Process for recovering olefins in polyolefin plants
    35.
    发明授权
    Process for recovering olefins in polyolefin plants 有权
    在聚烯烃工厂中回收烯烃的方法

    公开(公告)号:US09073808B1

    公开(公告)日:2015-07-07

    申请号:US14486382

    申请日:2014-09-15

    Abstract: A process for recovering unreacted olefin in a polyolefin manufacturing process comprising the treatment of a purge bin vent gas. The process involves cooling and condensing the vent gas (purge stream), which contains at least an olefin, a paraffin, and nitrogen, to produce a liquid condensate and an uncondensed (residual) gas stream. Both streams are then passed through membrane separation steps. The membrane separation of the uncondensed gas stream results in a residue stream containing mostly nitrogen and/or paraffin and a permeate stream enriched in either C2+ hydrocarbons or olefin, depending on the type of separation. The permeate from this step is recirculated within the process prior to the condensation step. The membrane separation of the condensate results in a residue stream containing paraffin and a permeate stream enriched in olefin, which may be recycled to the polymerization reactor.

    Abstract translation: 一种在聚烯烃制造方法中回收未反应烯烃的方法,包括处理净化箱排气。 该方法包括冷却和冷凝含有至少一种烯烃,石蜡和氮气的排出气体(吹扫流),以产生液体冷凝物和未冷凝(残余)气流。 然后将两个流通过膜分离步骤。 未冷凝的气流的膜分离导致根据分离类型,主要含有氮和/或石蜡的残留物流和富含C 2 +烃或烯烃的渗透物流。 来自该步骤的渗透物在冷凝步骤之前在该过程中再循环。 冷凝物的膜分离产生含有石蜡和富含烯烃的渗透物流的残余物流,其可循环至聚合反应器。

    PREDICTIVE MODEL VALIDATION
    36.
    发明申请
    PREDICTIVE MODEL VALIDATION 审中-公开
    预测模型验证

    公开(公告)号:US20120197608A1

    公开(公告)日:2012-08-02

    申请号:US13444963

    申请日:2012-04-12

    CPC classification number: G06Q10/04 G06Q30/02 G06Q40/025

    Abstract: Models are generated using a variety of tools and features of a model generation platform. For example, in connection with a project in which a user generates a predictive model based on historical data about a system being modeled, the user is provided through a graphical user interface a structured sequence of model generation activities to be followed, the sequence including dimension reduction, model generation, model process validation, and model re-generation.In connection with a project in which a user generates a predictive model based on historical data about a system being modeled, the user is enabled to validate the model development process with cross-validation between at least two subsets of the historical data; the validated model development process is enabled to be reapplied.

    Abstract translation: 使用模型生成平台的各种工具和功能生成模型。 例如,关于用户根据关于正被建模的系统的历史数据生成预测模型的项目,通过图形用户界面提供要遵循的模型生成活动的结构化序列,所述序列包括维度 减少,模型生成,模型过程验证和模型重新生成。 关于用户根据关于正在建模的系统的历史数据生成预测模型的项目,用户能够通过历史数据的至少两个子集之间的交叉验证来验证模型开发过程; 验证的模型开发过程能够被重新应用。

    Handbag
    37.
    外观设计
    Handbag 有权

    公开(公告)号:USD533997S1

    公开(公告)日:2006-12-26

    申请号:US29251280

    申请日:2006-01-06

    Applicant: Marc Jacobs

    Designer: Marc Jacobs

    Predictive model generation
    38.
    发明申请
    Predictive model generation 有权
    预测模型生成

    公开(公告)号:US20050234688A1

    公开(公告)日:2005-10-20

    申请号:US10826630

    申请日:2004-04-16

    CPC classification number: G05B17/02

    Abstract: Models are generated using a variety of tools and features of a model generation platform. For example, in connection with a project in which a user generates a predictive model based on historical data about a system being modeled, the user is provided through a graphical user interface a structured sequence of model generation activities to be followed, the sequence including dimension reduction, model generation, model process validation, and model re-generation. Historical multi-dimensional data is received representing multiple variables transformed to be maximally predictive for at least one outcome variable to be used as an input to a predictive model of a commercial system, model development process is validated for at one or more sets of such variables and enabling a user of a model generation tool to combine at least two of the variables from the sets of variables.

    Abstract translation: 使用模型生成平台的各种工具和功能生成模型。 例如,关于用户根据关于正被建模的系统的历史数据生成预测模型的项目,通过图形用户界面提供要遵循的模型生成活动的结构化序列,所述序列包括维度 减少,模型生成,模型过程验证和模型重新生成。 接收的历史多维数据表示多个变量,以变换为对用作商业系统的预测模型的输入的至少一个结果变量进行最大预测,模型开发过程在一个或多个这样的变量集合 并使得模型生成工具的用户能够组合来自变量集合中的至少两个变量。

Patent Agency Ranking