Hitachi, Ltd.

Hitachi Engineering Co., Ltd.

Naoki Hara

Mikio Yoda

Shoji Watanabe

Kenji Baba

Hayao Yahagi

Ichiro Enbutsu

Harumi Matsuzaki

Shunsuke Nogita

Hiroshi Matsumoto

Fumio Maruhashi

Shunji Mori

Masahiko Ishida

Takashi Iida

Masakatsu Hiraoka

Kazushi Tsumura

Yoshikatsu Asada

Yuzi Yamasawa

Toshimitu Akiyama

Takashi Katori

Kenzi Baba

Bunchi Kimura

Misako Obuchi

A method and a system for causing a neural circuit model to learn typical past control results of a process and using the neural circuit model for supporting an operation of the process. The neural circuit model is caused to learn by using, as input signals, a typical pattern of values of input variables at different points in time and, as a teacher signal, its corresponding values of the control variable. An unlearned pattern of input variables is inputted to the thus-learned neuron circuit model, whereby a corresponding value of the control variable is determined. Preferably, plural patterns at given time intervals can be simultaneously used as patterns to be learned.

Supporting method and system for process operation

A method for causing a neural circuit model to learn typical past control results of a process and using the neural circuit model for supporting an operation of the process. The neural circuit model is caused to learn by using, as input signals, a typical pattern of values of input variables at different points in time and, as a teacher signal, its corresponding values of the control variable. An unlearned pattern of input variables is inputted to the thus-learned neuron circuit model, whereby a corresponding value of the control variable is determined. Preferably, plural patterns at given time intervals can be simultaneously used as patterns to be learned.

Supporting neural network method for process operation

When amounts of operation control variables and/or operation state evaluation variables of a plant are calculated through a multilayered neural network based on data indicating a plant state, and the calculated results are indicated to an operator, a plant operation support system has functions to analyze an internal causality between neurons in the neural network, and display quantitative guidance by association in the neural network and also the analyzed result of the internal causality between the neurons as an association reason.

Plant operation support system

In a water supply plant which cleans water taken in from such sources of intake water as lakes and marshes, dams, rivers and so on and delivers the water as city water, obstructions to water treatment is predicted and methods for preventing the obstruction are decided, by measuring kinds and quantity of plankton and comparing the measured data with rules representing relations among kinds and quality of plankton, obstructions to water treatment and counteractions to such obstructions stored in a rule base in advance.

System for controlling water treatment based on plankton monitoring

In order to speed up and simplify automated learning of rules by a neural network making use of fuzzy logic, data from a system is analyzed by a teaching data creation means which groups the data into clusters and then selects a representative data item from each group for subsequent analysis. The selected data items are passed to a rule extraction means which investigates relationships between the data items, to derive rules, but eliminates rules which have only an insignificant effect on the system. The results are candidate rules which are stored in a first rule base. The candidate rules are then compared with rules in a second rule base to check for duplication and/or contradiction. Only those rules which are not duplicated and not contradictory are stored in the second rule base. Hence, when fuzzy inference is used to control the system on the basis of rules in the second rule base, only valid rules which provide a significant effect on the system are used.

Method of automated learning, an apparatus therefor, and a system

Suspended substances, such as active sludge, in a liquor is treated in an apparatus for treating the liquor by predicting a suspension state on the basis of an amount of existing suspended substances in the liquor.

Process for treating suspended substances in liquor

A fish is bred in a transparent basin, into which water to be tested is supplied. A light source and a television camera are arranged in such a manner that images of the fish are taken by the camera as a silhouette. From the thus obtained fish images, the frequency distribution of the gravity centers of the fish images in the direction of the depth of water are obtained. The abnormality of the behavior of the fish is detected by comparison of the obtained frequency distribution with a reference distribution provided in advance.

Apparatus for monitoring the toxicant contamination of water by using

An injection control system of a flocculating agent comprises: a flocculating pool into which the inflow liquid flocculating agent is injected and which forms flocs of suspended matters in the liquid; flocculating agent injecting means for injecting the flocculating agent into the flocculating pool; floc image pickup means for photographing a state of the flocs in the flocculating pool and for converting luminance data of the flocs into an electric signal; image recognizing means for recognizing the shape of floc by binarizing the image signal derived from the floc image pickup means on the basis of a luminance level of each pixel; flocculation state deciding means for calculating a characteristic amount of a diameter distribution of the flocs on the basis of the floc shapes recognized by the image recognizing means; and injection amount control means for controlling an amount of the flocculating agent which is injected from the flocculating agent injecting means on the basis of the characteristic amount.

Injection control system of flocculating agent

The image of microorganisms contained in a sludge of an aeration tank is picked up by an image pickup device having the function of magnifying and picking up microorganism images. Binarizing processing is then made to obtain a binarized image from the resulting gray image, and the binarized image is subjected to thinning processing. The number of pixels of the image left after often the thinning processing is counted to measure the amount of filamentous microorganisms. In this manner, the amount of the filamentous microorganisms can be measured accurately irrespective of their thickness.

Growing community of inventors

Hitachi, Japan

Naoki Hara