Search

When data-driven algorithms, especially the ones based on deep neural networks (DNNs), replace classical ones, their superior performance often comes with difficulty in their analysis. On the way to compensate for this drawback, formal verification techniques, which can provide reliable guarantees on program behavior, were developed for DNNs. These techniques, however, usually consider DNNs alone, excluding real-world environments in which they operate, and the applicability of techniques that do account for such environments is often limited. In this work, we consider the problem of formally verifying a neural controller for the routing problem in a conveyor network. Unlike in known problem statements, our DNNs are executed in a distributed context, and the performance of the routing algorithm, which we measure as the mean delivery time, depends on multiple executions of these DNNs. Under several assumptions, we reduce the problem to a number of DNN output reachability problems, which can be solved with existing tools. Our experiments indicate that sound-and-complete formal verification in such cases is feasible, although it is notably slower than the gradient-based search of adversarial examples.The paper is structured as follows. Section 1 introduces basic concepts. Then, Section 2 introduces the routing problem and DQN-Routing, the DNN-based algorithm that solves it. Section 3 proposes the contribution of this paper: a novel sound and complete approach to formally check an upper bound on the mean delivery time of DNN-based routing. This approach is experimentally evaluated in Section 4. The paper is concluded with some discussion of the results and outline of possible future work.

Reliability of industrial automation software, which is usually ensured with testing and simulation, can be improved using formal analysis and, in particular, the technique of model checking. In model checking, considering the closed-loop composition of the plant model and the controller model allows checking a larger class of properties than in the more traditional open-loop case, where the model of the controller is verified alone. Constructing the formal model of the plant automatically may significantly reduce human workload and mitigate the human factor issue. Commonly, complex industrial plants and controllers have modular structure, and thus the problem of automatic construction of a modular plant model is important. This paper proposes two techniques which extend an earlier proposed method of monolithic plant model construction to the modular case.

A method for control finite state machine (FSM) induction in which an ant colony opti� mization algorithm is used for search optimization is proposed. The efficiency of this method is esti� mated using the generation of FSMs for controlling a model of an unmanned aerial vehicle (UAV). It is shown that the proposed method outperforms the method based on genetic algorithms both in terms of performance and quality.

Formal methods and languages are used to prove the correctness of various industrial systems, especially mission-critical ones. They can also be viewed as a means to provide safety and correctness demonstration to the stakeholders of such systems. In domains such as nuclear power plant engineering, the benefits from structured safety evidences would seem obvious. However, most stakeholders in nuclear power industry are not even familiar with formal notations. As a result, to promote the applications of formal methods in practice, the first step is to make formal specification languages (FSLs) more accessible. With user-friendly FSLs, users can focus on safety requirements rather than on their sophisticated formalization. This paper, as a preliminary work towards an integrated framework supporting transparent safety demonstration, reviews existing approaches applied to facilitate requirements formalization and formal specifications. Moreover, the common features of user-friendly languages and their tool supports are also summarized.

The paper addresses the problem of coverage testing of industrial automation software represented in the IEC 61499 standard, one of the recent standards for distributed control system design. Contrary to model-based testing (MBT), the paper focuses on implementation coverage, not model coverage. An approach based on evolutionary algorithms is presented which generates coverage test suites for both basic and composite IEC 61499 function blocks. It employs two third-party tools, FBDK and EvoSuite. The evaluation of the approach was performed on a set of control applications for two lab-scale demonstration plants. Results show that the approach is applicable and shows good performance at least on basic function blocks. The generated tests suites helped to discover several unreachable system parts, which pinpointed errors in the systems under test.

This report describes the application of potentiometric multisensor system for estimation of water samples toxicity in terms of Microtox ® analyzer—a widespread instrument for toxicity evaluation. The working principle of Microtox ® analyzer is based on a registration of luminescence from Vibrio fischeri bacteria. This luminescence depends on metabolism conditions and toxicity of the environment. Due to the fact that metabolism is influenced by multiple parameters the method is associated with certain limitations. Unlike this bioassay procedure the employment of multisensor system does not require the use of living organisms and can provide for faster toxicity evaluation. Fifty-five real and model polluted water samples, for which the toxicity was established by bioassay, were studied. The response of multisensor array processed with machine learning techniques allows for prediction of toxicity in terms of EC50 with relative errors of 20–25%. Taking into account the complexity of the task (simulation of complex biological reactions with inanimate instrument) this can be considered as a good promise for further research in this direction in order to develop instrumental alternative for toxicity assessment.

Our general objective in SAUNA (2015-2018) has been to develop integrated methods and tools for safety assessment and transparent safety demonstration of nuclear power plant instrumentation and control (I&C) systems. Due to the multidisciplinary nature of the nuclear power plant as a whole, I&C safety assessment calls for an overall safety point-of-view. We have worked towards that goal by 1) specifying model-based Systems Engineering approaches for I&C, 2) developing concepts and models for analysing Defence-in-Depth issues in I&C architectures, 3) integrating existing methods and finding novel tools for analysing overall safety (with particular focus on formal verification), and 4) developing model-based ways for attesting conformity in the I&C qualification process.