WorldWideScience
 
 
1

Computer aided monitoring of pump efficiency by using ART2 neural networks; ART2 nyurarunettowaku niyoru ponpuseino no rekka shindan shien  

Energy Technology Data Exchange (ETDEWEB)

As an application of ART2 neural networks, computer aided monitoring of pump efficiency is successfully examined for an industrial waste-liquid treatment process with measured data of valve openness and liquid flow rates. By running the neural networks in parallel, we confirm that accuracy to detect system changes is good, and the adjustment of classifier parameters is relatively easy. Investigating the resulting classes carefully, frequency of each class is correlated with pump efficiency. The relative amount of variables are also related to the classes. (author)

2000-05-10

2

Visualization of powder behavior for filling; Funmatsu juten kyodo no kashika gijutsu  

Energy Technology Data Exchange (ETDEWEB)

Further improvement of dimensional tolerance and elimination of such post-processing as cutting work are required for the maximum exhibition of the features of sintered parts. Powder behavior in fall filling and leveling off is observed with the prototype of visual apparatus for observing powder filling. It is found that the delay in the replacement of powder by air in the die and the fall along the angle of repose are the causes for the occurrence of particle size segregation, and that the diagonal downward slide of powder in upper layer only in leveling off is the cause for nonuniformity of the density. As a result, it is found that improvement of powder flowability and minimization of shaking are important for uniform and rapid filling of powder in a thin walled and complicated shape die cavity, and a guide for developing uniform filling method is made clear. Based on the result, a new uniform filling method for powder is under development to improve the flowability of powder. 9 ...

1998-09-15

3

Fault detection and fault diagnosis system for engine; Engine no kosho yochi shindan system  

Energy Technology Data Exchange (ETDEWEB)

The fault detection and diagnosis system for gas engines was developed to improve the reliability of cogeneration systems (CGS). Most of existing fault detection systems monitor the trend of each part condition of engines and diagnose faults based on trend change, resulting in slow detection. Although early detection systems are available, those are complex, expensive and poor in flexibility and applicability. Since CGSs combined with gas engines increased to 1/3 of the whole CGS, engine troubles cause possible serious faults. The fault diagnosis system was thus developed to prevent serious faults which can early detect, in particular, abnormal conditions of parts around a combustion chamber such as ignition plug, intake valve and exhaust valve by monitoring exhaust pressure waveforms in an exhaust collector. Since this system can detect progressive occurrence frequency of abnormal conditions and degradation of engine parts, it can transfer previous time management and preventive ...

1996-03-29