Industrial Data-Driven Processing Framework Combining Process Knowledge for Improved Decision Making—Part 1: Framework Development

Abstract

Data management systems are increasingly used in industrial processes. However, data collected as part of industrial process operations, such as sensor or measurement instruments data, contain various sources of errors that can hamper process analysis and decision making. The authors propose an operating-regime-based data processing framework for industrial process decision making. The framework was designed to increase the quality and take advantage of available process data use to make informed offline strategic business operation decisions, i.e., environmental, cost and energy analysis, optimization, fault detection, debottlenecking, etc. The approach was synthesized from best practices derived from the available framework and improved upon its predecessor by putting forward the combination of process expertise and data-driven approaches. This systematic and structured approach includes the following stages: (1) scope of the analysis, (2) signal processing, (3) steady-state operating periods detection, (4) data reconciliation and (5) operating regime detection and identification. The proposed framework is applied to the brownstock washing department of a dissolving pulp mill. Over a 5-month period, the process was found to be in steady-state 32% of the time. Twenty (20) distinct operating regimes were identified. Further processing with the help of data reconciliation techniques, principal component analysis and k-means clustering showed that the main drivers explaining the operating regimes are the pulp level in tanks, its density, and the shower wash water flow rate. Additionally, it was concluded that the top four persistently problematic sensors across the steady-state spans that would need to be verified are three flow meters (06FIC137, 06FIC152, and 06FIC433), and one consistency sensor (06NIC423). This information was relayed to process experts contacts at the plant for further investigation.

Industrial Data-Driven Processing Framework Combining Process Knowledge for Improved Decision-Making—Part 2: Framework Application Considering Activity-Based Costing Concepts

“…The result will provide insights and support informed decision making. The process data required to model it are processed based on the steps presented in [7]. Namely, in order to perform the activity-based costing analysis, the process information is acquired using signal processing, steady-state detection, and data reconciliation techniques for each operating regime (detected as part of the aforementioned framework).…”

“…Furthermore, the above reference studies focused on newsprint production or thermomechanical pulping mills, whereas this case study is more complex in that it considers the Therefore, operations-driven costing approaches combine the cost and the operating regimes, allowing one to assess the cost of each regime. A cost analysis is going to be applied in combination with the data processing framework proposed in Part 1 of this paper [7] to solve an optimization problem in the pulp and paper sector. The cost analysis approach used in Part 2 is consistent with the ODCA approach presented previously; the major difference resides in the processed data used in the cost analysis (data that were rigorously processed using the framework) and the emphasis put on operating regimes.…”

“…Thus, one strategy proposed to incrementally optimize or debottleneck the washing department operations is to identify opportunities requiring no capital investment (keeping the same equipment) based on data analysis performed using the framework presented in [7], which considered the operating regimes and production costs. The preferred (more efficient) washing operating conditions (regimes) will be identified as described in the following section.…”

“…In order to concretize the systematic approach proposed in [7] and its value, the operating costs of each regime are considered. These are not evaluated in an absolute way but rather in relation to the average production of dissolving pulp, which is the reference or baseline.…”

“…Furthermore, a cost analysis can only be as good as the process data provided to perform the analysis. In this perspective, a data management framework was proposed in Part 1 of this paper [7]. This framework considers, among the other steps, the reduction in measurement and process noise in process data.…”