6 results about "Logic optimization" patented technology

The application provides a method for generative heterogeneous logic optimization based on critical path partitioning. The method includes: converting a digital logic circuit into an And-Inverter Graph (AIG) format; partitioning the AIG using reinforcement learning based on critical path information of the circuit to obtain critical-path-aware partitions so as to reduce influence of critical path changes brought by the partitioning on timing performance; respectively and automatically exploring an optimized structure and synthesis flow suitable for each partition using the reinforcement learning method; selecting optimization operators for various structures using a reinforcement learning agent guided by area-delay metrics and optimizing each partition; and merging the optimized partitions in the AIG format. In the application, the digital logic circuit is partitioned based on critical paths, and reinforcement learning is used to explore and optimize structures and strategies based on area and delay.

The application discloses a kind of excitation regulator system grid-connected logic determination method, it is related to generator set excitation control and power system grid-connected control technical field, wherein the method includes: real-time acquisition includes three kinds of core signals of grid-connected switch combination signal, generator stator current signal, generator terminal voltage signal, and the three kinds of core signals collected are preprocessed;According to the operating characteristics of unit and test demand, set grid-connected state determination criterion parameter;Grid-connected state logic determination is executed to different scene;Based on the result of grid-connected state logic determination, logic optimization and abnormal alarm detection are carried out.The application uses the double core criterion of "combination signal + stator current", effectively resists the signal anomaly caused by contact jitter and loop looseness, avoids the no-load misjudgment when running with load, reduces the risk of reactive power fluctuation and protection misoperation.

This invention provides a method for constructing a logic optimization generation system based on reinforcement learning. The method includes: step S1, obtaining a training dataset; step S2, constructing an initial generation model, which includes a graph encoder, an average pooling layer, a word segmenter, and a sequence decoder; step S3, using the training dataset to iteratively train the initial generation model multiple times until convergence; step S4, using the converged initial generation model as a reference network and initializing a policy network and a value network, and using a reinforcement learning mechanism with human feedback to fine-tune the policy network and the value network, and using the fine-tuned policy network as a logic optimization generation system. The fine-tuning process includes multiple rounds of iterative optimization. In each round of iterative optimization, the graph structure representation of the logic circuit in the training dataset is used as the initial state input reference network, the policy network optimized in the previous round, and the value network to perform multiple interactions.

The present application relates to a kind of power grid outage notice optimization generation method and system based on large language model.The method includes: collecting power grid outage data for processing, obtain structured power grid outage data input into large language model, based on Prompt template generation strategy, Prompt diversity parameter control mechanism carries out semantic abstraction and intent modeling, extracts semantic elements;Using semantic elements for each different preset role perspective generates corresponding outage notification content, generates notification draft to carry out scene adaptation and style optimization, language proofreading and logic optimization, obtains each version of final power grid outage notice;And according to artificial feedback, large language model is optimized.Through generating outage notification content for different preset role perspective, the readability of notification content and user acceptance can be improved;Since scene adaptation, style optimization, logic optimization and other processing are carried out, the content accuracy, logic and language quality can be improved, and artificial intervention can be reduced.

This invention provides a fixedpoint_mult logic optimization method based on SIMD, comprising: S1: using SIMD instructions to save mask data and copy the data 16 times, storing them in the mask register; simultaneously calculating the integer parts of 16 copies of a / 2^pointpos and b / 2^pointpos, and storing them in registers a1 and b1 respectively; S2: using SIMD instructions to simultaneously calculate the fractional parts of 16 copies, and storing them in registers a2 and b2 respectively; S3: calculating the sum X1 of the multiplication of the integer and fractional parts; S4: using SIMD instructions to calculate the multiplication X2 of the fractional parts, calculating the sum X of X1 and X2, and storing X in the output address dst_ptr; then, simultaneously calculating in parallel to obtain 16 sets of fixed_point_mult output results, and storing them in the output address dst_ptr.

The application belongs to the technical field of electric digital data processing, and relates to a complex construction node steel bar arrangement logic optimization method. Steel bar geometric parameters and anchoring constraint relationships are extracted, a directed acyclic graph is constructed with steel bar sections as nodes, spatial occupation intersections as edges, and construction sequences and construction specifications as weights; spatial arrangement conflicts are converted into loop identification problems in the graph, and graph coloring processing is used to divide conflict edges into levels and give avoidance priorities; based on topological sorting traversal, bending avoidance directions and offset rules are determined according to coloring values; offset compensation calculation is performed through topological reverse sequence, offset values are reversely transmitted to non-conflict steel bar sections along the edges, and arrangement coordinates and bending node logic sequences are output. The application converts serial collisions into graph structure operations, overcomes chain collisions and local deadlocks caused by serial avoidance, and eliminates space occupation caused by avoidance.