A cognitive system relies on a pattern library having pattern images with known risk scores to detect potential fraud. Each pattern image begins with a Petri-net model for historical events. A state space representation is generated based on the Petri-net model, and an event pattern layer is established using event sequence vectors from the state space representation. An aggregator layer is also established. The pattern image is created from the event pattern layer and aggregator layer, while applying iterative clustering on the vectors to combine similarities into patterns. A risk score is assigned using supervised or unsupervised learning. The same methodology is used to generate a current pattern image for current events to be analyzed. The cognitive system provides a current risk score based on risk scores associated with likely matches (not necessarily exact) from the pattern library. If the current risk score exceeds a threshold, appropriate action is taken.

Disclosed herein is a method for lossless compression and regeneration of digital design data in a manner maintaining the native formats outputted by modeling software used with prime focus on reduction in file size, portability, interchangeability of file storage format and providing database management functions while being implemented as a plug-and-play add-on utility to existing modeling software. Feature-based extraction of design attributes serves as a core of this inventive method and software utility based thereon.

Methods and systems are presented in this disclosure for performing fast economic analysis of production by fracture-stimulated wells. A class of models can be defined by combining a simulated fracture geometry comprising a stimulated reservoir volume with accounting for fluid dynamics and phase transitions in the stimulated reservoir volume for modeling production in a plurality of reservoirs. An objective function related to the production in the plurality of reservoirs can be generated based on at least one model from the class of models. Parameters related to fracture stages of a fracture network can be then determined, based on the objective function, and communicated, via a computer network to a computing device, to be used for at least one of building or operating the fracture network in the reservoir.

Methods and systems are presented in this disclosure for performing fast economic analysis of production by fracture-stimulated wells. A class of models can be defined by combining a simulated fracture geometry comprising a stimulated reservoir volume with accounting for fluid dynamics and phase transitions in the stimulated reservoir volume for modeling production in a plurality of reservoirs. An objective function related to the production in the plurality of reservoirs can be generated based on at least one model from the class of models. Parameters related to fracture stages of a fracture network can be then determined, based on the objective function, and communicated, via a computer network to a computing device, to be used for at least one of building or operating the fracture network in the reservoir.

A thermal resistance analysis model includes: in a semiconductor integrated circuit comprising a die and a semiconductor chip disposed on the die, the die constituting a bottom inner node BI, the semiconductor chip including a local heat-generating portion constituting a junction node JN, the semiconductor chip constituting an additional plate node PN, a first thermal resistance JP between the junction node JN and the plate node PN; and a second thermal resistance PBI between the plate node PN and the bottom inner node BI, wherein the semiconductor integrated circuit is expressed by a multi-thermal resistance network. There is provided a thermal resistance analysis model with satisfactory precision as a thermal resistance analysis model of locally heat-generating semiconductor integrated circuits; and a semiconductor integrated circuit to which such a thermal resistance analysis model is applied.

A method for generating a reachability graph for recognizing a malfunction of a sensor system. The sensor system is operable with software configured to execute a number of tasks in a certain order. The method includes: generating a Petri net containing information about the tasks of the software of the sensor system and their order, each task being described by a relevant transition of the Petri net, which is executed by the software if required condition(s) for that task are fulfilled; initializing the Petri net by an initial marking, by corresponding conditions for executing at least one or more tasks of the software being set as fulfilled; propagating along the Petri net starting from the initial marking by determining tasks of the software for which the required conditions are fulfilled at each relevant propagation step; generating a reachability graph with nodes, which include information about fulfilled required conditions.

A method for generating a reachability graph for recognizing a malfunction of a sensor system. The sensor system is operable with software configured to execute a number of tasks in a certain order. The method includes: generating a Petri net containing information about the tasks of the software of the sensor system and their order, each task being described by a relevant transition of the Petri net, which is executed by the software if required condition(s) for that task are fulfilled; initializing the Petri net by an initial marking, by corresponding conditions for executing at least one or more tasks of the software being set as fulfilled; propagating along the Petri net starting from the initial marking by determining tasks of the software for which the required conditions are fulfilled at each relevant propagation step; generating a reachability graph with nodes, which include information about fulfilled required conditions.

A Kriging model-based optimal design method and device for a bulk acoustic resonator, and a storage medium are provided. The Kriging model-based optimal design method includes: determining a structure and a material of a resonator, establishing a corresponding MASON model, and performing one-dimensional simulation on the MASON model to obtain a simulation result; determining, based on the simulation result, a design variable for optimizing the resonator, and constructing a Kriging surrogate model; determining an optimization goal, constructing an optimization problem model based on the optimization goal and the Kriging surrogate model, and solving the optimization problem model to obtain an optimal solution; and reducing upper and lower limits of the design variable to improve optimization accuracy. The Kriging model-based optimal design method can predict a performance indicator of an unknown region based on a data characteristic of an existing variable, thereby saving a time cost of actually preparing a device.

A Kriging model-based optimal design method and device for a bulk acoustic resonator, and a storage medium are provided. The Kriging model-based optimal design method includes: determining a structure and a material of a resonator, establishing a corresponding MASON model, and performing one-dimensional simulation on the MASON model to obtain a simulation result; determining, based on the simulation result, a design variable for optimizing the resonator, and constructing a Kriging surrogate model; determining an optimization goal, constructing an optimization problem model based on the optimization goal and the Kriging surrogate model, and solving the optimization problem model to obtain an optimal solution; and reducing upper and lower limits of the design variable to improve optimization accuracy. The Kriging model-based optimal design method can predict a performance indicator of an unknown region based on a data characteristic of an existing variable, thereby saving a time cost of actually preparing a device.

Disclosed is an extend stochastic Petri nets (ESPN)-based method for modeling and representing process reliability of a flexible manufacturing system (FMS), falling within the technical field of flexible manufacturing. Modular division is performed on an FMS, and performance parameters of various process modules are acquired; ESPN septuple models corresponding to subnets of Petri nets are constructed according to the performance parameters of the various process modules; based on a process flow, the subnets of Petri nets are combined according to a set control approach; and numerical values of transitions with arbitrary distributions in a complete ESPN model are solved through numerical simulation. In the disclosure, the accuracy for evaluating the process reliability of the FMS is ensured.