基于區(qū)間預(yù)測模型的污水處理廠傳感器故障檢測

柴偉　池彬彬

摘? ?要：污水處理廠配備許多傳感器用于監(jiān)測出水水質(zhì)。傳感器的正常工作與否對保證出水水質(zhì)至關(guān)重要。給出了一種污水處理出水變量傳感器故障檢測方法。該方法根據(jù)入水和出水?dāng)?shù)據(jù)，采用徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)構(gòu)造出水變量預(yù)測模型;使用參數(shù)線性集員辨識(shí)算法得到網(wǎng)絡(luò)輸出權(quán)值的集合描述，從而使預(yù)測模型能夠給出出水變量的置信區(qū)間;以此置信區(qū)間為基礎(chǔ)獲得傳感器的故障檢測策略。由于置信區(qū)間描述了出水變量的存在范圍，當(dāng)傳感器測量值超出置信區(qū)間，則可推斷傳感器發(fā)生故障。此外，在設(shè)計(jì)傳感器故障檢測策略時(shí)還考慮了污水處理過程異常的影響。實(shí)驗(yàn)結(jié)果證實(shí)所提方法的有效性。

關(guān)鍵詞：污水處理;傳感器;故障檢測;集員辨識(shí);區(qū)間預(yù)測

中圖分類號(hào)：TP277? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?文獻(xiàn)標(biāo)識(shí)碼：A

Fault Detection of Sensors in Wastewater Treatment

Plants Using Interval Predictor Models

CHAI Wei1，2？覮， CHI Bin-bin1，2

（1. Faculty of Information Technology，School of Automation，Beijing University of Technology，Beijing 100124，China;

2. Beijing Key Laboratory of Computational Intelligence and Intelligent Systems，Beijing 100124，China）

Abstract：A wastewater treatment plant（WWTP） is equipped with a number of sensors for monitoring the quality of the effluent. The normal operation of the sensors is critical to ensuring the quality of the effluent. This paper presents a fault detection method for sensors measuring the effluent variables in the WWTP. According to the available influent and effluent data，the radial basis function neural network is used to construct the predictor models for the effluent variables. Linear-in-parameters set membership identification algorithm is used to obtain a description of the uncertain set of the vector representing the output weights of the neural network，so that the predictor model can give a confidence interval of the effluent variable. Basing on this confidence interval，the sensor fault detection strategy is obtained. Since the confidence interval describes the existence range of the effluent variable，when the measurement result exceeds the confidence interval，it can be inferred that the sensor has been faulty. Besides，the influence of abnormal operation of the WWTP is considered in designing the sensor fault detection strategy. The experimental results confirm the effectiveness of the proposed method.

Key words：wastewater treatment;sensor;fault detection;set membership identification;interval prediction

污水處理作為保護(hù)環(huán)境的重要措施得到廣泛關(guān)注。日益嚴(yán)格的出水排放標(biāo)準(zhǔn)要求污水處理廠配備先進(jìn)的自動(dòng)控制系統(tǒng)，而控制系統(tǒng)的有效運(yùn)行依賴于傳感器的可靠性。傳感器故障將導(dǎo)致能耗增加與出水水質(zhì)下降。盡管傳感器冗余可以提高可靠性，但也會(huì)帶來成本的增加。所以，為了有效降低故障的消極影響，需要在污水處理廠配置傳感器故障檢測與診斷系統(tǒng)[1]。

目前針對污水處理過程傳感器故障檢測與診斷方面的研究已經(jīng)取得較豐富的成果。文[2]根據(jù)機(jī)理模型設(shè)計(jì)狀態(tài)觀測器對執(zhí)行器和傳感器故障進(jìn)行檢測與診斷。……