Error compensation in machine tools: a neural network approach

For a non-idealized machine tool, each point in the workspace is associated with a tool point positioning error vector. If this error map can be determined, then it is possible to substantially improve the positioning performance of the machine by introducing suitable compensation into the control loop. This paper explores the possibility of using an artifical neural network (ANN) to compute this mapping. The training set for the ANN is obtained by mounting a physical artifact whose dimensions are precisely known in the machine's workspace. The machine, equipped with a touch trigger probe, measures the positions of features on the artifact. The difference between the machine reading and the known dimension is the machine error at that point in the workspace. Using standard modeling techniques, the kinematic error model for a CNC turning center was developed. This model was parameterized by measurement of the parametric error functions using a laser interferometer, electronic levels and a precision square. The kinematic model was then used to simulate the artifact-measuring process and develop the ANN training set. The effect of changing artifact geometry was explored and a machining operation was simulated using the ANN output to provide compensation. The results show that the ANN is capable of learning the error map of a real machine, and that ANN-based compensation can significantly reduce part-dimensional errors.     

Modeling mineral phase change chemistry of groundwater in a rural-urban fringe

This research paper aims to determine the genetic origin of the chemical elements in groundwater. It deals with the results of physicochemical parameters, to evaluate the hydro-geochemistry of groundwater in rural-urban fringe of district Bareilly, India. Pre- and post-monsoon sampling has been carried out, which reveals inter-seasonal variability effect on the hydro-geochemical processes. Geochemical modeling especially computation of saturation index was undertaken using the WATEQ4F model. Majority of samples fall in the category of undersaturation, which further suggests that groundwater still has potential to dissolve more minerals. Chemical categorizations of groundwater samples were performed with the help of the Aquachem model. Grouping of groundwater on the Piper diagram reveals a common composition and origin. In most of the area, water facies is of Ca(2+)-HCO(3)(-) type in both the seasons. It also indicates that in pre-monsoon, ion exchange is the dominant process, whereas in post-monsoon, both ion exchanges as well as reverse ion exchanges are reported in the groundwater of the study area.     

On Security and Reliability Using Cooperative Transmissions in Sensor Networks

Cooperative transmissions have received recent attention and research papers have demonstrated their benefits for wireless networks. Such benefits include improving the reliability of links through diversity and/or increasing the reach of a link compared to a single transmitter transmitting to a single receiver (single-input single-output or SISO). In one form of cooperative transmissions, multiple nodes can act as virtual antenna elements and provide diversity gain or range improvement using space-time coding. In a multi-hop ad hoc or sensor network, a source node can make use of its neighbors as relays with itself to reach an intermediate node with greater reliability or at a larger distance than otherwise possible. The intermediate node will use its neighbors in a similar manner and this process continues till the destination is reached. Thus, for the same reliability of a link as SISO, the number of hops between a source and destination may be reduced using cooperative transmissions as each hop spans a larger distance. However, the presence of malicious or compromised nodes in the network impacts the benefits obtained with cooperative transmissions. Using more relays can increase the reach of a link, but if one or more relays are malicious, the transmission may fail. However, the relationships between the number of relays, the number of hops, and success probabilities are not trivial to determine. In this paper, we analyze this problem to understand the conditions under which cooperative transmissions fare better or worse than SISO transmissions. We take into consideration additional parameters such as the path-loss exponent and provide a framework that allows us to evaluate the conditions when cooperative transmissions are better than SISO transmissions. This analysis provides insights that can be employed before resorting to simulations or experimentation.     

Control of a robotic orthosis for gait rehabilitation

Robot assisted gait training may help in producing rapid improvements in functional gait parameters. This paper presents new experimental results with an intrinsically compliant robotic gait training orthosis. The newly developed robotic orthosis has 6 degrees of freedom (DOFs). A trajectory tracking controller based on the boundary layer augmented sliding control (BASMC) law was implemented to guide the subject’s limbs on physiological gait trajectories. The compliance of the robotic orthosis sagittal plane hip and knee joints was also controlled, independently of the trajectory tracking control. The robotic orthosis and the control scheme were evaluated on three neurologically intact subjects walking on a treadmill. A maximum trajectory tracking error of 10° was recorded at the hip and knee sagittal plane joints. The results showed that subjects can walk in the robotic orthosis with comfort and the BASMC law was able to guide the subject’s limbs on reference physiological trajectories.     

Fraudulent Firm Classification: A Case Study of an External Audit

This paper is a case study of visiting an external audit company to explore the usefulness of machine learning algorithms for improving the quality of an audit work. Annual data of 777 firms from 14 different sectors are collected. The Particle Swarm Optimization (PSO) algorithm is used as a feature selection method. Ten different state-of-the-art classification models are compared in terms of their accuracy, error rate, sensitivity, specificity, F measures, Mathew’s Correlation Coefficient (MCC), Type-I error, Type-II error, and Area Under the Curve (AUC) using Multi-Criteria Decision-Making methods like Simple Additive Weighting (SAW) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The results of Bayes Net and J48 demonstrate an accuracy of 93% for suspicious firm classification. With the appearance of tremendous growth of financial fraud cases, machine learning will play a big part in improving the quality of an audit field work in the future.     

Development of real-time reference evapotranspiration at the regional scale using satellite-based observations

Real-time data of reference evapotranspiration (ET₀) at different space-time scales are essential to regional agricultural drought assessment, water accounting at the watershed to basin scale, and provide irrigation advisory to farmers. Here, we present a data-fusion approach that integrates satellite-based insolation product (8 km) from an Indian geostationary satellite (Kalpana-1) sensor (VHRR; Very High Resolution Radiometer) and high-resolution (~ 5 km) short-range weather forecast into an FAO56 model based on the classical Penman–Monteith (P-M) formulation. Five year (2009–2013) mean monthly estimates from the daily ET₀ product over the Indian landmass were found to vary between 10 and 350 mm. It increased from January to May (70–350 mm), followed by a decrease to reach the lowest in November (10–140 mm), thus typically showing unimodal distribution. The comparison of daily space-based and station-based estimates (at six ground stations) produced a root mean square deviation (RMSD) ranging from 21% to 38% for 977 paired data sets with the correlation coefficient (r) varying from 0.32 to 0.82. The error was reduced from 25% to 10% with an increase in ‘r’ from 0.43 to 0.98 for daily to 10 day summation period. Spatial grid-to-grid comparison of monthly ET₀ estimates with Global Data Assimilation System (GDAS) potential evapotranspiration (PET) showed RMSD within a range of 1.4–18.4% for most of the months, except for two. Further ET₀ analysis over normal and drought years showed that it could be used for comprehensive drought assessment with other existing indicators.     

Physico‐mechanical properties of nano‐polystyrene‐decorated graphene oxide–epoxy composites

Nano‐polystyrene (nPS)‐decorated graphene oxide (GO) hybrid nanostructures were successfully synthesized using stepwise microemulsion polymerization, and characterized using Fourier transform infrared (FTIR) spectroscopy, X‐ray diffraction (XRD), field‐emission scanning electron microscopy and transmission electron microscopy. XRD and FTIR spectra revealed the existence of a strong interaction between nPS and GO, which implied that the polymer chains were successfully grafted onto the surface of the GO. The nPS‐decorated GO hybrid nanostructures were compounded with epoxy using a hand lay‐up technique, and the effect of the nPS‐decorated GO on the mechanical, thermal and surface morphological properties of the epoxy matrix was investigated using a universal tensile machine, Izod impact tester, thermogravimetric analysis and contact angle measurements with a goniometer. It was observed that in the epoxy matrix, GO improved the compatibility. © 2017 Society of Chemical Industry