Abstract: Methods and systems are provided for an insulation system of a stator. In one example, a method may include receiving images of the stator at a processor of a computing system and processing the images by converting the images to one or more of cluster-only images and binary masks. The images may be fed to an artificial intelligence (AI) model to obtain one or more of varnish estimates and void estimates to generate a training dataset which may be used to train a deep learning tool to estimate varnish fill percentages from the images and display the varnish fill percentages at a display device.

Abstract: Provided is an interactive dynamic fluid effect processing method, which includes: capturing a video and detecting position and pose change of a target object in the video; acquiring a position and pose mapping relationship between the target object and an object model corresponding to a first object displayed in a user display interface; determining position and pose change of the object model based on the position and pose change of the target object and the position and pose mapping relationship; and adjusting a position of a fluid displayed in the user display interface based on the position and pose change of the object model, and dynamically displaying movement change of the fluid in the user display interface.

Abstract: Calculation control for hybrid computing of Hamiltonian eigensolutions may be provided by selecting K basis states from an ansatz space of a chemical system, wherein the ansatz space is generated by a quantum computer system and includes fewer basis states than a whole basis space for the chemical system, wherein the K basis states are selected according to a selection protocol to define a core space for the chemical system; computing, via an eigensolver provided by a classical computer system, an eigensolution for the chemical system from the core space; and outputting the eigensolution for the chemical system.

Abstract: Systems and methods for cardiac radioablation treatment planning are disclosed. In some examples, a computing device receives an image volume and a dose matrix data. The computing device generates a first mesh of organ substructures for the organ based on substructure contours for the organ. Further, the computing device generates a second mesh of an isodose volume based on the dose matrix data. The computing device displays the first mesh of the organ substructures and the second mesh of the isodose volume within a same scene. In some examples, the computing device samples a plurality of dosage values, determines representative dosage values for each of a plurality of points along surfaces of a dose matrix, and generates an image for display based on the representative dosage values. In some examples, a segmentation model is generated for display based on the representative dosage values.

Abstract: By using the Al module, the method of the present invention calculates, i.e. predicts, the dependency Ci (pi) of a radiotherapy (RT) quality criterion C, from an adjustment of such a radiotherapy planning parameter pi. In this way, the decision making process in RT treatment plan optimization is streamlined by prediction of promising settings of one or more radiotherapy planning parameters p, before the actual time intensive iterative optimization process is carried out. This is achieved by applying an Al module, which has been trained to predict the specific behaviour of the dose optimization algorithm, i.e. the optimizer, with respect to geometric patient data, dose prescription and treatment indication data. Thus, a computer-implemented medical method of predicting a dependency Ci (pi) of a radiotherapy (RT) quality criterion Ci from an adjustment of a radiotherapy planning parameter p, is presented.

Abstract: A coal rock interface directional detection device based on elastic waves includes: a probe body including an elastic wave receiving device and an elastic wave excitation device spaced set at the top; a protective tube with one end connected to the adapter. The protective tube includes a collection circuit board inside the protective tube, and the collection circuit board is electrically connected to the elastic wave receiving device and the elastic wave excitation device; a sleeve, installed outside the protective tube, with one end connected to the side of the probe body near the adapter and with the other end connected to the side of the protective tube away from the adapter; and a control host, wirelessly connected with the acquisition circuit board. A coal rock interface directional detection method based on elastic waves applied in the coal rock interface directional detection device is also disclosed.

Abstract: Discussed herein are methods and systems for an interdependent series/suite of AI models. In one embodiment, a processor receives projection assumption inputs from a user device and executes a population builder machine learning model to predict a dynamic adjustment table. It applies the model to population data to generate a value population file, which simulates a subset of the population based on the predicted table. The file contains value cells representing instances of a product. The device then runs a mortality machine learning model to determine mortality data for the product using the simulated population. Finally, it executes a flow projection model to generate a projection report for the product, incorporating mortality data and projection assumptions.

Abstract: An energy management system for enhancing design and operation of a distributed energy resource system includes a two-level design system and a hierarchical optimization-based control system. The two-level design system includes a top-level designer configured to coordinate decentralized bottom-level designers for individual energy resources to seek a global target for the designed distributed energy resource system that satisfies the energy demand of a target deployment location within a confidence level, and multiple bottom-level designers configured to enhance detailed designs of local energy sub-systems.

Abstract: Systems and methods of determining an equivalent black oil model are disclosed. In one embodiment, a method of determining an equivalent black oil model of a reservoir includes generating three-dimensional PVT properties using a compositional model, calculating original fluid in place and reservoir performance characteristics from the three-dimensional PVT properties, and converting the three-dimensional PVT properties to a two-dimensional PVT table. The method further includes, until an equivalency metric is satisfied, generating one or more grouped PVT property tables, initializing a black oil model with the one or more grouped PVT property tables, calculating estimated fluid in place and estimated reservoir performance characteristics using the black oil model, and comparing the estimated fluid in place and the estimated reservoir performance characteristics with the original fluid in place and the reservoir performance characteristics to determine whether the equivalency metric is satisfied.

Abstract: A method and a device for determining a presence of tumor are provided. The method includes receiving a medical image associated with a patient. The medical image includes a region of interest associated with the patient. The method includes identifying one or more blood vessels associated with the region of interest in the medical image. The method includes determining a set of characteristics associated with the one or more blood vessels using a trained machine learning model. The method also includes determining whether the one or more blood vessels are feeder vessels associated with the tumor based on the set of characteristics associated with the one or more blood vessels. The method includes detecting a tumor region in the region of interest based on the feeder vessels, when the one or more blood vessels are the feeder vessels associated with the tumor.

Abstract: Forecasting resource allocation is disclosed. An example method includes receiving operating data from a resource; applying periodicity tests to the received operating data using a plurality of sketches of time series of prior operating data, the periodicity tests generating periodic components; applying regression models to the received operating data, the regression models collectively generating a trend component, each regression model being applied over a different time scale of a plurality of time scales; computing a trend model using the periodic components and a trend component; determining a random process describing the historical evolution of the trend model; and calculating and providing a mean prediction, an upper bound, and a lower bound for resource utilization at a future time using the trend model and a predicted distribution.

Abstract: An apparatus is provided comprising an acquisition unit configured to acquire a plurality of types of measurement data indicating a state of a target, a supplying unit configured to supply, in response to the plurality of types of measurement data being input, measurement data acquired by the acquisition unit to a model that outputs a state indication value indicating a quality of a state of the target, a setting unit configured to set, as data to be displayed, at least one piece of measurement data, among the plurality of types of measurement data, having a larger influence on the state indication value than a reference, and a display control unit configured to display the state indication value output from the model along with a measurement value of the data to be displayed.

Abstract: Receiving a dataset and parsing from the dataset an XP coordinate value on an x-axis, a YP coordinate value on a y-axis, and a ZP coordinate value on a z-axis all within a domain having 3-dimensional features. The x-axis and y-axis are perpendicular and define a horizontal earthbound main surface. The ZP coordinate value is on the z-axis perpendicular to the horizontal earthbound main surface. The XP, YP and ZP define a place associated with a 3-dimensional feature. Stored resource rules for places in the domain are accessed that indicate a first resource if the ZP has a first value, and a second resource if the ZP has a second value. One of the resource rules that applies to the place is identified based on XP, YP and ZP. A resource for the dataset is determined by applying the identified rule. The resource is caused to be transmitted.

Abstract: An information processing apparatus acquires vehicle state information for each of a plurality of vehicles. The information processing apparatus estimates road surface state information of a road surface on which each of the vehicles has traveled, based on the acquired vehicle state information for each of the vehicles. The information processing apparatus estimates the road surface state information by inputting the acquired vehicle state information to a trained model that outputs the road surface state information in a case where the vehicle state information is input and that has been trained in advance based on training data in which the vehicle state information and the road surface state information are associated with each other.

Abstract: Methods for tracking a signal origin by a spectrum analysis and management device are disclosed. Signal characteristics of other known emitters are used for obtaining a position of an emitter of a signal of interest. In one embodiment, frequency difference of arrival technique is implemented. In another embodiment, time difference of arrival technique is implemented.

Abstract: Three-dimensional solar power generation systems are described. The systems are characterized by a plurality of solar panels configured to include pole and equator facing panels and, in various embodiments additional top and/or side panels that form a segmented and dome-shaped assembly. The systems have improved efficiencies particularly with respect to early morning and evening power generation that enable improved power densities on a given land area as compared to traditional solar panel arrays. Methods of deploying the systems are also described.

Abstract: A predictive control method and system are provided for controlling a device or system. The control method and system involves receiving a setpoint signal as input; and performing closed loop control of the device or system by outputting a control signal according to the setpoint signal and a response model of the device or system using a predictive control algorithm. The predictive control algorithm is configured to implement control according to a polynomial representation for regulation, sensitivity and tracking and further implement non-linearity or time delay compensation using the response model. The closed loop control is tunable using an adjustable single parameter for accelerating or decelerating the closed loop control relative to an open loop control scenario.

Abstract: Scalable, configurable, complete spectrum universal health metrics monitors and bicorders are disclosed that record data or make selected determinations from a complete spectrum of health determinations regarding or utilizing sensor observations or people. Health metrics monitors utilize necessary resources and predetermined criteria in their making of selected health determinations. Health metrics monitors, bicorders and their operations are preferably a best performing blend of as simple, concise, and efficient as possible. Health metrics monitors may utilize measure points in their locating of selected analytically rich aspects, characteristics, or features of or from sensor observation-derived representations.

Abstract: A system and associated methods for organizing, representing, finding, discovering, and using data. Embodiments represent information and data in the form of a data structure termed a Feature Graph, that includes nodes and edges, where the edges serve to connect a node to one or more other nodes. A node in a Feature Graph may represent a variable, such as a measurable object, characteristic, or factor of a study. An edge in a Feature Graph may represent a measure of a statistical association between a node and one or more other nodes. Datasets that demonstrate or support the statistical association or measure the associated variable may be accessed through an identifier in a Feature Graph. An application may traverse a Feature Graph and aggregate and process data associated with a set of nodes or edges.

Abstract: The external heterogeneity in the Discrete Event System Specification (DEVS) for simulators refers to the ability to incorporate different types of models, each with potentially different behaviors, into a single simulation environment. In the DEVS framework, a system is composed of multiple individual models, each representing a component of the system. These models can be either atomic (cannot be decomposed further) or coupled (composed of other models). This gives DEVS its hierarchical nature. The atomic or coupled models can in DEVS Markov models be fundamentally different from each other. For example, one model might represent a deterministic rule-based decision process, while another model might represent a probabilistic random variable generator. These models have different state variables, different event sets, and different transition functions, but they can still interact with each other within the same simulation.

Abstract: A system for detecting and warning a user of an object in a path of a vehicle includes a detection module configured to detect an object in a path of a vehicle, and a control module in communication with the detection module. The control module is configured to receive vehicle data from one or more vehicle sensors, determine a height of the detected object, determine a ground clearance of the vehicle based on the received vehicle data, and in response to the height of the detected object being greater than a threshold based on the ground clearance of the vehicle, generate a signal to notify the user of the detected object. Other examples systems and methods for detecting and warning a user of an object in a path of a vehicle are also disclosed.

Abstract: A method may include obtaining data representing flow rates for a plurality of flow control devices. The method also includes determining total molar rates for a plurality of flows through pipe segments associated with each of the flow control devices based on the obtained data. The method also includes determining initial flow control device constraints based on the total molar rates for the plurality of flow control devices. The method also includes determining that one or more wellhead constraints would be violated based on the flow control device constraints. The method also includes determining adjusted flow control device constraints that result in the satisfaction of one or more wellhead constraints or constraints of others of the plurality of flow control devices. The method also includes determining an adjusted flow rate based on the adjusted device constraints that satisfy the wellhead and the flow control device constraints.

Abstract: Methods and systems are described herein for identifying matching parameters of groups of nodes in graphical representations. The system may generate, in a graphical user interface, a graphical representation of nodes representing users associated with an entity. The system may activate the graphical representation as links connecting pairs of nodes, with the links representing interactions between users. The system may identify a grouping of nodes having a level of local clustering indicative of undesired activity. The system may determine graphical parameters relating to the level of local clustering and may identify the same graphical parameters in other groupings of nodes in other graphical representations. The system may thus identify indications of undesired activity based on matching parameters of groups of nodes.

Abstract: Provided is a computer-implemented method for controlling an operation of a technical system automatically, including at least the steps of: acquiring information about a modified configuration of at least one sub-system included in the technical system; generating a virtual model of the technical system including the at least one sub-system with the modified configuration for an evaluation of the operation; adjusting the virtual model to provide a control instruction for the operation of the technical system, wherein the adjusted virtual model is configured to compare an evaluation value acquired from the evaluation with a target requirement in a cryptographic and to derive the control instruction based on the comparison; and controlling the operation of the technical system based on the control instruction.

Abstract: Method for non-invasively characterizing a heterogeneous medium using ultrasound, comprising a step of generating a series of incident ultrasonic waves, a step of recording an experimental reflection matrix Rui(t) defined between the input emission basis (i) and an output reception basis (u), a step of determining a response REP(r,?r) of the medium between an input virtual transducer (TVin) calculated based on an input focusing of the experimental reflection matrix that creates an input focal spot around a first point (P1), and an output virtual transducer (TVout) calculated based on an output focusing of the experimental reflection matrix that creates an output focal spot around a second point (P2), said response being expressed as a function of a central point (PC) of spatial position (r) in the medium located midway between the first and second points (P1, P2).

Abstract: A system for optimizing the positioning of a vehicle seat includes: a module for obtaining and saving at least one morphological parameter of a passenger on the seat; a seat positioning adjustment module having at least one sensor within the vehicle, controlling the positioning; and a module for determining the positioning adjustment to be applied as a function of the morphological parameter. The system is configured to: determine at least one adjustment change that optimises passenger comfort to be applied during vehicle operation, automatically alter the position of the seat to achieve the adjustment change, or signal the passenger of the adjustment change to be applied, via an interaction module, and guide the passenger to manually achieve the adjustment change, via a predetermined sound or light signal.

Abstract: A behavior recognition device for recognizing behaviors of a semiconductor manufacturing apparatus includes a storage device and a control unit. The storage device is configured to store log data of the semiconductor manufacturing apparatus. The control unit is cooperatively connected to the storage device, and configured to build a transition state model based on the log data to analyze behaviors related to wafer transfer sequences and manufacturing operations of the semiconductor manufacturing apparatus.

Abstract: A real-time technique for identifying truth-telling data in a data stream includes determining, based on a situational map of the data stream, an expected range of values for incoming data points associated with a trend in the data stream. The technique further includes receiving, in the incoming data points, a data point that is outside the expected range of values. The data point that is outside the expected range of values is stored for an analysis of the trend after receiving more of the incoming data points. The analysis of the trend is executed using the data point that is outside the expected range of values for the analysis to indicate whether the trend in the data stream has changed.

Abstract: A method for characterizing organic matter in a geological rock formation includes performing a Raman spectroscopy measurement on a rock sample to acquire a Raman spectrum of the rock sample. The method includes analyzing the Raman spectrum of the rock sample to determine data characterizing at least one Raman spectral feature corresponding to the rock sample, inputting the data characterizing the at least one Raman spectral feature corresponding to the rock sample into a computation model that determines a value of a property of organic matter in the rock sample, and storing or outputting or displaying the value of the property of organic matter in the rock sample. In embodiments, the property of organic material in the rock sample can be a property of kerogen in the rock sample, or a property of asphaltenes or bitumen in the rock sample.

Abstract: Methods and systems of using at least one hardware processor to train a machine learning algorithm to identify one or more predictive drug molecular features and/or predictive gene biomarkers for cancer treatment is provided. In some embodiments, the method uses at least one cancer drug discovery data set to train at least one learning algorithm in a prediction model, and uses a xenograft mouse model to validate the prediction model, with biological response fed back to the prediction model to further train the learning algorithm.

Abstract: An approach for providing a lower cost real time location system in less trafficked areas of a building. This approach uses on-board audio capabilities of a mobile device to receive a room response trace resulting from a self-generated acoustic signal. By comparing the room response trace to a modeled room response trace, the location of the mobile device is determined.

Abstract: An information processing apparatus for editing a document including first and second types of different objects. The apparatus includes at least one processor and at least one memory coupled to the at least the processor and having stored thereon instructions, when executed by the at least the processor, and cooperating to act as a change unit configured, based on a user instruction, to change a paper size of the document from a first paper size to a second, different from the first, and an adjustment unit configured to adjust a size of the object included in the document based on the second. The adjustment unit adjusts the size of a first type of object in the plurality of objects such that an aspect ratio of the specific object is maintained and an aspect ratio of the second type of object corresponds to an aspect ratio of the second paper size.

Abstract: A design support method capable of accurately obtaining predicted values, while also considering production conditions of a metal material, and of reducing the time required for design is provided. The design support method uses a calculator to support design of metal material with desired characteristics and includes searching for design conditions yielding the desired characteristics using a prediction model for predicting a characteristic value of the metal material from the design conditions, the prediction model being constructed based on past performance data associating the design conditions, including chemical composition and production conditions of the metal material, with the characteristic value. The design support method also includes presenting at least the chemical composition and production conditions among the design conditions that are searched for and correspond to the desired characteristics.

Abstract: Aspects of the present disclosure relate to a well analog recommendation system. The well analog recommendation system may generate numerical representations indicative of text-based descriptions within a well report and/or well log associated with a well. Further, the well analog recommendation system may generate a well analog output that may include one or more text-based characterizations associated with one or more additional wells that are determined based on the numerical representation. For example, the well analog recommendation system may compare the numerical representation of the well to one or more numerical representations associated with the one or more additional wells and output the one or more text-based characterizations when the numerical representations are approximately equal or above a threshold.

Abstract: A method for generating a representation of a three-dimensional protective device includes accessing a scan of anatomical data of a target and identifying a reference model of a closest size or proportion to a size or proportion of the target. The method further includes creating a boundary of a three-dimensional protective device using the reference model and the scan of anatomical data of the target. Additionally, the method includes generating a representation of a continuous, three-dimensional surface of the three-dimensional protective device that corresponds to the scan of anatomical data and the reference model within the boundary of the three-dimensional protective device.

Abstract: Drilling parameters for a wellbore operation can be determined based on resonance speeds. For example, a system can receive real-time data for a drilling operation that is concurrently occurring with receiving the real-time data. The system can determine, for a drilling depth, a rotations-per-minute (RPM) value corresponding to a resonance speed based on a weight-on-bit (WOB) value and the real-time data. The system can generate a plot of the WOB value and the RPM value corresponding to the resonance speed. The system can determine drilling parameters for the drilling operation based on the plot. The drilling parameters can exclude, for the WOB value, the RPM value corresponding to the resonance speed.

Abstract: To easily evaluate the performance of an earphone-type device used for otoacoustic authentication at low cost. A generation unit (31) generates earhole shape data indicating the three-dimensional shape of an individual's ear canal, on the basis of data on the internal structure of an individual's earhole, a center line calculation unit (32) calculates the center line of the ear canal, on the basis of the ear canal shape data, and a dividing unit (33) divides the ear canal into a plurality of layers perpendicular to the center line, and calculates, for each of the divided layers, parameters indicating the shape of the ear canal.

Abstract: A model predictive maintenance (MPM) system for building equipment includes one or more processing circuits including one or more processors and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations. The operations include obtaining one or more performance indicators for the building equipment and determining whether a trigger condition has been satisfied based on the one or more performance indicators. The operations include triggering a model predictive maintenance process to generate a maintenance schedule for the building equipment in response to determining that the trigger condition has been satisfied. The operations include initiating a maintenance activity for the building equipment in accordance with the maintenance schedule.

Abstract: Disclosed are a computer-implemented method, a system and a computer program product for model exploration. Model feature importance of each model of a plurality of models can be obtained, the plurality of models can be grouped into a plurality of model clusters based on the model feature importance of each model, and the model feature importance can be presented by box-plot or confidence interval.

Abstract: Methods, systems and computer readable media for estimating ampacity of single and multiple bare overhead conductors in a range of ambient temperatures within a single simulation, are described.

Abstract: A processor may receive user information for a request payload from an external device and data describing a plurality of user interface (UI) elements configured to be presented in a UI of the external device. The processor may select a machine learning (ML) model from a plurality of ML models using a contextual bandit ML model that is trained based on the user information. The processor determines at least one recommended user interface (UI) element with a selected ML model, based on the user information and the data describing the plurality of UI elements. The at least one recommended UI element may be presented in the UI of the external device. The processor may receive event data indicating a user interaction with the at least one recommended UI element in the UI of the external device. The contextual bandit ML model may be re-trained based on the event data.

Abstract: Systems and methods for an enterprise computing platform may include a server that may include a desktop-as-a-service module, a user behavior analytics module, a remote monitoring and management module, an analytics-as-a-service module, an insider threat prevention and monitoring module, and a project tracker module. The server or modules may provide remote desktop sessions in an efficient and convenient manner, may analyze user behavior and automatically execute corrective actions in response to rules violations, and may monitor and manage multiple computer systems and computing sessions as to their statuses, versions, authentication, or compliance.

Abstract: A system for a water generation apparatus of a vehicle includes a sensing device that detects an environmental condition of a geographical area associated with the vehicle. A display device is configured to present a depiction of the geographical area. A controller is in communication with the sensing device and the display device. The controller is configured to determine at least one water generation estimate for the water generation apparatus based on the environmental condition and the geographical area. The controller is further configured to generate a modified representation of the geographical area based on the at least one water generation estimate and the depiction of the geographical area. The controller is further configured to communicate an instruction to present the modified representation at the display device.

Abstract: This disclosure describes techniques for identifying users that are enrolled for use of a user-recognition system and updating enrollment data of these users over time. To enroll in the user-recognition system, the user may initially scan his or her palm. The resulting image data may later be used when the user requests to be identified by the system by again scanning his or her palm. However, because the characteristics of user palms may change over the time, the user-recognition system may continue to build more and more data for use in recognizing the user, in addition to removing older data that may no longer accurately represent current characteristics of respective user palms.

Abstract: At a machine learning service, a determination is made that an analysis to detect whether at least a portion of contents of one or more observation records of a first data set are duplicated in a second set of observation records is to be performed. A duplication metric is obtained, indicative of a non-zero probability that one or more observation records of the second set are duplicates of respective observation records of the first set. In response to determining that the duplication metric meets a threshold criterion, one or more responsive actions are initiated, such as the transmission of a notification to a client of the service.

Abstract: In one embodiment, a method to monitor a patient's heart health is described. The method may include processing at least one electrocardiogram (ECG) signal and diagnosing an episode of nonsustained ventricular tachycardia (NSVT) based at least in part on the processing of the at least one ECG signal. In some embodiments, the NSVT episode may satisfy an NSVT time duration and a QRS criterion. The NSVT time duration may be between 5 seconds and 15 seconds. In some instances, the QRS criterion may be a temporary QRS template of two sequential incoming QRS complexes. In some embodiments, the method may determine a similarity between the temporary QRS template and at least two subsequent QRS complexes by calculating a feature correlation coefficient between the QRS template and the subsequent QRS complexes.

Abstract: A device applies a pre-function w=P(x) to an input signal x to obtain a first result w and applies a LUT to the first result w, wherein the LUT represents a main function ƒw(w) defined for a second grid of values Gw such that the pre-function P(x) is piecewise defined on a first grid Gx of signal values, where Gw=P(Gx). The device can further obtain the pre-function P(x), piecewise defined on the first grid Gx of the signal x and calculate the LUT with the second grid Gw=P(Gx). The piecewise pre-function P(x) can be obtained from a second pre-function Q(x) by applying Q(x) to signal values x to calculate the second grid Gw=Q(Gx) and defining the pre-function P(x) piecewise on the first grid Gx by linear interpolation of the values of the second grid Gw such that P(Gx)=Q(Gx).

Abstract: The present disclosure belongs to the field of computational hydraulics and aims at providing a construction method and system for a hydrodynamic joint computation model, a device, and a medium.

Abstract: A computer implemented method for determining performance of a semiconductor device is provided. The method includes providing training data comprising input state values and training capacitance values to a neural network executing on a computer system; processing the input state values through the neural network to generate modeled charge values; converting the modeled charge values to modeled capacitance values; determining, by the computer system, whether the training capacitance values of the training data are within a threshold value of the modeled capacitance values utilizing a loss function that omits the modeled charge values; and in response to determining that the training capacitance values of the training data are within the threshold value of the modeled capacitance values, converting, by the computer system, the neural network to a circuit simulation code to generate a converted neural network.

Abstract: According to a storage battery of an embodiment includes a first battery module and a second battery module connected in parallel with the first battery module. The number of first cells connected in series in the first battery module is M, and the number of second cells connected in series in the second battery module is N. When an open circuit voltage at SOC=X % of the first cells and the second cells are Va1 (X) and Va2 (X), respectively, the voltages of the battery modules are M×Va1 (X)<N×Va2 (X) in the range where the SOC of the cell is 0% to 30%, and M×Va1 (X)>N×Va2 (X) in the range where the SOC of the cell is 70% to 100%.