QUESTION: What is the basis for the PEMS predictive engine? Is it a neural network or a first principle (physical correlation and gas theory)?

ANSWER: The engine is a statistical hybrid model.  It neither a neural network nor a first principle type, but it is an empirical method.  CMC's SmartCEM™ utilizes a patented (pending) process known and shared collectively amongst the various CMC products as the 'Assist' engine. The model does not use theoretical formulation such as a first principle model.  The empirical SmartCEM™ model utilizes historical emissions and process data to predict emissions.  The system uses the historical data collected during normal operation as part of a training dataset to model the process and predict emissions. This feature allows the system to predict the value of any failed input (or pollutant emission data in lieu of CEMS) with the accuracy of the system entirely dependent on the range and quality of the training dataset. The system is deterministic in that a given set of inputs (process variables or lack of them) along with a given fixed training dataset will yield a single result for each value to be predicted.  The model is unique in its ability to be developed by non-specialized staff that has no familiarity with the process, pollution control, or the methodology used by the model.  Customers and third party consultants can update the model without support of the manufacturer's engineering support.

QUESTION: Does SmartCEM™-75 replace a CEMS? If so, what do we do with the existing CEMS we have installed onsite.

ANSWER: SmartCEM™-75 was designed to work with a CEMS or temporary mobile system to provide data acquisition, display of real-time and averaged emission data, and report generation to meet regulatory compliance requirements. In one mode of operation, the CEMS provides a critical role in the optimization of the process, but not a mandatory role in compliance monitoring of the exhaust emissions. SmartCEM™-75 provides real-time analysis of process efficiency and predictive capability for any failed input. SmartCEM™-75 can operate without a CEMS when certified as a primary continuous monitoring system for the source through a petition for approval of an alternate monitoring system (40 CFR Part 75, Subpart E) or utilizing performance specification testing promulgated by U.S. EPA (40 CFR Part 60, PS-16 draft).

If you have an existing CEMS, we would recommend that the CEMS not be removed, but that it is turned off during most of the year to save in operational, maintenance, and support costs. The CEMS would be used to retrain the model if new operating or ambient conditions are encountered or following a major maintenance event and for tuning or optimization of the combustion controls. The plant can certify the CEMS along with SmartCEM™-75 as a backup system if a testing team is mobilized for a relative accuracy test audit. If the CEMS is operated according to 40 CFR Part 60 Reference Methods, the existing CEMS can be used by the source owner to recertify the SmartCEM™-75 system each year in lieu of an annual certification test (typically performed by an independent third party testing team). CMC would provide support to both an existing CEMS and the SmartCEM™-75 system.

QUESTION: What are the accuracy and reliability levels achieved by SmartCEM™-75 and what other statistical analyses are required to certify SmartCEM™-75 under 40CFR Part 75, Subpart E?

ANSWER: The accuracy of the system is entirely dependent on the quality of the training dataset including the emission testing data and the site configuration of the SmartCEM™-75. The accuracies achieved under the demonstration on gas turbines to date have been comparable to a CEMS at < 10% relative accuracy even at very low levels of NOx (less than 10 ppmv). SmartCEM™-75 has consistently met the EPA requirement of < 7.5% relative accuracy for NOx compliance under 40 CFR Part 75.  SmartCEM™-75 reliability approaches 100% in our installations, typically better than the majority of CEMS installed to date. Typically from 72 hours to 720 hours of data is required to meet the requirements of 40 CFR Part 75, Subpart E. The statistical analysis of the data for Subpart E certification includes the F-test, t-test, correlation, and variance analysis along with the bias test.  CMC provides a Subpart E package for Part 75 Subpart E certification that includes all statistical analyses along with the required submittal and report.

QUESTION: Is the first correlation valid for a long time or should we tune SmartCEM™-75 each year?

ANSWER: The validity of the SmartCEM™-75 model is entirely dependent on the training dataset and the quality assurance program in place at the site. If a comprehensive model is developed initially, there would be no reason to limit the range of time that it would be valid. If a site had ten units varying in age from 1 to ten years of age, we would recommend initial testing of older and newer units and pool the data to build into the training dataset a model that would be valid for all units up to ten years of age. The advantage of having an existing CEMS onsite is clear in cost savings associated with quality assurance events either required by regulation or for combustion efficiency and model retraining purposes as the unit ages, following maintenance, or in response to an operating change (such as switching the fuel type, quality, or supplier). The model can easily be retrained if data is required for any ambient or other operating conditions not encountered during the initial training operations. The system keeps track of when the model is valid for a given set of process data in real-time.

Requirements for a periodic or annual recertification test would be dependent on the local regulatory requirements and the facility quality assurance program. We would recommend an annual retraining (and recertification if required) event to be scheduled following any turbine tuning or extensive annual maintenance activities (also typically performed on an annual basis), but this would not be mandatory. The PEMS can be retuned at any time (periodically or continuously) using existing CEMS equipment or by mobilizing temporary or mobile emission monitoring equipment and collecting the process data concurrently. We anticipate that pending rule changes from EPA will include an annual relative accuracy test of PEMS under 40 CFR Part 75 as a minimum.

QUESTION: Is the prediction just valid for NOx? Does the model work for CO? What other process and emission parameters can be predicted with Smart75?

ANSWER: The prediction is valid for any emission or process data in the initial training dataset that can be correlated with the available process data. The model was developed initially with NOx, CO, CO2, O2, SO2, and Total Hydrocarbon data. Particulate, PM10, PM25, opacity, and other emission parameters could also be predicted with the Assist feature of SmartCEM™-75. Good predictive capabilities are achieved by including in the training dataset good quality emission data collected under a broad range of operating and ambient conditions.

The accuracy of the prediction for NOx emission rates from gas turbines has been the most extensively studied and demonstrated to date. Other pollutant emission rates that have been established to be accurately modeled by SmartCEM™-75 include CO, SO2, and Hydrocarbon emission rates, as well as, exhaust gas O2 and CO2. Other turbine parameters such as exhaust temperature and flow rate have also been evaluated and show good accuracy. Hydrocarbon, CO, SO2, NOx, and O2 have also been demonstrated to be accurately modeled from sewage sludge incinerators and industrial boilers.

QUESTION: What kind of instrumentation and process inputs are needed to train the model and what interface is required to the SmartCEM™-75?

ANSWER: SmartCEM™-75 utilizes any quality assured process or emission data for model generation. Typically around a dozen parameters are utilized in a simple cycle gas turbine model with more parameters required associated with any add-on pollution control technologies. Ambient data is utilized when it is available. There are no mandatory inputs required for a given model (with the exception of the unit load in megawatts and the fuel mass flow rate along with the emission data for the compliance parameters to be modeled in the training dataset). The system analyzes the training dataset to determine which of the available inputs or control system data is relevant to the model. Instrumentation and field devices that are determined to be used in the emission model may be subjected to additional quality controls per the local regulatory requirements and the site quality assurance program.

Interfacing with existing control and emission monitoring systems can be accomplished using serial communications, Ethernet connectivity, or through hardwiring to remote I/O devices. CMC can provide the hardware and equipment required or the system can be configured to utilize any standard 'Windows' based technology such as OPC, ODBC, OLE, DDE, etc. to extract the data from the turbine control system. This interface between existing control and monitoring systems with the CMC server deployed onsite can eliminate the need for hardwiring I/O to the SmartCEM™-75 system. Hardwire interfaces range from economical Ethernet-ready devices to a custom programmable controller with data buffering and uninterruptible operation guaranteeing near 100% data availability.

QUESTION: Is SmartCEM™-75 also valid during start-up and shutdown of the unit?

ANSWER: The model is valid during normal operation of the turbine, during start-ups and during shutdowns, as well as, trips, interruptions etc. The accuracy of the model during startups and shutdowns is demonstrated, however, the statistics improve, as more transition data is included in the training dataset.  It is important to include startup and shutdown data along with other data from transient operations in the initial historical training dataset to ensure accuracy of predictions for these operating conditions.

QUESTION: What other uses could SmartCEM™-75 be applied to? Can the system be used to model turbine combustion efficiency? Can the system be used to provide input for scheduling of maintenance activity?

ANSWER: The model was developed for the purpose of providing operators with real-time feedback as to unit efficiency, combustion efficiency, and emission rates. The rate in change of unit efficiency normalized for ambient and other operating conditions can be used to determine when maintenance should be scheduled and following completion of maintenance activities, if the unit was restored to optimal combustion efficiency.

QUESTION: Could you provide references for PEMS installations? What types of turbines have been certified with the SmartCEM™-75 product to date?

ANSWER: Two sites have passed the statistical requirements of 40 CFR Part 75 Subpart E to date, with certification pending immediately:

1.       1GW Generating Cogen Station - Dearborn, Michigan - Dry, Low-NOx Simple Cycle Turbine (GE 7FA) certification received per 40 CFR Part 75, Subpart E.  Two combined cycle gas turbines and three boilers firing natural gas and blast furnace gas have also recently been certified under 40 CFR Part 75.

2.       Virginia Power Producer - Steam Injection Gas/Oil Fired Combined Cycle Turbine (GE Frame 6) certification pending 40 CFR Part 75, Subpart E as part of EPA PEMS Demonstration.

3.       Florida Utilities Authority - 35 MW Simple Cycle Turbine certification and EPA Demonstration completed.

There are several other projects that have certified under 40 CFR Part 60 including boiler operations with low-NOx gas fired burners and no additional pollution control devices.

1. Bowling Green State University steam plant - Three Gas Fired Boilers under 40 CFR Part 60 with Low-NOx burner system
2. GM Flint North - Two Gas Fired Boilers under 40 CFR Part 60 with Low-NOx burner system.

There are several demonstration projects in place:

1. U.K. Gas Turbine project - demonstration in progress.
2. OEM small turbine PEMS demonstration in progress.

QUESTION: What are the steps required to move forward with an installation? Who do we contact for a proposal for SmartCEM™-75?

ANSWER: Contact Mr. Brian Swanson at CMC Solutions (U.S. 248-960-1632) or via email at Support@CMCSolutions.org. The first step in the process will be to develop site-specific datasheets for each of the sources to be monitored to identify the specific needs of the customer. CMC will provide a proposal that may include computer hardware, CEMS, mobile emission equipment, training, onsite support, certification testing, commissioning, and warrantee. The software will be delivered (typically within 30 days of receipt of purchase order) and certification can be scheduled anytime following startup and collection of the training data. Training data is typically collected for a period of up to 30 days during normal operation to develop the model. Sites with existing CEMS may have available data to build a model without additional testing or training. Certification can typically be achieved within 60 to 90 days of receipt of your purchase order of SmartCEM™-75.