Air compression station multi-device optimal energy efficiency allocation method and system based on multi-source data

Abstract

The application discloses a multi-device optimal energy efficiency distribution method and system of an air compression station based on multi-source data, relates to the technical field of air compression station energy efficiency management distribution, and comprises the following steps: calculating total gas production flow according to workshop gas demand and pipeline pressure drop, and calculating pipeline target pressure according to pipeline resistance, atmospheric pressure and leakage loss; inputting real-time operation data into a preset optimal energy efficiency distribution model, solving the optimal energy efficiency distribution model based on a particle swarm algorithm, and outputting real-time device operation frequency instructions; the objective function of the optimal energy efficiency distribution model is a function of minimizing the total energy consumption of all devices; the calculation model of device energy consumption is a binary function fitted according to nameplate parameters and historical operation data; the variables of the binary function are device load rate and operation frequency; and the constraint conditions of the optimal energy efficiency distribution model include flow balance, pressure fluctuation limitation and device operation frequency range. The application greatly reduces energy consumption and significantly improves the energy efficiency level and pressure stability of the air compression station group.

Description

Technical Field

[0001] This invention relates to the field of energy efficiency management and allocation technology for air compressor stations, and in particular to a method and system for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data. Background Technology

[0002] Traditional air compressor stations employ single-point pressure control and fixed-frequency regulation, failing to balance the dynamic total air production flow with the target pressure, resulting in high energy consumption and poor pressure stability. Furthermore, existing equipment energy consumption models (such as Schneider Electric solutions) rely solely on single equipment nameplate parameters, failing to dynamically correlate operating frequency, load rate, and actual operating conditions, leading to insufficient prediction accuracy. Multi-equipment collaborative allocation strategies (such as parallel compressor load allocation algorithms) ignore differences in equipment energy consumption, causing high-energy-consuming units to operate excessively.

[0003] Therefore, a method and system for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data was developed to solve the above problems. Summary of the Invention

[0004] This invention proposes a method and system for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data, in order to solve the problems of high energy consumption and poor pressure stability in existing air compressor stations.

[0005] The present invention achieves the above objectives through the following technical solutions:

[0006] This invention provides a method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data, including:

[0007] Acquire gas production data and gas consumption data. Gas production data includes equipment nameplate parameters, real-time operating data, and historical operating data. Gas consumption data includes workshop gas demand and pipeline pressure drop. Operating data includes operating frequency, operating power, operating pressure, and operating load.

[0008] Calculate the total gas production flow rate based on the workshop's gas demand and pipeline pressure drop, and calculate the pipeline target pressure based on pipeline resistance, atmospheric pressure, and leakage loss;

[0009] Real-time operating data is input into a preset optimal energy efficiency allocation model. The optimal energy efficiency allocation model is solved based on the particle swarm optimization algorithm, and real-time equipment operating frequency commands are output. The objective function of the optimal energy efficiency allocation model is to minimize the sum of energy consumption of all equipment. The calculation model of equipment energy consumption is a binary function obtained by fitting nameplate parameters and historical operating data. The variables of the binary function are equipment load rate and operating frequency. The constraints of the optimal energy efficiency allocation model include flow balance, pressure fluctuation limit, and equipment operating frequency range.

[0010] Furthermore, the formulas for calculating the total gas production flow rate and the target pipeline pressure are as follows:

[0011] ;

[0012] ;

[0013] in For the total gas production flow rate, For the target pressure of the pipeline, Let J represent the gas demand of the j-th workshop. For pipeline pressure drop, Atmospheric pressure. Let the resistance of the k-th segment of the pipeline be... For leakage losses, M represents the total number of workshops and N represents the total number of pipeline sections.

[0014] Furthermore, the expression for the equipment energy consumption model is as follows:

[0015] ;

[0016] ;

[0017] in For equipment efficiency, For equipment energy consumption, Let η represent the equipment load rate, η∈[0,1], and a, b, c, and d be the model fitting parameters. f is the operating power, and f is the operating frequency.

[0018] Furthermore, a∈[-0.05,0.02], b∈[0.001,0.01], c∈[-0.0005,0.002], d∈[0.8,1.2].

[0019] Furthermore, the expression for the optimal energy efficiency allocation model is as follows:

[0020] ;

[0021] Where i represents the device number, and N1 is the total number of devices. For safety margin factor, The pressure fluctuation range is given by t, where t is the running time. For the pipeline outlet pressure, Let i be the gas production of the i-th device. This represents the total gas demand of all workshops. These are the minimum and maximum values ​​of the device frequency. Let i be the operating frequency of the i-th device. Let t be the equipment load rate of the i-th device, and t be the running time.

[0022] Furthermore, the safety margin factor ranges from 0.02 to 0.05, and the allowable pressure fluctuation range is ±50 Pa.

[0023] Furthermore, in the particle swarm optimization algorithm, the particle dimension is N1×2, corresponding to frequencies respectively. and load factor The fitness function takes the total energy consumption. The reciprocal of the sum, the convergence condition is that the rate of change of the optimal solution is <1% for 50 consecutive generations.

[0024] Furthermore, the particle swarm optimization algorithm is an improved particle swarm optimization algorithm, in which:

[0025] The formula for calculating adaptive inertia weight is:

[0026] w=w_max-(w_max-w_min)*iter / max_iter;

[0027] Dynamic acceleration constant:

[0028] c1=2+0.5sin(iter / max_iter*π),c2=2-0.5cos(iter / max_iter*π);

[0029] The speed update formula is:

[0030] v_id^{k+1}=w*v_id^k+c1*r1*(pbest_id-x_id^k)+c2*r2*(gbest_d-x_id^k);

[0031] The position update formula is: x_id^{k+1}=x_id^k+v_id^{k+1};

[0032] in, Here, w_max is the maximum inertia weight, w_min is the minimum inertia weight, c1 and c2 are acceleration constants, r1 and r2 are random numbers, iter is the iteration number, max_iter is the maximum iteration number, pbest_id is the empirical optimal position of the individual particle, v_id is the velocity, x_id is the position, and k is the current iteration number. Compared to the traditional particle swarm optimization algorithm, the improved particle swarm optimization algorithm, apart from the aforementioned adaptive inertia weight calculation formula, the improved dynamic acceleration constant, and the velocity update formula, retains the same calculation steps. That is, the improved formulas are directly used to replace the corresponding calculation formulas in the traditional particle swarm optimization algorithm.

[0033] Furthermore, the operating data of the equipment is the operating data of the equipment under a load rate of 20%-100%.

[0034] This invention also provides an optimal energy efficiency allocation system for multiple devices in an air compressor station based on multi-source data, comprising:

[0035] The data acquisition module is used to acquire data from the gas production end and the gas consumption end. The gas production end data includes the nameplate parameters of the equipment, real-time operating data, and historical operating data. The gas consumption end data includes the gas demand of the workshop and the pipeline pressure drop. The operating data includes the operating frequency, operating power, operating pressure, and operating load.

[0036] The calculation module is used to calculate the total gas production flow rate based on the gas demand of the workshop and the pipeline pressure drop, and to calculate the target pipeline pressure based on the pipeline resistance, atmospheric pressure and leakage loss.

[0037] The energy efficiency allocation module is used to input real-time operating data into a preset optimal energy efficiency allocation model, solve the optimal energy efficiency allocation model based on the particle swarm optimization algorithm, and output real-time equipment operating frequency commands. The objective function of the optimal energy efficiency allocation model is to minimize the sum of energy consumption of all equipment. The calculation model of equipment energy consumption is a binary function obtained by fitting nameplate parameters and historical operating data. The variables of the binary function are equipment load rate and operating frequency. The constraints of the optimal energy efficiency allocation model include flow balance, pressure fluctuation limit, and equipment operating frequency range.

[0038] The beneficial effects of this invention are as follows:

[0039] The present invention proposes an optimal energy efficiency allocation method and system for multiple devices in an air compressor station based on multi-source data. Through dynamic allocation using an equipment-level energy efficiency model, it greatly reduces energy consumption and significantly improves the energy efficiency level and pressure stability of the air compressor station group. Attached Figure Description

[0040] Figure 1 This is a flowchart of the optimal energy efficiency allocation method for multiple devices in an air compressor station based on multi-source data, as described in this application. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0042] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0043] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0044] like Figure 1 As shown, a method and system for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data includes:

[0045] S1: Acquire gas production end data and gas consumption end data. Gas production end data includes equipment nameplate parameters, real-time operating data, and historical operating data. Gas consumption end data includes workshop gas demand and pipeline pressure drop. Operating data includes operating frequency, operating power, operating pressure, and operating load. The collected multi-source data, namely gas production end data and gas consumption end data, can be preprocessed by the edge computing gateway before entering the subsequent steps.

[0046] S2: Calculate the total gas production flow rate based on the workshop's gas demand and pipeline pressure drop, and calculate the pipeline target pressure based on pipeline resistance, atmospheric pressure, and leakage loss;

[0047] S3: Input real-time operating data into the preset optimal energy efficiency allocation model, solve the optimal energy efficiency allocation model based on particle swarm optimization algorithm, and output real-time equipment operating frequency command. The objective function of the optimal energy efficiency allocation model is to minimize the sum of energy consumption of all equipment. The calculation model of equipment energy consumption is a binary function obtained by fitting the nameplate parameters and historical operating data. The least squares method or a multiple regression algorithm that can achieve the fitting effect can be used for fitting. The variables of the binary function are equipment load rate and operating frequency. The constraints of the optimal energy efficiency allocation model include flow balance, pressure fluctuation limit, and equipment operating frequency range. The flow constraint is that the total gas production flow of the equipment is not less than the total gas demand of the workshop. The pressure constraint is that the pipeline outlet pressure is not less than the difference between the pipeline target pressure and the allowable pressure fluctuation range. The frequency constraint is that the operating frequency of the equipment is within the preset frequency range.

[0048] In one embodiment, the formulas for calculating the total gas production flow rate and the target pipeline pressure are as follows:

[0049] ;

[0050] ;

[0051] in For the total gas production flow rate, For the target pressure of the pipeline, Let J represent the gas demand of the j-th workshop. For pipeline pressure drop, Atmospheric pressure. Let the resistance of the k-th segment of the pipeline be... For leakage losses, M is the total number of workshops and N is the total number of pipeline sections. The pipeline pressure drop is calculated using Darcy's formula, and the standard value of atmospheric pressure is 101325 Pa.

[0052] In one embodiment, the expression for the device energy consumption model is as follows:

[0053] ;

[0054] ;

[0055] in For equipment efficiency, For equipment energy consumption, Let η represent the equipment load rate, η∈[0,1], and a, b, c, and d be the model fitting parameters. f is the operating power, and f is the operating frequency.

[0056] In one embodiment, ad is calibrated by least squares as: a∈[-0.05,0.02], b∈[0.001,0.01], c∈[-0.0005,0.002], d∈[0.8,1.2].

[0057] In one embodiment, the expression for the optimal energy efficiency allocation model is as follows:

[0058] ;

[0059] Where i represents the device number, and N1 is the total number of devices. For safety margin factor, The pressure fluctuation range is given by t, where t is the running time. For the pipeline outlet pressure, Let i be the gas production of the i-th device. This represents the total gas demand of all workshops. These are the minimum and maximum values ​​of the device frequency. Let i be the operating frequency of the i-th device. Let t be the equipment load rate of the i-th device, and t be the running time.

[0060] In one embodiment, the safety margin factor ranges from 0.02 to 0.05, and the allowable pressure fluctuation range is ±50 Pa.

[0061] In one embodiment, the particle dimension in the particle swarm optimization algorithm is N1×2, corresponding to frequencies respectively. and load factor The fitness function takes the total energy consumption. The reciprocal of the sum, the convergence condition is that the rate of change of the optimal solution is <1% for 50 consecutive generations.

[0062] In one embodiment, the particle swarm optimization algorithm of this invention is an improved particle swarm optimization algorithm. Compared with the traditional particle swarm optimization algorithm, the improved particle swarm optimization algorithm of this invention has the following improvements:

[0063] The formula for calculating adaptive inertia weight is:

[0064] w=w_max-(w_max-w_min)*iter / max_iter;

[0065] Dynamic acceleration constant:

[0066] c1=2+0.5sin(iter / max_iter*π),c2=2-0.5cos(iter / max_iter*π);

[0067] The speed update formula is:

[0068] v_id^{k+1}=w*v_id^k+c1*r1*(pbest_id-x_id^k)+c2*r2*(gbest_d-x_id^k);

[0069] The position update formula is: x_id^{k+1}=x_id^k+v_id^{k+1};

[0070] in, For inertia weights, w_max is the maximum inertia weight, w_min is the minimum inertia weight, c1 and c2 are acceleration constants, r1 and r2 are random numbers, iter is the iteration number, max_iter is the maximum iteration number, pbest_id is the empirical optimal position of the individual particle, v_id is the velocity, x_id is the position, k is the current iteration number, and gbest_id is the global optimal position of the entire swarm.

[0071] It should be noted that, apart from the above improvements, the implementation steps of the improved particle swarm algorithm of this invention are consistent with those of the traditional particle swarm algorithm, so the steps of the entire particle swarm algorithm will not be described in detail here.

[0072] Traditional particle swarm optimization (PSO) algorithms use fixed inertia weights, making it difficult to balance global search and local exploration capabilities. The improved algorithm employs linearly decreasing adaptive inertia weights. Larger weights are used in the early stages of iteration to enhance global search capabilities and explore a wider solution space; the weights are reduced in the later stages of iteration to strengthen local search capabilities and achieve precise convergence to the optimal solution. This effectively avoids premature convergence and improves solution accuracy.

[0073] In traditional particle swarm optimization (PSO) algorithms, the learning factor is a fixed value. Improved PSO algorithms introduce a dynamic acceleration constant that varies sinusoidally / cosinely with the iteration number. In the early iterations, c1 is larger, enhancing the particles' ability to learn from their own historical bests and increasing population diversity; in the later iterations, c2 is larger, enhancing the particles' ability to learn from the global optimum of the swarm and accelerating convergence. This dynamic adjustment mechanism improves the algorithm's global optimization capability and convergence speed.

[0074] In one embodiment, the operating data of the device is the operating data of the device at a load rate of 20%-100%.

[0075] In one embodiment, the present invention also provides an optimal energy efficiency allocation system for multiple devices in an air compressor station based on multi-source data, comprising:

[0076] The data acquisition module is used to acquire data from the gas production end and the gas consumption end. The gas production end data includes the nameplate parameters of the equipment, real-time operating data, and historical operating data. The gas consumption end data includes the gas demand of the workshop and the pipeline pressure drop. The operating data includes the operating frequency, operating power, operating pressure, and operating load.

[0077] The calculation module is used to calculate the total gas production flow rate based on the gas demand of the workshop and the pipeline pressure drop, and to calculate the target pipeline pressure based on the pipeline resistance, atmospheric pressure and leakage loss.

[0078] The energy efficiency allocation module is used to input real-time operating data into a preset optimal energy efficiency allocation model, solve the optimal energy efficiency allocation model based on the particle swarm optimization algorithm, and output real-time equipment operating frequency commands. The objective function of the optimal energy efficiency allocation model is to minimize the sum of energy consumption of all equipment. The calculation model of equipment energy consumption is a binary function fitted based on nameplate parameters and historical operating data. The variables of the binary function are equipment load rate and operating frequency. The constraints of the optimal energy efficiency allocation model include flow balance, pressure fluctuation limit, and equipment operating frequency range. The flow constraint is that the total gas production flow of the equipment is not less than the total gas demand of the workshop. The pressure constraint is that the pipeline outlet pressure is not less than the difference between the pipeline target pressure and the allowable pressure fluctuation range. The frequency constraint is that the equipment operating frequency is within a preset frequency range.

[0079] The advantages of this invention compared to the prior art are as follows:

[0080] 1. Energy efficiency optimization: Through dynamic allocation using equipment-level energy efficiency models, overall energy consumption is reduced by 18%-25%;

[0081] 2. Pressure stability: Target pressure fluctuation range ≤ ±0.05 bar (better than ±0.1 bar in the prior art);

[0082] 3. Dynamic adaptability: Supports real-time updates of nameplate parameters, pipeline topology, and load rate, with an adaptability rate of ≥95%.

[0083] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data, characterized in that, include: Acquire gas production data and gas consumption data. Gas production data includes equipment nameplate parameters, real-time operating data, and historical operating data. Gas consumption data includes workshop gas demand and pipeline pressure drop. Calculate the total gas production flow rate based on the workshop's gas demand and pipeline pressure drop, and calculate the pipeline target pressure based on pipeline resistance, atmospheric pressure, and leakage loss; Real-time operating data is input into a preset optimal energy efficiency allocation model. The optimal energy efficiency allocation model is solved based on the particle swarm optimization algorithm, and the real-time equipment operating frequency command is output. The objective function of the optimal energy efficiency allocation model is to minimize the sum of energy consumption of all equipment. The calculation model of equipment energy consumption is a binary function obtained by fitting the nameplate parameters and historical operating data. The variables of the binary function are equipment load rate and operating frequency. The constraints of the optimal energy efficiency allocation model include flow balance, pressure fluctuation limit, and equipment operating frequency range. The formulas for calculating the total gas production flow rate and the target pipeline pressure are as follows: ； ； in For the total gas production flow rate, For the target pressure of the pipeline, Let J represent the gas demand of the j-th workshop. For pipeline pressure drop, Atmospheric pressure. Let the resistance of the k-th segment of the pipeline be... For leakage losses, M represents the total number of workshops and N represents the total number of pipeline sections.

2. The method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data according to claim 1, characterized in that, The expression for the equipment energy consumption model is as follows: ； ； in For equipment efficiency, For equipment energy consumption, Let η represent the equipment load rate, η∈[0,1], and a, b, c, and d be the model fitting parameters. f is the operating power, and f is the operating frequency.

3. The method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data according to claim 2, characterized in that, a∈[-0.05,0.02], b∈[0.001,0.01], c∈[-0.0005,0.002], d∈[0.8,1.2].

4. The method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data according to claim 2, characterized in that, The expression for the optimal energy efficiency allocation model is as follows: ； Where i represents the device number, and N1 is the total number of devices. For safety margin factor, The pressure fluctuation range is given by t, where t is the running time. For the pipeline outlet pressure, Let i be the gas production of the i-th device. This represents the total gas demand of all workshops. These are the minimum and maximum values ​​of the device frequency. Let i be the operating frequency of the i-th device. Let t be the equipment load rate of the i-th device, and t be the running time.

5. The method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data according to claim 4, characterized in that, The safety margin factor ranges from 0.02 to 0.05, and the allowable pressure fluctuation range is ±50 Pa.

6. The method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data according to claim 4, characterized in that, The particle swarm optimization algorithm uses particles with a dimension of N1×2, which correspond to frequencies respectively. and load factor The fitness function takes the total energy consumption. The reciprocal of the sum, the convergence condition is that the rate of change of the optimal solution is <1% for 50 consecutive generations.

7. A method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data, as described in claim 1 or 6, characterized in that, The particle swarm optimization algorithm is an improved version, in which: The formula for calculating adaptive inertia weight is: w=w_max-(w_max-w_min)*iter / max_iter; Dynamic acceleration constant: c1=2+0.5sin(iter / max_iter*π),c2=2-0.5cos(iter / max_iter*π); The speed update formula is: v_id^{k+1}=w*v_id^k+c1*r1*(pbest_id-x_id^k)+c2*r2*(gbest_id-x_id^k); The position update formula is: x_id^{k+1}=x_id^k+v_id^{k+1}; Where w is the inertia weight, w_max is the maximum inertia weight, w_min is the minimum inertia weight, c1 and c2 are acceleration constants, r1 and r2 are random numbers, iter is the iteration number, max_iter is the maximum iteration number, pbest_id is the empirical optimal position of the individual particle, v_id is the velocity, x_id is the position, k is the current iteration number, and gbest_id is the global optimal position of the entire swarm.

8. The method for optimal energy efficiency allocation of multiple devices in an air compressor station based on multi-source data according to claim 1, characterized in that, The operating data of the equipment refers to the operating data of the equipment at a load rate of 20%-100%.

9. A multi-equipment optimal energy efficiency allocation system for an air compressor station based on multi-source data, characterized in that, include: The data acquisition module is used to acquire data from the gas production end and the gas consumption end. The gas production end data includes the nameplate parameters of the equipment, real-time operating data, and historical operating data. The gas consumption end data includes the gas demand of the workshop and the pipeline pressure drop. The calculation module is used to calculate the total gas production flow rate based on the gas demand of the workshop and the pipeline pressure drop, and to calculate the target pipeline pressure based on the pipeline resistance, atmospheric pressure and leakage loss. The energy efficiency allocation module is used to input real-time operating data into a preset optimal energy efficiency allocation model, solve the optimal energy efficiency allocation model based on the particle swarm optimization algorithm, and output real-time equipment operating frequency commands. The objective function of the optimal energy efficiency allocation model is to minimize the sum of energy consumption of all equipment. The calculation model of equipment energy consumption is a binary function obtained by fitting nameplate parameters and historical operating data. The variables of the binary function are equipment load rate and operating frequency. The constraints of the optimal energy efficiency allocation model include flow balance, pressure fluctuation limit, and equipment operating frequency range. The formulas for calculating the total gas production flow rate and the target pipeline pressure are as follows: ； ； in For the total gas production flow rate, For the target pressure of the pipeline, Let J represent the gas demand of the j-th workshop. For pipeline pressure drop, Atmospheric pressure. Let the resistance of the k-th segment of the pipeline be... For leakage losses, M represents the total number of workshops and N represents the total number of pipeline sections.

Images