the blade loads. The pod unit and propeller performance in ice are presented. Ice-related loads, which were obtained when the blade was inside the ice block, are introduced and discussed. During the propeller–ice interaction, a blade can experience the path generated by the previous blade, which is called the shadowing effect. The effects of shadowing, depth of cut, azimuthing angle, and advance coefficient on propulsor performance are presented and discussed.     

Trip distribution for limited destinations: a case study for grocery shopping trips in the Netherlands

In this paper, we introduce a new trip distribution model for destinations that are not homogeneously distributed. The model is a gravity model in which the spatial configuration of destinations is incorporated in the modeling process. The performance was tested on a survey with reported grocery shopping trips in the Dutch city of Almelo. The results show that the new model outperforms the traditional gravity model. It is also superior to the intervening opportunities model, because the distribution can be described as a function of travel costs, without increasing the computational time. In this study, the distribution was described by a simple function of Euclidean distance, which provides a good fit to the survey data. The slope of the distribution is quite steep. This shows that most trips are made to nearby supermarkets. However, a significant fraction of trips, mainly made by car, still goes to supermarkets further away. We argue that modeling of these trips by the new method will improve traffic flow predictions.     

Full vehicle simulation using thermomechanically coupled hybrid neural network shock absorber model

In the case of full vehicle models, the technique of multi-body simulation (MBS) is frequently used to study their highly non-linear dynamic behaviour. Many non-linearities in vehicle models are induced by force elements like springs, shock absorbers, bushings and tires. Commonly, spline functions are used to represent the force responses of these components. If the non-linear relationships are more complicated, the spline approximations are no more accurate. An alternative approach is based on empirical neural networks which are based on the mathematical approximation of measured data. It is well known that neural networks are able to represent and predict complex component responses accurately. The aim of this paper is to perform a dynamic full vehicle simulation using a thermomechanically coupled hybrid neural network shock absorber model. In this shock absorber model, the spline approach is combined with a temperature-dependent neural network. Based on a displacement-controlled excitation on a four post test rig in the ADAMS/Car MBS software, a rugged test track is simulated. In this way, the front and rear shock absorbers are dynamically loaded with comfort-relevant frequencies in the range of 0.75-30 Hz and velocity amplitudes up to 2 m/s. By the simulation, stability of the hybrid neural network model is demonstrated. Furthermore, the damping force, the vertical acceleration of the chassis and the required simulation times are compared. The standard spline approach is used as a reference.     

Assessment of diesel combustion noise overall level in transient operation

Combustion noise in passenger cars powered with direct injection (DI) diesel engines is frequently the main reason why end-users are reluctant to drive this type of vehicle. Thus, the great potential of diesel engines for environment preservation — due to their lower CO₂ emissions — could be missed. This situation worsens with the current design trends (engine downsizing) and the emerging new diesel combustion concepts (Homogeneous Charge Compression Ignition-HCCI, Premixed Charge Compression Ignition-PCCI, etc.), which are intrinsically noisy. This negative feature can be even more critical in transient operation due to the contribution of the temporal changes of both source and transmission path on engine noise. Therefore, combustion noise must be considered as an additional essential factor in engine development, together with performance, emissions and driveability. Thus, suitable evaluation procedures that can be integrated into the global engine development process in a timely and cost-effective manner are imperative. Regarding the evaluation procedures, most of the work available in the literature addressed combustion noise at steady operation. To surpass this limitation, two possible approaches — adapted from the classical and multiple regression methods — for the overall level assessment of combustion noise in transient conditions are evaluated in this paper.     

Longhaul feeder services in an era of changing technology: an Asia-Pacific perspective

Traditional liner carriers, operating in the highly competitive commercial environment of the last few years, have attempted to lower the marginal cost of each box carried. Technological improvements in both construction and propulsion systems have led to a steady growth in carrying capacity. Ships of 600+ TEUs are now in service and, as a result of this trend, have displaced 'smaller' ships from the major east-west trades. The more competitive environment of these trades has in turn led to a redeployment of ships in the 2500+ TEU range to the north-south trades. The result has been a rapid increase in north-south capacity, including feeder services and falling freight rates. Despite the current excess supply in shipping and historically low freight rates, significant developments in technology have created opportunities for new fast containerships. The paper analyses the key economic factors in the differentiation of the new fast ship technology from the traditionally designed containerships and demonstrates the potential financial viability to owners of these new 'greyhounds'.     

A new methodology for incident detection and characterization on surface streets

In this paper, a new methodology is presented for real-time detection and characterization of incidents on surface streets. The proposed automatic incident detection approach is capable of detecting incidents promptly as well as characterizing incidents in terms of time-varying lane-changing fractions and queue lengths in blocked lanes, lanes blocked due to incidents, and incident duration. The architecture of the proposed incident detection approach consists of three sequential procedures: (1) Symptom Identification for identification of incident symptoms, (2) Signal Processing for real-time prediction of incident-related lane traffic characteristics and (3) Pattern Recognition for incident recognition. Lane traffic counts and occupancy are the only two major types of input data, which can be readily collected from point detectors. The primary techniques utilized in this paper include: (1) a discrete-time, nonlinear, stochastic system with boundary constraints to predict real-time lane-changing fractions and queue lengths and (2) a pattern-recognition-based algorithm employing modified sequential probability ratio tests (MSPRT) to detect incidents. Off-line tests based on simulated as well as video-based real data were conducted to assess the performance of the proposed algorithm. The test results have indicated the feasibility of achieving real-time incident detection using the proposed methodology.     

Identification of potential sites for deep-ocean waste isolation with a geographic site-selection model

Identification of optimal sites for the isolation of waste on the abyssal seafloor was performed with two approaches: by the traditional method of map overlays of relevant attributes, and by a specially developed, automated Site-Selection Model (SSM). Five initial, Surrogate Sites, identified with the map-overlay approach, were then compared with the more rigorously produced scores from the SSM. The SSM, a process for optimization of site locations, accepts subjective, expert-based judgments and transforms them into a quantitative, reproducible, and documented product. The SSM is adaptable to any siting scenario. Forty-one factors relevant to the isolation scenario, including 21 weightable factors having a total of 123 scorable categories, have been entered into the SSM. Factors are grouped under project definition, unique environments, anthropogenic, geologic, biologic, weather, oceanographic and distance criteria. The factor scores are linked to a georeferenced database array of all factors, corresponding to 1°×1° latitude–longitude squares. The SSM includes a total of 2241 one-degree squares within 1000 n.m. of the U.S. coasts, including the western North Atlantic, the Gulf of Mexico, and the eastern North Pacific. Under a carefully weighted and scored scenario of isolation, the most favorable sites identified with the SSM are on the Hatteras and Nares Abyssal Plains in the Atlantic. High-scoring sites are also located in the Pacific abyssal hills province between the Murray and Molokai Fracture Zones. Acceptable 1° squares in the Gulf of Mexico are few and of lower quality, with the optimum location on the northern Sigsbee Abyssal Plain. Two of the five Surrogate Site locations, on the Hatteras and Sigsbee Abyssal Plains, correspond to the best SSM sites in each ocean area. Two Pacific and a second Atlantic Surrogate Site are located in low-scoring regions or excluded by the SSM. Site-selection results from the SSM, although robust, are an initial attempt to quantify the site-selection process. The SSM database exposes a significant lack of high-quality information for many areally mappable attributes on the abyssal seafloor, particularly bottom-current speed and measures of biologic productivity and flux. Terminologies and classifications of some measures, such as sediment types, suffer from parochialism and vary by ocean. Considerable research is needed even for a broad understanding of the environmental measures required to make sound societal decisions about use of the abyssal seafloor for disposal or other purposes.     

Damage Accumulation in Rail Steel under Rolling with Slippage and Its Analysis

Experimental research results of surface damage accumulation in rail steel under rolling with slippage are presented. Hertz contact for two rollers made of rail and wheel steels was realized in the test. The influence of loading regime upon wear of rail is considered. The estimation of characteristics of surface fracture resistance for rail steel is made. The method to predict the life of rail steel under given conditions of regular loading is proposed.