Beihang University

Other

Shunkun Yang

Xiaodong Gou

Qi Yao

Tingting Huang

Wenjing Liu

Daqing Li

Yushu Xie

Chong Bian

Ke Li

Zheng Zheng

Donghao Wang

Liping Pang

Haopeng Wu

Yan Kan

Pengjiao Li

Minghao Yang

Hongman Li

Qi Shao

Fuping Zeng

Zhiyu Duan

A multi-modal multi-objective testing data generation method based on topology adaptive resonance theory is disclosed. The method considers that that the test aircraft under what kind of external disturbance or its own system fault conditions will be close to multiple index thresholds of unreliable or unsafe state at the same time as a black box optimization testing problem. The testing data is generated through optimization algorithms to test the aircraft state under different disturbance conditions. This type of black box optimization problem belongs to multi-modal multi-objective optimization problems. The testing problem can be solved using a multi-modal multi-objective particle swarm optimization algorithm based on adaptive resonance topology network. The external disturbance variable parameter combination encountered by the aircraft is regarded as the particle position, and the optimal parameter combination is found by iteratively updating the particle position.

Multi-modal multi-objective testing data generation method based on topology adaptive resonance theory

The present disclosure relates to a multi-classification non-intrusive identification and detection method for an electrical signal based on naive Bayes, including an expert database module and a signal classification module. An electrical signal training sample of a known category is built based on historical and real-time aircraft signals. Classification is performed based on a built naive Bayes model classifier, to obtain an aircraft signal classification result. P(yi) is separately calculated for each category, a conditional probability is calculated for each feature, and a classification result of a sample signal is obtained through statistic acquisition by using a probability comparison algorithm. A next status is predicted by using a time series prediction method after electrical signal data is classified and determined by using a naive Bayes algorithm.

Multi-classification and prediction method for electrical signal of aircraft small sample based on naive Bayes

The present invention discloses a software reliability simulation analysis method based on virtual reality and a complex network, which realizes a two-layer network displaying the coupling of a task network and a function complex network in a virtual reality environment and is convenient for technicians to observe the operation of the network from multiple perspectives. On the basis of a technology of virtual reality, the present invention determines the task simulation based on an operation section, observes the flow of codes and the number of passing through function nodes in real time during the execution of a task, and calculates and assesses the importance degree of the nodes. The task simulation method based on the operation section is more convincing for the assessment of the importance of the nodes.

Software reliability simulation analysis method based on virtual reality and complex network

A construction method of a test case constraint control technology based on epigenetics includes steps of: 1: defining a fitness function, a genetic coding method, and a constraint control rule; 2: initializing parameters: setting a population size, an evolution number, and a termination fitness function value; 3: initializing a population: randomly generating an initial population; 4: performing evolution termination judgment; 5. performing constraint regulation based on the epigenetics: performing constraint methylation and constraint acetylation according to the constraint control rule; 6: selecting individuals; 7: completing epigenetic evolution of the population; and 8: outputting a test case set; wherein through the above steps, construction of an epigenetic test case constraint control technology is completed, so as to design test cases that are more in line with the actual operation conditions of the software, find more potential software failures, and improve the quality of software testing.

Construction method of test case constraint control technology based on epigenetics

A method for establishing fault diagnosis technique based on contingent Bayesian networks, comprising steps of: step (1) determining a domain of an unknown object to be reasoned; step (2) defining a model structure by adopting a first-order logic language; step (3) generating a Blog model; step (4) transforming the Blog model into the contingent Bayesian networks; step (5) defining the contingent Bayesian networks; step (6) learning parameters of the contingent Bayesian networks; and step (7) reasoning a fault of the contingent Bayesian networks by utilizing a Markov chain Monte Carlo Method. By the steps mentioned above, establishing fault diagnosis technique based on contingent Bayesian networks is achieved.

Method for establishing fault diagnosis technique based on contingent Bayesian networks

A construction method of a software accelerated testing technology based on a noise resonance includes steps of: (1), collecting a source code of software to be tested; (2), automatically generating software test cases based on an intelligent evolving method, until information same or similar as a fault phenomenon is searched; (3), starting a saturation noise mode, and meanwhile exerting all controllable noise sources at a maximum intensity; (4), exerting all the controllable noise sources at a minimum intensity; (5), starting a strategy noise interference mode, and generating a noise resonance; (6), continuously exerting noises at a noise intensity able to generate the noise resonance; and (7), generating effective test sequences. Through the above steps, construction of the software accelerated testing technology based on the noise resonance is completed, which helps software testers accelerate recurrence of a software fault during testing and update the software to increase a reliability thereof.

Construction method of software accelerated testing technology based on noise resonance

Growing community of inventors

Beijing, China

Shunkun Yang