Method and apparatus for scheduling air compression system

Abstract

The application discloses a method and device for scheduling an air compression system, and relates to the field of energy. The method comprises the following steps: obtaining power consumption of the air compression system under a plurality of candidate operation state combinations and a plurality of candidate gas flow combinations; determining a target operation state combination and a target gas flow combination from the plurality of candidate operation state combinations and the plurality of candidate gas flow combinations based on the power consumption corresponding to the plurality of candidate operation state combinations and the plurality of candidate gas flow combinations; and adjusting the operation state of each air compressor in the air compression system and the gas flow combination according to the target operation state combination and the target gas flow combination. The method selects the combination with the minimum power consumption from the plurality of candidate operation state combinations and the plurality of candidate gas flow combinations, and schedules the air compression system according to the combination with the minimum power consumption, so that the effect of reducing the energy consumption of the air compression system is achieved, and intelligent operation of the air compression system is realized.

Description

Technical Field

[0001] This application relates to the energy field, and in particular to a method and apparatus for scheduling an air compressor system. Background Technology

[0002] Compressed air is the second largest power source after electricity and is widely used in various fields. Currently, most air compressor systems are controlled by stand-alone programmable logic controllers (PLCs). However, when multiple units are operating in parallel, this control method results in asynchronous loading and unloading of the air compressors, uneven load distribution, and continuous venting in some units, leading to energy waste. Therefore, optimizing the operation of air compressor units has become a key focus for enterprises.

[0003] In existing technologies, air compressor units are dispatched by issuing dispatch instructions via telephone, with operators making adjustments based on their personal experience. However, dispatching air compressor units using existing technologies suffers from drawbacks such as low resource utilization and high power consumption in the air compression system. Summary of the Invention

[0004] In view of this, this application provides a method and apparatus for scheduling an air compressor system, thereby reducing the energy consumption of the air compressor system.

[0005] The method for scheduling an air compressor system provided in this application is implemented as follows:

[0006] Obtain the power consumption of the air compressor system under multiple candidate operating state combinations and multiple candidate gas production flow rate combinations;

[0007] Based on the power consumption corresponding to multiple candidate operating state combinations and multiple candidate gas production flow combinations, a target operating state combination and a target gas production flow combination are determined from the multiple candidate operating state combinations and multiple candidate gas production flow combinations. The power consumption corresponding to the target operating state combination and the target gas production flow combination is the minimum among the multiple candidate operating state combinations and multiple candidate gas production flow combinations.

[0008] Based on the target combination of operating states and the target combination of gas production flow, adjust the operating states and gas production flow combinations of each air compressor in the air compressor system.

[0009] Optionally, the multiple candidate operating state combinations include a first candidate operating state combination, and the multiple candidate gas production flow rate combinations include a first candidate gas production flow rate combination. The power consumption of the air compressor system under the multiple candidate operating state combinations and the multiple candidate gas production flow rate combinations is obtained, including:

[0010] The suction pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor in the first candidate gas production flow rate combination are input into the power consumption prediction model. The first air compressor is any air compressor in the first candidate gas production flow rate combination that is in operation.

[0011] The power consumption prediction model is used to process the suction pressure, ambient temperature, discharge pressure and candidate gas production flow of the first air compressor, and output the power consumption of the first air compressor.

[0012] Based on the power consumption of the first air compressor, the power consumption of the air compressor system under the first candidate operating state combination and the first candidate gas production flow rate combination is obtained.

[0013] Optionally, the power consumption prediction model is trained based on the historical intake pressure, historical ambient temperature, historical discharge pressure, historical production flow rate, and historical power consumption of each air compressor in the air compressor system.

[0014] Optionally, the power consumption prediction model is a neural network model.

[0015] Optionally, based on the power consumption corresponding to multiple candidate operating state combinations and multiple candidate gas production flow rate combinations, a target operating state combination and a target gas production flow rate combination are determined from the multiple candidate operating state combinations and multiple candidate gas production flow rate combinations, including:

[0016] Based on the fitness of each candidate population in multiple candidate populations, the target population is determined from the multiple candidate populations. Each candidate population represents an air compressor system under a candidate operating state combination. Each individual in the candidate population represents an air compressor in the air compressor system. The fitness represents the power consumption corresponding to the candidate population.

[0017] Optionally, before determining the target population from multiple candidate populations based on the fitness of each candidate population, the method further includes:

[0018] Crossover and mutation operations are performed on the codes of each individual in the initial population to obtain a candidate population. The code of each individual represents the operating status of the air compressor corresponding to that individual.

[0019] Optionally, based on the power consumption corresponding to multiple candidate operating state combinations and multiple candidate gas production flow rate combinations, a target operating state combination and a target gas production flow rate combination are determined from the multiple candidate operating state combinations and multiple candidate gas production flow rate combinations, including:

[0020] Based on the power consumption, required air supply, minimum air output of each air compressor, and maximum air output of each air compressor corresponding to multiple candidate operating state combinations and multiple candidate air output flow combinations, a target operating state combination and a target air output flow combination are determined from the multiple candidate operating state combinations and multiple candidate air output flow combinations. The power consumption corresponding to the target operating state combination and the target air output flow combination is the lowest among the multiple candidate operating state combinations and multiple candidate air output flow combinations, and the target air output flow combination meets the required air supply. Furthermore, the air output flow of each air compressor in the target air output flow combination is within the range of the minimum air output to the maximum air output of the corresponding air compressor.

[0021] This application also provides an apparatus for scheduling an air compressor system, comprising: an acquisition unit, a determination unit, and an adjustment unit;

[0022] The acquisition unit is used to acquire the power consumption of the air compressor system under multiple candidate operating state combinations and multiple candidate gas production flow combinations.

[0023] The acquisition unit is also used to obtain the power consumption of the air compressor system under the first candidate operating state combination and the first candidate gas production flow combination based on the power consumption of the first air compressor, wherein the first air compressor is any air compressor in the first candidate gas production flow combination that is in the operating state.

[0024] The determining unit is used to determine the target operating state combination and the target gas production flow combination from the multiple candidate operating state combinations and the multiple candidate gas production flow combinations based on the power consumption corresponding to the multiple candidate operating state combinations and the multiple candidate gas production flow combinations, wherein the power consumption corresponding to the target operating state combination and the target gas production flow combination is the minimum among the multiple candidate operating state combinations and the multiple candidate gas production flow combinations.

[0025] The determining unit is also used to determine the target population from multiple candidate populations based on the fitness of each candidate population in multiple candidate populations. Each candidate population in multiple candidate populations represents an air compressor system under a candidate operating state combination. Each individual in the candidate population represents an air compressor in the air compressor system. The fitness represents the power consumption corresponding to the candidate population.

[0026] The regulating unit is used to adjust the operating status and gas production flow combination of each air compressor in the air compressor system according to the target operating status combination and the target gas production flow combination.

[0027] Optionally, the device further includes: an input unit, an output unit, or an encoding unit;

[0028] The input unit is used to input the suction pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor in the first candidate gas production flow rate combination into the power consumption prediction model.

[0029] The output unit is used to process the suction pressure, ambient temperature, discharge pressure and candidate gas production flow of the first air compressor through the power consumption prediction model, and output the power consumption of the first air compressor.

[0030] The coding unit is used to perform crossover and mutation operations on the coding of each individual in the initial population to obtain a candidate population. The coding of an individual represents the operating status of the air compressor corresponding to that individual.

[0031] This application also provides a computer device, including: a processor coupled to a memory, the memory storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the processor to enable the computer device to implement a method for scheduling an air compressor system.

[0032] Therefore, the beneficial effects of this application are: it provides a method and apparatus for scheduling an air compressor system, which involves acquiring the power consumption of the air compressor system under multiple candidate operating state combinations and multiple candidate gas production flow combinations, determining a target operating state combination and a target gas production flow combination from the multiple candidate operating state combinations and multiple candidate gas production flow combinations based on the power consumption corresponding to the multiple candidate operating state combinations and multiple candidate gas production flow combinations, wherein the power consumption corresponding to the target operating state combination and the target gas production flow combination is the minimum among the multiple candidate operating state combinations and multiple candidate gas production flow combinations, and adjusting the operating state and gas production flow combination of each air compressor in the air compressor system according to the target operating state combination and the target gas production flow combination. By selecting the combination with the minimum power consumption from the multiple candidate operating state combinations and multiple candidate gas production flow combinations, and scheduling the air compressor system according to the combination with the minimum power consumption, the energy consumption of the air compressor system is reduced, and the intelligent operation of the air compressor system is realized. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0034] Figure 1 This is a flowchart of the first embodiment of this application;

[0035] Figure 2 This is a flowchart of the second embodiment of this application;

[0036] Figure 3 This is a schematic diagram of a neural network model according to this application;

[0037] Figure 4 This is a flowchart of the third embodiment of this application;

[0038] Figure 5 This is a flowchart of the fourth embodiment of this application;

[0039] Figure 6 This is a schematic diagram of an apparatus according to this application;

[0040] Figure 7 This is a schematic diagram of a computer device according to this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] The inventors discovered that the scheduling of air compressor systems using existing technologies depends on the operator's skill level and experience, and the scheduling accuracy has certain deviations and lags. This application reduces the unit's energy consumption and the lag in regulation by selecting the combination with the lowest power consumption from multiple candidate operating state combinations and multiple candidate gas production flow combinations, and scheduling the air compressor system according to the combination with the lowest power consumption.

[0043] In this embodiment of the application, the device for scheduling the compressed air system may include, but is not limited to, computer equipment.

[0044] The computer device may include: a processor coupled to a memory, the memory storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the processor to enable the computer device to implement a method for scheduling an air compressor system.

[0045] Please see Figure 1 The specific steps of the first embodiment of this application are as follows:

[0046] S101: The computer acquires the power consumption of the air compressor system under multiple candidate operating state combinations and multiple candidate gas production flow combinations.

[0047] The air compressor system is an air compression system.

[0048] In some implementations, an optimized scheduling model is pre-built, and the optimized scheduling model is solved based on a genetic algorithm to obtain multiple candidate combinations of operating states and multiple candidate combinations of gas production flow rates.

[0049] In some implementations, a power consumption prediction model is pre-built to obtain the power consumption of the air compressor system under multiple candidate operating state combinations and multiple candidate gas production flow rate combinations. The power consumption prediction model can be built based on a neural network model. The power consumption prediction model is trained based on the historical intake pressure, historical ambient temperature, historical discharge pressure, historical gas production flow rate, and historical power consumption of each air compressor in the air compressor system.

[0050] S102: The computer determines the target operating state combination and the target gas production flow combination from the multiple candidate operating state combinations and the multiple candidate gas production flow combinations based on the power consumption corresponding to the multiple candidate operating state combinations and the multiple candidate gas production flow combinations.

[0051] The power consumption corresponding to the target operating state combination and the target gas production flow rate combination is the lowest among multiple candidate operating state combinations and multiple candidate gas production flow rate combinations.

[0052] S103: The computer adjusts the operating status and gas production flow combination of each air compressor in the air compressor system according to the target operating status combination and the target gas production flow combination.

[0053] In some implementations, the computer sends the target combination of operating states and the target combination of gas production flow to the built-in control system of the air compressor system. The built-in control system of the air compressor system adjusts the operating states and gas production flow combinations of each air compressor in the air compressor system to minimize the energy consumption of the air compressor system.

[0054] In the first embodiment of this application, by selecting the combination with the lowest power consumption from multiple candidate operating state combinations and multiple candidate gas production flow combinations, and scheduling the air compressor system according to the combination with the lowest power consumption, the energy consumption and regulation lag of the air compressor system are reduced, thereby achieving the enterprise's goal of energy saving and consumption reduction and realizing the intelligent operation of the air compressor system.

[0055] In the second embodiment, a detailed description of how to construct the power consumption prediction model is provided; please refer to [link to relevant documentation]. Figure 2 and Figure 3 The specific steps of the second embodiment of this application are as follows:

[0056] S201: The computer acquires historical data on ambient temperature, air compressor intake pressure, air production flow rate, exhaust pressure, and current within a preset time threshold.

[0057] The preset time threshold can be 24 hours, 12 hours, or 36 hours, or it can be set according to actual needs.

[0058] Ambient temperature, air compressor intake pressure, air production flow rate, exhaust pressure, and air compressor current are parameters that have a significant impact on air compressor power consumption. The computer can also obtain other parameters that have a significant impact on air compressor power consumption based on actual needs.

[0059] In some implementations, the computer collects historical data on ambient temperature, air compressor intake pressure, air production flow rate, exhaust pressure, and current within a preset time threshold from a real-time database.

[0060] S202: The computer determines the power consumption of the air compressor based on the current of the air compressor.

[0061] In some implementations, the power consumption of the air compressor is calculated according to the following formula:

[0062] In the formula, P is the power consumption of the air compressor, U is the voltage of the air compressor, and I is the current of the air compressor. The power factor.

[0063] S203: The computer normalizes the input and output datasets.

[0064] The input dataset consists of historical data on ambient temperature, air compressor intake pressure, air production flow rate, and exhaust pressure within a preset time threshold obtained by the computer.

[0065] The output dataset is the power consumption of the air compressor, determined by the computer based on the air compressor's current.

[0066] In some implementations, the input and output datasets are normalized using the following formula, mapping them to [0,1]:

[0067] In the formula, x i For data that has undergone normalization preprocessing, For the normalized data, x max x is the maximum value in the dataset containing the data before normalization. min It is the minimum value in the dataset containing the data before normalization.

[0068] If the ambient temperature in the input dataset is normalized, then x i The first ambient temperature is the temperature before normalization (the first ambient temperature can be any ambient temperature in the input dataset). x represents the first ambient temperature after normalization. max x is the maximum ambient temperature in the input dataset. min The minimum ambient temperature in the input dataset.

[0069] S204: The computer initializes the power consumption prediction model based on the first initial parameters.

[0070] The initial parameters include learning efficiency, maximum number of convergence attempts, and minimum error. Learning efficiency can be set to any value between 0.01 and 0.25, for example, a learning efficiency of 0.075 can be selected, or the learning efficiency can be set according to the actual situation. Maximum number of convergence attempts can be set to 200, or the maximum number of convergence attempts can be set according to the actual situation. Minimum error can be set to 0.000001, or the minimum error can be set according to the actual situation.

[0071] In some implementations, the computer also determines the number of output layer nodes, the number of hidden layer nodes (the number of hidden layer nodes is generally less than the number of output layer nodes minus one) and the number of output layer nodes based on the model's input and output. In this embodiment, the number of output layer nodes is 4, the number of hidden layer nodes is 2, and the number of output layer nodes is 1.

[0072] S205: The computer divides the input and output datasets into training, testing, and validation sets.

[0073] The ratio of training set, test set, and validation set can be set according to actual needs.

[0074] S206: The computer determines whether the maximum number of convergence attempts has been reached.

[0075] If the maximum number of convergence attempts is not reached, execute steps S207-S208; if the maximum number of convergence attempts is reached, execute step S209.

[0076] S207: The computer randomly selects a set of data from the training set, determines the outputs of the hidden layer and the output layer, and determines the error between the output layer output and the expected output.

[0077] The expected output is the data of the output dataset corresponding to the data randomly selected by the computer from the training set.

[0078] The error between the output layer output and the expected output can be the root mean square difference between the output layer output and the expected output, or it can be obtained from other algorithms.

[0079] S208: The computer determines whether the error is less than or equal to the minimum error.

[0080] If the error is less than or equal to the minimum error, then execute S209; if the error is greater than the minimum error, then return to S206.

[0081] S209: The computer is tested using a test set and validated using a validation set to complete the construction of the power consumption prediction model.

[0082] In some implementations, the computer will also update the power prediction model's dataset with real-time data collected from the real-time database, and then dynamically update the power prediction model in real time.

[0083] In the second embodiment of this application, by constructing a power consumption prediction model, the power consumption of each air compressor in the air compressor system under different loads can be predicted. Then, the power consumption of each air compressor is added together to obtain the total power consumption of the air compressor system, which provides data support for the scheduling and control of the air compressor system and guides the optimization direction for scheduling optimization.

[0084] The third embodiment describes how to implement the scheduling of the air compressor system by combining the construction and use of an optimized scheduling model.

[0085] Please see Figure 4 The specific steps of the third embodiment of this application are as follows:

[0086] S401: The computer initializes the optimized scheduling model based on the second initial parameters.

[0087] The second set of initial parameters includes population size, crossover probability, mutation probability, and maximum number of iterations. The population size can be set to 100, or other values ​​as needed. The crossover probability can be set to any value between 0.4 and 0.99, such as 0.65, or other values ​​as needed. The mutation probability can be set to any value between 0.001 and 0.1, such as 0.002, or other values ​​as needed. The maximum number of iterations can be set to 100, or other values ​​as needed.

[0088] In some implementations, the optimization scheduling model includes an objective function with the total power consumption of the air compressor system as the objective, as follows:

[0089] In the formula, PC represents the total power consumption of the compressed air system, and P... i Let be the power consumption of the i-th air compressor, and n be the total number of air compressors in the air compressor system.

[0090] In some other implementations, the optimized scheduling model includes three constraints.

[0091] The first constraint is a gas supply balance constraint:

[0092] In the formula, Q i Let Q be the air production flow rate of the i-th air compressor. N This represents the total gas supply required by the system.

[0093] The second constraint is the gas production constraint: Q min <Qi max .

[0094] In the formula, Q min Let Q be the minimum air output of the i-th air compressor. max Let be the maximum air output of the i-th air compressor.

[0095] The third constraint is a start / stop constraint:

[0096] In the formula, k represents the operating state of the air compressor, 0 represents the off state, and 1 represents the operating state.

[0097] S402: The computer encodes the individuals in the population to obtain the initial population.

[0098] Individuals in a population are like air compressors in an air compressor system; a single individual in a population is like an air compressor within an air compressor system.

[0099] The code represents the operating status of the air compressor corresponding to an individual in the population. The code can be binary or other methods. When using binary encoding, a code of 0 represents that the air compressor corresponding to that individual is off, and a code of 1 represents that the air compressor is running.

[0100] S403: The computer performs crossover and mutation operations on the codes of each individual in the initial population to obtain a candidate population.

[0101] In some implementations, the crossover operation uses single-point crossover, and the mutation operation uses polynomial mutation.

[0102] S404: The computer determines whether the maximum number of iterations has been reached.

[0103] If the maximum number of iterations has not been reached, execute S405; if the maximum number of iterations has been reached, execute S406.

[0104] S405: The computer predicts the fitness of candidate populations using a power consumption prediction model.

[0105] The candidate population represents an air compressor system in a candidate combination of operating states. Each individual in the candidate population represents an air compressor in the air compressor system.

[0106] Fitness represents the power consumption of the candidate population; the smaller the fitness, the smaller the total power consumption of the compressed air system.

[0107] After S405 is executed, it returns to S404.

[0108] ​In some implementations, the computer inputs the intake pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor in the first candidate gas production flow rate combination into the power consumption prediction model. The power consumption prediction model processes the intake pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor, outputs the power consumption of the first air compressor, and obtains the power consumption of the air compressor system under the first candidate operating state combination and the first candidate gas production flow rate combination based on the power consumption of the first air compressor.

[0109] The first candidate operating state combination is any one of the multiple candidate operating state combinations.

[0110] The first candidate gas production flow combination is any one of the multiple candidate gas production flow combinations.

[0111] The first air compressor is any air compressor in operation among the first candidate gas production flow combinations. In a specific implementation, the total power consumption of the air compressor system is obtained by predicting the power consumption of all air compressors in the system.

[0112] S406: The computer determines the target population from multiple candidate populations based on the fitness of each candidate population.

[0113] In some implementations, the target operating state combination and the target gas production flow combination are determined from multiple candidate operating state combinations and multiple candidate gas production flow combinations based on the power consumption, required gas supply, minimum gas production of each air compressor, and maximum gas production of each air compressor.

[0114] The power consumption corresponding to the target operating state combination and the target gas production flow combination is the lowest among multiple candidate operating state combinations and multiple candidate gas production flow combinations, and the target gas production flow combination meets the required gas supply, and the gas production flow of each air compressor in the target gas production flow combination is within the range of the minimum gas production to the maximum air volume of the corresponding air compressor.

[0115] In other implementations, the computer also uses a roulette wheel selection strategy to determine the target population from multiple candidate populations.

[0116] S407: The computer adjusts the operating status and gas production flow combination of each air compressor in the air compressor system according to the target population.

[0117] In some implementations, the computer adjusts the operating status and gas production flow combination of each air compressor in the air compressor system according to the target combination of operating status and target combination of gas production flow.

[0118] In the third embodiment of this application, by optimizing the scheduling model, the target population can be quickly determined, thereby knowing the load distribution of each air compressor in the air compressor system. Without changing the original PLC control system, the group control of the air compressor system is realized, and the closed-loop control of online adjustment and optimization of the air compressor system is realized.

[0119] The following section describes how to schedule an air compressor system using a specific scenario, taking a system with three air compressors, each with a rated air production flow rate of 95 m³ / h. 3 / min, the required flow rate of the air compressor system is 180m³ / min. 3 / min.

[0120] Please see Figure 5 The specific steps of the fourth embodiment of this application are as follows:

[0121] S501: Computer-initiated optimization scheduling model with a population size of 100, a crossover probability of 0.65, a mutation probability of 0.002, and a maximum number of iterations of 100.

[0122] The objective function for optimizing the scheduling model is: The first constraint is: The second constraint is: 0m 3 / min i <95m 3 / min.

[0123] S502: The computer encodes the individuals in the population to obtain the initial population.

[0124] S503: The computer performs single-point crossover and polynomial mutation operations on the code of each individual in the initial population to obtain a candidate population.

[0125] S504: The computer determines whether the maximum number of iterations has been reached.

[0126] If the maximum number of iterations has not been reached, execute S505; if the maximum number of iterations has been reached, execute S506.

[0127] S505: The computer predicts the fitness of candidate populations using a power consumption prediction model.

[0128] After S505 is executed, it returns to S504.

[0129] S506: The computer determines the target population from multiple candidate populations based on the fitness of each candidate population in the roulette wheel selection strategy.

[0130] Referring to the example in the fourth embodiment, the target population is characterized by the No. 1 air compressor being in operation with a load of 90m. 3 ​ / min, power consumption is 580.7kW, No. 2 air compressor is in the off state, load is 0m 3 / min, power consumption is 0kW, air compressor No. 3 is in operation, load is 90m 3 The power consumption was 566.3kW / min, while the total power consumption of the air compressor system for the target population was 1147kW, which was the lowest among the candidate populations.

[0131] In some implementations, the air compressor system is manually scheduled. The manual scheduling scheme sets air compressor number one to be running with a load of 92m³. 3 The power consumption is 582.37kW, and the No. 2 air compressor is in operation with a load of 88m³ / min. 3 / min, power consumption is 614.24kW, No. 3 air compressor is in the off state, load is 0m 3 / min, with a power consumption of 0kW, the total power consumption of the air compressor system in the manual scheduling scheme is 1196.61kW, which is higher than the total power consumption of the scheduling scheme in the optimized scheduling model.

[0132] S507: The computer adjusts the operating status and gas production flow combination of each air compressor in the air compressor system according to the target population.

[0133] Referring to the example in the fourth embodiment, the computer adjusts the No. 1 air compressor to be in operation, with an air production flow rate of 90m³, based on the target population. 3 / min, adjust air compressor No. 2 to the off state, and the air production flow rate is 0m³ / min. 3 Adjust the No. 3 air compressor to running state with an air production flow rate of 90 m³ / min. 3 / min.

[0134] In the fourth embodiment of this application, the air compressor system is scheduled by optimizing the scheduling model, so that the air compressor system consumes the least amount of energy. This not only shortens the time for manually formulating scheduling plans and adjusting and controlling, but also reduces the company's energy consumption and improves the company's production efficiency and energy utilization rate.

[0135] Please see Figure 6 This application provides a device 600 for scheduling an air compressor system, including: an acquisition unit 601, a determination unit 602, and an adjustment unit 603.

[0136] Acquisition unit 601: used to acquire the power consumption of the air compressor system under multiple candidate operating state combinations and multiple candidate gas production flow combinations.

[0137] Optionally, the acquisition unit 601 is further configured to obtain the power consumption of the air compressor system under the first candidate operating state combination and the first candidate gas production flow combination based on the power consumption of the first air compressor, wherein the first air compressor is any air compressor in the first candidate gas production flow combination that is in the operating state.

[0138] Determining unit 602: Based on the power consumption corresponding to multiple candidate operating state combinations and multiple candidate gas production flow combinations, determine the target operating state combination and the target gas production flow combination from multiple candidate operating state combinations and multiple candidate gas production flow combinations, wherein the power consumption corresponding to the target operating state combination and the target gas production flow combination is the minimum among multiple candidate operating state combinations and multiple candidate gas production flow combinations.

[0139] Optionally, the determining unit 602 is further configured to determine a target population from multiple candidate populations based on the fitness of each candidate population in the multiple candidate populations, where each candidate population represents an air compressor system under a candidate operating state combination, each individual in the candidate population represents an air compressor in the air compressor system, and the fitness represents the power consumption corresponding to the candidate population.

[0140] Adjustment unit 603: Used to adjust the operating status and gas production flow combination of each air compressor in the air compressor system according to the target operating status combination and the target gas production flow combination.

[0141] Optionally, the device may further include an input unit 604, an output unit 605, or an encoding unit 606.

[0142] Input unit 604: used to input the suction pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor in the first candidate gas production flow rate combination to the power consumption prediction model.

[0143] Output unit 605: is used to process the suction pressure of the first air compressor, ambient temperature, discharge pressure of the first air compressor, and candidate gas production flow rate of the first air compressor through a power consumption prediction model, and output the power consumption of the first air compressor.

[0144] Encoding unit 606: used to perform crossover and mutation operations on the encoding of each individual in the initial population to obtain a candidate population. The encoding of an individual represents the operating status of the air compressor corresponding to that individual.

[0145] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0146] It should be noted that the above embodiments of the device for scheduling an air compressor system are only illustrative examples of the division of functional modules to realize the function of scheduling an air compressor system. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device for scheduling an air compressor system can be divided into different functional modules to complete all or part of the functions described above. In addition, the device for scheduling an air compressor system and the method embodiment for scheduling an air compressor system provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0147] Figure 7 This is a schematic diagram of the structure of a computer device 700 provided in an embodiment of this application.

[0148] The computer device 700 includes at least one processor 701, a memory 702, and at least one network interface 703.

[0149] Processor 701 is, for example, a general-purpose central processing unit (CPU), a network processor (NP), a graphics processing unit (GPU), a neural-network processing unit (NPU), a data processing unit (DPU), a microprocessor, or one or more integrated circuits for implementing the embodiments of this application. For example, processor 701 includes application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. A PLD is, for example, a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), generic array logic (GAL), or any combination thereof.

[0150] Memory 702 may be, for example, read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions; random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions; electrically erasable programmable read-only memory (EEPROM); compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, digital universal discs, Blu-ray discs, etc.); magnetic disk storage media or other magnetic storage devices; or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Optionally, memory 702 exists independently and is connected to processor 701 via internal connection 704. Alternatively, memory 702 and processor 701 may be integrated together.

[0151] Network interface 703 uses any transceiver-like device for communicating with other devices or communication networks. Network interface 703 includes, for example, at least one of a wired network interface or a wireless network interface. The wired network interface is, for example, an Ethernet interface. The Ethernet interface is, for example, an optical interface, an electrical interface, or a combination thereof. The wireless network interface is, for example, a wireless local area network (WLAN) interface, a cellular network interface, or a combination thereof.

[0152] In some embodiments, processor 701 includes one or more CPUs, such as Figure 7 CPU0 and CPU1 are shown in the diagram.

[0153] In some embodiments, the computer device 700 may optionally include multiple processors, such as Figure 7 The processors 701 and 705 are shown. Each of these processors is, for example, a single-core processor (CPU) or a multi-core processor (CPU). A processor here may optionally refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0154] In some embodiments, the computer device 700 further includes an internal connection 704. The processor 701, memory 702, and at least one network interface 703 are connected via the internal connection 704. The internal connection 704 includes pathways for transmitting information between the aforementioned components. Optionally, the internal connection 704 is a single board or a bus. Optionally, the internal connection 704 may be divided into an address bus, a data bus, a control bus, etc.

[0155] In some embodiments, the computer device 700 further includes an input / output interface 706. The input / output interface 706 is connected to an internal connection 704.

[0156] In some embodiments, the input / output interface 706 is used to connect to an input device to receive commands or data input by a user through the input device, as described in the above embodiments. Input devices include, but are not limited to, keyboards, touchscreens, microphones, mice, or sensing devices, etc.

[0157] In some embodiments, the input / output interface 706 is also used to connect to an output device. The input / output interface 706 outputs intermediate and / or final results generated by the processor 701 executing the above method embodiments through the output device. The output device includes, but is not limited to, a display, printer, projector, etc.

[0158] Optionally, the processor 701 implements the method in the above embodiments by reading program code stored in the memory 702, or the processor 701 implements the method in the above embodiments by internally stored program code. When the processor 701 implements the method in the above embodiments by reading program code stored in the memory 702, the memory 702 stores program code 710 that implements the method provided in the embodiments of this application.

[0159] For more details on how processor 701 implements the above functions, please refer to the descriptions in the previous method embodiments, which will not be repeated here.

[0160] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0161] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for scheduling an air compressor system, characterized in that, The method includes: The power consumption of the air compressor system is obtained under multiple candidate operating state combinations and multiple candidate gas production flow combinations; wherein, the power consumption is calculated by a power consumption prediction model, which is trained based on the historical intake pressure, historical ambient temperature, historical exhaust pressure, historical gas production flow, and historical power consumption of each air compressor in the air compressor system. Based on the power consumption corresponding to the multiple candidate operating state combinations and the multiple candidate gas production flow combinations, a target operating state combination and a target gas production flow combination are determined from the multiple candidate operating state combinations and the multiple candidate gas production flow combinations. The power consumption corresponding to the target operating state combination and the target gas production flow combination is the minimum among the multiple candidate operating state combinations and the multiple candidate gas production flow combinations. Based on the target combination of operating states and the target combination of gas production flow, adjust the operating states and gas production flow combinations of each air compressor in the air compressor system. The method further includes: scheduling the air compressor system using an optimized scheduling model, wherein the construction process of the optimized scheduling model includes: initializing the optimized scheduling model according to second initial parameters, the second initial parameters including population size, crossover probability, mutation probability, and maximum number of iterations; encoding the individuals in the population to obtain an initial population; performing crossover and mutation operations on the encoding of each individual in the initial population to obtain a candidate population; predicting the fitness of the candidate population using a power consumption prediction model; determining a target population from multiple candidate populations based on the fitness of each candidate population; and adjusting the operating status and gas production flow combination of each air compressor in the air compressor system according to the target population. The optimized scheduling model includes three constraints: The first constraint is a gas supply balance constraint: ; In the formula, Let i be the air production flow rate of the i-th air compressor. This represents the total gas supply required by the system. The second constraint is the gas production constraint: ; In the formula, Let be the minimum air output of the i-th air compressor. Let be the maximum air output of the i-th air compressor; The third constraint is a start / stop constraint: ; In the formula, k represents the operating state of the air compressor, 0 represents the off state, and 1 represents the operating state.

2. The method according to claim 1, characterized in that, The plurality of candidate operating state combinations includes a first candidate operating state combination, and the plurality of candidate gas production flow rate combinations includes a first candidate gas production flow rate combination. The step of obtaining the power consumption of the air compressor system under the plurality of candidate operating state combinations and the plurality of candidate gas production flow rate combinations includes: The suction pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor in the first candidate gas production flow rate combination are input into the power consumption prediction model. The first air compressor is any air compressor in the first candidate gas production flow rate combination that is in operation. The power consumption prediction model processes the intake pressure of the first air compressor, the ambient temperature, the exhaust pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor to output the power consumption of the first air compressor. Based on the power consumption of the first air compressor, the power consumption of the air compressor system under the first candidate operating state combination and the first candidate gas production flow rate combination is obtained.

3. The method according to claim 1, characterized in that, The power consumption prediction model is a neural network model.

4. The method according to claim 1, characterized in that, The step of determining the target operating state combination and the target gas production flow combination from the multiple candidate operating state combinations and the multiple candidate gas production flow combinations based on the power consumption corresponding to the multiple candidate operating state combinations and the multiple candidate gas production flow combinations includes: Based on the fitness of each candidate population in multiple candidate populations, a target population is determined from the multiple candidate populations. Each candidate population represents an air compressor system under a candidate operating state combination. Each individual in the candidate population represents an air compressor in the air compressor system. The fitness represents the power consumption corresponding to the candidate population.

5. The method according to claim 4, characterized in that, Before determining the target population from the multiple candidate populations based on the fitness of each candidate population, the method further includes: Crossover and mutation operations are performed on the codes of each individual in the initial population to obtain the candidate population, where the code of each individual represents the operating status of the air compressor corresponding to that individual.

6. The method according to claim 1, characterized in that, The step of determining the target operating state combination and the target gas production flow combination from the multiple candidate operating state combinations and the multiple candidate gas production flow combinations based on the power consumption corresponding to the multiple candidate operating state combinations and the multiple candidate gas production flow combinations includes: Based on the power consumption, required air supply, minimum air output of each air compressor, and maximum air output of each air compressor corresponding to the multiple candidate operating state combinations and the multiple candidate air output flow combinations, a target operating state combination and a target air output flow combination are determined from the multiple candidate operating state combinations and the multiple candidate air output flow combinations. The power consumption corresponding to the target operating state combination and the target air output flow combination is the lowest among the multiple candidate operating state combinations and the multiple candidate air output flow combinations, and the target air output flow combination meets the required air supply. Furthermore, the air output flow of each air compressor in the target air output flow combination is within the range of the minimum air output to the maximum air output of the corresponding air compressor.

7. A device for scheduling an air compressor system, characterized in that, The device includes: an acquisition unit, a determination unit, and an adjustment unit; The acquisition unit is used to acquire the power consumption of the air compressor system under multiple candidate operating state combinations and multiple candidate gas production flow combinations; wherein, the power consumption is calculated by a power consumption prediction model, which is based on the air compressor's intake pressure, ambient temperature, exhaust pressure and candidate gas production flow as input parameters. The acquisition unit is further configured to obtain the power consumption of the air compressor system under the first candidate operating state combination and the first candidate gas production flow combination based on the power consumption of the first air compressor, wherein the first air compressor is any air compressor in the first candidate gas production flow combination that is in the operating state. The determining unit is configured to determine a target operating state combination and a target gas production flow combination from the multiple candidate operating state combinations and the multiple candidate gas production flow combinations based on the power consumption corresponding to the multiple candidate operating state combinations and the multiple candidate gas production flow combinations, wherein the power consumption corresponding to the target operating state combination and the target gas production flow combination is the minimum among the multiple candidate operating state combinations and the multiple candidate gas production flow combinations. The determining unit is further configured to determine a target population from the multiple candidate populations based on the fitness of each candidate population in the multiple candidate populations, wherein each candidate population represents an air compressor system under a candidate operating state combination, each individual in the candidate population represents an air compressor in the air compressor system, and the fitness represents the power consumption corresponding to the candidate population. The adjustment unit is used to adjust the operating status and gas production flow combination of each air compressor in the air compressor system according to the target operating status combination and the target gas production flow combination. The device for scheduling the air compressor system is further configured to schedule the air compressor system using an optimized scheduling model. The construction process of the optimized scheduling model includes: initializing the optimized scheduling model based on second initial parameters, the second initial parameters including population size, crossover probability, mutation probability, and maximum number of iterations; encoding individuals in the population to obtain an initial population; performing crossover and mutation operations on the encoding of each individual in the initial population to obtain a candidate population; predicting the fitness of the candidate population using a power consumption prediction model; determining a target population from multiple candidate populations based on the fitness of each candidate population; and adjusting the operating status and gas production flow combination of each air compressor in the air compressor system according to the target population. The optimized scheduling model includes three constraints: The first constraint is a gas supply balance constraint: ; In the formula, Let i be the air production flow rate of the i-th air compressor. This represents the total gas supply required by the system. The second constraint is the gas production constraint: ; In the formula, Let be the minimum air output of the i-th air compressor. Let be the maximum air output of the i-th air compressor; The third constraint is a start / stop constraint: ; In the formula, k represents the operating state of the air compressor, 0 represents the off state, and 1 represents the operating state.

8. The apparatus according to claim 7, characterized in that, The device further includes: an input unit, an output unit, or an encoding unit; The input unit is used to input the suction pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor in the first candidate gas production flow rate combination into the power consumption prediction model. The output unit is used to process the suction pressure of the first air compressor, the ambient temperature, the discharge pressure of the first air compressor, and the candidate gas production flow rate of the first air compressor through the power consumption prediction model, and output the power consumption of the first air compressor. The encoding unit is used to perform crossover and mutation operations on the encoding of each individual in the initial population to obtain a candidate population. The encoding of each individual represents the operating status of the air compressor corresponding to that individual.

9. A computer device, characterized in that, The computer device includes: a processor coupled to a memory, the memory storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the processor to enable the computer device to implement the method of any one of claims 1-6.

Images