Kabushiki Kaisha Toshiba

Toshiba Solutions Corporation

Makoto Kano

Hiroyuki Suzuki

Junichi Nakamura

Junichi Yamamoto

Satoshi Sekine

Norikazu Hosaka

Yasuomi Une

Tsuyoshi Shimada

Shinichiro Kawano

Hideyuki Aisu

Kiyoshi Matsui

Naoki Imasaki

Kyoko Makino

According to one embodiment, there is provided a charging management system. Based on an estimated duration from a time when an electric vehicle having arrived at each of a charging facilities starts charging until the charging is complete, the system determines the charging facility a charging facility utilization of which is to be recommended to be one of the charging facilities related to a path to a destination which has a shortest maximum wait time from a time when a plurality of electric vehicles arrive at the charging facility until the charging is complete, and reports information indicative of the determined charging facility to the electric vehicle not having arrived at the charging facility.

Charging management system

According to an embodiment, there is provided a consumed power amount estimation apparatus including an estimation unit configured to estimate a power amount necessary for an electric vehicle having a similar power consumption tendency to run, based on a parameter used to compensate for information affecting power consumption by running of the electric vehicle based on consumed power amount information of each of a plurality of electric vehicles having similar power consumption tendencies.

Consumed power amount estimation apparatus

According to one embodiment, a charge management apparatus includes an input unit, a first estimation unit, a determination unit, a generation unit, and an output unit. The input unit accepts an input of traffic demand data indicative of a number of vehicles. The first estimation unit estimates charge wait times at plural charge stations based on the traffic demand data. The determination unit compares the estimated charge wait times at the respective charge stations, and determines whether a desired condition is satisfied. The generation unit generates charge recommendation information indicative of a charge station according to a determination result. The output unit outputs the charge recommendation information to an external terminal.

Charge management apparatus

Each of a plurality of units 2 has the learning section 9 which updates the parameters PRM and performs learning. The learning means 9 modifies the parameters PRM based on the error signal OS' propagated from one unit to another. To build a system consisting of such units 2, the user uses the GUI or some other method to select the units 2 as well as the signal paths for connecting the units via the user interface, displays the system configuration status, and adjusts the functions of units 2. Therefore, an easy-to-build data processing system and a system-build system and method used to build such a system can be provided.

Data processing system, system-build system, and system-build method

A function for compensating an error between a teacher signal and an output signal with a weight value is defined. A multilayered neural network is changed so that the function becomes minimum. Thus, the multilayered neural network can be adaptively controlled.

System for controlling an object and medium using neural networks

A control apparatus for controlling a control amount of a control target by changing an operating amount which is supplied to the control target, comprises an adjusting section for calculating an adjustment signal in accordance with the control amount measured by the control target and a target control amount, an operating section for transmitting an operating amount to the control target in accordance with the adjustment signal calculated by the adjusting section, an observation data storing section for storing observation data having control amounts and operating amounts observed previously, and a learning section for learning internal parameters for the adjusting section in accordance with response time taken for the control target from input of the operating amount from the operating section to the control target to appearance of an influence of the operating amount on the control amount and observation data stored in the observation data storing section.

Intelligent control apparatus

A control method of controlling a controlled system according to the invention comprises the first step of inputting a current and future target controlled variable to a first neural network model which performs learning using a past target controlled variable for the controlled system as an input signal and a past manipulated variable as a teacher signal, thereby obtaining a current virtual manipulated variable, the second step of causing a second neural network model, which have learnt to predict a behavior of the controlled system, to receive the virtual manipulated variable obtained in the first step and a controlled variable obtained from the controlled system at a current time, thereby obtaining a predicted controlled variable, the third step of obtaining an error of the predicted controlled variable obtained in the second step with respect to the target controlled variable, the fourth step of obtaining a correction amount for the virtual manipulated variable in accordance with a back propagation calculation of the second neural network model, using the error obtained in the third step, thereby correcting the virtual manipulated variable with the correction amount, and the fifth step of outputting the virtual manipulated variable corrected in the fourth step to the controlled system.

Control method and apparatus using two neural networks

This invention relates to a predictive control method and apparatus for controlling a nonlinearly controlled object, such as a manipulator. The method and apparatus can control an object having unknown dynamic characteristics and can compensate for disturbances. A multi-layered neural network is provided as an identification model for the object to the controlled. A controlled variable signal received from the object and a manipulated variable signal for controlling the object are fed into the neural network to predict a future value of the controlled variable signal using forward calculation. The predicted future value is compared with a desired control variable value to produce an error value. The error value is input to the neural network to compute a correction value for the manipulated variable signal using back-propagation. The correction value is used to modify the manipulated variable signal value to thereby control the object.

Growing community of inventors

Urayasu, Japan

Makoto Kano