Multi-site optimization of energy systems

Abstract

The present disclosure describes methods and systems for optimizing operation of an industrial steam and power utility system across multiple facilities. The method involves: for each energy system at each facility: (a) performing device level data verification on a plurality of respective power generation devices; (b) performing device-level data conditioning on the plurality of respective power generation devices; (c) performing site-level optimization on the plurality of respective power plants to determine plant operating parameters; determining: (i) a site-level constraint for the plurality of energy systems and (ii) a multi-site constraint across the plurality of energy systems; based on the site-level constraints and the multi-site constraints, device operating parameters of a plurality of respective power generation devices across the plurality of energy systems are optimized.

Description

[0001] Claiming priority

[0002] This application claims priority to U.S. Patent Application No. 18 / 348,885, filed July 7, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to computer-based methods, computer-readable media, and computer systems for implementing multi-site energy management (specifically, energy management of industrial steam, electricity, and utility systems across multiple facilities). Background Technology

[0004] In industrial operations, such as industrial steam, electricity, and utility systems, different types of processes consume various forms of energy, including steam, electricity, and others, to obtain outputs or produce desired products or compounds. For large-scale processes that consume significant amounts of steam, energy efficiency can be achieved by optimizing energy consumption through careful operation, design, or reconfiguration of the plant and the equipment used. This optimization is made possible by accurately and promptly measuring the operating parameters of each piece of equipment in the plant. Summary of the Invention

[0005] This disclosure describes computer-based methods, computer-readable media, and computer systems capable of optimizing the operation of industrial steam and power utility systems.

[0006] One aspect of the subject matter described in this specification can be embodied in a method that involves: for each energy system at each facility: (a) performing device-level data verification on multiple corresponding generating units; (b) performing device-level data conditioning on multiple corresponding generating units; (c) performing site-level optimization on multiple corresponding generating units to determine device operating parameters; determining: (i) site-level constraints of multiple energy systems and (ii) multi-site constraints across multiple energy systems; and optimizing the device operating parameters of multiple corresponding generating units across multiple energy systems based on the site-level constraints and the multi-site constraints.

[0007] The foregoing embodiments are implemented using the following: a computer-implemented method; a non-transitory computer-readable medium storing computer-readable instructions for performing the computer-implemented method; and a computer system including a computer memory interoperably coupled to a hardware processor configured to perform the computer-implemented method or the instructions stored on the non-transitory computer-readable medium. These and other embodiments may each optionally include one or more of the following features.

[0008] In some implementations, multiple energy systems include industrial plants, power plants, and renewable energy plants.

[0009] In some implementations, site-level constraints include the energy requirements of each energy system, the corresponding steam reserves of each energy system, the corresponding minimum number of boilers required to maintain the corresponding steam reserves of each energy system, and equipment limitations for multiple corresponding power generation devices of each energy system.

[0010] In some implementations, multi-site constraints include steam storage requirements across multiple energy systems, electricity storage requirements across multiple energy systems, emissions reduction targets across multiple energy systems, and minimum efficiency across multiple energy systems.

[0011] In some implementations, performing device-level data verification for a plurality of respective power generation devices involves: for each of the plurality of respective power generation devices: during the operation of each device, receiving measured operating physical parameter values ​​output by that device during the operation of that device; using the received operating physical parameter values ​​to determine mass balance and energy balance parameters associated with that device; and using the determined mass balance and energy balance parameters to verify the operation of that device.

[0012] In some implementations, optimizing the equipment operating parameters of multiple corresponding power generation devices based on site-level constraints and multi-site constraints involves: generating a global matrix that includes the site-level optimization results for each energy system; and using the global objective function and the global matrix of the site-level optimization results to optimize the equipment operating parameters of the multiple corresponding power generation devices.

[0013] In some implementations, operating parameters include cogeneration load management and boiler load management.

[0014] In some embodiments, the method also involves: displaying operating parameters on a display device via a user interface; and displaying benefits associated with the operating parameters on a display device via a user interface.

[0015] Details of one or more embodiments of these systems and methods are set forth in the accompanying drawings and the description below. Further features, objects, and advantages of these systems and methods will become apparent from the description, the drawings, and the claims. Attached Figure Description

[0016] Figure 1A A block diagram of a workflow for site optimization according to some implementations is shown.

[0017] Figure 1B A schematic representation of an industrial steam power and utility system operating multiple devices according to some embodiments is shown.

[0018] Figure 1C A schematic representation of multi-site optimization according to some implementation methods is shown.

[0019] Figure 2 This is a schematic representation of a user interface displayed on a computer monitor according to some embodiments.

[0020] Figure 3 A schematic representation of optimized operation implemented by a computer system on industrial steam power and utility systems, according to some embodiments, is shown.

[0021] Figure 4 A workflow is shown that illustrates an example data verification process for equipment in industrial steam power and utility systems, according to some implementations.

[0022] Figure 5 A workflow is shown that illustrates an example heat exchanger data verification process according to some implementation methods.

[0023] Figure 6 A workflow is shown that illustrates an example cogeneration data verification process according to some implementation methods.

[0024] Figure 7 A workflow is shown that illustrates an example boiler data verification process according to some implementation methods.

[0025] Figure 8 A workflow is shown that illustrates an example process heater data verification process according to some implementations.

[0026] Figure 9 A workflow is shown that illustrates a data verification process for mechanical drives and generators according to some implementations.

[0027] Figure 10 A workflow is shown that illustrates the data verification process for an electric motor pump / compressor according to some implementations.

[0028] Figure 11 A workflow is shown that illustrates a gas turbine data verification process according to some implementations.

[0029] Figure 12 A flowchart is shown illustrating an example method for data verification and optimization of industrial steam power and utility systems according to some implementations.

[0030] Figure 13 A schematic representation of multi-site optimization operation according to some implementation methods is shown.

[0031] Figure 14 A diagram showing the optimized operation of a combined heat and power (CHP) unit according to some implementation methods is presented.

[0032] Figure 15 A description of a multi-site optimization system according to some implementations is shown.

[0033] Figure 16 A flowchart is shown as an example method for multi-site optimization of industrial steam power and utilities according to some implementations.

[0034] Figure 17 It is a block diagram of an example computer system for providing computational functionality associated with the algorithms, methods, functions, processes, procedures and processes described in this disclosure.

[0035] Similar reference numerals and symbols in the various figures indicate similar elements. Detailed Implementation

[0036] Improved operation (e.g., optimized operation) of steam and electricity utility systems in enterprises with multiple facilities (e.g., power generation, oil, gas, and petrochemical facilities) can help reduce operating costs, increase operational efficiency, and reduce greenhouse gas (GHG) emissions, among other benefits.

[0037] This disclosure describes a real-time consulting system for controlling energy systems located in multiple facilities to improve the operation of the energy systems. The multiple facilities may include power generation facilities and industrial facilities. Industrial facilities may include utility systems that generate different energy flows (e.g., electricity, steam, water, cooling, and heating). As described in more detail below, facilities may include power generation equipment such as boilers, cogeneration units, steam turbines, and heat exchangers. Facilities may include multiple power generation technologies (e.g., renewable energy and industrial utility systems) as part of an energy generation portfolio to meet energy demands.

[0038] In some implementations, the real-time consultation system generates a digital twin for each energy system in each facility. The real-time consultation system uses the digital twins and optimization methods to optimize the operation of the energy systems at each site. The optimization methods then optimize the operation of energy systems across multiple sites. For this purpose, the optimization methods include site-level optimization methods and multi-site-level optimization methods. Site-level optimization methods are described below.

[0039] Site-level and multi-site-level optimization methods consider real-time operating data, thermodynamic properties, and energy correlations of equipment at each site. To optimize the energy system at a single site, the real-time advisory system considers several constraints, such as: (i) the closing material and energy balance of the energy system's baseline and optimized operation at that site; (ii) the minimum and maximum operating limits of the equipment at that site; and (iii) the steam and electricity storage requirements of the energy system at that site. Furthermore, to optimize multiple sites, the real-time advisory system considers constraints for global optimization, such as: (i) generating specific power output values ​​across facilities; and (ii) site-level and multi-site-level constraints, such as equipment operating limits.

[0040] In some implementations, the real-time consultation system provides an accurate consultation model that offers meaningful recommendations at both the site-level and multi-site-level. The real-time consultation system includes a layer for multi-site optimization, which performs generator optimization and / or load management at the enterprise level (e.g., multiple sites across an enterprise or industry). The real-time consultation system can perform multi-objective optimization using primary objective functions and global constraints (e.g., operating costs, carbon dioxide (CO2) emission reduction targets, system-level energy requirements, and power reserve requirements). Multi-site optimization considers real-time operating data, thermodynamic properties, and energy correlations representing the equipment at each site.

[0041] One challenge in implementing such a consulting system is that the accuracy of real-time data can be compromised due to a lack of instruments or uncalibrated measurements. This disclosure describes techniques to overcome this and other challenges by enabling a consulting system even without instruments or with incorrect / inappropriate calibration. To this end, this disclosure describes techniques using real-time operational data, thermodynamic properties, and energy correlations representing equipment in industrial steam and power utility systems.

[0042] This disclosure describes baseline and optimized operating conditions by considering constraints such as closed-loop material and energy balances, first at the device level and then at the system level. In these operations, operating physical parameter values ​​received from each device and their corresponding values ​​for the entire system are compared with maximum and minimum operating limits and steam and electricity storage requirements. The results of these comparisons are used to perform device and system validation. These results are also used to adjust the operating physical parameters of the device to optimize the performance and operation of each device, as well as industrial power and utility systems. The measured values ​​and comparison results are presented in real time to the user (e.g., a plant or device operator) via a user interface displayed on a computer monitor, allowing the user to adjust the operating physical parameters. In some cases, the measured values ​​and comparison results can be used to automatically adjust the operating physical parameters without human intervention (e.g., by sending computer commands to the device).

[0043] The techniques described in this disclosure can be used to achieve one or more of the following advantages. These techniques represent a simple and accurate real-time consultation model that can provide meaningful recommendations with potential benefits. Implementing these techniques provides plant operators with operational setpoints, even if the plant has limitations on key measurements. The techniques described herein do not require a complete set of measurements to close the heat and mass balance of steam. These techniques provide a reliable and accurate real-time closed-loop optimization that is inexpensive. These techniques utilize a method that addresses metering and measurement problems in industrial steam and power utility systems, providing recommended actions for achieving energy savings, improving system efficiency, and reducing CO2, and in some cases, implementing the recommended actions without human intervention.

[0044] Figure 1A A block diagram of a site optimization workflow 110 according to some embodiments is shown. The site optimization workflow 110 can be used for the digital twin generation and operational optimization of industrial steam and power utility systems (also referred to as "energy systems"). Figure 1B Examples of industrial steam, electricity, and utility systems are described below. In some examples, site optimization workflow 110 can be executed by a computer system including one or more data processing devices (e.g., one or more data processors) and a computer-readable medium (e.g., a non-transitory computer-readable medium) storing computer instructions that can be executed by the one or more data processing devices to perform the operation of site optimization workflow 110. The following is in conjunction with... Figure 17 To describe the example computer system.

[0045] Site optimization workflow 110 begins with step 112: performing device-level data validation at the facility. This device-level data validation will be described in detail below. For example, Figure 4 The workflow for an example data verification process for equipment used in industrial steam power and utility systems is shown. Figure 1A As shown, device-level data verification uses data history 122, which is a database storing historical data of the device. Additionally, users can manually input corrections to the device data, for example, via user interface 120, as part of the device-level data verification. Once device-level data verification is complete, the site optimization system proceeds to step 114.

[0046] At step 114, the site optimization workflow 110 involves performing device-level data conditioning at the facility level. Generally, data conditioning involves comparing and aligning data or measurements from various sources to ensure consistency, accuracy, and reliability. In this step, data is conditioned at the device level. Device-level data conditioning is described in more detail below.

[0047] At step 116, the site optimization workflow 110 involves system-level conditioning. In this step, conditioning data is performed at the level of each energy system (e.g., a manifold, which acts as a central distribution point for fluids or gases within the facility and includes multiple devices such as boilers and steam generators). System-level conditioning is described in more detail below. Figure 1A As shown, the results of system-level conditioning are stored in database 124.

[0048] At step 118, the site optimization workflow 110 involves overall site optimization. In this step, the overall operation of the site is optimized. Site optimization is described in more detail below. For example, Figure 3 A schematic representation of multi-site optimization operations is shown. Furthermore, as... Figure 1A As shown, site optimization results are stored in database 124. The results of energy system-level conditioning and site optimization can be displayed on user interface 120. As described in more detail below, user interface 120 can display advisory recommendations for adjusting loads on major equipment and indicate the potential benefits of such changes.

[0049] Figure 1B This is a schematic representation of an industrial steam, electricity, and utility system 100 (sometimes referred to as an "industrial plant") that operates including multiple devices such as a combined heat and power unit 102a, a steam turbine 102b, a boiler 102c, etc. The following list illustrates... Figure 1A The illustration shows the abbreviation.

[0050] BFW: Boiler feedwater flow rate

[0051] BD: Sewage discharge flow rate

[0052] CC: Wastewater Concentration Ratio

[0053] STM: Steam Flow Rate

[0054] H_: Entropy

[0055] HHV: Higher heating value of fuel

[0056] SF: Supplemental combustion flow

[0057] GT_load: Gas turbine load percentage (%)

[0058] W_rated_adj: Attenuation factor of gas turbine power output

[0059] S_eff: Isentropic efficiency of a steam turbine

[0060] MAX_W: Maximum power output when S_eff = 100%

[0061] W: Actual work from equipment (e.g., combined heat and power unit, steam turbine, etc.).

[0062] H_OUT: Export enthalpy

[0063] H_IN: Enthalpy of entry

[0064] H_ise: Ientropic enthalpy

[0065] H_OUT_M: Exit enthalpy of the MP extraction stage

[0066] H_OUT_L: Outlet enthalpy of the LP extraction stage

[0067] H_OUT_C: Outlet enthalpy during the condensation stage

[0068] X_C: Steam dryness of steam in the condensation stage of the existing turbine.

[0069] P_OUT_C: Pressure of steam during the condensation stage

[0070] CR: Process condensate recovery factor

[0071] Each device performs one or more processes, and system 100 collectively enables all devices to convert steam into energy. While performing one or more processes, each device outputs an operating physical parameter value. For example, operating physical parameters may include temperature, pressure, flow rate, or similar parameters experienced by the device. Operating physical parameters are values ​​representing the corresponding parameters, such as temperature, pressure, and flow rate. Multiple sensors (not shown) may be operatively coupled to each device to measure the operating physical parameters. The sensors (e.g., thermocouples for sensing temperature, pressure gauges for sensing pressure, flow meters for sensing flow rate, and similar sensors) may convert the sensed physical parameters into digital signals and transmit the signals to a destination.

[0072] In some implementations, the boiler model representation is controlled by the following equation:

[0073]

[0074] In some implementations, the combined heat and power unit model is controlled by the following equation:

[0075]

[0076] In some implementations, the steam turbine is controlled by the following equation:

[0077]

[0078] In some implementations, a multi-stage steam turbine is represented by the following equation:

[0079]

[0080] In some implementations, the steam user representation is controlled by the following equation:

[0081]

[0082] In some implementations, the desuperheating and pressure-reducing station is controlled by the following equation:

[0083]

[0084] In some implementations, the air-cooled condenser is controlled by the following equation:

[0085]

[0086] In some implementations, the degasser is controlled by the following equation:

[0087]

[0088] In some implementations, the pump is controlled by the following equation:

[0089]

[0090] In some implementations, the steam flash tank is controlled by the following equation:

[0091]

[0092] In some implementations, the steam manifold is controlled by the following equation:

[0093]

[0094] In some embodiments, system 100 is operatively coupled to computer system 104, which includes one or more data processing means 106a (e.g., one or more data processors) and a computer-readable medium 106b (e.g., a non-transitory computer-readable medium) storing computer instructions executable by the one or more data processing means 106a to perform the operations described in this disclosure. For each device in system 100, computer system 104 receives values ​​of operational physical parameters measured by sensors mounted on the device during operation of the device. For example, computer system 104 receives digital signals representing the values ​​of sensed operational physical parameters measured by sensors. Computer system 104 may store the received signals to perform the following processing.

[0095] In some implementations, the computer system 104 can use the received operating physical parameter values ​​to determine mass balance and energy balance parameters associated with the device from which the operating physical parameter values ​​are received. By using the determined mass balance and energy balance parameters, the computer system 104 can verify the operation of the device. This verification may include comparing the determined mass balance and energy balance parameters for the device with threshold mass balance and energy balance parameters. If the comparison reveals that the threshold parameters are met, the operation of the device is verified as satisfactory. Conversely, if the comparison reveals that the threshold parameters are not met, the operation of the device is verified as unsatisfactory. Determining such parameters includes referencing the following... Figures 4 to 12 The processing receives the values. In this way, computer system 104 can perform verification operations on each device in system 100.

[0096] In some implementations, after verifying the operation of each device in system 100 using mass balance and energy balance parameters determined for each device, computer system 104 can verify the operation of the overall system 100. To this end, computer system 104 can use the mass balance and energy balance parameters associated with each device to determine the mass balance and energy balance parameters associated with system 100. By using the mass balance and energy balance parameters determined for system 100, computer system 104 can verify the operation of the entire system 100. This verification may include comparing the mass balance and energy balance parameters determined for system 100 with system-wide threshold mass balance and energy balance parameters. If the comparison reveals that the threshold parameters are met, the operation of system 100 is verified as satisfactory. Conversely, if the result reveals that the threshold parameters are not met, the operation of system 100 is verified as unsatisfactory.

[0097] In some implementations, computer system 104 is operatively coupled to computer display 108. Real-time output of the determination and verification operations can be displayed on computer display 108. Figure 2 This is a schematic representation of the user interface 200 displayed on the computer monitor 108. The "Current Operation Summary" section discloses the process used to run the online optimization system. This process can be run automatically at a certain frequency (e.g., once per hour). The "System Efficiency" section shows the supply-side thermal efficiency for both actual and optimized operating conditions. The "Cogeneration Unit Load" section shows the load of the cogeneration system (boiler load) for both actual and optimized operating conditions. The "Boiler Load" section shows the load of the boiler system (boiler load) for both actual and optimized operating conditions. The "Energy KPIs" section shows the energy intensity KPIs (Key Performance Indicators) for both actual and optimized operating conditions. The "Operating Costs" section shows the operating costs for both actual and optimized operating conditions. The "CO2 Emissions" section shows the carbon dioxide emissions for both actual and optimized operating conditions.

[0098] Figure 1C A schematic representation of multi-site optimization 130 according to some embodiments is shown. Multi-site optimization 130 can be achieved by a multi-site optimization system (e.g., Figure 17 The computer system 1700 is used to execute this. Multi-site optimization 130 can be used for the digital twin generation and operational optimization of industrial steam and power utility systems across multiple facilities. For example... Figure 1C As shown, multi-site optimization involves performing single-site optimization 132 at each of the multiple facilities. Single-site optimization 132 can be performed sequentially or simultaneously.

[0099] Once single-site optimization 132 is complete, the multi-site optimization system generates a matrix of the single-site optimization results. As described in more detail below, the multi-site optimization system uses the optimization function and this matrix to perform multi-site optimization operation 134 to optimize the operation of multiple facilities. Multi-site optimization is also known as economic scheduling model (EDM). The multi-site optimization system then displays the results of the multi-site optimization on the user interface 136. Figure 1C As shown, the user interface 136 displays information such as the benefits of optimization (e.g., cost reduction, steam system efficiency, and CO2 emission reduction) and the equipment to be turned on / off at each site to achieve optimization. Additionally, the user interface 136 displays information such as process steam requirements, power inputs and outputs, and / or cost savings associated with various actions.

[0100] Figure 3 It is a schematic representation of the optimized operation implemented by computer system 104 on system 100. Figure 3 The optimization operation is shown to be cyclical. For example, at step 302, computer system 104 performs a data verification operation at the device level. Computer system 104 performs step 302 for each device in system 100. In some embodiments, computer system 104 may perform the data verification operation in parallel for all devices. At step 304, after performing the data verification operation for all devices in system 100, computer system 104 conditions the baseline operating conditions of each device. At step 306, computer system 104 performs mass and energy balance for the entire system 100. Optionally, at step 308, computer system 104 performs optimization and uses the results of the previous steps to identify a consultative optimal setpoint for the entire system 100. At step 310, computer system 104 displays the results of performing the previous steps (including any outputs and trends) on computer display 108, for example.

[0101] At step 312, computer system 104 repeats the cycle of steps 302, 304, 306, 308, and 310. In some embodiments, computer system 104 may repeat the cycle at a certain frequency (e.g., once per hour or once for each different duration, which may vary in response to user input). In this way, computer system 104 can periodically monitor system 100 at both the device and system levels, implement verification and optimization measures, and provide verification and optimization outputs to be displayed in the user interface. Reference Figures 4 to 11 Here's an example to describe the verification process.

[0102] Figure 4 This illustrates a workflow for an example data verification process 400 for equipment used in industrial steam power and utility systems. The data verification process 400 is a general process applicable to any equipment located in or capable of being used in system 100. Process 400 includes multiple operations, each of which can be at least partially implemented by computer system 104. For this purpose, computer-executable code can be stored in computer-readable medium 106b and executed by data processing device 106a. When these operations are implemented, computer system 104 receives operational physical parameter values ​​from the equipment and compares the received values ​​with thresholds associated with the equipment. In some embodiments, computer system 104 may process the received values ​​to determine mass balance and energy balance parameters and compare the determined parameters with threshold parameters.

[0103] Alternatively, process 400 can be implemented in multiple levels arranged in a hierarchical structure. Example process 400 includes three levels—first level 402, second level 404, and third level 406. Some processes may have more levels, while others may have fewer. First level 402 may represent the root level, while the last level (e.g., third level 406) may represent a leaf level, with no or no intermediate levels, such as second level 404. In operation, computer system 104 may first implement the root level and then implement subsequent levels down the hierarchy until the leaf level. For each level (except the leaf level), computer system 104 may determine an output and use the determined output as the input to the next lower level in the hierarchy.

[0104] For example, computer system 104 may perform step 410 in first level 402 to extract status data for each device. The status data is received from sensors installed on the device. For example, the status data is a DCS tag providing the on / off status of the device. In the context of this disclosure, "producer" is a steam-generating device such as a boiler, a combined heat and power system, or a process heater with a convection section that generates steam connected to a steam header. In the context of this disclosure, "user" is a steam-consuming device such as a heat exchanger or a reboiler.

[0105] At point 412, computer system 104 verifies whether the user / producer is running. If computer system 104 determines that the user / producer is not running (decision branch "No"), computer system 104 reports a steam flow rate of zero, and the verification process ends. If computer system 104 determines that the user / producer is running (decision branch "Yes"), then at point 416, the computer system retrieves the steam flow rate value. The steam flow rate value and all other values ​​are retrieved from a data history system called the process interface (PI) system, which collects all information from the DCS in real time.

[0106] At this point, the implementation of the first level 402 has been completed. The computer system 104 transmits the extracted steam flow rate value as input to the second level 404.

[0107] Computer system 104 can implement step 418 in the second level to check whether the received steam flow rate value is within a threshold range (i.e., maximum and minimum value limits). If computer system 104 determines that the value is not within the threshold range (decision branch "No"), computer system 104 implements user correlations to quantify the steam flow rate as a function of the process zone feed rate (if applicable). Correlation equations are an alternative way to provide more accurate steam consumption values ​​for steam flow rates that may have erroneous readings, for example, due to DCS tag malfunction or sensor malfunction attached to the device, or both. These correlations are developed based on historical trends of key parameters that have a direct impact on steam consumption. These correlations are developed outside the system and are revised from time to time to have a more accurate representation of the equipment and its performance.

[0108] If computer system 104 determines that the value is within the threshold range (decision branch "Yes"), then computer system 104 uses the value extracted from the PI. The process refers to three categories—Class A, Class B, and Class C. Class A is used to distinguish accurate measurements from other measurements. Values ​​in Class A are reliable values ​​and will be subject to minimal adjustments to achieve energy and material balance in the steam manifold.

[0109] Returning to the decision branch "No," after implementing the user association at step 420, the computer system 104 checks whether the value is within the threshold range (i.e., the maximum and minimum value limits). If the computer system 104 determines that the value is not within the threshold range (decision branch "No"), then at step 430, the computer system 104 uses either the steam flow design value or the user-defined default value. Category C is used to distinguish accurate measurements from other measurements. Values ​​in Category C are given values ​​(i.e., default values, commonly used averages suggested by experienced users), where the design value is the value mentioned in the design document for that specific user. Neither is a reliable value, and significant adjustments will be made compared to Category A to achieve energy and material balance in the steam manifold.

[0110] If, at step 420, the computer system 104 determines that the value is within the threshold range (decision branch "Yes"), then the computer system 104 uses the relevant steam flow value. Category B is used to distinguish accurate measurements from other measurements. Values ​​in Category B are relatively more accurate than those in Category C. This value will be finely adjusted to achieve energy and material balance in the steam manifold. Optimization techniques will adjust the boundary limits of Categories A, B, and C in a consistent manner as needed to ensure that energy and material balance is always closed.

[0111] In this way, if computer system 104 determines that the operating physical parameter values ​​received from sensors attached to the devices in system 100 are accurate, then computer system 104 uses the values ​​in subsequent mass balance and energy balance determinations. If not, computer system 104 performs correlated operations to determine the closest approximation of the sensor values ​​that should be present, and uses the correlated value in the mass balance and energy balance determinations. Moving to step 428, computer system 104 reflects the steam values ​​in the steam meter, storing these values ​​along with a specific timestamp identifying when the value was determined in the database portion of the steam balance.

[0112] Computer system 104 outputs steam values ​​with categories (Class A - reliable values ​​that require no adjustment; Class B - good values ​​that require minimal adjustment; Class C - default values ​​that require some adjustment).

[0113] Computer system 104 can execute step 432 in third level 406 to report the received steam value as the output of second level 404. In some embodiments, computer system 104 can associate a weight with the received value based on the category associated with that value. Since class A values ​​are reliable, the weight can be 1. Since class B values ​​are less reliable, the weight can be less than 1. Since the reliability of class B values ​​is between that of class A and class C values, its weight can be between the weights of class A and class C values. Computer system 104 can output the steam value, its category, and optionally its weight as the output of verification process 400. As previously described, the optimization technique will adjust the boundary constraints of classes A, B, and C in a consistent manner as needed to ensure that energy and material balance is always closed.

[0114] Figures 5 to 12 These are example data validation workflows for heat exchangers, cogeneration systems, boilers, process heaters, mechanical drives and generators, motor pumps / compressors, and gas turbines. Each data validation process is substantially similar to data validation process 400. While data validation process 400 is generic for any device in system 100, Figures 5 to 12 Each data verification process shown is implemented with reference to a specific device.

[0115] For example, Figure 5This illustrates the workflow of a sample data verification process 500 for heat exchangers. Heat exchanger steam users include all facility reboilers and process heaters connected to different steam headers. The heat exchanger steam consumption data verification process 500 (HX-DVR) comprises three levels of verification and conditioning. At the first level 502, the exchangers are checked by the process steam outlet temperature to determine whether they are online or offline. The temperature limit considered for the exchanger is based on design data, historical data, or a combination of both. If the temperature is below the set limit, steam flow readings from the PI are disregarded, and the exchanger steam flow is reflected as zero. At the second level 504, the extracted steam flow readings are refined by minimum and maximum limits. At level 504, these limits are set based on the exchanger steam flow design data. If the extracted data from the PI is within the set limits, the PI value reading is reflected in the steam table as having category A. If the PI reading exceeds the minimum and maximum limits, relevant steam flow readings based on historical data are used. If the relevant value is within the minimum and maximum limits, it is reflected in the steam meter as having category B. At the end of the validation process, if the relevant value is not within the minimum and maximum limits, the design steam flow reading with category C is used. The third level of validation 506 is to ensure that the reported values ​​in the steam meter can close the balance and adjust the steam flow values ​​according to their category: Category A – a reliable value that requires no adjustment, Category B – a good value that requires minimal adjustment, and Category C – a default value that requires some adjustment. For any PI reading of a heat exchange-specific operating parameter value received by a sensor (e.g., implemented as a distributed control system), regardless of the problem associated with that PI value, there is always a reliable value representing that specific operating physical parameter as the output of the data validation process 500, thereby ensuring a reliable system with accurate results as much as possible.

[0116] Figure 6 This illustrates the workflow of an example cogeneration data verification process 600 for a cogeneration system. The cogeneration data verification process 600 (CGN-DVR) forms part of an online CHP model (i.e., a combined thermal and electrical system model) for an industrial plant, which is an optimized model developed to represent the steam and electrical systems of an industrial facility.

[0117] The validation process 600 comprises three levels of data validation and conditioning. Key measurements related to the cogeneration system from the DCS are used as inputs to determine the current operating status of cogeneration equipment such as gas turbines and heat recovery steam generators (HRSGs). In the first level 602, the gas turbine status is checked to see if it is online or offline. The power generation and steam flow from the HRSG can be used to check if the cogeneration system is operational. The power and steam limits for which the cogeneration system is considered online are typically based on design data, historical data, or a combination of both. On the other hand, if the temperature is below the set limits, steam flow readings from the PI are disregarded, and the HRSG steam flow is reflected as zero. In the second level 602, interrelated variables are conditioned to ensure that the measured and conditioned parameters are within 2% error. The extracted power, steam flow, fuel flow, and chimney temperature values ​​are constrained within reasonable upper and lower limits. If the extracted data from the PI is within the set limits, the PI value reading is reflected in the model. If the PI reading exceeds the minimum and maximum limits, a relevant value based on historical data is used. If the relevant value is within the minimum and maximum limits, it is reflected in the model. At the end of validation process 600, if the relevant value is not within the minimum and maximum limits, the design data is used. The third (and final) level of validation 606 ensures that the reported values ​​in the model achieve a closed-loop balance.

[0118] Figure 7 This illustrates the workflow of an example boiler data verification process 700. For boiler data verification and conditioning, raw PI data for boiler steam, BFW, fuel flow, and chimney temperature are received. Verification steps are implemented to identify whether the boiler is operating. This step is based on whether the fuel gas (chimney) temperature is below 150°C. o F. If so, the boiler is off and the flow rate is reported as zero. If the boiler is running, another cross-check is performed based on steam, fuel, and BFW flow rates and boiler efficiency. If the boiler efficiency determined based on the heat input / output method is greater than 90%, the boiler efficiency is calculated using the correlation equation (below), and the fuel value is adjusted accordingly. If the efficiency is within the range, fuel consumption is verified based on expected and actual values. If the error is within 2%, the fuel value is used directly or adjusted to be within the 2% error range. The input to the boiler efficiency correlation equation is the stack temperature (Stack Temp). o F) and excess oxygen (Excess O2, %). Both are collected from PI data. Relevant parameters (AO2, BO2, AT, BT) are generated for each specific boiler and are updated periodically (e.g., annually or at different durations).

[0119]

[0120] Figure 8 This illustrates the workflow of an example process heater data verification process 800. Verification process 800 (PH-DVR) is part of an online CHP model of an industrial plant 100. The process heater can be in the form of a furnace or a waste heat boiler. For this unit, PI data is extracted for the generated steam, BFW, fuel flow rate, and chimney temperature. The verification step is then implemented to identify whether the boiler is operating. This step is based on whether the fuel gas (chimney) temperature is below 150°C. o F. If so, the process heater is off and the flow rate is reported as zero. If the process heater is running, another cross-check is performed based on steam, fuel, and BFW flow rates and boiler efficiency. If the boiler efficiency determined based on the heat input / output method is greater than 90%, the boiler efficiency is calculated using the correlation equation (below), and the fuel value is adjusted accordingly. If the efficiency is within the range, fuel consumption is verified based on expected and actual values. If the error is within 2%, the fuel value is used directly or adjusted to be within the 2% error range. The input to the boiler efficiency correlation equation is the stack temperature (Stack Temp). o F) and excess oxygen (Excess O2, %). Both are collected from PI data. Relevant parameters (AO2, BO2, AT, BT) are generated for each specific boiler and are updated periodically (e.g., annually or at different durations).

[0121]

[0122] Figure 9This illustrates the workflow of a data verification process 900 for mechanical drives and generators. The data verification process 900 (ST-DVR) covers mechanically driven equipment such as compressors, pumps, and blowers. These turbines typically operate at speeds associated with the process equipment they drive. For mechanical drives and generators, PI data is retrieved for each stage of the steam turbine (i.e., inlet, extraction, induction, etc.), RPM, and the driven process steam flow rate. Verification steps are then performed to identify whether the unit is operating. This is based on whether the RPM is below the design range for operation. If the mechanical drive and generator are operating, another cross-check is performed based on the steam flow rate. Steam turbine efficiency is based on the relationship between actual operation and isentropic operation extracted from the steam temperature of the turbine. If a steam flow rate PI label for steam flowing to the steam turbine exists and the value is within the minimum and maximum range, that value is used on the model. If no steam reading exists or the reading is outside the minimum and maximum range, a correlation is used to quantify the expected steam consumption based on the process parameters associated with the steam turbine, or the design value is used. This value is then modified by the data conditioning layer within acceptable limits.

[0123] Figure 10 This illustrates the workflow of the motor pump / compressor data verification process 1000. These motors include all equipment motors driving all pumps and compressors. The data verification process 1000 (MT-DVR) comprises three levels of verification and conditioning. In the first level 1002, the motor status is extracted from the PI (Power Injection Point) to check whether the motor is on or off. If the motor is off, its power consumption is considered zero. If the motor is on, verification at the second level 1004 is performed. In the second level 1004, a check is performed to determine if an available power consumption PI tag exists. If an available motor power consumption PI tag exists, power consumption data is extracted from the PI system. If the motor power consumption PI tag is unavailable, the motor power consumption is determined based on other pump process parameters (e.g., differential pressure, flow rate, differential temperature, specific gravity, etc.). In the final verification level 1006, if the determined value is outside design limits due to a failure degree in other used process parameters, the motor power consumption design rate is used as the user default value.

[0124] Figure 11This illustrates the workflow of the gas turbine data validation process 1100 (GT-DVR). Process 1100 is implemented in three levels of data validation and conditioning. Key measurements related to the simple cycle gas turbine unit from the DCS are used as inputs to determine the current operating conditions of the gas turbine. In the first level 1102, the gas turbine status is checked to see if it is online or offline. The generator or mechanical drive unit (e.g., pump or compressor) is used to check if the unit is operable. The power limit for the gas turbine unit to be considered online is typically based on design data, historical data, or a combination of both. In the second level 1104, interrelated variables are conditioned together to ensure that the measured and conditioned parameters are within 2% error. The extracted power, fuel flow, and chimney temperature values ​​are constrained within reasonable upper and lower limits. If the extracted data from the PI is within the set limits, the PI value reading is reflected in the model. If the PI reading exceeds the minimum and maximum limits, the PI value reading based on design data, historical data, or a combination of both is used. If the relevant value is within the minimum and maximum limits, it is reflected in the model. At the end of the validation process, if the relevant value is not within the minimum and maximum limits, the design value is used. The final level of validation (Level 1106) ensures that the reported values ​​in the model are balanced.

[0125] Gas turbine efficiency (%) = BHP output or MW output of the driven equipment / fuel consumption of the gas turbine unit

[0126] Each data verification process described above is implemented by computer system 104 as computer-executable instructions. Subsequently, computer system 104 performs overall steam system data conditioning to ensure that the balance is closed in the most accurate possible manner. Computer system 104 follows these steps to implement steam system data verification and conditioning to close the balance:

[0127] 1. PI data related to the following variables will be retained as is for establishing baseline conditions:

[0128] a. Boiler steam generation

[0129] b. Steam and electricity generation in the combined heat and power unit system

[0130] c. Desuperheating and depressurization steam flow rate

[0131] d. Excess steam flow

[0132] 2. Adjustments will be made for steam process users with PI issues or high errors, and these adjustments will follow the process determined for each equipment flow chart.

[0133] 3. The adjustment factor for each steam user is the decision variable of the optimization layer, which aims to close the balance of each manifold and the steam balance of the entire system.

[0134] Computer system 104 achieves the problem formula of minimizing error and achieving closed-loop equilibrium on each other manifold and the entire steam system by executing the following equation: Objective function = Minimum manifold error Subject to the following constraints:

[0135] - Keep the steam from the boiler constant.

[0136] - Steam and electricity production from the combined heat and power unit remain unchanged.

[0137] -The flow rate of the desuperheating and pressure reducing station remains constant.

[0138] - The steam consumption of the equipment will be adjusted between minimum and maximum limits based on the specific flowchart of each equipment / user.

[0139] In some implementations, computer system 104 implements an optimization layer that provides advisory recommendations to adjust the loads of key equipment in the operating facility, which helps improve the efficiency of the steam and power systems and reduce carbon dioxide emissions. Computer system 104 achieves optimization by executing an objective function affected by variables and constraints. The objective function aims to minimize facility operating costs, including fuel costs, electricity import and export costs, and makeup water and water treatment costs. Variables in the optimization include the steam and power loads of key equipment in the steam system (e.g., all equipment whose validation process is described above). The optimization process is affected by several constraints representing operational and equipment limitations. Examples include:

[0140] - Meets all steam and electricity needs of the facility.

[0141] - The demand for steam, electricity, fuel and water is affected by contractual agreements with third parties or joint suppliers;

[0142] -Environmental regulations concerning carbon dioxide emissions or other similar requirements;

[0143] -Energy and material balance of the steam and electricity networks within the facility;

[0144] - Device maximum and minimum output limits;

[0145] -Non-negative flow rates in the steam distribution network;

[0146] - The steam and electricity reserves required for the facility;

[0147] - The minimum number of operating devices that meet reliability requirements (if applicable).

[0148] Figure 12 This is a flowchart illustrating an example of a method 1200 for data verification and optimization of an industrial steam, power, and utility system. Method 1200 is implemented by a computer system (e.g., computer system 104) in an industrial plant (e.g., industrial plant 100) that implements the steam and power system. The industrial plant includes multiple devices, including a combined heat and power system and a steam turbine. At 1202, for each device, the computer system (during operation of each device) receives measured values ​​of operating physical parameters output by that device during its operation. At 1204, the computer system 104 uses the received operating physical parameter values ​​to determine mass balance and energy balance parameters associated with that device. At 1206, the computer system 104 uses the determined mass balance and energy balance parameters to verify the operation of that device. After verifying the mass balance and energy balance parameters of multiple devices, at 1208, the computer system 104 uses the mass balance and energy balance parameters of each device to determine the mass balance and energy balance parameters associated with the industrial plant. At 1210, computer system 104 verifies the operation of the industrial plant using the determined mass balance and energy balance parameters associated with the industrial plant. At 1212, computer system 104 displays the output of the verification operation. At 1214, the computer system waits for a predetermined duration (e.g., one hour, or less or more than one hour) and repeats steps 1202 to 1212. The verification solution implemented by computer system 104 eliminates erroneous readings and ensures accurate representation of the steam and electrical utility systems of the operating facility.

[0149] In some implementations, the real-time advisory system includes a layer for multi-site optimization that performs generator set optimization and / or load management at the enterprise level (e.g., across multiple sites within an enterprise or industry). This optimization layer is responsible for the entire generator set across multiple sites within the enterprise. The optimization layer provides advisory recommendations to adjust the loads of generator sets and boiler load management at each site. The objective function of this layer is to improve (e.g., optimize) operating costs, system efficiency, and CO2 emission reduction. The optimization layer also includes constraints on site-specific operational limitations.

[0150] Figure 13 A schematic representation of a multi-site optimization operation 1300 according to some embodiments is shown. The multi-site optimization operation 1300 can be performed by a multi-site optimization system (e.g., a project management information system (PMIS)). Specifically, the multi-site optimization system can periodically perform the multi-site optimization operation 1300 to optimize the operation of industrial steam power and utility systems at multiple facilities. Figure 13 The optimization operation is shown to be cyclical.

[0151] At step 1302, the multi-site optimization system performs a data verification operation for one or more sites. In some examples, step 1302 involves performing a data verification operation for each device at each site. Figure 3 Step 302 describes the process of performing data verification operations for each device.

[0152] At step 1304, the multi-site optimization system adjusts the baseline operating conditions of each device. Figure 3 Step 304 describes the process of conditioning the baseline operating conditions for each device's data.

[0153] In step 1306, the multi-site optimization system performs optimization and identifies the optimal setup point for consultation at each site. Figure 3 Step 306 describes the process of optimizing and identifying the optimal setup point for a site. Note that a multi-site optimization system can perform site-level optimizations sequentially or simultaneously.

[0154] At step 1308, the multi-site optimization system identifies site-level constraints, including energy demand, steam reserves, and equipment limitations. Additionally, the multi-site optimization system identifies multi-site constraints, including steam and electricity reserves and emission targets.

[0155] At step 1310, the multi-site optimization system performs global optimization on all generating units, including industrial, power generation, and renewable facilities. To optimize the energy system at a single site, the real-time consultation system considers several constraints, such as: (i) the closing material and energy balance of the energy system's baseline and optimized operation at that site; (ii) the minimum and maximum operating limits of the equipment at that site; and (iii) the steam and electricity storage requirements of the energy system at that site. Furthermore, to optimize multiple sites, the real-time consultation system considers constraints for global optimization, such as: (i) generating specific power output values ​​across facilities; and (ii) site-level and multi-site-level constraints, such as equipment operating limits.

[0156] In some implementations, the multi-site optimization system generates a global matrix of optimization results for each site. The optimization results for each site include equipment in an on / off state, the optimized steam load of the operating equipment, the electrical load of the operating equipment, and other data described herein. The multi-site optimization system then uses this matrix (e.g., to initialize the optimization function), the global objective function, the decision variables of the global objective function, and constraints to perform multi-site optimization. Initialization using a matrix of site-level optimizations can facilitate faster and more efficient convergence to the optimal solution. In some examples, the objective function aims to minimize total operating costs across the enterprise. Total operating costs include fuel costs, electricity import costs, electricity export costs, makeup water costs, and water treatment costs. In some examples, decision variables in the optimization include, but are not limited to, the steam and electricity loads of the cogeneration unit, power generation, seawater desalination, and renewable energy. In some examples, multi-site optimization is affected by one or more constraints that represent operational and equipment limitations, such as:

[0157] - Meets the steam and electricity needs of each facility, while also meeting the needs across multiple sites;

[0158] - The demand for steam, electricity, fuel and water is affected by contractual agreements with third parties;

[0159] -Environmental regulations concerning CO2 emissions or other similar requirements;

[0160] -Energy and material balance of the steam and electricity networks within the facility;

[0161] - Device maximum and minimum output limits;

[0162] -Non-negative flow rates in the steam distribution network;

[0163] - The steam and electricity reserves required for each facility;

[0164] - The minimum number of operational devices required to meet reliability requirements (if applicable). This may include forcing a device to be shut down during transport and installation (T&I).

[0165] In some implementations, once the optimization operation is complete, the multi-site optimization system provides advisory recommendations to adjust the loads of key equipment in the operating facility. This helps improve the efficiency of the steam and power systems and reduce CO2 emissions, thereby lowering overall operating costs. Specifically, based on multi-site optimization, the system can perform cogeneration unit load management (identifying which units are on / off), boiler load management, and surplus steam minimization. In addition to recommending actions for cogeneration unit load management, boiler load management, and surplus steam minimization, the system can also determine the benefits of performing each action. Both the actions to be performed and the benefits can be provided on the user interface.

[0166] At step 1312, the multi-site optimization system repeats the loop of steps 1302, 1304, 1306, 1308, and 1310. In some embodiments, the multi-site optimization system may repeat the loop at a certain frequency (e.g., once per hour or once for each different duration, which may vary in response to user input). In this way, the multi-site optimization system can periodically monitor multi-site facilities at both the device and system levels, implement verification and optimization measures, and provide verification and optimization outputs to be displayed in the user interface.

[0167] In some implementations, the user interface includes suggested actions for achieving optimization across multiple facilities. Specifically, the user interface depicts suggestions for specific facilities among the multiple facilities. Suggestions may include boilers to be turned on / off (e.g., boiler 1 is on, boiler 2 is off), cogeneration units to be turned on / off, and equipment operating parameters for various devices including steam generators, deaerators, and steam turbines. The user interface depicts the benefits achieved by the suggested actions. For example, the user interface includes comparisons of operating costs, steam system efficiency, and CO2 emission reductions between baseline and optimized operating conditions.

[0168] The user interface may also include suggested operating parameters for the equipment at the facility. Suggested operating parameters include suggested loads for cogeneration units and boilers. Additionally, suggested operating parameters include blower on / off indicators. Furthermore, the user interface includes representations of the benefits of the suggested actions. The user interface includes graphs depicting cost improvements, system efficiency improvements, and KPI improvements.

[0169] Figure 14 Figure 1400 illustrates optimized operation of a combined heat and power (CHP) unit according to some implementation methods. Figure 1400 is another example of actions suggested by a multi-site optimization system to achieve optimization. In this example, A through N each refer to a facility. Figure 14As shown, Figure 1400 depicts: (i) the baseline number of units operating at each facility, (ii) the maximum number of units at that facility, and (iii) the number of optimized units based on multi-site optimized operation.

[0170] Figure 15 A depiction of a multi-site optimization system 1500 according to some embodiments is shown. For example... Figure 15 As shown, the results of multi-site optimization operations (displayed as the company's optimal utility operation) can be accessed from multiple management areas (e.g., management areas at different facilities). The results of multi-site optimization operations include: (i) the baseline number of units operating at each facility, (ii) the maximum number of units at that facility, and (iii) the optimized number of units based on the multi-site optimization operation. Furthermore, each facility can access recommendations for adjusting the loads of its key equipment, which helps improve steam and power system efficiency and reduce CO2 emissions. Additionally, each facility can use information displayed on the graphical user interface to perform cogeneration unit load management (identifying which units are on / off), boiler load management, and surplus steam minimization.

[0171] Figure 16 This is a flowchart illustrating an example of a multi-site optimization method 1600 for multiple energy systems (e.g., industrial steam power and utility systems) across multiple facilities. Method 1600 is implemented by a computer system (e.g., computer system 1700) that manages the multiple energy systems. Each energy system includes multiple power generation devices, such as combined heat and power systems and steam turbines.

[0172] Method 1602 involves: for each energy system at each facility: performing device-level data verification for multiple corresponding power generation devices; performing device-level data conditioning for multiple corresponding power generation devices; and performing site-level optimization for multiple corresponding power generation devices to determine device operating parameters.

[0173] At 1604, method 1600 involves determining: (i) site-level constraints for multiple energy systems and (ii) multi-site constraints across multiple energy systems;

[0174] Method 1606 involves optimizing the equipment operating parameters of multiple corresponding power generation devices across multiple energy systems based on site-level constraints and multi-site constraints.

[0175] In some implementations, multiple energy systems include industrial plants, power plants, and renewable energy plants.

[0176] In some implementations, site-level constraints include the energy requirements of each energy system, the corresponding steam reserves of each energy system, the corresponding minimum number of boilers required to maintain the corresponding steam reserves of each energy system, and equipment limitations for multiple corresponding power generation devices of each energy system.

[0177] In some implementations, multi-site constraints include steam storage requirements across multiple energy systems, electricity storage requirements across multiple energy systems, emissions reduction targets across multiple energy systems, and minimum efficiency across multiple energy systems.

[0178] In some implementations, performing device-level data verification for a plurality of respective power generation devices includes: for each of the plurality of respective power generation devices: during operation of each device, receiving measured operating physical parameter values ​​output by the device during operation of the device; using the received operating physical parameter values ​​to determine mass balance and energy balance parameters associated with the device; and using the determined mass balance and energy balance parameters to verify the operation of the device.

[0179] In some implementations, optimizing the equipment operating parameters of multiple corresponding power generation devices based on site-level constraints and multi-site constraints involves: generating a global matrix that includes the site-level optimization results for each energy system; and using the global objective function and the global matrix of the site-level optimization results to optimize the equipment operating parameters of the multiple corresponding power generation devices.

[0180] In some implementations, operating parameters include cogeneration unit load management and boiler load management.

[0181] In some embodiments, the method further includes: displaying operating parameters on a display device via a user interface; and displaying benefits associated with the operating parameters on a display device via a user interface.

[0182] Figure 17This is a block diagram of an example computer system 1700 (e.g., computer system 104) for providing computational functionality associated with the algorithms, methods, functions, processes, flows, and procedures described in this disclosure, according to some embodiments of this disclosure. The computer 1702 shown is intended to encompass any computing device, such as a server, desktop computer, laptop / notebook computer, wireless data port, smartphone, personal data assistant (PDA), tablet computing device, or one or more processors within these devices, including physical instances, virtual instances, or both. Computer 1702 may include input devices capable of accepting user information, such as a keypad, keyboard, and touchscreen. Additionally, computer 1702 may include output devices capable of conveying information associated with the operation of computer 1702. This information may include digital data, visual data, or audio information, or a combination of information. This information may be presented in a graphical user interface (UI) (or GUI).

[0183] Computer 1702 can be used as a client, network component, server, database, persistence, or component for a computer system performing the subject matter described in this disclosure. The illustrated computer 1702 is communicatively coupled to network 1730. In some embodiments, one or more components of computer 1702 can be configured to operate in different environments, including a cloud-based environment, a local environment, a global environment, or a combination of environments.

[0184] From a high-level perspective, computer 1702 is an electronic computing device operable for receiving, transmitting, processing, storing, and managing data and information associated with the described subject matter. According to some embodiments, computer 1702 may also include or be communicatively coupled to an application server, email server, web server, cache server, streaming data server, or a combination of servers.

[0185] Computer 1702 can receive requests from client applications (e.g., executed on another computer 1702) via network 1730. Computer 1702 can respond to received requests by processing them using software applications. Requests can also be sent to computer 1702 from internal users (e.g., from a command console), external (or third-party), automation applications, entities, individuals, systems, and computers.

[0186] Each component of computer 1702 can communicate using system bus 1703. In some implementations, any or all components of computer 1702 (including hardware or software components) can be connected to each other or to interface 1704 (or a combination of both) via system bus 1703. The interface can use application programming interface (API) 1712, service layer 1713, or a combination of API 1712 and service layer 1713. API 1712 may include specifications for routines, data structures, and object classes. API 1712 may be independent of or dependent on a computer language. API 1712 may refer to a complete interface, a single function, or a set of APIs.

[0187] Service layer 1713 can provide software services to computer 1702 and other components communicatively coupled to computer 1702 (whether or not shown). The functionality of computer 1702 can be accessible to all service consumers using this service layer. Software services (e.g., software services provided by service layer 1713) can provide reusable, defined functionality through defined interfaces. For example, the interface can be software written in JAVA, C++, or a language that provides data in Extensible Markup Language (XML) format. Although shown as an integrated component of computer 1702, in alternative embodiments, API 1712 or service layer 1713 can be shown as a separate component relative to other components of computer 1702 or other components communicatively coupled to computer 1702. Furthermore, without departing from the scope of this disclosure, any or all portions of API 1712 and / or service layer 1713 can be implemented as a submodule or auxiliary module of another software module, enterprise application, or hardware module.

[0188] Computer 1702 includes interface 1704. Although in Figure 17 While shown as a single interface 1704, two or more interfaces 1704 may be used depending on the specific needs, expectations, or particular implementation and functionality of computer 1702. Interface 1704 can be used by computer 1702 to communicate with other systems (whether shown or not) connected to network 1730 in a distributed environment. Typically, interface 1704 may include or be implemented using logic encoded in software or hardware (or a combination of software and hardware) operable for communicating with network 1730. More specifically, interface 1704 may include software supporting one or more communication protocols associated with the communication. Therefore, the hardware of network 1730 or the interface can be used to transmit physical signals both within and outside the illustrated computer 1702.

[0189] Computer 1702 includes processor 1705. Although in Figure 13The computer 1702 is shown as a single processor 1705, but two or more processors 1705 may be used depending on the specific needs, expectations, or particular implementation and functions described herein. Generally, the processor 1705 can execute instructions and manipulate data to perform operations of the computer 1702, including the use of any algorithms, methods, functions, processes, flows, and procedures as described herein.

[0190] Computer 1702 also includes database 1706, which can store data from computer 1702 and other components connected to network 1730 (whether or not shown). For example, database 1706 may be internal memory storing data consistent with this disclosure, a conventional database, or another database. In some embodiments, database 1706 may be a combination of two or more different database types (e.g., a mixture of internal memory and conventional databases), depending on the specific needs, expectations, or particular implementation and described functionality of computer 1702. Although in Figure 17 While shown as a single database 1706, two or more databases (of the same, different, or combined types) may be used depending on the specific needs, expectations, or particular implementation and functionality of computer 1702. Although database 1706 is shown as an integrated component of computer 1702, in alternative embodiments, database 1706 may be external to computer 1702.

[0191] Computer 1702 further includes memory 1713, which can store data for computer 1702 or a combination of components that can be connected to network 1730 (whether or not shown). Memory 1713 can store any data consistent with this disclosure. In some embodiments, depending on the specific needs, expectations, or particular implementation and described functionality of computer 1702, memory 1713 may be a combination of two or more different types of memory (e.g., a combination of semiconductor and magnetic storage devices). Although in Figure 17 While shown as a single memory 1713, two or more memories 1713 (of the same, different, or combined types) may be used depending on the specific needs, expectations, or particular implementation and functionality of the computer 1702. Although the memory 1713 is shown as an internal component of the computer 1702, in alternative embodiments, the memory 1713 may be external to the computer 1702.

[0192] Application 1708 may be an algorithmic software engine that provides functionality according to the specific needs, expectations, or specific implementations of computer 1702 and the described functionality. For example, application 1708 may be used as one or more components, modules, applications, etc. Furthermore, although shown as a single application 1708, application 1708 may be implemented as multiple applications 1708 on computer 1702. Additionally, although shown as being inside computer 1702, in alternative implementations, application 1708 may be outside computer 1702.

[0193] Computer 1702 may also include power supply 1714. Power supply 1714 may include a rechargeable or non-rechargeable battery that can be configured to be user- or non-user-replaceable. In some embodiments, power supply 1714 may include power conversion and management circuitry (including recharging, backup, and power management functions). In some embodiments, power supply 1714 may include a power plug for allowing computer 1702 to be plugged into a wall outlet or power source to, for example, power computer 1702 or charge a rechargeable battery.

[0194] Any number of computers 1702 may exist, associated with or outside the computer system containing computer 1702, each computer 1702 communicating via network 1730. Furthermore, the terms "client," "user," and other suitable terms may be used interchangeably without departing from the scope of this disclosure. Additionally, this disclosure includes the possibility that a plurality of users may use one computer 1702 and that a user may use multiple computers 1702.

[0195] For the purposes of this disclosure, the terms “real-time,” “real-time (fast) (RFT),” “near real-time (NRT),” “quasi-real-time,” or similar terms (as understood by one of ordinary skill in the art) mean that actions and responses are close in time, such that an individual perceives the action and response as occurring substantially simultaneously. For example, the time difference between the response to the display of data (or the time difference for initiating the display) after an individual has performed an action to access data can be less than 1 millisecond, less than 1 second, less than 5 seconds, etc. In another example, the time difference between the response to sending (e.g., to display or process) a measurement value after the measurement value can be less than 1 millisecond, less than 1 second, less than 5 seconds, etc. While the requested data does not need to be displayed (or the display initiated) immediately, nor does the operation need to be performed immediately, there is no artificial delay in displaying (or initiating the display) or performing the operation, taking into account the processing limitations of the computing system and the time required for, for example, to collect, accurately measure, analyze, process, store, or transmit data (or a combination of these or other functions).

[0196] Although this specification contains numerous specific implementation details, these details should not be construed as limiting any scope of the invention or the scope of the claims, but rather as descriptions of features specific to particular embodiments of the invention. Specific features described in this specification within the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. Furthermore, although features may be described above as functioning in certain combinations and even initially claimed in this way, one or more features from a claimed combination may be removed from the combination in some cases, and the claimed combination may be for sub-combinations or variations thereof.

[0197] Similarly, although operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or in sequential order, or requiring the execution of all shown operations to achieve the desired result. In some contexts, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated into a single software product or packaged into multiple software products.

[0198] Therefore, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes described in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing may be advantageous.

Claims

1. A method performed by a computer system managing multiple energy systems located in multiple facilities, the multiple energy systems comprising multiple corresponding power generation devices, and the method comprising: For each energy system at each facility: Perform device-level data verification on the aforementioned multiple corresponding power generation devices; Perform device-level data conditioning on the aforementioned multiple corresponding power generation devices; as well as Site-level optimization is performed on the multiple corresponding power generation devices to determine the device operating parameters; Determine: (i) site-level constraints of the multiple energy systems and (ii) multi-site constraints across the multiple energy systems; Based on the site-level constraints and the multi-site constraints, the equipment operating parameters of the multiple corresponding power generation devices across the multiple energy systems are optimized.

2. The method according to claim 1, wherein, The multiple energy systems include industrial plants, power plants, and renewable energy plants.

3. The method according to claim 1, wherein, The site-level constraints include the energy requirements of each energy system, the corresponding steam reserves of each energy system, the corresponding minimum number of boilers required to maintain the corresponding steam reserves of each energy system, and the equipment limitations of the multiple corresponding power generation devices of each energy system.

4. The method according to claim 1, wherein, The multi-site constraints include steam storage requirements across the multiple energy systems, electricity storage requirements across the multiple energy systems, emission reduction targets across the multiple energy systems, and minimum efficiency across the multiple energy systems.

5. The method according to claim 1, wherein, Performing device-level data verification on the aforementioned multiple corresponding power generation devices includes: For each of the plurality of power generation devices: During the operation of each device, the measured values ​​of the operating physical parameters output by the device during the operation of the device are received; The received operating physical parameter values ​​are used to determine the mass balance and energy balance parameters associated with the device; and The operation of the device was verified using the determined mass balance and energy balance parameters.

6. The method according to claim 1, wherein, Based on the site-level constraints and the multi-site constraints, optimizing the equipment operating parameters of the multiple corresponding power generation devices includes: Generate a global matrix that includes site-level optimization results for each energy system; and The equipment operating parameters of the plurality of corresponding power generation devices are optimized using a global objective function and the global matrix of the site-level optimization results.

7. The method according to claim 1, wherein, The operating parameters include cogeneration load management and boiler load management.

8. The method according to claim 1, further comprising: The operating parameters are displayed on a display device via a user interface; as well as The benefits associated with the operating parameters are displayed on the display device via the user interface.

9. One or more computer systems for managing multiple energy systems located in multiple facilities, said multiple energy systems including multiple corresponding power generation devices, and said one or more computer systems comprising: One or more processors are configured to perform operations, the operations including: For each energy system at each facility: Perform device-level data verification on the aforementioned multiple corresponding power generation devices; Perform device-level data conditioning on the plurality of corresponding power generation devices; and Site-level optimization is performed on the multiple corresponding power generation devices to determine the device operating parameters; Determine: (i) site-level constraints of the multiple energy systems and (ii) multi-site constraints across the multiple energy systems; Based on the site-level constraints and the multi-site constraints, the equipment operating parameters of the multiple corresponding power generation devices across the multiple energy systems are optimized.

10. One or more computer systems according to claim 9, wherein, The multiple energy systems include industrial plants, power plants, and renewable energy plants.

11. One or more computer systems according to claim 9, wherein, The site-level constraints include the energy requirements of each energy system, the corresponding steam reserves of each energy system, the corresponding minimum number of boilers required to maintain the corresponding steam reserves of each energy system, and the equipment limitations of the multiple corresponding power generation devices of each energy system.

12. One or more computer systems according to claim 9, wherein, The multi-site constraints include steam storage requirements across the multiple energy systems, electricity storage requirements across the multiple energy systems, emission reduction targets across the multiple energy systems, and minimum efficiency across the multiple energy systems.

13. One or more computer systems according to claim 9, wherein, Performing device-level data verification on the aforementioned multiple corresponding power generation devices includes: For each of the plurality of power generation devices: During the operation of each device, the measured values ​​of the operating physical parameters output by the device during the operation of the device are received; The received operating physical parameter values ​​are used to determine the mass balance and energy balance parameters associated with the device; and The operation of the device was verified using the determined mass balance and energy balance parameters.

14. One or more computer systems according to claim 9, wherein, Based on the site-level constraints and the multi-site constraints, optimizing the equipment operating parameters of the multiple corresponding power generation devices includes: Generate a global matrix that includes site-level optimization results for each energy system; and The equipment operating parameters of the plurality of corresponding power generation devices are optimized using a global objective function and the global matrix of the site-level optimization results.

15. One or more computer systems according to claim 9, wherein, The operating parameters include cogeneration load management and boiler load management.

16. The computer system of claim 9, further comprising: The operating parameters are displayed on a display device via a user interface; as well as The benefits associated with the operating parameters are displayed on the display device via the user interface.

17. A non-transitory computer storage medium encoded with instructions that, when executed by one or more computers managing multiple energy systems located in multiple facilities and including multiple corresponding power generation devices, cause the one or more computers to perform operations, the operations including: For each energy system at each facility: Perform device-level data verification on the aforementioned multiple corresponding power generation devices; Perform device-level data conditioning on the aforementioned multiple corresponding power generation devices; as well as Site-level optimization is performed on the multiple corresponding power generation devices to determine the device operating parameters; Determine: (i) site-level constraints of the multiple energy systems and (ii) multi-site constraints across the multiple energy systems; Based on the site-level constraints and the multi-site constraints, the equipment operating parameters of the multiple corresponding power generation devices across the multiple energy systems are optimized.

18. The non-transitory computer storage medium according to claim 17, wherein, The multiple energy systems include industrial plants, power plants, and renewable energy plants.

19. The non-transitory computer storage medium according to claim 17, wherein, The site-level constraints include the energy requirements of each energy system, the corresponding steam reserves of each energy system, the corresponding minimum number of boilers required to maintain the corresponding steam reserves of each energy system, and the equipment limitations of the multiple corresponding power generation devices of each energy system.

20. The non-transitory computer storage medium according to claim 17, wherein, The multi-site constraints include steam storage requirements across the multiple energy systems, electricity storage requirements across the multiple energy systems, emission reduction targets across the multiple energy systems, and minimum efficiency across the multiple energy systems.

Images