Construction of flame image classification criteria and reference database for municipal solid waste incineration process

The flame combustion state inside the furnace is important feedback information for intelligent optimization control of the municipal solid waste incineration (MSWI) process. However, none of the existing studies on the identification of MSWI combustion state have proposed a combustion state classification criteria, which with actual physical significance and interpretability for the incineration characteristics of MSWI. As a result, it is difficult to build a recognition model for the MSWI process based on the domain expert cognitive mechanism and valid reference data. To solve this problem, combined with the experience of industry experts and research results in related fields, the construction of MSWI process flame combustion state classification criteria and benchmark database was studied in this paper. Firstly, the problem of combustion state identification is described, and the existing methods of combustion state identification based on combustion lines are analyzed. Next, the classification criteria are elaborated based on normal combustion, partial combustion, channeling combustion and smoldering combustion. Then, the image database of the flame-burning state which can be used for machine learning is constructed. Finally, the flame-burning image database is modeled and tested based on a variety of classical algorithms in the field of machine vision. The results show that the accuracy of most methods for flame state classification is more than 80%. The validity of the proposed classification criteria and flame image database is greatly validated.

I. Introduction

Municipal solid waste incineration (MSWI) is a popular way of municipal solid waste (MSW) treatment worldwide [1]. Compared with traditional treatment methods such as landfill and compost, MSWI can complete the reduction, resource and harmless treatment of MSW in a relatively short time [2], [3]. So it is an incomparable advantage of traditional treatment methods. At present, in the field of MSWI, in order to timely adjust the process control parameters and maintain the stability of the combustion state, experienced operation experts are generally required to observe and judge the flame combustion state in real time. At the same time, because the evaluation index of the incineration effect cannot be quantified, it can only be adjusted according to the experienced judgment. However, due to the different operation strategies of experts, the incineration effect is not the same. Therefore, if the manual experience can be converted into the system knowledge, the system will have the ability to self-identify the combustion state and maintain combustion stability. It will greatly simplify the optimization process of the control system. Also, the operation stability of the MSWI industry will be improved. This is more conducive to reducing the environmental pollution.