CANN PID控制性能指标API

PidControlPerformanceMetrics API【免费下载链接】mat-chem-sim-pred面向工业领域聚焦计算仿真、预测两大核心场景构建面向流程工业机理数据双轮驱动的领域计算层推动AI for Science在材料化学领域的深度应用。项目地址: https://gitcode.com/cann/mat-chem-sim-predextern C uint64_t aclnnPidControlPerformanceMetricsGetWorkspaceSize( int64_t batch, int64_t sample_count); extern C int32_t aclnnPidControlPerformanceMetrics( void* pv, void* sp, void* lsl, void* usl, void* mv_variance, void* metrics, int64_t batch, int64_t sample_count, float sample_interval, float settle_band, void* workspace, uint64_t workspace_size, void* stream);参数参数说明pvDevice 输入shape[batch, sample_count]float32spDevice 输入shape[batch, sample_count]float32lslDevice 输入shape[batch]float32uslDevice 输入shape[batch]float32mv_varianceDevice 输入shape[batch]float32metricsDevice 输出shape[batch, 20]float32batch回路数量sample_count每条回路窗口采样点数sample_interval采样间隔用于 IAE/ISE/ITAE/settling_timesettle_band稳定带abs(sp - pv) settle_band视为稳定workspaceDevice workspaceworkspace_sizeworkspace 大小streamACL stream输出指标顺序mean_pv,std_pv_sample,std_pv_population,cp,cpk,pp,ppk,harris_index,iae,ise, itae,mae,rmse,max_abs_error,out_ratio,out_count,overshoot,undershoot,settling_time,final_abs_error【免费下载链接】mat-chem-sim-pred面向工业领域聚焦计算仿真、预测两大核心场景构建面向流程工业机理数据双轮驱动的领域计算层推动AI for Science在材料化学领域的深度应用。项目地址: https://gitcode.com/cann/mat-chem-sim-pred创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考