Alerta

基于相空间重构的区间2型T-S模糊模型短期风速预测

Resumen de: CN122241072A

本发明涉及基于相空间重构的区间2型T‑S模糊模型短期风速预测，属于新能源电力系统智能预测与先进控制技术领域，解决了现有风速预测模型误差大、时间长、逻辑不可解析的问题。包括：采集当前时刻之前的风速数据进行预处理，得到风速时间序列；对所述风速时间序列进行相空间重构，得到相空间轨迹矩阵；将所述相空间轨迹矩阵输入训练好的区间2型T‑S模糊模型，输出短期风速预测值；其中，所述区间2型T‑S模糊模型中前件采用不规则高斯隶属函数描述输入变量的模糊特征，所述不规则高斯隶属函数的左右标准差可调。实现了对风速序列混沌特征的有效提取和短期风速的实时预测。

变电站电压互感器采样通道的非线性特征压缩、初筛、分级评估离线诊断方法

Resumen de: CN122241406A

本发明公开了一种变电站电压互感器采样通道的非线性特征压缩、初筛、分级评估离线诊断方法，该方法面向变电站电压互感器采样通道的离线风险评估需求，首先以核主成分分析与熵权赋值相结合的方式构建统一输出的健康判别因子，降低冗余并增强跨站点鲁棒性，引入极限学习机完成样本向量的离线初筛，聚焦符合异常判定条件的异常采样通道片段以提升批处理效率，基于模糊隶属函数、预定义风险等级与评分之间的单调映射关系，实现初筛候选样本的多级风险分级，并结合趋势量对风险演化进行修正进行风险决策，使评分在分界区附近保持稳定且对突变更敏感。具有在多扰动、非平稳等运行干扰条件下提高对电压测量链路的离线数据故障诊断与定位能力的效果。

多级灵敏度引导-多目标优化的海上高抗补偿站配置方法

Resumen de: CN122246787A

本发明公开了一种多级灵敏度引导‑多目标优化的海上高抗补偿站配置方法，首先构建含风电集群、高压海缆及补偿装置的全系统模型，确立以投资成本、系统网损及电压稳定裕度为核心的多目标优化函数与约束；其次提出三级混合灵敏度分析框架，依次计算节点电压对无功注入、网损对补偿容量及模态稳定裕度对补偿位置的灵敏度，据此加权筛选关键候选节点以显著缩减搜索空间，通过改进的多目标粒子群优化算法在候选解空间内高效搜索，获得兼顾经济性与技术性的Pareto最优解集；最后运用模糊决策理论从解集中选取综合满意度最高的方案作为最终配置，为深远海风电送出系统的高抗补偿站选址定容提供了经济、可靠且高效的工程解决方案。

基于模糊数学的砾性土液化潜力指数计算及灾害预测方法

Resumen de: CN122241342A

基于模糊数学的砾性土液化潜力指数计算及灾害预测方法，属于地震工程与岩土工程技术领域，旨在解决传统LPI方法对砾性土深层液化低估、模型不确定性难量化、灾害等级硬分段的技术问题。该方法先整合12个砾性土液化关键影响因素，通过MCMC‑BN模型预测各深度液化概率；再采用双曲线深度加权函数计算深度权重，积分得到值；最后构建梯形隶属度函数模糊评估模型，依最大隶属度原则判定轻微、中等、严重液化灾害等级。本发明同步量化参数与模型不确定性，提升深层液化识别率，实现灾害等级平滑分类，预测精度与分类准确率显著提高，物理意义明确且操作简便，适用于砾性土场地，评估精度高、能有效处理各类不确定性且工程实用性强。

基于改进FMEA的LNG储罐区喷淋水系统风险评估方法

Resumen de: CN122243181A

本发明涉及风险评估技术领域，尤其涉及一种基于改进FMEA的LNG储罐区喷淋水系统风险评估方法，包括确定LNG储罐区喷淋水系统中潜在的失效模式和风险指标，各专家根据费马模糊语言术语集进行评价并转为费马模糊数，通过费马模糊加权平均算子和专家权重计算各风险指标的综合评价，采用改进的DEMATEL确定主观权重，采用熵权法确定客观权重，通过线性加权获得综合权重；通过拓展的CoCoSo方法计算各风险指标对各失效模式的评价分数，根据各风险指标对各失效模式的评价分数进行风险优先级排序。本发明扩大了模糊信息的表达范围，提高评估过程灵活性的同时考虑评价信息间的相互关联，能够得到更为可靠的风险评估结果。

DEVICE AND METHOD FOR ASSISTING IN MONITORING THE MISSION STATUS OF AT LEAST ONE AIRCRAFT

Resumen de: US20260167321A1

0000 A method for assisting in monitoring the mission status of at least one aircraft, through the monitoring of at least one operational criterion during the execution of the mission, includes the following steps: determination of a polynomial function representing the at least one operational criterion, each monomial of which is a product of constants and/or variables, each variable being a characteristic quantity of a set of characteristic quantity(ies) associated with the operational criterion; by partial derivative of the polynomial function, determination of the impact of the variation of each characteristic quantity on the value of the operational criterion; and return of the impact of each characteristic quantity to an operator of the aircraft, conducive to using the impact to identify at least one source of execution anomaly of the mission.

MULTI-TASK COLLABORATIVE ATTENTION TSK FUZZY SYSTEM MODELING METHOD FOR FERMENTED FOOD SAFETY ASSESSMENT

Nº publicación: US20260170369A1 18/06/2026

Solicitante:

JIANGNAN UNIV [CN]
JIANGNAN UNIVERSITY

Resumen de: US20260170369A1

The present invention belongs to the field of intelligent computing, and specifically relates to a multi-task collaborative attention TSK fuzzy system modeling method, which is used to provide an interpretable multi-task intelligent evaluation model for fermentation food safety assessment. The method includes two main parts: a new multi-task TSK fuzzy system model structure and a multi-task collaborative optimization process. In the intelligent evaluation model, the proposed multi-task collaborative processing unit is used to perform collaboration among multiple evaluation tasks. By using the multi-task feature selection layer and task attention structure respectively to extract the unique information of each task and the relevant information between tasks, the evaluation performance of each evaluation task can be better improved. In the collaborative optimization process, the present invention uses multi-task collaborative regularization to achieve more efficient mining and utilization of the unique information of each task.