International Business Machines Corporation

Thk Co., Ltd.

Mitsubishi Electric Corporation

Satoshi Hara

Masashi Ishii

Katsuya Fukushima

Tomofumi Mizuno

Shogo Wakuta

Akira Suzuki

Tetsuro Morimura

Hiroki Niwa

Shigeki Hayashi

Kazuto Oga

Takayuki Katsuki

Gakuto Kurata

Seiji Takeda

Shigeru Nakagawa

Tomoki Takegami

Takahito Ida

Toshihiro Takahashi

Sadayuki Inoue

Shigeru Aihara

Hiroki Yanagisawa

Toshihiro Wada

Rudy Raymond Harry Putra

Makiko Kise

Yuruki Okada

Hisatoshi Fukumoto

Hidemasa Muta

Raymond Harry Rudy

Hiroki Ishihara

Sho Shiraga

Toshinari Itoko

Satoru Nagai

Yasunori Yamada

Yukihiro Yoshida

Hiroto Nishiguchi

Yukihiro Yamada

The present invention more suitably adjusts a pressure at a tip of a shaft in an actuator configured to generate a negative pressure at the tip of the shaft, to pick up a workpiece with the shaft. A negative pressure-generating structure to be applied to the actuator includes an insertion hole into which the shaft is inserted in a state where a space is formed between the shaft and a wall surface of the insertion hole, an inner space formed inside the negative pressure-generating structure, which communicates with a hollow part of the shaft through a communication hole formed in the shaft, and an air passage connected to the inner space, the air passage being a passage of air when air in the inner space is sucked to generate the negative pressure at the tip of the shaft.

Negative pressure-generating structure and actuator

Provided is an actuator including a shaft, a drive part that moves the shaft, a fixing part disposed around the shaft, the shaft being moved relative to the fixing part, a detecting part that detects a force applied to the shaft on a side closer to the drive part than to the fixing part, and a control device that obtains a first force that is detected by the detecting part in a predetermined period of a period during which the shaft is being moved before the shaft applies the force to a workpiece, and after the predetermined period, controls the drive part based on the force detected by the detecting part and the first force.

Actuator

Provided is a sensing device to be applied to an actuator including a shaft that is movable in an axial direction, the shaft including a hollow part formed on at least a tip side of the shaft such that an interior of the shaft is hollow, the actuator being configured to generate a negative pressure in the hollow part to suction a workpiece to a tip of the shaft, thereby picking up the workpiece. The sensing device includes a flow sensor provided in a middle of an air passage to detect a flow rate of air flowing through the air passage, the air passage being a passage through which air sucked out from the hollow part flows when the negative pressure is applied to the hollow part, and a pressure sensor provided in a middle of the air passage, to detect a pressure in the air passage.

Actuator sensing device and actuator control system

The present invention reduces tact time for a pick-and-place operation by an actuator. In a housing of the actuator, an air passage being a passage of air when sucking air from a hollow part of a shaft is provided. Furthermore, a sucking valve that sucks air from the hollow part of the shaft through the air passage and a suction detecting sensor to detect that a workpiece is suctioned onto a tip of the shaft are provided in the air passage. Then, in the housing, the air passage is disposed at a position on a side opposite to a linear motion motor that moves the shaft in an axial direction of the shaft, via the shaft.

A computer implemented method for training a neural network to capture a structural feature specific to a set of chemical compounds is disclosed. In the method, the computer system reads an expression describing a structure of the chemical compound for each chemical compound in the set and enumerates one or more combinations of a position and a type of a structural element appearing in the expression for each chemical compound in the set. The computer system also generates training data based on the one or more enumerated combinations for each chemical compound in the set. The training data includes one or more values with a length, each of which indicates whether or not a corresponding type of the structural element appears at a corresponding position for each combination. Furthermore, the computer system trains the neural network based on the training data for the set of the chemical compounds.

Neural network for chemical compounds

A device for controlling a storage battery system is provided. The device includes: a state information calculator configured to calculate state information on each of batteries of a plurality of storage battery modules; a conversion efficiency characteristics calculator configured to calculate a power conversion efficiency of each of DC/DC converters of the plurality of storage battery modules; and a storage battery module selector configured to select one or a plurality of storage battery modules to be used while the storage battery system is charged or discharged and to determine a charge power or a discharge power of each of the selected storage battery modules, based on the state information of the batteries and the power conversion efficiencies of the DC/DC converters.

Device and method for controlling a storage battery system

An actuator system that picks up workpieces aims to shorten tact time and to reduce damages to workpieces. The actuator system includes an actuator that picks up a workpiece, an external force detection sensor that detects a physical quantity that is correlated with an external force that is applied to the workpiece, a head unit that is connected to the actuator and the external force detection sensor without a communication network, the head unit being configured to control the actuator based on a sensing result from the external force detection sensor when a pickup request signal that is a signal requesting pickup of the workpiece is received, and a control device that is connected to the head unit over the communication network, the control device being configured to transmit the pickup request signal to the head unit.

Actuator system

Provided is an actuator in which a load applied to a shaft and a workpiece is controlled. The actuator includes a support part that rotatably supports the shaft, a linear motion motor that moves the shaft in a direction of a central axis, a connecting member that is at least a part of a member connecting a mover of the linear motion motor and the support part, a strain gauge that detects strain of the connecting member, and a control device that controls the linear motion motor, based on the strain detected by the strain gauge.

In an actuator, an unnecessarily large load is prevented from being applied to a shaft and a workpiece. There are included a force sensor, an output of which is according to a force applied to a connecting member connected to the shaft, an amplifier that amplifies the output of the force sensor, and a low-pass filter, and a load applied to the shaft is detected based on an output from the amplifier until the shaft or a member associated with the shaft comes in contact with another member, and thereafter, the load applied to the shaft is detected based on an output from the low-pass filter.

In a storage battery system charging control device, on the basis of estimated temperature data until the end of life of a storage battery calculated by a power estimation unit, an ambient temperature estimation unit, and a temperature estimation unit, and a deterioration coefficient stored in a data storage unit, a capacity retention calculation unit sequentially calculates capacity retention data with respect to each state of charge until the end of life of the storage battery, using the state of charge as a parameter. A cumulative capacity calculation unit calculates a cumulative capacity corresponding to each state of charge, on the basis of the rated capacity of the storage battery and the capacity retention data. A charging control voltage determination unit determines charging control voltage on the basis of the cumulative capacities calculated by the cumulative capacity calculation unit.

Storage battery system charging control device, storage battery system, and storage battery charging control method

Probability density ratios may be estimated by a method including obtaining a first sample set including a plurality of first samples and a second sample set including a plurality of second samples, wherein each of the first samples and the second samples is represented as a vector including a plurality of parameters, constructing at least one decision tree estimating a ratio of probability density p(x)/q(x) based on the first sample set and the second sample set, wherein p(x) is a probability density of the first samples corresponding to an input vector x and q(x) is a probability density of the second samples corresponding to the input vector x.

Probability density ratio estimation

Optimized learning settings of neural networks are efficiently determined by an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to train a first neural network with a learning setting; extract tentative weight data from the first neural network with the learning setting; calculate an evaluation value of the first neural network with the learning setting; and generate a predictive model for predicting an evaluation value of a second neural network with a new setting based on tentative weight data of the second neural network by using a relationship between the tentative weight data of the first neural network and the evaluation value of the first neural network.

Efficient determination of optimized learning settings of neural networks

Anomalous sensors are detected using an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to obtain a plurality of healthy sensor data, wherein each of the healthy sensor data includes a plurality of sensed values of a corresponding sensor among a plurality of sensors in normal operation, generate a healthy data distribution of at least two sensors among the plurality of sensors based on the plurality of healthy sensor data, and generate a function of a parameter probability distribution of the plurality of sensors under a condition of sensor data of the plurality of sensors based on the healthy data distribution, each parameter indicating whether the corresponding sensor is healthy or anomalous.

Detecting anomalous sensors

Methods and apparatus are provided for estimating anomalous sensors. The apparatus includes a target data acquiring section to acquire a plurality of sets of target data serving as an examination target, each set of target data being output by a plurality of sensors. The apparatus further includes a calculating section to calculate, for each of a plurality of sensor groups such that each sensor group includes at least two sensors among the plurality of sensors, a degree of difference of a target data distribution of the plurality of sets of target data relative to a reference data distribution of output from the sensor group. The apparatus additionally includes an estimating section to estimate one or more sensors among the plurality of sensors to be a source of outlierness, based on a calculation result of the calculating section.

Growing community of inventors

Tokyo, Japan

Satoshi Hara