A method to regenerate the control logic automatically from plant operation data is proposed. In this method, the control logic is learned by the inductive learning algorithm. Almost the same control logic as the installed control logic is obtained in a simulation.

Automatic regeneration of sequence programs for the operating plants

Today, many plants built in the 1960s will probably be replaced or maintained. However, it is difficult to replace or maintain them because the installed sequential control logic documents are seldom still in existence. Therefore, we have proposed an automatic regeneration method (SPAIR) in order to solve this problem. SPAIR regenerates sequential control logic that is expressed on a ladder diagram from the input and output data of a target control unit and its supplementary specifications, which indicate the information about timers and interior coils. Time series data is compressed and translated into training data using the specifications. The training data are processed by inductive learning and transformed into control logic. We have developed the SPAR-System in order to edit all kinds of data, generate target logic for plants, and to easily verify the inferred logic simulation plant. Simulation experiments confirmed that control logic that is regenerated by SPAIR behaves in the same way as the installed control logic of a target plant model.

Automatic regeneration of sequence programs for operating plants

In this paper, a method to divide a large-scale logic program is proposed. The hierarchical structure of the given logic program can be found by using graph theory. An illustrative example of elevator control program is shown as application of the proposed theory.

http://ieeexplore.ieee.org/iel5/9792/30882/01432211.pdf

Structure analysis of logic control programs

At present, some substations have carried out sequential control pilot applications, but there are generally problems such as inconsistent operation methods, narrow operation coverage, incomplete typical functions, and complicated manual intervention links. The article constructs a multi-objective comprehensive evaluation model of operation mode based on the one-key sequential control operation mode of different application scenarios. This article establishes the weights of various indicators including operation efficiency, economic benefits and other factors, conducts a comprehensive evaluation and proposes an optimal operation mode. Through actual cases, the article also analyzes the functional transformation scheme of one-key sequence control technology of intelligent substation.

https://iopscience.iop.org/article/10.1088/1742-6596/1861/1/012113/pdf

Study on Optimal Operation Mode of One-key Sequence Control in Substation

Implementation of PCs' Program According to Description of Sequential Control with Total Sequential Function Chart

To replace or maintain many industrial plants developed in the 1960s is quite hard, because the documents of installed sequential control logics seldom remain. SPAIR is an automatic regeneration method of control logic to cope with this problem. In SPAIR, the control logic for operating plants is automatically regenerated from the input and output data of the control unit and supplementary specification by an inductive learning algorithm. When SPAIR is applied to the regeneration of real operating plants, it is necessary to verify if the regenerated sequential control programs can accurately control such plants. For this purpose, the SPAR-System, in which SPAIR is installed, has been developed. The SPAR-System can edit the data and logic of plants and can verify the inferred logic on the simulation plant model easily.

K. Kakihara

Papers

Automatic regeneration system for sequential control programs

Automatic regeneration of sequence programs for operating plants