Applications of artificial intelligence to condition-based maintenance

In this paper we discuss interesting developments of expert systems for machine diagnosis and condition-based maintenance. We review some elements of condition-based maintenance and its applications, expert systems for machine diagnosis, and an example of machine diagnosis. In the last section we note some problems to be resolved so that expert systems for machine diagnosis may gain wider acceptance in the future.

Molecular approaches for the detection of Schistosoma mansoni: possible applications in the detection of snail infection, monitoring of transmission sites, and diagnosis of human infection

The detection of specific DNA sequences by polymerase chain reaction (PCR) has proved extremely valuable for the analysis of genetic disorders and the diagnosis of a variety of infectious disease pathogens. However, the application to the detection of Schistosoma mansoni is rare, despite a recommendation of the World Health Organization that a major focus of research on schistosomiasis should be on the development and evaluation of new strategies and tools for control of the disease. In this context, a few studies were published for the detection of the parasite in snails, monitoring of cercariae in water bodies, and diagnosis of human infection. The present minireview describes sensitive and specific PCR based systems to detect S. mansoni, indicating possible applications in the detection of snail infection, monitoring of transmission sites, and diagnosis of human infection.

Aeration condition of a clayey oxisol under long-term no-tillage

The hypothesis of this study was that the absence of soil tillage in long-term no-tillage (NT) systems can be detrimental to soil aeration. The objective was to assess the aeration condition of an Oxisol (Rhodic Ferrasol), very clayey texture (750 g kg-1 of clay; 200 g kg-1 of sand), after 30 years of cultivation under NT. The physical property soil air permeability (Ka) is sensitive to changes in the soil pore system. Aside from Ka, the air-filled porosity (ε a) and indices of pore continuity (K1 and N), derived from the relationship between Ka and εa, were used as indices of soil aeration. From the soil layers 0.0-0.1 and 0.1-0.2 m, 240 undisturbed samples were collected along a transect perpendicular to the crop rows, at three sampling positions: corn plant row (CR); center of the interrow (INT); and the equidistant point between CR and INT (PE). The properties Ka and εa were determined at soil matric potentials (Ψm) of -2, -4, -6, -10, -30, and -50 kPa. Soil bulk density (BD) was also determined. The results confirmed the hypothesis. In the 0.0-0.1 m layer, Ka, K1, N and Ψa were significantly greater and BD significantly lower in CR than at the other sampling positions. At a Ψm of -10 kPa, the Ka of CR was 6.9 and 8.4 times higher than in PE and INT, respectively, in the 0.0-0.1 m layer. The properties Ka, K1 and N were sensitive enough to detect changes in the pore system and their differences between the sampling positions demonstrated the importance of the spatial location for soil sampling. Tilling the crop rows provides better soil aeration under NT.

Physical Properties of a Hapludox after Three Decades under Different Soil Management Systems

ABSTRACT Changes in soil physical properties due to different management systems occur slowly, and long-term studies are needed to assess soil quality. The objectives of this study were to evaluate the effects of soil management systems and liming methods on the physical properties of a Latossolo Bruno Alumínico típico (Hapludox). A long-term experiment that began in 1978 with conventional and no-tillage systems was assessed. In addition, different liming methods (no lime, incorporated lime, and lime on the soil surface) have been applied since 1987 and were also evaluated in this study. Moreover, an area of native forest was evaluated and considered a reference for the natural condition of the soil. Soil physical properties were evaluated in layers to a depth of 1.00 m. Compared to native forest, the conventional tillage and no-tillage systems had higher soil bulk density, penetration resistance, and microporosity, and lower aggregate stability and macroporosity. Compared to the conventional tillage system, long-term no-tillage improved the structure of the Hapludox, as evidenced by increased microporosity and aggregate stability, especially in the soil surface layer. In no-tillage with lime applications sporadically incorporated, soil physical properties did not differ from no-tillage without lime and with lime applied on the soil surface, indicating that this practice maintains the physical quality of soil under no-tillage. Liming in a conventional tillage system improved soil aggregation and reduces penetration resistance in the soil layers near the soil surface. No-tillage was the main practice related to improvement of soil physical quality, and liming methods did not influence soil physical properties in this soil management system.

Use of data mining and spectral profiles to differentiate condition after harvest of coffee plants

This study aimed at identifying different conditions of coffee plants after harvesting period, using data mining and spectral behavior profiles from Hyperion/EO1 sensor. The Hyperion image, with spatial resolution of 30 m, was acquired in August 28th, 2008, at the end of the coffee harvest season in the studied area. For pre-processing imaging, atmospheric and signal/noise effect corrections were carried out using Flaash and MNF (Minimum Noise Fraction Transform) algorithms, respectively. Spectral behavior profiles (38) of different coffee varieties were generated from 150 Hyperion bands. The spectral behavior profiles were analyzed by Expectation-Maximization (EM) algorithm considering 2; 3; 4 and 5 clusters. T-test with 5% of significance was used to verify the similarity among the wavelength cluster means. The results demonstrated that it is possible to separate five different clusters, which were comprised by different coffee crop conditions making possible to improve future intervention actions.

Health management practices and disease prevalence in dairy sheep systems in Argentina

A cross-sectional survey of 19 dairy sheep farms in Argentina was carried out with the purpose to know farm management, health practices, and occurrence and mortality of diseases. The survey comprised 40% of all sheep milking farms in Argentina. A questionnaire was conducted by way of personal interviews with sheep owners during farm visits. The proportions of farms reporting routine vaccination for clostridial diseases, contagious ecthyma, pneumonia and mineral and vitamin parenteral administration were 63%, 47.3%, 16.6% and 42.1% respectively. Regular treatment against lice was used in 37.5% of the farms, and 89.5% o the farmers treated against gastrointestinal nematodes (GIN). The mean number of GIN drenches per farm was 2.26±1.78 annually. In 68.4% of the milking flocks the California Mastitis Test was regularly done and 55.6% of the farmer managers had sampled their flocks once a year for Brucella ovis antibodies. During the pre-mating period respectively 68.4% and 50% of farmers clinically examined their rams and ewe for general health and teeth condition. The udders of ewes were frequently inspected at the start of each milking period. The most important parasite problems noticed were GIN (reported by 57.9% of farmers), lice (57.9%) and scabies (10.5%) and the most frequent infectious diseases were ecthyma (73.7%), pneumonia and other respiratory problems (57.9%), clinical mastitis (55.6%), clostridial diseases (36.9%) and foot lameness (35.2%). Photosensitivity (47.4%) and ruminal acidosis (42.1%) were reported as other frequent toxic or metabolic disorders. Owners mentioned that the mean lifespan or milk productive time per ewe was 4.5±1.4 years. Perinatal lamb mortality was 8.5% and the total flock mortality rates, above the first 24 h of life was 6.9%. The high rates of lamb mortality during the pre-weaning (10.3%) and post-weaning (5.9%) periods indicate that this problem, as well as the most prevalent diseases, should be the subject of further studies.

Serial superficial digital flexor tendon biopsies for diagnosing and monitoring collagenase-induced tendonitis in horses

The purpose of this investigation was to demonstrate the feasibility of a biopsy technique by performing serial evaluations of tissue samples of the forelimb superficial digital flexor tendon (SDFT) in healthy horses and in horses subjected to superficial digital flexor tendonitis induction. Eight adult horses were evaluated in two different phases (P), control (P1) and tendonitis-induced (P2). At P1, the horses were subjected to five SDFT biopsies of the left forelimb, with 24 hours (h) of interval. Clinical and ultrasonographic (US) examinations were performed immediately before the tendonitis induction, 24 and 48 h after the procedure. The biopsied tendon tissues were analyzed through histology. P2 evaluations were carried out three months later, when the same horses were subjected to tendonitis induction by injection of bacterial collagenase into the right forelimb SDFT. P2 clinical and US evaluations, and SDFT biopsies were performed before, and after injury induction at the following time intervals: after 24, 48, 72 and 96 h, and after 15, 30, 60, 90, 120 and 150 days. The biopsy technique has proven to be easy and quick to perform and yielded good tendon samples for histological evaluation. At P1 the horses did not show signs of localised inflammation, pain or lameness, neither SDFT US alterations after biopsies, showing that the biopsy procedure per se did not risk tendon integrity. Therefore, this procedure is feasible for routine tendon histological evaluations. The P2 findings demonstrate a relation between the US and histology evaluations concerning induced tendonitis evolution. However, the clinical signs of tendonitis poorly reflected the microscopic tissue condition, indicating that clinical presentation is not a reliable parameter for monitoring injury development. The presented method of biopsying SDFT tissue in horses enables the serial collection of material for histological analysis causing no clinical signs and tendon damage seen by US images. Therefore, this technique allows tendonitis to be monitored and can be considered an excellent tool in protocols for evaluating SDFT injury.

Vibration analysis for Bearing outer race condition diagnostics

This paper investigates defect detection methodologies for rolling element bearings through vibration analysis. Specifically, the utility of a new signal processing scheme combining the High Frequency Resonance Technique (HFRT) and Adaptive Line Enhancer (ALE) is investigated. The accelerometer is used to acquire data for this analysis, and experimental results have been obtained for outer race defects. Results show the potential effectiveness of the signal processing technique to determine both the severity and location of a defect. The HFRT utilizes the fact that much of the energy resulting from a defect impact manifests itself in the higher resonant frequencies of a system. Demodulation of these frequency bands through use of the envelope technique is then employed to gain further insight into the nature of the defect while further increasing the signal to noise ratio. If periodic, the defect frequency is then present in the spectra of the enveloped signal. The ALE is used to enhance the envelope spectrum by reducing the broadband noise. It provides an enhanced envelope spectrum with clear peaks at the harmonics of a characteristic defect frequency. It is implemented by using a delayed version of the signal and the signal itself to decorrelate the wideband noise. This noise is then rejected by the adaptive filter that is based upon the periodic information in the signal. Results have been obtained for outer race defects. They show the effectiveness of the methodology to determine both the severity and location of a defect. In two instances, a linear relationship between signal characteristics and defect size is indicated.