Biological wastewater treatment generates huge amounts of waste sludge which need to be dewatered and eventually dried to minimize transportation and incineration costs. A characteristic feature of sludge in this context is that it turns into a sticky substance during its drying process inducing fouling problems in the drying installation. At the wastewater treatment plant of Monsanto in Antwerp, Belgium, one enclosed centrifuge-dryer system is used to dry the sludge. In the past, this installation had to be shut down regularly due to dryer fouling problems. To avoid these operational problems, a binary logistic regression analysis is presented in this research based on a 5-year database, resulting in an empirical model for the evaluation of the dryer fouling risk as a function of the sludge feed characteristics. The model inputs are the sludge volume index (SVI) and the dosing of clay additive and tertiary (flotation) sludge, the latter containing polyaluminumchloride (PACl), to the sludge feed of this particular system.
By exploiting the knowledge captured by this model, the derived control strategy is based on the value of the SVI. Whenever the SVI is high the original high clay dosing to the feed needs to be maintained. At moderate SVI values, implying an intrinsically better sludge dewaterability, the strategy dictates a reduction in the clay dosing to the sludge feed to have a reduced sludge solids dryness after dewatering, thereby avoiding that the sludge exhibits its most sticky phase when passing the most fouling sensitive part of the dryer. When the SVI is lower than 50 mL/g the control strategy states that conditioning of the sludge with PACl is required to mask the stickiness instead of postponing it, avoiding that the stickiness of the sludge already hampers the dewatering stage of the process.
Treatment of industrial and municipal wastewater generates huge amounts of excess activated sludge, mainly as a result of increasingly stringent environmental regulations. According to Sanin et al. [1] the sludge production rate amounts to 60 g dry solids/person/day on average for the European Union Member Countries. Because the cost for the waste sludge handling can amount to 50% of the total operational cost of the wastewater treatment plant (WWTP) [1], sludge minimization techniques are extensively being studied. However, the remaining excess sludge still has to be treated, for which thermal drying, after a first mechanical dewatering step, is an essential processing step to reduce the sludge volume (and related costs) for further downstream processing like storage, transportation and (co-)incineration [2] and [3].
Carleton and Heywood [4] formulate a general truth in solid–liquid separation processes in that many of the problems in these unit operations do not arise from a failure of the equipment to perform its basic function, but from difficulties in discharging the thickened product and in its subsequent handling. Difficulties arise because conventional designs optimize only the unit operations and do not take into account the (changing) nature of the product or possible handling problems [4].
In industrial sludge drying installations, the stickiness phenomenon of drying sludge is a major issue, which is the case, e.g., in the combined centrifuge-dryer (Centridry®) operation of Monsanto's WWTP in Antwerp, Belgium, where a mechanical dewatering step of the sludge is combined with a flash drying stage of the resulting solids [5]. During the progress of drying, the sludge has a plastic-rubbery, pasty consistency at some intermediate moisture content range, referred to as the sticky phase of drying activated sludge [6], [7] and [8]. The sticky phase of the Monsanto sludge appears in the range from approximately 25% to 40% dry solids (DS) in the case the sludge comprises 51% inorganic material [6]. At that moment, when partially dried, the sludge tends to agglomerate and adhere to the dryer walls, changing its hydrodynamics as a result of lump formation and subsequent growth onto the dryer walls. These lumps result in operational problems, hereby significantly reducing the dryer capacity [5]. Researchers describe this property of drying sludge appropriately as a phenomenon, to illustrate the very little that is known about this complex sludge property [7] although, recently, the existence of the sticky phase of drying sludge is proposed by Peeters [9] to be the result of the formation of a dense, strong and stiff rigid network of extracellular polymeric substances as a result of the reduction in the sludge's water content during the course of drying.
To avoid the stickiness related fouling problems in dryer installations, a relationship between this fouling phenomenon and the sludge feed characteristics needs to be derived, which is accomplished in this work through a binary logistic regression based model. To this end, an extended database has been compiled covering almost 5 years of operational experience with the Centridry® technology on site, including a wide variation in the sludge settleability, expressed in terms of the sludge volume index (SVI), and feed stream characteristics. To the best of the authors’ knowledge, so far, no other studies can be found that correlate sludge feed characteristics with the fouling issues in a sludge dryer. Moreover, although the binary logistic regression tool is well-established in the field of, e.g., social sciences research, medicine and business-economics, it has rarely been used in the (bio)chemical process industry to model process issues that are binary in nature (like, e.g., plugging of equipment or piping, or the blinding of filters), to improve process control. Hence, this case study could serve as an example of how this powerful statistical tool can be used in the (bio)chemical industry to attain better process control.
Binary logistic regression is a generically applicable tool when a prediction has to be made about the presence/absence of a certain parameter in (bio-)chemical synthesis, processing and (reaction) engineering, based on the values of a set of explanatory variables. The approach used in this work, using the binary logistic regression tool to gain insight in the fouling (not) appearing in an industrial sludge dryer to allow better process control of the stickiness phenomenon herein, clearly demonstrates the power of this statistical tool for process optimization engineers. It makes these binary (and hence, almost by definition less ‘preferred’ process phenomena because they are not continuous) tangible for the process engineer.
In conclusion, from this analysis (and previous work) follows that control of the sludge solids dryness at the early stage of the flash dryer under study is critical to avoid drying sludge sticking to the dryer wall. By controlling the sludge dryness at the early stage of the dryer, e.g., by changing the clay dosing, one controls the place where the sludge goes through the sticky phase in the dryer. For sludge with an SVI below 50 mL/g, lowering the clay dosing does not help anymore; in that case the addition of PACl is recommended.