作者：
Bai, PengWang, KangchengZhao, Yun-BoKang, YuFang, WenhaoUSTC
Dept Automat Hefei Peoples R China Anhui Univ
Inst Artificial Intelligence Hefei Comprehens Natl Sci Ctr AHU IAI AI Joint Lab Iefei Peoples R China USTC
Inst Artificial Intelligence Hefei Comprehens Natl Sci Ctr Inst Adv Technol Iefei Peoples R China
Functional testing is a crucial process to guarantee the quality of electronic products. In recent years, the cost of functional testing has been rising with the increasing complexity of products, and reducing testing...
详细信息
ISBN:
(纸本)9798331540845;9789887581598
Functional testing is a crucial process to guarantee the quality of electronic products. In recent years, the cost of functional testing has been rising with the increasing complexity of products, and reducing testing costs is of great significance to the economic efficiency of electronic manufacturing enterprises. Related research has not yet fully considered the issue of the non-uniform distribution of functional testing samples in practical applications, making it challenging to ensure the effectiveness of reducing testing costs. Motivated by the concept of TCP congestion control algorithms, this article presents an enhanced congestion control algorithm tailored for the functional testing process and proposes a method to reduce testing costs accordingly. The proposed method can design dynamically changing testing strategies based on optimal modeling. On the simulation data closely resembles the actual data, the proposed method can significantly reduce the testing costs compared to the pure optimization modeling method.
This paper proposes a method for efficiently organizing, managing, and visualizing road traffic accident data through knowledge graph technology. It begins by outlining the construction process of the road traffic acc...
详细信息
The wastewater treatment process (WWTP) is characterized by unknown nonlinearity and external disturbances, which complicates the tracking control of dissolved oxygen concentration (DOC) within operational constraints...
详细信息
The wastewater treatment process (WWTP) is characterized by unknown nonlinearity and external disturbances, which complicates the tracking control of dissolved oxygen concentration (DOC) within operational constraints. To address this issue, a data-driven tube-based robust predictive control (DTRPC) strategy is proposed to achieve stable tracking control of DOC and satisfy the system constraints. First, a tube-based robust predictive control (TRPC) strategy is designed to deal with system constraints and external disturbances. Specifically, a nominal controller is designed to ensure that the nominal output accurately tracks the set-point under tightened constraints, while an auxiliary feedback controller is designed to suppress disturbances and restore the nominal performance of the disturbed WWTP. Second, two fuzzy neural network identifiers are employed to provide accurate predictive outputs for the controlprocess, overcoming the challenges of modeling the WWTP with strong nonlinearity and unknown dynamics. Third, the generalized multiplier method is utilized to solve the constrained optimization problem to obtain the nominal control law, and the gradient descent algorithm is used to obtain the auxiliary control law. The implementation of this composite controller ensures the satisfaction of the system constraints and the effective suppression of disturbances. Finally, the feasibility and stability of the proposed DTRPC strategy are guaranteed through rigorous theoretical analysis, and its effectiveness is demonstrated through the simulations on the benchmark simulation model No.1.
Landslide dams consist of unconsolidated heterogeneous material and lack engineering measures to drain water and control pore water pressure. They may be porous and seepage through them could potentially lead to pipin...
详细信息
Landslide dams consist of unconsolidated heterogeneous material and lack engineering measures to drain water and control pore water pressure. They may be porous and seepage through them could potentially lead to piping failure. In this research, the internal processes within a long-existing landslide dam are assessed under transient seepage force. The implemented approach includes a 3D finite element numerical simulation executing fully coupled flow-deformation and consolidation methods based on hydraulic data measurements and geotechnical laboratory tests. The nonlinear constitutive model 'Hardening Soil' is applied to accurately calculate the stressinduced pore water pressure, effective stress, deformation, and flow. Further, the possibility of slope failure due to seepage force is investigated through the strength reduction method. The results highlight the dependency of the seepage flow on the corresponding variation of the relative permeability and saturation in the soil mediums under different rates of seepage force. Small rates of seepage force, however, impose deformation at the dam's crown. High effective stress is obtained at negative small rates of seepage force where the long duration of fluctuation is modeled. In the drawdown simulation, there is a reverse relation between effective stress and the rate of the seepage force. Through the modelingprocess and based on the measured data, two seepage paths are detected within the landslide dam, while their activation depends on the lake level. The modeling approach and the required dataanalysis are suggested for utilization in further studies regarding the seepage process understanding at the long-existing landslide dams and their hazard assessments in addition to the common geomorphological approaches.
Modern business environments are governed by a wide range of data in various data formats. Despite the importance of integrating the data and control-flow perspective, existing business process modelling languages hav...
详细信息
ISBN:
(纸本)9783031342400;9783031342417
Modern business environments are governed by a wide range of data in various data formats. Despite the importance of integrating the data and control-flow perspective, existing business process modelling languages have only limited capability to precisely describe data-driven processes. In this paper, we propose a new approach called JSON-Nets, a variant of high-level Petri nets, that utilizes JSON technologies to integrate complex data objects in executable process models. We introduce JSON-Nets using an illustrative example and provide a formal specification, as well as a prototypical implementation of a modelling tool to evaluate our conception.
The coordination of traffic flow among regions is necessary for a large-scale road traffic network to avoid local congestions and improve the overall traffic efficiency. In this paper, by incorporating the random char...
详细信息
The coordination of traffic flow among regions is necessary for a large-scale road traffic network to avoid local congestions and improve the overall traffic efficiency. In this paper, by incorporating the random characteristic of traffic flow, we formulate the problem of perimeter traffic flow control for a multi-region traffic network as a Markov decision process with adaptive state definition. Based on stochastic macroscopic fundamental diagrams (MFD) of regions, a state transition probability model is proposed to describe the state changes of the multi-region traffic network under different perimeter control policies. With the stochastic MFD-based state transition probabilities rather than counting from the historical data, a policy iteration algorithm with perturbation analysis is introduced to get the optimal perimeter control policy in real-time without the requirement of online or offline learning. The proposed method is compared with the classic perimeter control methods by simulation, which indicates its effectiveness in mitigating the congestion and improving the network throughput, as well as the promising implementation prospect.
Business processes require continuous changes or interventions to remain efficient and competitive over time. However, implementing these changes-such as reordering or adding new tasks- can negatively affect the overa...
详细信息
ISBN:
(纸本)9783031790584;9783031790591
Business processes require continuous changes or interventions to remain efficient and competitive over time. However, implementing these changes-such as reordering or adding new tasks- can negatively affect the overall process performance. A longstanding problem in Business process Management is that of forecasting ex-ante the values that process performance measures will assume after implementing changes. To achieve this, the concept of Digital process Twins, which extends the well-established Digital Twin paradigm, paves the way for new interesting opportunities. Digital process Twins enable enhanced what-if analysis by virtually predicting process performance under various changes, thus allowing for informed decision-making before actuating process changes in the real world. However, despite recognition as one of the new key enablers of modern process re-engineerization, a comprehensive approach to implementing Digital process Twins is still lacking. This paper proposes a novel conceptual architecture for deploying Digital process Twins to address this gap. Additionally, we introduce Dolly, a framework that implements such conceptual architecture using a multi-modeling approach combining domain data and processmodeling along with a data-driven process simulation technique.
The complexity of industrial processes imposes a lot of challenges in building accurate and representative causal models for abnormal events diagnosis, control and maintenance of equipment and process units. This pape...
详细信息
The complexity of industrial processes imposes a lot of challenges in building accurate and representative causal models for abnormal events diagnosis, control and maintenance of equipment and process units. This paper presents an innovative data-driven causality modeling approach using interpretable machine learning and process mining techniques, in addition to human expertise, to efficiently and automatically capture the complex dynamics of industrial systems. The approach tackles a significant challenge in the causality analysis community, which is the discovery of high-level causal models from low-level continuous observations. It is based on the exploitation of event data logs by analyzing the dependency relationships between events to generate accurate multi-level models that can take the form of various state-event diagrams. Highly accurate and trustworthy patterns are extracted from the original data using interpretable machine learning integrated with a model enhancement technique to construct event data logs. Afterward, the causal model is generated from the event log using the inductive miner technique, which is one of the most powerful process mining techniques. The causal model generated is a Petri net model, which is used to infer causality between important events as well as a visualization tool for real-time tracking of the system's dynamics. The proposed causality modeling approach has been successfully tested based on a real industrial dataset acquired from complex equipment in a Kraft pulp mill located in eastern Canada. The generated causality model was validated by ensuring high model fitness scores, in addition to the process expert's validation of the results.
Wire Arc Additive Manufacturing (WAAM) offers significant potential for producing large, complex components with short lead times. While progress in WAAM technology has primarily been made in the field of gas metal ar...
详细信息
Wire Arc Additive Manufacturing (WAAM) offers significant potential for producing large, complex components with short lead times. While progress in WAAM technology has primarily been made in the field of gas metal arc welding (GMAW), plasma arc welding (PAW) has not yet been sufficiently researched. PAW offers distinct advantages due to its ability to easily separate heat input from material deposition, thereby providing greater flexibility in parameter optimization than GMAW. Meeting stringent geometric specifications is crucial to the success of any WAAM process. This entails precise determination of initial process parameters, and online parameter adjustments while stabilizing the build process. To address this challenge, we propose a hybrid modeling approach that integrates physics-based principles and data-driven insights. This approach yields static models, validated by experimental analysis, that facilitates the prediction of energy and material inputs to achieve desired bead geometries. Additionally, a model-based height error estimator is introduced that does not rely on any vision-based measurement systems, further enhancing applicability and economic viability. The developed models are integrated into a two-degree-of-freedom control strategy and validated by building representative workpieces. The validation demonstrates the potential of the proposed approach in predicting and controlling WAAM processes.
data analytics is pivotal in assessing the technical characteristics and performance of Battery Energy Storage Systems (BESS), underpinning BESS modeling, optimization, and control. PNNL has collected diverse and comp...
详细信息
ISBN:
(纸本)9798350308235
data analytics is pivotal in assessing the technical characteristics and performance of Battery Energy Storage Systems (BESS), underpinning BESS modeling, optimization, and control. PNNL has collected diverse and comprehensive real-world BESS operational datasets in collaboration with the Electric Power Research Institute and multiple Washington State utilities, allowing for BESS analytics and modeling. However, raw datasets frequently harbor anomalies from measurement errors and equipment malfunctions, impacting BESS reliability and analysis accuracy. To address the challenge, this paper presents a methodology for the rapid detection of anomalous charge or discharge cycles within BESS operational data, expediting the cleaning process while ensuring data integrity. Using case studies from real BESS operational datasets, we demonstrate that the proposed method detects anomalies and aids in their resolution, improving system performance characterization. It also reveals recurring data anomaly sources, offering insights for data cleaning. Practitioners can gain valuable insights from the identified anomalous cycles in the real-world datasets along with the investigative process for root cause analyses and essential data cleaning steps.
暂无评论