Hitachi, Ltd.

Keiro Muro

Kei Suzuki

Kazuaki Iwamura

Minoru Ogushi

Toshiyuki Odaka

Hiromitsu Nakagawa

Shoji Suzuki

Masakazu Takahashi

Machiko Asaie

Sadaki Nakano

Yasuei Nomoto

Kazuo Tsutsui

Yoshiko Nagasaka

Satoshi Yamaguchi

Shinji Fujiwara

Yoshihiro Wakisaka

Hiroyuki Ota

Hiroaki Ozaki

Yukio Funyu

Takuya Komatsuda

Nobuhiro Ishimaru

Shintaro Hatsumoto

Shu Tezuka

Takehiro Urano

Qi Xiu

Cheng Luo

Munoru Ogushi

Yoichi Kawachiya

Norimasa Shibata

Takuro Yasui

A manufacturing condition setting automating apparatus includes: a quality judging unit that computes a present process quality from facility data at predetermined time intervals, and judges whether or not it is in a quality tolerance range; a manufacturing condition candidate creating unit that computes a feature quantity, searches a database for condition change cases having similar feature quantities, tabulates condition change cases basis on whether the condition change cases are successes or failures, and outputs manufacturing condition candidates in descending order of rates of successes; an imbalance-preventing manufacturing condition candidate creating unit that changes scores that decide ranks of manufacturing condition candidates, and creates a ranking of manufacturing condition candidates; and a manufacturing condition output unit that outputs a set value of a condition change of a top manufacturing condition candidate to the manufacturing facility, and registers a new condition change in the condition change history.

Manufacturing condition setting automating apparatus and method

Indexes having local features are automatically selected from sensor data of a plurality of sensors. Sensor data of the plurality of sensors, each associated with the plurality of indexes, is partitioned into a plurality of blocks. A principal component analysis is applied to the sensor data of each of the partitioned blocks and a plurality of principal components are extracted from each of the blocks. A migration distance evaluation unit extracts, from two different blocks, two principal components that form a principal component pair, and calculates a migration distance between each of the principal components regarding the extracted principal component pair. A migration factor index detection unit detects, as a migration factor index, an index among the plurality of indexes configuring the principal components having a large migration distance among the migration distances between each of the principal components calculated by the migration distance evaluation unit.

Index selection device and method

To optimize an operation of a manufacturing facility by presenting a countermeasure for improving quality, even in a manufacturing process where the product quality changes even under constant manufacturing conditions. A countermeasure recommendation device includes a data acquisition unit for collecting a plurality of pieces of facility data, and assigning a label for each process to each piece of the facility data; a countermeasure detection unit for creating countermeasure record data; a countermeasure recommendation unit for calculating the characteristic amount, extracting the characteristic amount, and selecting the countermeasure related to the extracted characteristic amount; and a countermeasure presentation unit for presenting the countermeasure in a visualized state.

Countermeasure recommendation device and countermeasure recommendation method

A traceability estimation unit generates batch combination output data configured by a plurality of combinations of a batch in the first process and a batch in the second process, and the feature of the batch. The traceability estimation unit estimates the combination of the batch in the first process and the batch in the second process, which is used as traceability, from the plurality of the combinations of the batches in the batch combination output data by using the feature.

Analysis system

A traceability system includes: a Equipment table that stores production data of a product manufactured in a first process, in which an individual ID is appended to a product; a Equipment table that stores production data of a product manufactured in a second process, in which an individual ID is not appended to a product; a training data setting unit that creates a training data table that stores the Equipment table and the Equipment table, which are correlated with each other; a feature amount extracting unit that calculates a cycle time of a predetermined number of products manufactured in the past in the first process; a model creation section that creates a production time estimation model for estimating a production time at which a product has been manufactured in the second process on the basis of the cycle time of the products; and a production time estimating unit.

Traceability system and method for traceability

An analysis method performed by a computer analyzes analysis data acquired from a system which includes a plurality of devices to manufacture a product. The computer manages a set of values of each field of the analysis data as a column, analyzes a correspondence from a value belonging to a first target column to a value belonging to a second target column, specifies a surjection column pair which is a set of the first target column and the second target column which have a surjective correspondence, generates graph information to manage a graph of tree structure indicating a connection relation of the column by connecting a graph which has nodes of the first target column and the second target column of the surjection column pair, and performs a yield analysis to specify a parameter affecting an evaluation value using the graph information.

Analysis method and computer

An analysis control device controls an analysis based on time series data for each of a plurality of sensors corresponding to a plurality of components that constitute a target device. The analysis control device acquires sensor data sets belonging to an analysis target time zone among the time series data of each of the plurality of sensors. Each sensor data set includes measurement values measured by a sensor. The analysis control device calculates an evaluation value according to a simple evaluation by using two or more sensor data sets corresponding to the sensor among the plurality of sensor data sets belonging to the analysis target time zone. The analysis control device sets an execution order of the analysis based on the measurement values of the sensor within a restricted time corresponding to the analysis target time zone in a descending order of the calculated evaluation value.

Time series data analysis control method and analysis control device

A computer system acquires information on a first present input subset selected from first present input data for a first step from a run-time log of the first step, determines whether or not first cache data corresponding to the first present input subset for the first step is present in a cache area with reference to management information, and determines the first cache data as present output data for the first present input data in a case where the first cache data is present.

Computer system

An information processing system includes: a document reception unit configured to receive multiple pieces of document data; a data storage unit configured to store the received multiple pieces of document data; and a correspondence relation estimation unit configured to estimate a correspondence relation at least between an item in a first document data and an item in a second document data out of the multiple pieces of document data stored in the data storage unit. The correspondence relation estimation unit includes an item-item coupling relation extraction unit configured to extract a coupling relation among items in the first document data and a coupling relation among items in the second document data, and a word relationship extraction unit configured to extract a relevance between a word that appears in an item in the first document data and a word that appears in an item in the second document data.

Informationimage processing system and informationimage processing method

The analysis system executes an analysis process which takes as input data at least portions of: time series data of a plurality of instances of value data which each include times and values; and analysis data which includes data which has been outputted by previous analysis processes. Each of the one or more objects is a process definition conforming to a user operation. In the analysis process, the analysis system skips at least one of: an execution of a process conforming to an object which matches any previous object; an execution of a process conforming to an object for a scope block and process description, among a plurality of scope blocks which constitute the scope to be analyzed, which match a scope block and process description which are associated with any stored data block; and/or the storage of a data block which matches any stored data block.

Analysis system and analysis method for executing analysis process with at least portions of time series data and analysis data as input data

An event flow system connecting nodes, for which processes are defined, from an upstream side to a downstream side by an event which is generated due to a certain process and is used by another process to realize a process flow is provided. The event flow system includes: a process flow builder configured to build a process flow using a plurality of nodes, one or more events, and a reverse event that sends a predetermined request, from a downstream node to an upstream node disposed further toward an upstream side than the downstream node; and a process flow executer configured to execute a process defined for each of the plurality of nodes according to the event and the reverse event.

Event flow system and event flow control method

A series data distributed processing system including a parallel processing system and a distributed series data management unit managing distributed series data, wherein: the parallel processing system includes, on each computing device, a data block, a data block processing server for processing the data block, and a block processing integration server for processing a result from the data block processing server, the data block being formed from a plurality of values each associated with one of a plurality of sequential labels in the series data; and the distributed series data management unit includes a distributed information management database for managing data blocks, which retains management data, including sequential label ranges, which refer to ranges of sequential labels in the data blocks, series IDs corresponding to value names in the data blocks, and meta-information identifying computing devices retaining the data blocks.

System and method for parallel processing data blocks containing sequential label ranges of series data

Disclosed is a computer system provided with a plurality of sensors provided in a plurality of devices to observe a predetermined amount, and a server for examining the physical amount transmitted from the sensors, wherein the plurality of devices are classified into a first device group and a plurality of second device groups, a plurality of second examination rules indicating the examination methods of the physical amount are set in the plurality of second device groups, the server calculates the similarity between the first device group and each of the second device groups, and, on the basis of the calculated similarity, a first examination rule to be set in the first device group is extracted from the plurality of second examination rules set in the plurality of second device groups.

Computer system and rule generation method

In a system manages a plurality of pieces of sensor information in a plant, or the like, it can be reducing an amount of data stored in a database and easily a processing for searching a place of an anomaly and an anomaly cause. A database management method for use in a computer for managing a database, the database management method including: a step of analyzing a query; a step of generating a first inquiry for searching the database for compressed data; a step of generating a second inquiry for executing a search of time-series data; a step of extracting given data from the obtained time-series data, based on a response result of the second inquiry; and a step of generating an output result by extracting data to be output to a client computer from the given data.

Database management method, computer, sensor network system and time-series data management method

A sensor-Net system includes sensor nodes which are in intermittent operation so as to save power by repeating activated state and inactivated state at a regular interval. Synchronization of time in the system is executed by aligning to the intermittent operation of the sensor nodes. A management server issues a setTime command for configuring the time to each gateway node at a specified interval. Each router node sets or corrects the time of it based on the time received from the gateway node and thereafter turns ON the time configuration flag for each sensor node in order to expand the setTime command to all of its sibling sensor nodes. The router node, upon reception of a polling, which is a command request, from the sensor node, obtains the time at that time, then uses the time to generate a setTime command to transmit to that sensor node.

Growing community of inventors

Tokyo, Japan

Keiro Muro