-
公开(公告)号：EP4231027A1
公开(公告)日：2023-08-23
申请号：EP21880115.7
申请日：2021-10-12
申请人： Resonac Corporation
发明人： KURAUCHI, Yuji , MINAMI, Takuya , ITO, Yuji , KOHNO, Daisuke , INOUE, Hirofumi , OKUNO, Yoshishige
IPC分类号： G01R31/392 , G01R31/367 , G01R31/378 , G06N20/00 , H01M10/44 , H01M10/48
摘要： Provided is a lithium ion battery lifetime prediction method that does not require training data for a machine learning to be prepared again, even when modifications of materials and design occur, and can indicate a cycle life in the form of a probability distribution. The lithium ion battery lifetime prediction method according to the present invention executes, by a computer, step (a) of acquiring training data including cycle measurement data and lifetime data of a battery, step (b) of learning a lifetime prediction model using the training data with respect to one or more cycle numbers at which a prediction is made, to acquire a set of learned lifetime prediction models corresponding to the cycle numbers at which the prediction is made, respectively, step (c) of successively acquiring cycle measurement data for prediction of a battery that is a prediction target, up to the cycle numbers at which the prediction is made, respectively, and step (d) of inputting the cycle measurement data for prediction acquired up to the cycle numbers at which the prediction is made, to the learned lifetime prediction models of the corresponding cycle numbers at which the prediction is made, and acquiring a probability distribution of a lifetime at the cycle numbers at which the prediction is made, respectively, as an output.
-
公开(公告)号：EP4456076A1
公开(公告)日：2024-10-30
申请号：EP22910998.8
申请日：2022-12-13
申请人： Resonac Corporation
发明人： NISHINO, Shogo , AONUMA, Naoto , MIYAKOSHI, Koji , KAKUDA, Kohsuke , MINAMI, Takuya , TAKEMOTO, Shimpei
摘要： A design support device supports design of a first compound and design of a second compound containing the first compound, and the design support device includes a first design condition proposing unit configured to propose a candidate for design condition information for the first compound that satisfies required property information for the first compound that is input; and a first property predicting unit configured to perform property prediction of the second compound based on design condition information for the second compound that is input.
-
公开(公告)号：EP4362031A1
公开(公告)日：2024-05-01
申请号：EP22828446.9
申请日：2022-06-22
申请人： Resonac Corporation
发明人： AONUMA, Naoto , TAKEMOTO, Shimpei , MINAMI, Takuya , KAKUDA, Kohsuke , OKUNO, Yoshishige , TAKASHI, Hiroko
摘要： A physical property prediction device for predicting a physical property of a compound including: a generation unit configured to generate a first stage trained model, by using, as training data, first stage synthesis information and synthesis result information; a generation unit configured to generate second stage through last stage trained models, by using, as training data, n-th stage (n≥2) synthesis information, n-th stage synthesis result information, and n-1-th stage synthesis result information; a reception unit configured to receive a synthesis information setting for the compound for which the physical property is predicted; a prediction unit configured to predict a physical property value of a product synthesized by the first stage chemical reaction of the compound; a prediction unit configured to repeat, from a second stage chemical reaction to a last stage chemical reaction of the compound, a process of predicting a physical property value of a product synthesized by the n-th stage chemical reaction of the compound; and an output unit configured to output a predicted physical property value.
-
4.发明公开
公开(公告)号：EP4343620A1
公开(公告)日：2024-03-27
申请号：EP22804477.2
申请日：2022-04-14
申请人： Resonac Corporation
发明人： KAKUDA, Kohsuke , FUJIMORI, Takahiro , LEE, Haein , TAKEMOTO, Shimpei , MINAMI, Takuya , OKUNO, Yoshishige
摘要： Prediction accuracy is increased in a prediction device using a trained model. A prediction device includes: a first trained model and a second trained model configured to respectively output first output data and second output data in response to input of input data of a prediction target; and an output portion configured to obtain the first output data and the second output data and calculate a weighted average value or take a weighted majority, thereby outputting prediction data. The first trained model is configured such that prediction accuracy for the input data of an interpolation region becomes higher than in the second trained model. The second trained model is configured such that prediction accuracy for the input data of an extrapolation region becomes higher than in the first trained model.
-
公开(公告)号：EP4414993A1
公开(公告)日：2024-08-14
申请号：EP22878389.0
申请日：2022-09-28
申请人： Resonac Corporation
发明人： LEE, Haein , MINAMI, Takuya , OKUNO, Yoshishige
摘要： A composition for obtaining a target physical property value is search for more efficiently. A composition search method for a material includes a step of constructing a prediction model by learning training data in which information related to a composition of a material is set as an explanatory variable and a value of a physical property of the material is set as an objective variable; a step of calculating a predicted value of the physical property by inputting, into the prediction model, prediction data for newly searching for a composition; a step of calculating an influence degree of each explanatory variable on prediction by using the training data and the prediction model; a step of calculating a weighted distance of the prediction data with respect to the training data by using the influence degree; and a step of displaying a relationship between the predicted value and the weighted distance, and outputting corresponding prediction data as a search candidate.
-
6.发明公开
公开(公告)号：EP4401082A1
公开(公告)日：2024-07-17
申请号：EP22864609.7
申请日：2022-08-31
申请人： Resonac Corporation
发明人： MINAMI, Takuya , HASHIZUME, Naoki
IPC分类号： G16C20/30 , G16C20/40 , G06F16/907
CPC分类号： G16C20/30 , G16C20/40 , G06F16/907
摘要： A compound safety prediction device (1A) according to the present invention comprises: an input unit (10) for inputting the structural formula of at least one molecule; a safety prediction unit (20) for predicting a safety evaluation of the molecule and computing a confidence score level of the prediction; a similar molecule data searching unit (30) for acquiring the safety evaluation data of a similar molecule similar to the molecule; and an output unit (80) for outputting the result of prediction of the safety evaluation of the molecule, the confidence score level of the prediction, and the safety evaluation data of the similar molecule.
-
公开(公告)号：EP4398257A1
公开(公告)日：2024-07-10
申请号：EP22864393.8
申请日：2022-08-25
申请人： Resonac Corporation
发明人： KAKUDA, Kohsuke , MINAMI, Takuya , AONUMA, Naoto , TAKEMOTO, Shimpei , TAKASHI, Hiroko , OKUNO, Yoshishige
IPC分类号： G16C20/70
CPC分类号： G16C20/70
摘要： A property prediction device for prediction of a property of a composite material composed of raw materials in a plurality of raw material categories. The property prediction device includes a prediction model creating part configured to create a prediction model by using a training dataset of a composite material including a raw material in a first raw material category and a raw material in a second raw material category to perform machine learning of a correspondence relationship between a property of the composite material, which is an objective variable, versus a mixing amount of the raw material in the first raw material category and a weighted feature of the raw material in the second raw material category, which are explanatory variables; and a prediction part configured to input, as explanatory variables, a mixing amount of a raw material in the first raw material category and a weighted feature of a raw material in the second raw material category, that are created based on prediction data of a composite material whose property is to be predicted, into the prediction model so as to predict the property of the composite material corresponding to the prediction data.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.012 秒)
