基于微分代数神经网络的含新能源区域电网端口动态特性学习方法

高比例新能源渗透背景下,建立能够准确描述复杂环境因素影响下含新能源的区域电网端口特性动态模型,对于新型电力系统动态分析至关重要。为此,提出了一种基于微分代数神经网络的含新能源区域电网端口动态特性学习方法。该方法利用微分代数神经网络,基于区域电网接入点的时序量测以及光照强度、温度等环境量测数据,学习以神经网络表达的端口特性模型。所得模型由初始状态提取模块、微分神经网络模块、代数神经网络模块组成,可直接接入电力系统暂态仿真器中,用于分析电力系统整体动态特性。在IEEE-39节点系统中对该方法进行仿真验证,测试结果表明：所得模型能够适应不同环境场景,准确率高,验证了方法的有效性。该建模方法仅依赖端口时序量测,在新型电力系统动态分析中具有较大的应用潜力。     

考虑单峰分布的电热综合能源系统风险调度

不确定可再生能源并入电热综合能源系统后将引发系统运行风险,而通过合理量化风险,实现风险可控性和调度经济性平衡是电热综合能源系统风险调度的关键。依据随机风电功率的单峰分布特性构建矩模糊集并以此刻画风电功率的不确定性,同时采用分布鲁棒机会约束方法来刻画系统的运行风险,进而建立了电热综合能源系统的分布鲁棒风险调度模型。在此基础上,从风险发生概率和经济成本的角度,提出了评估不确定风电功率引发运行风险的量化指标：均值风险概率和风险调度成本。最后,以改进的巴厘岛电热综合能源系统为例进行算例分析,验证了所提模型及其风险评估指标的可行性和有效性,并给出了电热综合能源系统的最优调度决策。     

计及配电公司特许经营权的产消者点对点交易模型

在针对配电系统层面设计点对点电力交易机制时,需要考虑配电公司所拥有的特许经营权,通过设计适当的网络收费模式有效补偿配电系统基础设施所有者的投资和运行成本。提出一种计及配电公司特许经营权的产消者点对点交易模型。基于配电公司和产消者之间的主从互动关系,建立基于电气距离的过网费定价双层博弈模型,上层为以配电公司收益最大为目标的过网费价格决策模型,下层为考虑过网费的产消者最优调度模型;基于卡罗需-库恩-塔克(KKT)条件将双层博弈模型转化为单层混合整数规划问题,进而得到过网费价格;利用交替方向乘子法分布式求解产消者点对点实时交易电量和交易电价。IEEE 33节点配电系统的仿真结果验证了所提模型能在保证配电系统安全运行的基础上保障所有产消者利益,且能合理补偿配电公司因放弃部分特许经营权而产生的收益损失。     

计及多模态分量的新能源电力系统节点频率分析方法

“双碳”背景下,大规模新能源接入电力系统,频率响应空间分布差异扩大,此时各节点频率响应中的非全局分量可能主导频率稳定问题,而对于此类问题的研究目前尚不充分。为此,基于频率响应模态分解思路,提出新能源电力系统节点频率响应量化分析方法。首先,用惯量-阻尼-调频系统统一结构近似各类型设备频率-有功传递函数。然后,基于二次特征值分析方法将各节点频率响应进行分解,获得共模频率与若干差模频率的表达式。进一步地,解析了各频率分量的最大偏移量、变化率等关键特征量,并类比总惯量与全局频率变化率间的对应关系,针对各节点各模态频率分量定义了节点模态惯量指标。所提频率分解方法与指标直观地展示了电力系统中各差模频率的节点分布差异。最后,仿真验证了所提频率分解方法和指标的有效性。     

基于价值分解深度强化学习的分布式光伏主动电压控制方法

针对主动电压控制问题,深度强化学习能够有效地解决数学优化方法在精确性和实时性方面的不足。但传统多智能体深度强化学习方法存在信用分配、过度泛化等问题,难以学习到全局最优的协调策略,控制效果较差。为此,提出了一种基于价值分解深度强化学习的分布式光伏主动电压控制方法。将主动电压控制问题建模为分布式部分可观测马尔可夫决策过程,然后基于中心化训练和去中心化执行框架,提出分解式价值网络、集中式策略梯度2项改进措施：将全局价值网络分解为个体价值网络和混合网络,并采用所有智能体的当前策略进行集中参数更新。改进的IEEE 33节点配电网系统的算例结果表明,所提方法表现出了优越的稳压减损控制性能,且在训练速度、场景鲁棒性等方面具备一定的优势。     

海上风电交流送出线路继电保护优化设计

针对海上风电运行环境恶劣、平台面积资源有限以及电缆线路电容电流显著等问题,提出一种适用于海上风电送出线路的高压线路保护与电抗器保护一体化设计的新方案。首先,将输电线路和电抗器视为一个电气设备,设计了集成优化整体方案,避免了传统的电抗器支路电流的迭代计算。然后,对比研究了传统差动和行波差动对电缆线路电容电流的补偿效果,提出了线路保护优化处理技术。通过引入更为适合的线路零序电流作为电抗器零序差动的制动电流,提出了电抗器保护功能优化策略。最后,仿真实验验证了所提的优化处理技术能够提高海缆线路差动保护和电抗器零序差动保护的灵敏性和可靠性。     

Efficient skeleton curve-guided five-axis sweep scanning based on optimal traversing of multiple connected skeleton curves

The five-axis sweep scanning approach is an emerging surface inspection technology which could tremendously boost the inspection efficiency through working in the way of continuous scanning. While inspecting the surfaces with multiple connected skeleton curves, the topological complexity brings conflict between achieving efficient inspection and working in continuous manner. Recently, a skeleton curve-guided five-axis sweep scanning method was proposed to tackle this problem but the resulting inspection path has to inspect the entire surface in a round-trip way. The manner of round-trip inspection pulls down the entire inspection efficiency and should be avoided as much as possible. In this paper, we present an improved skeleton curve-guided five-axis sweep scanning method to generate a more efficient five-axis scanning path for the surface with multiple connected skeleton curves. The proposed method starts from the framework of existing skeleton curve-guided five-axis sweep scanning method. Under the unique kinematic requirements of efficient five-axis sweep scanning, an integer linear programming optimization approach is utilized to optimally connect the inspection paths on independent surface patches and form a shorter skeleton curve-based sweep scanning path as compared with the existing skeleton curve-guided five-axis sweep scanning method. The resulting inspection path is composed of the single-pass inspection for most of the surface and the round-trip inspection for a small part of the surface. The comparison experiments are conducted on two surfaces with multiple connected skeleton curves. Experiment results show that the proposed method significantly outperforms the method provided by the leading commercial software Apexblade and the original skeleton curve-guided five-axis sweep scanning method.     

Multiple source partial knowledge transfer for manufacturing system modelling

Transfer learning has shown its attractiveness for manufacturing system modelling by leveraging previously acquired knowledge to assist in training the target model, whereas most techniques focus on single-source transfer settings. Since there are usually multiple source domains available in practice, multi-source transfer learning is attracting more attention. Existing researches regard the source instance or the source model as the basic information granularity, which makes it difficult to reduce the global shift and the local discrepancy across domains simultaneously. Therefore, this paper presents a multiple source partial knowledge transfer method (MSPKT) for manufacturing system modelling tasks, in which partial knowledge is defined as a novel information granularity between the instance granularity and model granularity. Firstly, TSK (Takagi-Sugeno-Kang) fuzzy system is introduced as the basic learner to represent partial knowledge effectively. Then, we design a transferability measurement of partial knowledge by considering the similarity and reliability to support transfer learning with multiple source domains. Finally, a synthetic dataset and two manufacturing system datasets are used to verify the effectiveness of the proposed method.     

Sparse identification for ball-screw drives considering position-dependent dynamics and nonlinear friction

Establishing accurate dynamic models in a form that is suitable for integration with model-based control methods, is of great significance for further improving the dynamic motion control precision of ball-screw drives. However, due to the nonlinear time-varying factors such as position-dependent dynamics and nonlinear friction disturbance, it is difficult to model the dynamic characteristics of ball-screw drives accurately, concisely and efficiently. To overcome this challenge, a sparse identification method for ball-screw drives is proposed. Ball-screw drives are modeled as discrete-time linear parameter-varying systems under nonlinear friction disturbance, and two types of dictionary function libraries are designed to represent the position-dependent dynamics and nonlinear friction respectively. After constructing the regression form of the system model, a stepwise sparse regression policy is proposed to solve all the coefficients of dictionary functions. The proposed method is verified in both simulation and real environments. The results both show that by the proposed method, an accurate and linearizable dynamic model of ball-screw drives can be identified only using the data from only one global random excitation experiment covering the working stroke.     

Plasma Enhanced Lithium Coupled with Cobalt Fibers Arrays for Advanced Energy Storage

Construction of high efficiency and stable Li metal anodes is extremely vital to the breakthrough of Li metal batteries. In this study, for the first time, groundbreaking in situ plasma interphase engineering is reported to construct high-quality lithium halides-dominated solid electrolyte interphase layer on Li metal to stabilize & protect the anode. Typically, SF₆ plasma-induced sulfured and fluorinated interphase (SFI) is composed of LiF and Li₂S, interwoven with each other to form a consecutive solid electrolyte interphase. Simultaneously, brand-new vertical Co fibers (diameter: ≈5 µm) scaffold is designed via a facile magnetic-field-assisted hydrothermal method to collaborate with plasma-enhanced Li metal anodes (SFI@Li/Co). The Co fibers scaffold accommodates active Li with mechanical integrity and decreases local current density with good lithiophilicity and low geometric tortuosity, supported by DFT calculations and COMSOL Multiphysics simulation. Consequently, the assembled symmetric cells with SFI@Li/Co anodes exhibit superior stability over 525 h with a small voltage hysteresis (125 mV at 5 mA cm⁻²) and improved Coulombic efficiency (99.7%), much better than the counterparts. Enhanced electrochemical performance is also demonstrated in full cells with commercial cathodes and SFI@Li/Co anode. The research offers a new route to develop advanced alkali metal anodes for energy storage.