本文選題：報(bào)警閾值 + 優(yōu)化��； 參考：《青島科技大學(xué)》2017年碩士論文

【摘要】：現(xiàn)代化工生產(chǎn)中,為了提高生產(chǎn)過程的安全性和穩(wěn)定性,通常需要使用報(bào)警管理系統(tǒng)對(duì)一些過程變量進(jìn)行報(bào)警閾值設(shè)置。閾值設(shè)置不合理會(huì)產(chǎn)生過多無(wú)效報(bào)警,增加操作負(fù)荷,嚴(yán)重時(shí)會(huì)引發(fā)事故,導(dǎo)致報(bào)警系統(tǒng)失效。因此,對(duì)設(shè)置不合適的變量報(bào)警閾值進(jìn)行優(yōu)化是十分必要的。本文通過TE(Tennessee Eastman,田納西-伊斯曼)過程和某工業(yè)原油常減壓操作實(shí)例,對(duì)多變量報(bào)警閾值優(yōu)化新方法進(jìn)行了研究。針對(duì)多變量報(bào)警閾值優(yōu)化方法,本文主要做了兩方面研究。一方面,提出了基于PCA(Principal Component Analysis,主成分分析)權(quán)重和Johnson轉(zhuǎn)換的多變量報(bào)警閾值優(yōu)化方法。通過PCA計(jì)算變量權(quán)重,對(duì)變量數(shù)據(jù)進(jìn)行Johnson正態(tài)轉(zhuǎn)換,利用概率密度估計(jì)求出FAR(False Alarm Rate,誤報(bào)率)和MAR(Missed Alarm Rate,漏報(bào)率),在滿足FAR降低且報(bào)警數(shù)目不超過國(guó)際標(biāo)準(zhǔn)中規(guī)定的單位時(shí)間內(nèi)限制的報(bào)警數(shù)目(通常平均每分鐘不超過一個(gè)報(bào)警)的情況下優(yōu)化報(bào)警閾值。另一方面,提出了基于報(bào)警聚類和ACO(Ant Colony Optimization,蟻群優(yōu)化)的多變量報(bào)警閾值優(yōu)化方法。通過標(biāo)準(zhǔn)化歐式距離(Euclidean Distance,歐幾里得距離)實(shí)現(xiàn)報(bào)警聚類,利用熵權(quán)法求出變量權(quán)重,擬合出變量在正、異常狀態(tài)下的概率密度函數(shù)。添加報(bào)警延時(shí),建立關(guān)于誤報(bào)率、漏報(bào)率和AAD(Average Alarm Delay,平均報(bào)警延時(shí))的目標(biāo)函數(shù),利用ACO算法優(yōu)化目標(biāo)函數(shù)。這兩種方法在一定程度上都實(shí)現(xiàn)了優(yōu)化閾值的目的。通過TE過程和某工業(yè)原油常減壓操作實(shí)例對(duì)本文研究方法進(jìn)行了驗(yàn)證。結(jié)果表明,與傳統(tǒng)方法相比,該方法更能有效減少報(bào)警次數(shù)和報(bào)警率,在報(bào)警閾值優(yōu)化方面具有優(yōu)勢(shì)。
[Abstract]:In modern chemical production, in order to improve the safety and stability of the production process, alarm management system is usually used to set the alarm threshold for some process variables. The unreasonable setting of threshold will cause too many invalid alarms, increase the operating load, and lead to accidents when serious, which will lead to the failure of alarm system. Therefore, it is necessary to optimize the setting of inappropriate variable alarm threshold. Based on the TE(Tennessee Eastman (Tennessee Eastman) process and an example of an industrial crude oil operating under atmospheric and vacuum pressure, a new method of multivariable alarm threshold optimization is studied in this paper. Aiming at the optimization method of multivariable alarm threshold, this paper mainly researches on two aspects. On the one hand, a multivariable alarm threshold optimization method based on PCA(Principal Component Analysis (PCA) weight and Johnson conversion is proposed. The variable weight is calculated by PCA, and the variable data is transformed by Johnson normality. Using probability density estimation to calculate FAR(False Alarm rate (false alarm rate) and MAR(Missed Alarm rate, false alarm rate, the number of alerts (usually not exceeding the average per minute per minute) within the limit of the number of alerts per unit time specified in the international standard for satisfying the decrease of FAR and not exceeding the limit per unit time specified in international standards An alarm) is optimized in the case of an alarm threshold. On the other hand, a multivariable alarm threshold optimization method based on alarm clustering and ACO(Ant Colony optimization (ant colony optimization) is proposed. The alarm clustering is realized by Euclidean distance (Euclidean distance), the weight of variables is calculated by entropy weight method, and the probability density function of variables in positive and abnormal state is fitted. The objective function of false alarm rate, false alarm rate and AAD(Average Alarm delay (average alarm delay) is established by adding alarm delay. ACO algorithm is used to optimize the objective function. To some extent, these two methods achieve the purpose of optimizing the threshold. The method of this paper is verified by te process and an example of an industrial crude oil operating at atmospheric and vacuum pressure. The results show that compared with the traditional method, this method can effectively reduce the alarm frequency and alarm rate, and has advantages in the optimization of alarm threshold.
【學(xué)位授予單位】：青島科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TQ086

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李會(huì)云;;化工生產(chǎn)中安全運(yùn)行的重要性[J];科技展望;2015年19期

2 王佳;李宏光;;過程參數(shù)滋擾報(bào)警的一類自適應(yīng)管理策略[J];化工學(xué)報(bào);2015年10期

3 田文德;史曉楠;王春利;李傳坤;;基于數(shù)據(jù)過濾的化工過程報(bào)警優(yōu)化[J];現(xiàn)代化工;2015年04期

4 胡翔;劉翰諾;;報(bào)警器在化工生產(chǎn)中的應(yīng)用[J];化學(xué)工程與裝備;2015年04期

5 肖丹卉;李宏光;臧灝;;化工過程多變量報(bào)警閾值優(yōu)化方法[J];控制工程;2015年02期

6 王鶯;王靜;姚玉璧;王勁松;;基于主成分分析的中國(guó)南方干旱脆弱性評(píng)價(jià)[J];生態(tài)環(huán)境學(xué)報(bào);2014年12期

7 臧灝;李宏光;楊帆;黃德先;;流程工業(yè)報(bào)警系統(tǒng)傳統(tǒng)評(píng)估方法分析及改進(jìn)[J];化工學(xué)報(bào);2014年11期

8 蔡海東;;化工安全生產(chǎn)中存在的普遍問題及其對(duì)策研究[J];中國(guó)石油和化工標(biāo)準(zhǔn)與質(zhì)量;2014年07期

9 高麗霄;李宏光;;過程報(bào)警事件分組的Petri-FCM方法[J];計(jì)算機(jī)工程與設(shè)計(jì);2013年03期

10 劉恒;劉振娟;李宏光;;基于數(shù)據(jù)驅(qū)動(dòng)的化工過程參數(shù)報(bào)警閾值優(yōu)化[J];化工學(xué)報(bào);2012年09期

相關(guān)碩士學(xué)位論文 前2條

1 肖丹卉;結(jié)合優(yōu)先級(jí)的多變量過程報(bào)警閾值優(yōu)化方法[D];北京化工大學(xué);2014年

2 劉恒;基于數(shù)據(jù)驅(qū)動(dòng)的過程參數(shù)報(bào)警閾值優(yōu)化[D];北京化工大學(xué);2012年

，

本文編號(hào)：1788010