Cloud-based Condition Research Articles

Encoding 3D Point Contexts for Self-Supervised Spall Classification Using 3D Bridge Point Clouds

Geometric features, such as normal and curvature, have been prominently used for point cloud-based unsupervised spall classification. In addition, some researchers use hand-crafted features (e.g., out-of-plane distance, eccentricity, principal curvatures in 2D slices). These features perform well in low noise settings; however, the performance tapers down significantly when the quality of point clouds is affected by factors such as higher noise and inconsistent point-to-point spacing. Instead of relying purely on handcrafted features, the research presented in this paper investigates the potential for combining domain knowledge with deep learning to automatically learn better quality defect-sensitive features for point cloud-based spall classification. Specifically, generic three dimensional (3D) shape and 3D neighborhood features have been encoded as inputs to a deep autoencoder network for self-supervised spall classification from point clouds. Overall, this approach only resulted in marginal improvement over classification results from the current state-of-the-art unsupervised approach that uses handcrafted features. However, significant improvement in the results were observed in datasets that had higher noise levels. Given that noise is pervasive in datasets from outdoor settings like civil infrastructure, this added robustness to noise improves the reliability of point cloud-based condition assessment for concrete bridges.

AVTR receives substantial orders for its cloud-based condition monitoring tools

UK-based AVT Reliability Ltd (AVTR) has won orders worldwide, worth £8 million, for its Cloud/Internet of Things and Remote Data Centre (RDC) business.

Assessing the impact of 3D point neighborhood size selection on unsupervised spall classification with 3D bridge point clouds

The performance of point cloud-based defect classification algorithms depends on the quality of the computed geometric features, which in turn is strongly affected by the selection of the neighborhood size of local 3D points. Many existing algorithms select a single scene-specific value as the neighborhood size parameter and apply it uniformly to all 3D points while computing features. By doing so, some defect features end up being smoothened out at locations where the selected neighborhood size is larger than the optimal choice for those points. Conversely, geometric features might not always capture the local 3D structure if they are calculated based on less than optimal number of neighbors. This paper investigates and assesses the relationship between neighborhood size selection and the performance of point cloud-based unsupervised spall classification algorithms in a quantitative manner. Among the presented neighborhood selection approaches, an entropy-based approach that incorporates a tailored optimal neighborhood size for every point in a point cloud, resulted in a significant improvement over the performance of current state-of-the-art approaches. The performed quantitative study also demonstrated the robustness of this approach to variables, such as subsampling percentage, maximum neighborhood size and different noise levels. The implemented research testbed is comprised of statistically significant number of spall defect datasets generated from five different bridges. The outcome of this research is expected to improve the reliability of point cloud-based condition assessment for concrete bridges.

A cloud-based condition monitoring system for fault detection in rotating machines using PROFINET process data

This work presents a methodology for a cloud-based condition monitoring system for fault detection and identification in rotating machines, such as uncoupling, angular and parallel misalignment, by data mining PROFINET network and PROFIdrive profile process data. The proposed methodology involves a new strategy for feature selection of unsupervised data set and employs SVM (Support Vector Machine) and OCSVM (One-Class Support Vector Machine) for operation status classification. The present diagnostic system represents a low-cost solution to the manufacturing process of small and medium enterprises, because it does not require dedicated sensors for fault detection and high featured hardware, and it employs an online cloud-based services. The experimental tests resulted in an accuracy between 87.5% and 100%, and high robustness among different operating conditions. In addition, the proposed feature selection strategy reduced the total execution time by 97.5%.

Cloud-Based Battery Condition Monitoring and Fault Diagnosis Platform for Large-Scale Lithium-Ion Battery Energy Storage Systems

Performance of the current battery management systems is limited by the on-board embedded systems as the number of battery cells increases in the large-scale lithium-ion (Li-ion) battery energy storage systems (BESSs). Moreover, an expensive supervisory control and data acquisition system is still required for maintenance of the large-scale BESSs. This paper proposes a new cloud-based battery condition monitoring and fault diagnosis platform for the large-scale Li-ion BESSs. The proposed cyber-physical platform incorporates the Internet of Things embedded in the battery modules and the cloud battery management platform. Multithreads of a condition monitoring algorithm and an outlier mining-based battery fault diagnosis algorithm are built in the cloud battery management platform (CBMP). The proposed cloud-based condition monitoring and fault diagnosis platform is validated by using a cyber-physical testbed and a computational cost analysis for the CBMP. Therefore, the proposed platform will support the on-board health monitoring and provide an intelligent and cost-effective maintenance of the large-scale Li-ion BESSs.

A Climatology and Case Study of Continental Cold Season Dense Fog Associated with Low Clouds

Abstract This study focuses on dense fog cases that develop in association with low clouds and sometimes precipitation. A climatology of weather conditions associated with dense fog at Peoria, Illinois, for October–March 1970–94 indicated that fog forming in the presence of low clouds is common, in 57% of all events. For events associated with low pressure systems, low clouds precede dense fog in 84% of cases. Therefore, continental fogs often do not form under the clear-sky conditions that have received the most attention in the literature. Surface cooling is usually observed prior to fog on clear nights. With low cloud bases, warming or no change in temperature is frequent. Thus, fog often forms under conditions that are not well understood, increasing the difficulty of forecasting fog. The possible mechanisms for fog development under low cloud-base conditions were explored for an event when dense fog covered much of Illinois on 7 November 2006. Weather Surveillance Radar-1988 Doppler (WSR-88D) and rawinsonde observations indicated that evaporating precipitation aloft was important in moistening the lower atmosphere. Dense fog occurred about 6 h following light precipitation at the surface. The surface was nearly saturated following precipitation, but relative cooling was needed to overcome weak warm air advection and supersaturate the lower atmosphere. Surface (2 m) temperatures were near or slightly cooler than ground temperatures in most of the region, suggesting surface sensible heat fluxes were not important in this relative cooling. Sounding data indicated drying of the atmosphere above 800 hPa. Infrared satellite imagery indicated deep clouds associated with a low pressure system moved east of Illinois by early morning, leaving only low clouds. It is hypothesized that radiational cooling of the low cloud layer was instrumental in promoting the early morning dense fog.

A new formula for determining the atmospheric longwave flux at the ocean surface at mid‐high latitudes

The accuracy of two empirical formulae used in recent climatological studies to estimate the atmospheric longwave flux at the ocean surface from ship meteorological reports has been evaluated using research cruise measurements from the northeast Atlantic. The measurements were obtained with a pyrgeometer and corrected for differential heating of the pyrgeometer dome and shortwave transmission through the dome. The formulae tested were from Clark et al. [1974] and Bignami et al. [1995]; neither was capable of providing consistently reliable estimates of the longwave flux. Clark overestimated the mean measured longwave of 341.1 Wm−2 by 11.7 Wm−2, while Bignami underestimated by 12.1 Wm−2. A new formula is developed that expresses the effects of cloud cover and other parameters on the longwave through an adjustment to the measured air temperature. The air temperature is adjusted by the amount necessary to obtain the effective temperature of a blackbody with a radiative flux equivalent to that from the atmosphere. A simple parameterization of the adjustment in terms of the total cloud amount gives longwave estimates that have an improved mean bias error with respect to the measurements of −1.3 Wm−2. The new formula is still biased under overcast, low cloud base conditions. However, by including a dependence on dew point depression in the formula, this bias is resolved, and the mean error reduced to 0.2 Wm−2. The new formula has been tested using measurements made on two subsequent cruises and found to agree to within 2 Wm−2 in the mean at middle‐high latitudes.

A Method for Validating FSSP Measurements Using Observational Data

A validation method of measurements from the forward-scattering spectrometer probe (FSSP) allowing preliminary analysis and verification of rough data is presented. It is based on the comparison of observed spectral distributions from undiluted cloudy air with theoretical adiabatic ones. The latter are obtained using an ascending adiabatic cloud-parcel model and the corresponding cloud-base conditions. A two-step approach is used to correct observed spectral distributions and is illustrated with data collected during the 1985 Joint Hawaii Warm Rain Project (JHWRP). The procedure provides an alternate way of obtaining the response matrix for an FSSP and can be used to validate the laboratory-derived response matrix. The results obtained (spectral characteristics and liquid water contents) agree well with the ones calculated from the laboratory characterization, which was made after the experiment, taking into account the laser beam nonuniformities.

Generation of available buoyant energy by cloud glaciation

The available buoyant energy (ABE, energy from the environment which becomes available to a parcel for buoyant accelerations) arising from glaciation is computed by integrating upward the differences in temperature between a parcel that undergoes instantaneous and isenthalpic freezing followed by an ice-saturation ascent, and one that experiences only a water-saturation ascent from the same initial cloud base conditions. This quantity is computed for three initial cloud base conditions representative of tropical, High Plains summertime, and Great Lakes wintertime cumuli. Substantial increases in parcel updraft speed are realized for all clouds if the ABE arising from glaciation is completely converted to parcel kinetic energy. Variations of the three components of parcel heating involved in the glaciation process (i.e., (1) release of latent heat of fusion from freezing of liquid water, (2) cooling or warming from sublimation or deposition as vapor pressure adjusts from water saturation to ice saturation at the post glaciation temperature, and (3) the additional warming or cooling relative to the intial water-saturation adiabat as the parcel follows an icesaturation ascent to a specified upper reference level) are also determined as functions of glaciation temperature. It is found that sublimation substantially counteracts the parcel warming arising from the freezing of liquid water in the case of warm moist cumuli. In addition, it is found that in some instances ice-saturation ascent following glaciation can produce cooling relative to the initial departure from the water saturation adiabat. This was indicated for Great Lakes wintertime cumuli and also for warm moist cumuli with glaciations at very cold temperatures. The effect upon the buoyancy force, of the change in the mass of condensate during glaciation, is small and can usually be neglected.

Experimental cumulus dynamics

Cumulus dynamics is approached as an experimental science. Its development since 1947 is briefly reviewed and the current convection models described, in particular models evolved from laboratory studies, such as the ‘starting plume’.A preliminary series of experiments on real tropical cumuli has been conducted as a method for testing and improving models and for assessing the range of applicability of the laboratory results. A silver iodide seeding technique was used in a joint U. S. Weather Bureau‐U. S. Navy experimental program called Project Stormfury. Eleven tropical cumulus clouds were probed by instrumented aircraft on four days in August 1963. Six were seeded by dropping pyrotechnic silver iodide generators into their tops at intervals of 100 meters or less; five were studied as ‘controls.’ All control clouds died without further growth. Of the treated clouds, one was seeded by misunderstanding when its top was below 10,000 feet; it collapsed. The remaining five treated clouds grew. Of these, three were seeded at low enough elevations so that natural glaciation was unlikely; these are called the ‘test’ clouds. All three test clouds were observed to ‘explode’ in two phases. The first phase was a vertical growth of 10,000–20,000 ft, occupying 10–12 minutes; the second was a horizontal expansion, with the resulting giant cloud persisting more than 30 minutes. Using laboratory and theoretical results, we construct a dynamic model of the first growth phase and test it against the aircraft measurements and photographic data. The model predicts tower ascent rates, excess temperatures, and water contents, with environment and cloud base conditions as input. It predicts that unmodified clouds could not have attained the observed heights. Furthermore, the postulated effects of seeding (fusion heating, expansion, and altered precipitation fallout) are incorporated into the model and are shown able to account for the excessive growth of the test clouds following treatment. A set of extensive control calculations shows that the main deductions are insensitive to the existing uncertainties in the input data and the modeling assumptions. Improved experiments are suggested to resolve some of the basic questions in cumulus dynamics, as well as seeding effects.

I—Decca for Helicopter Operations

For a number of years helicopter operations will mainly take place at operating altitudes between 500 and 2000 ft. Due to the inaccuracies of existing pressure altimeters vertical separation less than 1000 ft. cannot be applied and therefore maximum use will have to be made of lateral and longitudinal separation possibilities if the development of helicopter operations in high density areas is not to be impeded. As far as possible helicopter operations will be kept apart from fixed-wing traffic but this may be difficult to achieve in terminal areas where departing and arriving fixed-wing aircraft are at low altitude and the available airspace is restricted.It is, therefore, essential that the navigational aid on which air traffic control base safe separation should be one which enables the helicopter pilot to adhere strictly to his pre-determined track and also provides him with an accurate measurement of progress along track. Quite apart from the air traffic control aspect, since the helicopter flies low, frequently in poor horizontal visibility and low cloud-base conditions, accurate track keeping is essential from the standpoint of avoiding obstructions or high ground in the vicinity of the route. Accurate and solid coverage over a wide area at low altitude is therefore an important requirement of any helicopter aid system, particularly in a high traffic density area such as western Europe.