In European Seveso Legislation for the control of the hazard of major accidents (Directive 2015/12/UE), the Safety Management System SMS is an essential obligation for managers and the authorities are required to periodically verify its adequateness through periodical inspections at Seveso sites. One of the pillars of the SMS is the collection and analysis of documents on accidents, near misses and possibly anomalies, in order to identify weaknesses and implement continuous improvement. In Italy, for a few years, the documents, gathered from all Italian Seveso sites by the inspectors, have been archived and used for research purposes. The archive currently contains some 4000 reports, collected in five years by some 100 inspectors throughout Italy. The paper discusses in the detail the challenges faced to extract the knowledge hidden in the documents and make it usable through the design of a robust model. For this aim, Machine Learning techniques have been used as a preprocessing of the reports for extracting the concepts and their relations, organized into an entity-relation model. The effectiveness of this methodology and its potentiality are pointed out by investigating a few hot topics, exploiting the information contained in the repository.

No abstract

Attention to be paid to the aging of industrial facilities has been growing in the last ten years, both by public authorities and industrial executives. Many process plants, operating in Europe, have reached or exceeded their project nominal life and the safe management of aging is an urgent question. Failures, due to aged chemical process plants, cause the release of hazardous materials with severe consequences for people and workers. To counteract this phenomenon, plant operators carry out many technical activities, including non-destructive controls on piping and vessels, by adopting sophisticated methods (e.g. Risk Based Inspection RBI). The European Directive 2012/18/UE (Seveso III) for the control of Major Accident Hazard (MAH) introduced a few requirements for the safe aging of critical equipment, which must be verified during mandatory audits. The aim of this work is to present a synthetic methodology that can be useful for both Seveso auditors and industrial managers for evaluating the adequacy of the measures to control the aging of critical equipment. To achieve a synthetic assessment of the adequacy of the aging management programs, a compensated index method has been developed, which is a simple and easy-to-use tool. The use of an index method inevitably introduces a degree of uncertainty. However, if it is compared to other qualitative methods, such a tool offers the advantage of a major clarity in the assessment process. This paper discusses a practical application of the method within inspection programs, as required by the art. 27 of Seveso III Directive.

In European Seveso Legislation for the control of the hazard of major accidents (Directive 2015/12/UE), the Safety Management System SMS is an essential obligation for managers and the authorities are required to periodically verify its adequateness through periodical inspections at Seveso sites. One of the pillars of the SMS is the collection and analysis of documents on accidents, near misses, and possible anomalies, in order to identify weaknesses and implement continuous improvement. In Italy, for a few years, the documents, gathered from all Italian Seveso sites by the inspectors, have been archived and used for research purposes. The archive currently contains some 4000 reports, collected in 5 years by some 100 inspectors throughout Italy. This paper discusses in detail the challenges faced to extract the knowledge hidden in the documents and make it usable through the design of a robust model. For this aim, machine learning techniques have been used for preprocessing of the reports for extracting the concepts and their relations, organized into an entity-relation model. The effectiveness of this methodology and its potentiality are pointed out by investigating a few hot topics, exploiting the information contained in the repository.

No abstract