A A 2 K

K − 1 ) + a 2 · φ CO ( k − 1 ) + a 3 · φ CO 2 ( k − 1 ) + a 4 · φ CH 4 ( k − 1 ) + a 5 · T max ( k − 1 ) , (8) u 2 ≡ V O 2 ( k ) = a 0 + a 1 · V air ( k − 1 ) V O 2 ( k − 1 ) + a 2 · φ CO ( k − 1 ) + a 3 · φ CO 2 ( k − 1 ) + a 4 · φ CH 4 ( k − 1 ) + a 5 · T max ( k − 1 ) . (9) The third model type aims to achieve the necessary temperature for syngas production. The models regarding the ratio of gasification agents and the maximum temperature T m a x in the channel are in the linear and quadratic form. The structure of the model is as the following [25]: u 1 ≡ V air ( k ) = a 0 + a 1 · V air ( k − 1 ) V O 2 ( k − 1 ) + a 2 · T max ( k − 1 ) + a 3 T max 2 ( k − 1 ) , (10) u 2 ≡ V O 2 ( k ) = a 0 + a 1 ·

T p 1 ) T p 2 / ( 1 − T p 2 ) give 95% confidence limits for the odds ratio in the absence of covariates. 3.2. The Common Odds RatioConsider K independent studies (or strata from the same study), where from the kth study, we have observations for two independent binomial random variables X 1 k and X 2 k with respective success probabilities p 1 k and p 2 k , and respective sample sizes n 1 k and n 2 k , k = 1, 2, ...., K. Thus, the odds ratio from the kth study is δ k = p 1 k / ( 1 − p 1 k ) p 2 k / ( 1 − p 2 k ) , k = 1, 2, ...., K. Assuming that the odds ratio is the same across the K studies, we have δ 1 = δ 2 = . . . . = δ K = δ (say). 3.2.1. An Approximate GPQ for the Common Odds RatioAn approximate GPQ for each δ k , to be denoted by T δ k , can be constructed from the kth study, proceeding as mentioned in Section 3.1. We now combine these GPQs in order to obtain an approximate GPQ for the common odds ratio δ. For this, we propose a weighted average of the study-specific GPQs on the log scale. The weights that we shall use are motivated as follows. For i = 1, 2, if p ^ i k denote sample proportions from the kth study, and if δ ^ k = p ^ 1 k / ( 1 − p ^ 1 k ) p ^ 2 k / ( 1 − p ^ 2 k ) , k = 1, 2, ...., K, then using the delta method, an approximate variance of log ( δ ^ k ) , say 1 / w k , is given by: 1 / w k = 1 n 1 k p 1 k + 0.5 + 1 n 1 k ( 1 − p 1 k ) + 0.5 + 1 n 2 k p 2 k + 0.5 + 1 n 2 k ( 1 − p 2 k ) + 0.5 , where we have also used a continuity correction. Noting that log ( δ ) = ∑ k = 1 K w k log ( δ k ) / ∑ k = 1 K w k , an approximate GPQ T δ for the common odds ratio can be obtained from log ( T δ ) = ∑ k = 1 K T w k log ( T δ k ) / ∑

. . , K [ 31 ] (reduced result).1: A ← ( K [ 31 ] & 0 b 1 ) ≪ 6 2: B ← ( K [ 31 ] & 0 b 10 ) ≪ 5 3: C ← ( K [ 31 ] & 0 b 1111111 ) 4: K [ 16 ] ← K [ 16 ] ⨁ ( ( A ⨁ B ⨁ C ) ≪ 1 ) 5: K [ 8 ] ← K [ 8 ] ⨁ K [ 24 ] ⨁ ( ( K [ 23 ] ≪ 7 ) ∣ ( K [ 24 ] ≫ 1 ) ) ⨁ ( ( K [ 23 ] ≪ 6 ) ∣ ( ( K [ 24 ] ≫ 2 ) ) ⨁ ( ( K [ 23 ] ≪ 1 ) ∣ ( K [ 24 ] ≫ 7 ) ) 6: K [ 0 ] ← K [ 0 ] ⨁ K [ 16 ] ⨁ ( K [ 16 ] ≫ 2 ) ⨁ ( K [ 16 ] ≫ 7 ) 7:forl = 1 to 7 do8: K [ i + 8 ] ← K [ i + 8 ] ⨁ K [ i + 24 ] ⨁ ( ( K [ i + 23 ] ≪ 7 ) ∣ ( K [ i + 24 ] ≫ 1 ) ) ⨁ ( ( K [ i + 23 ] ≪ 6 ) ∣ ( K [ i + 24 ] ≫ 2 ) ) ⨁ ( ( K [ i + 23 ] ≪ 1 ) ∣ ( K [ i + 24 ] ≫ 7 ) ) 9: K [ i ] ← K [ i ] ⨁ K [ i + 16 ] ⨁ ( ( K [ i + 15 ] ≪ 7 ) ∣ ( K [ i + 16 ] ≫ 1 ) ) ⨁ ( ( K [ i + 15 ] ≪ 6 ) ∣ ( K [ i + 16 ] ≫ 2 ) ) ⨁ ( ( K [

− 1 ) + a 2 · φ CO ( k − 1 ) + a 3 · φ CO 2 ( k − 1 ) + a 4 · φ CH 4 ( k − 1 ) + a 5 · T ( k − 1 ) , (6) u 2 ≡ V o 2 ( k ) = a 0 + a 1 · V O 2 ( k − 1 ) + a 2 · φ CO ( k − 1 ) + a 3 · φ CO 2 ( k − 1 ) + a 4 · φ CH 4 ( k − 1 ) + a 5 · T ( k − 1 ) , (7) where k represents the control step of the sampling period τ 0 ; V a i r and V O 2 represent the flow rates of injected air and oxygen to the mixture (m 3 /h); φ i is the concentration of CO, CO 2 , and CH 4 in the syngas (%); and T represents the coal temperature in the gasification channel ( ∘ C).The second type of model refers to the ratio of the flow rates of gasification agents and the highest temperature in the gasification channel T m a x . The structure of this model is the following [25]: u 1 ≡ V air ( k ) = a 0 + a 1 · V air ( k − 1 ) V O 2 (