An online optimization method for the energy consumption of multiple devices in an air separation unit based on cluster analysis

Abstract

The present invention relates to the technical field of energy consumption optimization of air separation units, and specifically to an online optimization method for the energy consumption of multiple devices of an air separation unit based on cluster analysis. By monitoring the production process according to production planning data, production progress data is obtained, and gas demand data is predicted. Through a clustering algorithm, the gas demand data is identified to obtain a gas demand subset, and the gas demand pattern is determined. The time distribution data of the gas demand subset is obtained, and the working cycle of the air separation unit is divided to obtain a regulation cycle. Taking the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit within the regulation cycle as constraints, a first energy consumption analysis model is constructed. Taking the second energy consumption between the first energy consumption analysis model and the regulation cycle as a constraint, a second energy consumption analysis model is constructed. The present invention performs real-time regulation on the air separation unit according to the second energy consumption analysis model.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption optimization of air separation units, and specifically to an online optimization method for the energy consumption of multiple devices of an air separation unit based on cluster analysis. Background Art

[0002] Air separation units are characterized by high energy consumption and long cycles, consuming a large amount of energy during operation; the problem of energy consumption optimization has attracted increasing attention, and it is necessary to optimize the energy consumption of air separation units.

[0003] In the prior art, the energy consumption optimization of air separation units mainly adopts a static optimization strategy based on physical modeling; by establishing mechanism models of single devices such as compressors and heat exchangers, and performing offline simulation calculations based on preset operating condition parameters. However, such solutions have three key technical defects: the data processing dimension is single, only considering the steady-state parameters at the device level, and not constructing a multi-dimensional feature vector including production plan data, user demand fluctuation curves, and environmental parameters; the calculation architecture lacks real-time performance, and traditional numerical calculation methods are difficult to solve multi-variable coupling equations within a time scale of seconds; the optimization strategy lacks self-adaptability, and when encountering production schedule changes or sudden demand fluctuations, it is unable to update the control strategy through an online learning mechanism.

[0004] In the context of the rapid development of computer technology, data-driven optimization methods provide a new solution path for the above problems. Especially cluster analysis technology, which can effectively extract operating condition feature patterns by reconstructing the feature space of multi-source heterogeneous data.

[0005] Therefore, an online optimization method for the energy consumption of multiple devices of an air separation unit based on cluster analysis is proposed. Summary of the Invention

[0006] The purpose of the present invention is to provide an online optimization method for the energy consumption of multiple devices of an air separation unit based on cluster analysis. By monitoring the production process according to production planning data, production progress data is obtained, and gas demand data is predicted; the gas demand data is identified through a clustering algorithm to obtain a gas demand subset and determine the gas demand pattern; the time distribution data of the gas demand subset is obtained, and the working cycle of the air separation unit is divided to obtain a regulation cycle; taking the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit within the regulation cycle as constraint conditions, a first energy consumption analysis model is constructed; a second energy consumption analysis model is constructed according to the constraint between the first energy consumption analysis model and the second energy consumption within the regulation cycle; and the air separation unit is regulated in real time according to the second energy consumption analysis model.

[0007] To achieve the above purpose, the present invention provides the following technical solution: An online optimization method for the energy consumption of multiple devices of an air separation unit based on cluster analysis, including:

[0008] S10. Obtain production planning data, monitor the production process according to the production planning data, and obtain production progress data;

[0009] S20. Make a prediction based on the production planning data and the production progress data to obtain gas demand data; the gas demand data is time series data;

[0010] S30. Identify the gas demand data through a clustering algorithm, divide it to obtain gas demand subsets; identify the gas demand subsets to determine gas demand patterns;

[0011] S40. Obtain the time distribution data of the gas demand subsets, divide the working cycle of the air separation unit according to the time distribution data, and obtain a regulation cycle;

[0012] S50. Use the energy consumption of the air separation unit, gas demand subsets, gas demand patterns, and internal coupling parameters of the air separation unit within the regulation cycle as constraint conditions to construct a first energy consumption analysis model;

[0013] S60. Use the second energy consumption between the first energy consumption analysis model and the regulation cycle as a constraint condition to construct a second energy consumption analysis model; perform real-time regulation on the air separation unit according to the second energy consumption analysis model.

[0014] The process of obtaining the gas demand data is as follows:

[0015] Collect production planning data and monitor the production process with the production planning data;

[0016] Divide the production process according to the current moment to obtain a first period and a second period; the first period is the completed production process, and the second period is the production process to be completed;

[0017] Obtain the production data of the first period, including first production parameters and first gas demand parameters; determine the production progress data according to the first production parameters and the production planning data;

[0018] Predict the second production parameters based on the production planning data and the production progress data; use the first production parameters and the first gas demand parameters as references, and determine the second gas demand parameters according to the second production parameters; use the second gas demand parameters as the gas demand data.

[0019] The gas demand data includes gas demand types, gas demand intensities, gas fluctuation data, and gas quality data;

[0020] The process of identifying gas demand subsets from the gas demand data is as follows:

[0021] Identify the gas demand data through a clustering algorithm, and conduct a clustering analysis based on the gas demand type, gas demand intensity, gas fluctuation data, and gas quality data to obtain a gas demand subset.

[0022] The gas demand patterns include a stable demand pattern, a transient demand pattern, and a fluctuating demand pattern;

[0023] The process of determining the gas demand pattern is as follows:

[0024] Identify the data characteristics of the gas demand type, gas demand intensity, gas fluctuation data, and gas quality data in the gas demand subset to obtain a gas demand fluctuation coefficient;

[0025] Set a gas demand fluctuation threshold to identify the gas demand fluctuation coefficient and determine the gas demand pattern.

[0026] The process of constructing the first energy consumption analysis model is as follows:

[0027] Use the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit within the regulation period as constraint conditions; including:

[0028] Use the internal coupling parameters of the air separation unit as the first constraint condition;

[0029] Use the gas demand subset and the gas demand pattern as the second constraint condition;

[0030] Use the energy consumption of the air separation unit within the regulation period as the third constraint condition;

[0031] Set a deviation threshold for the second constraint condition according to the gas demand pattern and the production progress data.

[0032] The internal coupling parameters of the air separation unit are obtained according to the composition equipment and working process of the air separation unit, including:

[0033] Obtain the first coupling data of the air separation unit, and the first coupling data is determined by the coupling relationship between the equipment included in the air separation unit;

[0034] Obtain the second coupling data of the air separation unit, and the second coupling data is determined by the state change of the air during the working process of the air separation unit;

[0035] Obtain the internal coupling data of the air separation unit according to the first coupling data and the second coupling data.

[0036] The process of constructing the second energy consumption analysis model is as follows:

[0037] Obtain the first energy consumption data identified by the first energy consumption analysis model during the adjustment period of the air separation unit;

[0038] Identify the second energy consumption data generated by the transition between different gas demand patterns based on historical data;

[0039] Determine the constraint conditions based on the first energy consumption data and the second energy consumption data, so as to determine the equipment parameters when the energy consumption is minimized during the working cycle of the air separation unit.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] 1. The present invention identifies and predicts production planning data and production progress data, divides the production process according to the current moment, and obtains a first period and a second period; the first period is the completed production process, and the second period is the production process to be completed; using the first production parameters and the first gas demand parameters as references, determine the second gas demand parameters according to the second production parameters; use the second gas demand parameters as gas demand data; it can accurately determine the gas demand according to the production planning data and the production progress data.

[0042] 2. The present invention determines gas demand data through gas demand types, gas demand intensities, gas fluctuation data, and gas quality data; then identifies the gas demand data according to the clustering algorithm, and determines the gas demand subset through the data identification of each data dimension; accurately divides the stages according to the gas demand data; identifies the gas demand fluctuation coefficient for the gas demand data of each stage, and determines the gas demand pattern; thus accurately classifies different gas demand stages and provides a basis for energy consumption optimization.

[0043] 3. The present invention constructs a first energy consumption analysis model with the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit during the regulation period as constraint conditions; constructs a second energy consumption analysis model with the second energy consumption between the first energy consumption analysis model and the regulation period as a constraint condition; thus accurately determines the equipment parameters with the minimum energy consumption during the working cycle of the air separation unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic flow chart of an online optimization method for the multi-device energy consumption of an air separation unit based on clustering analysis according to the present invention;

[0045] Figure 2 It is a schematic diagram for obtaining gas demand data according to the present invention;

[0046] Figure 3 It is a schematic diagram of the structure of the second energy consumption analysis model according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] Embodiment 1

[0049] The present invention proposes an online optimization method for the energy consumption of multiple devices in an air separation unit based on cluster analysis, as Figure 1 shown, including:

[0050] S10. Obtain production planning data, monitor the production process according to the production planning data, and obtain production progress data.

[0051] S20. Make a prediction based on the production planning data and the production progress data to obtain gas demand data; the gas demand data is time series data.

[0052] The process of obtaining the gas demand data is as follows:

[0053] Collect production planning data and monitor the production process with the production planning data;

[0054] Divide the production process according to the current moment to obtain a first period and a second period; the first period is the completed production process, and the second period is the production process to be completed;

[0055] Obtain the production data of the first period, including the first production parameters and the first gas demand parameters; determine the production progress data according to the first production parameters and the production planning data;

[0056] Predict the second production parameters based on the production planning data and the production progress data; use the first production parameters and the first gas demand parameters as references, and determine the second gas demand parameters according to the second production parameters; take the second gas demand parameters as the gas demand data. The process of obtaining the gas demand data is as Figure 2 shown.

[0057] The present invention identifies and predicts the production planning data and the production progress data, divides the production process according to the current moment to obtain a first period and a second period; the first period is the completed production process, and the second period is the production process to be completed; uses the first production parameters and the first gas demand parameters as references, and determines the second gas demand parameters according to the second production parameters; takes the second gas demand parameters as the gas demand data; and can accurately determine the gas demand according to the production planning data and the production progress data.

[0058] S30. Identify the gas demand data through a clustering algorithm, and divide it to obtain gas demand subsets; identify the gas demand patterns for the gas demand subsets.

[0059] The gas demand data includes gas demand types, gas demand intensities, gas fluctuation data, and gas quality data;

[0060] The process of identifying gas demand subsets based on the gas demand data is as follows:

[0061] Identify the gas demand data through a clustering algorithm, perform clustering analysis based on gas demand types, gas demand intensities, gas fluctuation data, and gas quality data, and divide to obtain gas demand subsets.

[0062] Gas demand types refer to the types of gases that can be separated from the air, such as oxygen, nitrogen, and argon, etc.; gas demand intensity describes the average demand for gas during the gas demand subset, including average flow rate and average air pressure; gas fluctuation data describes the fluctuation characteristics of gas demand over time, including fluctuation amplitude and fluctuation frequency, which helps optimize the timing and quantity of gas supply; gas quality data describes the characteristics of gas composition, purity, humidity, etc., to ensure the smooth progress of the production process.

[0063] The present invention determines gas demand data through gas demand types, gas demand intensities, gas fluctuation data, and gas quality data; then identifies the gas demand data through a clustering algorithm, and determines gas demand subsets based on the data identification conditions of each data dimension; accurately divides according to the gas demand data.

[0064] The gas demand patterns include a stable demand pattern, a transient demand pattern, and a fluctuating demand pattern;

[0065] The process of determining the gas demand pattern is as follows:

[0066] Identify the data characteristics of gas demand types, gas demand intensities, gas fluctuation data, and gas quality data in the gas demand subsets to obtain a gas demand fluctuation coefficient;

[0067] Set a gas demand fluctuation threshold to identify the gas demand fluctuation coefficient and determine the gas demand pattern.

[0068] The calculation process of the gas fluctuation coefficient is as follows:

[0069] ;

[0070] Wherein, represents the gas fluctuation coefficient; represents the first gas fluctuation factor; Represents the first gas fluctuation weight; Represents the second gas fluctuation factor; Represents the second gas fluctuation weight.

[0071] The first gas fluctuation factor reflects the data differences between different subsets of gas demands, and is obtained by balancing the time spans of the current gas demand subset and the historical gas demand subset, and then according to the data similarity;

[0072] The second gas fluctuation factor reflects the gas fluctuations within the current gas demand subset, and its calculation formula is:

[0073] ;

[0074] Wherein, Represents the demand intensity factor of the gas Identified according to the gas demand intensity; Represents the gas Fluctuation characteristic factor, identified according to the gas fluctuation data; Represents the gas Quality fluctuation factor, identified according to the gas quality data; Represents the gas Internal fluctuation weight; Represents the gas demand intensity threshold; Represents the number of gas types.

[0075] The process of determining the gas demand pattern according to the gas demand fluctuation threshold is:

[0076] ;

[0077] Wherein, Represents the gas demand pattern; Represents the first gas demand fluctuation threshold; Represents the second gas demand fluctuation threshold; when Takes the value of 1, it is a stable demand pattern; when Takes the value of 2, it is a fluctuating demand pattern; when Takes the value of 3, it is a transient demand pattern.

[0078] The present invention identifies the data characteristics of the gas demand types, gas demand intensity, gas fluctuation data and gas quality data in the gas demand subset to obtain the gas demand fluctuation coefficient; sets the gas demand fluctuation threshold to identify the gas demand fluctuation coefficient, and determines the gas demand pattern; including stable demand pattern, transient demand pattern and fluctuating demand pattern; thus accurately classifying different gas demand stages and providing a basis for energy consumption optimization.

[0079] S40. Obtain the time distribution data of the gas demand subset, divide the working cycle of the air separation unit according to the time distribution data, and obtain the regulation cycle.

[0080] S50. Construct a first energy consumption analysis model with the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit within the regulation cycle as constraint conditions.

[0081] The construction process of the first energy consumption analysis model is as follows:

[0082] Take the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit within the regulation cycle as constraint conditions; including: taking the internal coupling parameters of the air separation unit as the first constraint condition; taking the gas demand subset and the gas demand pattern as the second constraint condition; taking the energy consumption of the air separation unit within the regulation cycle as the third constraint condition; and setting a deviation threshold for the second constraint condition according to the gas demand pattern and the production progress data.

[0083] The internal coupling parameters of the air separation unit are obtained according to the composition equipment and working process of the air separation unit, including: obtaining the first coupling data of the air separation unit, where the first coupling data is determined by the coupling relationship between the equipment included in the air separation unit; obtaining the second coupling data of the air separation unit, where the second coupling data is determined by the state change of air during the working process of the air separation unit; and obtaining the internal coupling data of the air separation unit according to the first coupling data and the second coupling data.

[0084] The present invention determines the first coupling data by the coupling relationship between the equipment included in the air separation unit, determines the second coupling data by the state change of air during the working process of the air separation unit, and obtains the internal coupling parameters of the air separation unit; then takes the internal coupling parameters of the air separation unit as the first constraint condition; takes the gas demand subset and the gas demand pattern as the second constraint condition, and sets a deviation threshold for the second constraint condition according to the gas demand pattern and the production progress data; takes the energy consumption of the air separation unit within the regulation cycle as the third constraint condition; thereby achieving the optimal energy consumption within the regulation cycle while meeting the gas demand.

[0085] S60. Construct a second energy consumption analysis model with the second energy consumption between the first energy consumption analysis model and the regulation cycle as a constraint condition; and perform real-time regulation on the air separation unit according to the second energy consumption analysis model.

[0086] The composition of the second energy consumption analysis model is as Figure 3 shown, and the construction process is as follows:

[0087] Obtain the first energy consumption data identified by the first energy consumption analysis model within the adjustment period of the air separation unit; identify the second energy consumption data generated by the transition between different gas demand patterns according to historical data; determine the constraint conditions based on the first energy consumption data and the second energy consumption data, so as to determine the equipment parameters when the energy consumption is minimized within the working period of the air separation unit.

[0088] This application obtains the first energy consumption data identified by the first energy consumption analysis model within the adjustment period of the air separation unit; identifies the second energy consumption data generated by the transition between different gas demand patterns according to historical data; determines the constraint conditions based on the first energy consumption data and the second energy consumption data, so as to accurately determine the equipment parameters when the energy consumption is minimized within the working period of the air separation unit.

[0089] This application monitors the production process according to the production planning data to obtain the production progress data, and predicts the gas demand data; identifies the gas demand data through the clustering algorithm to obtain the gas demand subset and determine the gas demand pattern; obtains the time distribution data of the gas demand subset, and divides the working period of the air separation unit to obtain the regulation period; constructs the first energy consumption analysis model with the energy consumption, gas demand subset, gas demand pattern, and internal coupling parameters of the air separation unit within the regulation period as the constraint conditions; constructs the second energy consumption analysis model with the second energy consumption between the first energy consumption analysis model and the regulation period as the constraint condition; and performs real-time regulation on the air separation unit according to the second energy consumption analysis model.

[0090] Embodiment 2

[0091] As an indispensable core equipment in the metallurgical industry, the air separation unit mainly separates the main components in the air through the low-temperature rectification method or the pressure swing adsorption method; the air separation unit has the characteristics of high energy consumption, strong coupling, high safety risk, large operating condition fluctuations, and long-term operation; the energy efficiency problem of the air separation unit has a significant impact on the overall production efficiency and energy consumption.

[0092] The present invention proposes a multi-equipment energy consumption online optimization method for an air separation unit based on cluster analysis, which is used for online optimization of the energy consumption of the air separation unit in the steel smelting process; it includes:

[0093] S10. Obtain the production planning data, and monitor the production process according to the production planning data to obtain the production progress data.

[0094] Obtain the production planning data of steel smelting, and monitor the production process according to the production planning data to obtain the current production progress.

[0095] S20. Predict the gas demand data according to the production planning data and the production progress data; the gas demand data is time series data.

[0096] The process of obtaining the gas demand data is as follows:

[0097] Collect production planning data and monitor the production process with the production planning data;

[0098] Divide the production process according to the current moment to obtain a first period and a second period; the first period is the completed production process, and the second period is the production process to be completed;

[0099] Obtain the production data of the first period, including first production parameters and first gas demand parameters; determine the production progress data according to the first production parameters and the production planning data;

[0100] The first production parameters include important parameters in the iron and steel smelting process, including:

[0101] The output of blast furnace ironmaking, usually measured by the weight of iron ore processed per hour; the furnace temperature, the temperature inside the blast furnace, and the oxygen consumption is closely related to the temperature; the furnace gas composition, the gas produced by the blast furnace contains carbon monoxide, carbon dioxide, nitrogen, etc., and the composition and pressure of these gases are crucial for operation control, etc.;

[0102] The first gas demand parameter is the gas demand data during the production process of the first production parameters; during the iron and steel smelting process, the gas supply support provided by the air separation unit usually includes the following aspects:

[0103] Oxygen supply, oxygen is used to blow into the furnace during blast furnace smelting to improve the combustion efficiency, increase the furnace temperature, and promote the reduction reaction of iron ore; nitrogen supply, nitrogen is often used as a cooling and protective gas in blast furnace operation to prevent the oxidation of metals in the furnace; argon supply, argon as a protective gas can isolate oxygen and other impurity gases in the air to prevent metal oxidation, and at the same time in the converter or electric furnace, argon can also protect the furnace lining from being corroded by high-temperature metals or slag.

[0104] Predict the second production parameters based on the production planning data and the production progress data; determine the second gas demand parameter according to the second production parameters with the first production parameters and the first gas demand parameters as references; use the second gas demand parameter as the gas demand data.

[0105] The present invention identifies and predicts the production planning data and the production progress data, divides the production process according to the current moment to obtain a first period and a second period; the first period is the completed production process, and the second period is the production process to be completed; determines the second gas demand parameter according to the second production parameters with the first production parameters and the first gas demand parameters as references; uses the second gas demand parameter as the gas demand data; and can accurately determine the gas demand according to the production planning data and the production progress data.

[0106] S30. Identify the gas demand data through a clustering algorithm, divide it to obtain gas demand subsets; identify the gas demand patterns for the gas demand subsets.

[0107] The gas demand data includes gas demand types, gas demand intensities, gas fluctuation data, and gas quality data;

[0108] The process of identifying gas demand subsets based on the gas demand data is as follows:

[0109] Identify the gas demand data through a clustering algorithm, perform cluster analysis based on gas demand types, gas demand intensities, gas fluctuation data, and gas quality data, and divide to obtain gas demand subsets.

[0110] Gas demand types refer to the types of gases that can be separated from the air, such as oxygen, nitrogen, and argon, etc.; gas demand intensity describes the average demand for gas during the gas demand subset period, including average flow rate and average air pressure; gas fluctuation data describes the fluctuation characteristics of gas demand over time, including fluctuation amplitude and fluctuation frequency, which helps optimize the timing and quantity of gas supply; gas quality data describes the characteristics of gas composition, purity, humidity, etc., to ensure the smooth progress of the production process.

[0111] By identifying the gas demand data of the steel smelting process, Table 1 is obtained.

[0112] Table 1 Gas Demand Data Table

[0113]

[0114] The present invention determines gas demand data through gas demand types, gas demand intensities, gas fluctuation data, and gas quality data; then identifies the gas demand data according to the clustering algorithm, and determines gas demand subsets based on the data identification conditions of each data dimension; accurately divides the stages according to the gas demand data.

[0115] The gas demand patterns include a stable demand pattern, a transient demand pattern, and a fluctuating demand pattern;

[0116] The process of determining the gas demand pattern is as follows:

[0117] Identify the data characteristics of gas demand types, gas demand intensities, gas fluctuation data, and gas quality data in the gas demand subset to obtain a gas demand fluctuation coefficient;

[0118] Set a gas demand fluctuation threshold to identify the gas demand fluctuation coefficient and determine the gas demand pattern.

[0119] The calculation process of the gas fluctuation coefficient is as follows:

[0120] ;

[0121] wherein, represents the gas fluctuation coefficient; represents the first gas fluctuation factor; represents the first gas fluctuation weight; represents the second gas fluctuation factor; represents the second gas fluctuation weight.

[0122] The first gas fluctuation factor reflects the data difference between different gas demand subsets, which is obtained by balancing the time span between the current gas demand subset and the historical gas demand subset and then according to the data similarity;

[0123] The second gas fluctuation factor reflects the gas fluctuation within the current gas demand subset, and its calculation formula is:

[0124] ;

[0125] wherein, represents the demand intensity factor of the gas and is identified according to the gas demand intensity; represents the fluctuation characteristic factor of the gas and is identified according to the gas fluctuation data; represents the quality fluctuation factor of the gas and is identified according to the gas quality data; represents the internal fluctuation weight of the gas ; represents the gas demand intensity threshold; represents the number of gas types.

[0126] The process of determining the gas demand pattern according to the gas demand fluctuation threshold is as follows:

[0127] ;

[0128] wherein, represents the gas demand pattern; represents the first gas demand fluctuation threshold; represents the second gas demand fluctuation threshold; when takes the value of 1, it is a stable demand pattern; when takes the value of 2, it is a fluctuating demand pattern; when takes the value of 3, it is a transient demand pattern.

[0129] The present invention identifies the data characteristics of the types of gas demand, gas demand intensity, gas fluctuation data, and gas quality data in the gas demand subset to obtain a gas demand fluctuation coefficient; sets a gas demand fluctuation threshold to identify the gas demand fluctuation coefficient and determines the gas demand pattern; including a stable demand pattern, a transient demand pattern, and a fluctuating demand pattern; thereby accurately classifying different gas demand stages and providing a basis for energy consumption optimization.

[0130] S40. Obtain the time distribution data of the gas demand subset, and divide the working cycle of the air separation unit according to the time distribution data to obtain a regulation cycle.

[0131] S50. Using the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit within the regulation cycle as constraint conditions, construct a first energy consumption analysis model.

[0132] The construction process of the first energy consumption analysis model is as follows:

[0133] Using the energy consumption of the air separation unit, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit within the regulation cycle as constraint conditions; including:

[0134] Taking the internal coupling parameters of the air separation unit as the first constraint condition; taking the gas demand subset and the gas demand pattern as the second constraint condition; taking the energy consumption of the air separation unit within the regulation cycle as the third constraint condition; according to the gas demand pattern and the production progress data, set a deviation threshold for the second constraint condition. The deviation threshold is used to balance the relationship between the production progress and the gas demand standard.

[0135] The internal coupling parameters of the air separation unit are obtained according to the composition equipment and working process of the air separation unit, including:

[0136] Obtain the first coupling data of the air separation unit, where the first coupling data is determined by the coupling relationship between the equipment included in the air separation unit; obtain the second coupling data of the air separation unit, where the second coupling data is determined by the state change of the air during the working process of the air separation unit; obtain the internal coupling data of the air separation unit according to the first coupling data and the second coupling data.

[0137] Through the identification of the first coupling data and the second coupling data, obtain coupling characteristic data, where the coupling characteristic data includes: thermodynamic coupling, fluid network coupling, control logic coupling, safety constraint coupling, material balance coupling.

[0138] Thermodynamic coupling involves the energy exchange between different units, such as how the heat generated by the compressor is utilized by other parts, or how the temperature gradient in the distillation column affects the efficiency of other equipment.

[0139] The coupling of fluid networks may involve changes in pressure, flow rate, and phase state, and it is necessary to analyze the pressure balance and flow rate distribution at each node; for example, air is compressed and then enters the precooling system, then enters the molecular sieve, and finally enters the rectification column.

[0140] The coupling of control logic includes that each subsystem of the air separation unit needs to be coordinated and controlled, such as pressure control, temperature control, liquid level control, etc.; there may be mutual influences between these control loops. For example, adjusting the reflux ratio of one column may affect the pressure of another column, and it is necessary to analyze the interaction of control strategies and overall stability.

[0141] The coupling of safety constraints involves the safe operation of the entire system, such as the setting of safety valves for pressure vessels, explosion-proof measures for oxygen concentration, and anti-freezing protection for low-temperature equipment. These safety measures need to be closely combined with process parameters and control logic to ensure that the system can be safely shut down or adjusted in case of abnormalities.

[0142] The coupling of material balance refers to the mass conservation of each component in the entire system; for example, the material balance of the rectification column will affect the product purity and recovery rate, and it is necessary to analyze the material flow and distribution between each column, and how to maintain the balance by adjusting operating parameters.

[0143] The present invention determines the first coupling data based on the coupling relationship between the devices included in the air separation unit, determines the second coupling data based on the state change of air during the operation of the air separation unit, and obtains the internal coupling parameters of the air separation unit; then uses the internal coupling parameters of the air separation unit as the first constraint condition; uses the gas demand subset and gas demand pattern as the second constraint condition, and sets a deviation threshold for the second constraint condition according to the gas demand pattern and production progress data; uses the energy consumption of the air separation unit during the regulation period as the third constraint condition; thus, on the basis of meeting the gas demand, the optimal energy consumption during the regulation period is achieved.

[0144] S60. Construct a second energy consumption analysis model based on the first energy consumption analysis model and the second energy consumption during the regulation period as constraint conditions; perform real-time regulation on the air separation unit according to the second energy consumption analysis model.

[0145] The construction process of the second energy consumption analysis model is as follows:

[0146] Obtain the first energy consumption data identified by the first energy consumption analysis model during the adjustment period of the air separation unit;

[0147] Identify the second energy consumption data generated by the transition between different gas demand patterns according to historical data;

[0148] Determine the constraint conditions based on the first energy consumption data and the second energy consumption data, so as to determine the equipment parameters when the energy consumption is minimized during the operation period of the air separation unit.

[0149] To verify the energy consumption optimization effect of the present invention, a comparison scheme is selected for verification; the comparison scheme is a static optimization strategy based on a physical model, which is calculated based on working conditions and parameters without considering dynamic changes; Table 2 is obtained after multiple rounds of verification; where the production completion degree refers to the production progress completed within the specified time; the energy consumption comparison takes the energy consumed by the present application obtained from each verification as the reference standard, and then obtains the ratio of the energy consumption of the comparison scheme for comparison.

[0150] Table 2 Verification Data Table of the Comparison Scheme

[0151]

[0152] It can be seen from Table 2 that the method of the present application can optimize the energy consumption in real time on the basis of ensuring the completion progress of the production task, and the optimization effect is higher than that of the comparison scheme.

[0153] The present application obtains the first energy consumption data identified by the first energy consumption analysis model within the adjustment period of the air separation unit; identifies the second energy consumption data generated by the transition between different gas demand patterns according to historical data; determines the constraint conditions according to the first energy consumption data and the second energy consumption data, so as to accurately determine the equipment parameters when the energy consumption is the smallest within the working period of the air separation unit.

[0154] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An online optimization method for energy consumption of multiple devices in an air separation unit based on cluster analysis, characterized in that: include: S10. Obtain production planning data, monitor the production process according to the production planning data, and obtain production progress data; S20. Predicting based on production planning data and production progress data to obtain gas demand data; the gas demand data is time series data; S30. Identify the gas demand data by clustering algorithm and divide it into gas demand subsets; identify the gas demand subsets and determine the gas demand pattern; S40. Obtaining the time distribution data of the gas demand subset, dividing the working cycle of the air separation unit according to the time distribution data, and obtaining the control cycle; S50. Taking the energy consumption of the air separation unit within the control period, the gas demand subset, the gas demand pattern, and the internal coupling parameters of the air separation unit as constraints, a first energy consumption analysis model is constructed; The construction process of the first energy consumption analysis model is as follows: The energy consumption, gas demand subset, gas demand pattern, and internal coupling parameters of the air separation unit within the regulation cycle are taken as constraints; including: The internal coupling parameters of the air separation unit are taken as the first constraint condition; The gas demand subset and the gas demand pattern are used as the second constraint; The energy consumption of the air separation unit within the regulation period is taken as the third constraint; setting a deviation threshold for the second constraint condition based on the gas demand pattern and production schedule data; The internal coupling parameters of the air separation unit are obtained according to the components and working process of the air separation unit, including: Acquire first coupling data of the air separation unit, where the first coupling data is determined by a coupling relationship between devices included in the air separation unit; Acquire second coupling data of the air separation unit, where the second coupling data is determined by a state change of air during operation of the air separation unit; Obtaining internal coupling data of the air separation unit according to the first coupling data and the second coupling data; S60. Based on the first energy consumption analysis model and the second energy consumption between the control cycles as a constraint condition, a second energy consumption analysis model is constructed; and the air separation unit is controlled in real time according to the second energy consumption analysis model; The construction process of the second energy consumption analysis model is as follows: Acquire first energy consumption data identified by a first energy consumption analysis model within an adjustment period of the air separation unit; Obtaining second energy consumption data generated by the transition between different gas demand modes according to historical data identification; The constraint condition is determined according to the first energy consumption data and the second energy consumption data, so as to determine the equipment parameters when the energy consumption is the minimum during the working cycle of the air separation unit.

2. The method for online optimization of energy consumption of multiple devices in an air separation unit based on cluster analysis according to claim 1 is characterized in that: The process of obtaining the gas demand data is as follows: Collecting production planning data, and monitoring the production process with the production planning data; The production process is divided according to the current moment to obtain a first period and a second period; the first period is the completed production process, and the second period is the production process to be completed; Acquiring production data for a first period, including a first production parameter and a first gas demand parameter; Determine production schedule data according to the first production parameter and the production planning data; A second production parameter is predicted based on the production planning data and the production progress data; a second gas demand parameter is determined based on the second production parameter with reference to the first production parameter and the first gas demand parameter; and the second gas demand parameter is used as gas demand data.

3. The method for online optimization of energy consumption of multiple devices in an air separation unit based on cluster analysis according to claim 1 is characterized in that: The gas demand data includes gas demand type, gas demand intensity, gas fluctuation data and gas quality data; The process of identifying and obtaining the gas demand subset according to the gas demand data is as follows: The gas demand data is identified through a clustering algorithm, and cluster analysis is performed based on the gas demand type, gas demand intensity, gas fluctuation data, and gas quality data to obtain gas demand subsets.

4. The method for online optimization of energy consumption of multiple devices in an air separation unit based on cluster analysis according to claim 1 is characterized in that: The gas demand mode includes a stable demand mode, a transient demand mode and a fluctuating demand mode; The process of determining the gas demand mode is as follows: Identify the data features of gas demand type, gas demand intensity, gas fluctuation data and gas quality data in the gas demand subset to obtain the gas demand fluctuation coefficient; A gas demand fluctuation threshold is set to identify the gas demand fluctuation coefficient and determine the gas demand mode.

Images