Slopping index for LD converters based on sound and image data fusion by fuzzy Kalman filter

Abstract

The LD (Linz Donawitz) steelmaking process is the most used in the steel industry due to its highvolume capacity and low cost per ton of steel produced. However, the basic oxygen steelmaking process in LD converters is subjected to potential steel charge overflows, often called 'slopping'. Besides yield losses, slopping events can damage the environment and expose employees to danger. More than ever, steelmaking plants need to avoid this type of event to keep producing as environmental impacts are no more tolerable by society. Steelmaking plants already use different methods to monitor and detect slopping events, but they are often limited and unreliable. Therefore, this paper proposes a multi-sensor data fusion process to generate a reliable slopping index to warn operators of potential slopping events and detect the triggered ones. The work is based on sound and image data (67 heats with 27 slopping events) collected on previous trials at a 350-ton LD converter. The Kalman filter was applied as a data fusion agent of two indexes, one resulted from computer vision analysis of the LD converter mouth (image data), the other resulted from digital signal analysis of sound captured on the converter's hood (sound data). Fuzzy sets were applied for adaptative tuning of the Kalman filter to improve the data fusion process. Besides the increase of alarm accuracy and heat classification, the data fusion index worked better on different scenarios and produced a more reliable indicator for a slopping prevention system.

A Modified Strong Tracking Adaptive Kalman Filter for Precision Clock Synchronization System

“…According to formula (8), with the increase of the number of iterations, d (k ) continues to decrease to very small, resulting in almost no effect of Z on the calculation of R. Therefore, the estimated value of the filtering model gradually deviates from the measured value, resulting in the loss of tracking effect, and the final actual clock of AKF gradually divergence. As the calculation of a in formula (18) in STAKF is susceptible to measurement outliers, and the estimation of R is also susceptible to outliers, the estimated value of network delay fluctuates greatly, The MSTAKF algorithm is composed of MST algorithm and MAKF algorithm. Fuzzy reasoning is used to correct the outliers in the measurement value and measurement noise, which ensures the tracking effect and avoids the influence of outliers.…”

“…According to literature [18,19], the measurement value and measurement noise can correct the prediction of the state to obtain the estimated value of the state, which satisfies the following relationship:…”

Acoustic Analysis of Slag Foaming in the BOF

“…The new study showed a seven per cent increase in accuracy using the combined system of image and acoustic processing [46]. This was further studied by De Menezes et al using a similar image and sound analysis system with a fuzzy Kalman filter for the data fusion [47]. A threshold alerting system was formed using the acoustic data, and a threshold alarm level was found using image data.…”

Značajke masovne proizvodnje sirovog čelika u Republici Hrvatskoj od 1954. do 2020. godine

“…4 Današnja proizvodnja čelika primarno se odvija u kisikovim konvertorima (KK) i elektrolučnim pećima (ELP). [5][6][7][8][9][10] Neovisno kojim se postupkom (KK ili ELP) dobije primarna talina, za izradu kvalitetnijih čelika provodi se dorada čelika u loncu nekim od brojnih postupaka sekundarne metalurgije (npr. lonac-peć, otplinjavanje u vakuumu).…”