Multi-agent air compressor intelligent control method, device and equipment and storage medium

Abstract

The invention discloses a multi-agent air compressor intelligent control method, device and equipment and a storage medium. The multi-agent intelligent control method for the air compressor comprises the steps that the current start-stop state and the gas consumption demand of an air compressor set are obtained through a start-stop scheduling agent; the optimal start-stop state corresponding to the air compressor unit is determined through the start-stop scheduling intelligent body based on the current start-stop state and the air consumption requirement of the air compressor unit; and the air compressor unit is intelligently controlled through the pressure control intelligent body based on the optimal start-stop state corresponding to the air compressor unit. According to the embodiment of the invention, the agent driving task can be realized through multi-agent cooperative driving and division of labor, so that the control efficiency of the air compressor can be effectively improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of intelligent control of industrial equipment, and in particular to a multi-agent intelligent control method and device for air compressors, equipment and storage medium. BACKGROUND

[0002] An air compressor (referred to as an air compressor) is a device for compressing gas, which is similar in structure to a water pump. The air compressor can convert the mechanical energy of a prime mover into gas pressure energy, providing a compressed air source for industrial production, medical treatment, construction and other fields.

[0003] In the process of implementing the present application, the applicant found that there are at least the following problems in the prior art:

[0004] In the prior art, the air compressor power-flow curve is fitted by historical data, and an integer programming model is established with the target of "minimum total power". The algorithm (such as genetic algorithm) is manually set to solve, which requires manual intervention of model parameters. Upper and lower threshold values are set to trigger the start and stop of the unit. However, the model training and dispatching control are decoupled, and the pressure control lags behind the actual demand, resulting in low control efficiency of the air compressor. SUMMARY

[0005] The present application provides a multi-agent intelligent control method and device for air compressors, equipment and storage medium, which can be driven by multiple agents to achieve the task of agent driving, thereby effectively improving the control efficiency of the air compressor.

[0006] In a first aspect, embodiments of the present application provide a multi-agent intelligent control method for air compressors, the method comprising:

[0007] obtaining, by a start-stop scheduling agent, a current start-stop state of an air compressor unit and a gas demand;

[0008] determining, by the start-stop scheduling agent, an optimal start-stop state corresponding to the air compressor unit based on the current start-stop state of the air compressor unit and the gas demand;

[0009] intelligently controlling, by a pressure control agent, the air compressor unit based on the optimal start-stop state corresponding to the air compressor unit.

[0010] Preferably, the start-stop scheduling agent determines the optimal start-stop state corresponding to the air compressor unit based on the current start-stop state of the air compressor unit and the gas demand, comprising:

[0011] the start-stop scheduling agent performs gas demand intention recognition on the gas demand to determine whether the current gas demand of the air compressor unit meets a preset gas supply condition;

[0012] If the current air consumption of the air compressor unit meets the preset air supply condition, the current start-stop state of the air compressor unit is determined as the optimal start-stop state corresponding to the air compressor unit by the start-stop scheduling intelligent agent.

[0013] Preferably, the method further comprises:

[0014] If the current air consumption of the air compressor unit does not meet the preset air supply condition, the current running data of the air compressor unit is collected by a data sensor;

[0015] A power consumption prediction model corresponding to the air compressor unit is determined based on the current running data of the air compressor unit by a prediction intelligent agent, and the power consumption prediction model is used to determine power consumption data under different air production according to the running data of the air compressor unit;

[0016] The optimal start-stop state corresponding to the air compressor unit is obtained by inputting the power consumption prediction model corresponding to the air compressor unit, the air consumption requirement and the current start-stop state into an optimization solver through the start-stop scheduling intelligent agent.

[0017] Preferably, the intelligent control of the air compressor unit based on the optimal start-stop state corresponding to the air compressor unit by the pressure control intelligent agent comprises:

[0018] The mother pipe pressure value is collected by a pressure sensor;

[0019] If the mother pipe pressure value is higher than the preset upper threshold, a first control instruction with a higher execution priority than the optimal start-stop state corresponding to the air compressor unit is determined by the pressure control intelligent agent;

[0020] The first control instruction is sent to an execution mechanism by the pressure control intelligent agent, so that the execution mechanism intelligently controls the air compressor unit based on the first control instruction.

[0021] Preferably, the method further comprises:

[0022] If the mother pipe pressure value is lower than the preset lower threshold, a second control instruction with a higher execution priority than the optimal start-stop state corresponding to the air compressor unit is determined by the pressure control intelligent agent;

[0023] The second control instruction is sent to the execution mechanism by the pressure control intelligent agent, so that the execution mechanism intelligently controls the air compressor unit based on the second control instruction.

[0024] Preferably, the method further comprises:

[0025] if the mother pipe pressure value is not higher than the preset upper threshold value and not lower than the preset lower threshold value, a third control instruction is generated by a pressure control agent based on the optimal start-stop state corresponding to the air compression unit;

[0026] The third control instruction is sent by the pressure control agent to the execution mechanism, so that the execution mechanism intelligently controls the air compression unit based on the third control instruction.

[0027] Preferably, the method further comprises:

[0028] The execution state feedback information sent by the execution mechanism is received by the pressure control agent, and the execution state feedback information is sent by the pressure control agent to the start-stop scheduling agent;

[0029] The current start-stop state of the air compression unit is updated by the start-stop scheduling agent based on the execution state feedback information.

[0030] In a second aspect, the embodiments of the present application further provide a multi-agent air compressor intelligent control device, which comprises:

[0031] An acquisition module is configured to acquire, by a start-stop scheduling agent, a current start-stop state of an air compression unit and a gas consumption demand;

[0032] A determination module is configured to determine, by a start-stop scheduling agent, an optimal start-stop state corresponding to the air compression unit based on the current start-stop state of the air compression unit and the gas consumption demand;

[0033] A control module is configured to intelligently control, by a pressure control agent, the air compression unit based on the optimal start-stop state corresponding to the air compression unit.

[0034] In a third aspect, the embodiments of the present application provide an electronic device, which comprises:

[0035] One or more processors;

[0036] A memory configured to store one or more programs,

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the multi-agent air compressor intelligent control method according to any of the embodiments of the present application.

[0038] In a fourth aspect, the embodiments of the present application provide a storage medium having a computer program stored thereon, which, when executed by a processor, implements the multi-agent air compressor intelligent control method according to any of the embodiments of the present application.

[0039] The embodiment of the present application provides a multi-agent air compressor intelligent control method, device, equipment and storage medium, the current start-stop state and the gas demand of the air compressor unit are acquired through the start-stop scheduling agent; the optimal start-stop state corresponding to the air compressor unit is determined through the start-stop scheduling agent based on the current start-stop state and the gas demand of the air compressor unit; the air compressor unit is intelligently controlled through the pressure control agent based on the optimal start-stop state corresponding to the air compressor unit. That is, in the technical solution of the present application, the air compressor unit can be intelligently controlled through multi-agent collaborative division and driving. In the prior art, only a single algorithm is used for driving, the model training and the scheduling control are decoupled, the pressure control lags behind the actual demand, and the air compressor control efficiency is low. Therefore, compared with the prior art, the multi-agent air compressor intelligent control method, device, equipment and storage medium provided by the embodiment of the present application can drive through multi-agent cooperation, and the agent driving task is realized through division, so that the air compressor control efficiency can be effectively improved; and the technical solution of the embodiment of the present application is simple and convenient, easy to popularize, and has a wider application range. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A flowchart of a multi-agent air compressor intelligent control method provided by an embodiment of the present application is shown.

[0041] Figure 2 A flowchart of a multi-agent air compressor intelligent control method provided by another embodiment of the present application is shown.

[0042] Figure 3 A flowchart of a multi-agent air compressor intelligent control method provided by another embodiment of the present application is shown.

[0043] Figure 4 A structural diagram of a multi-agent air compressor intelligent control device provided by an embodiment of the present application is shown.

[0044] Figure 5 A structural diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0045] In order to enable personnel in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0046] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0047] Figure 1 A flowchart of a multi-agent air compressor intelligent control method is provided for an embodiment of the present application. The method can be executed by a multi-agent air compressor intelligent control device or electronic equipment, which can be implemented by software and / or hardware, and can be integrated into any intelligent device with network communication function. As shown in Figure 1 The multi-agent air compressor intelligent control method can include the following steps:

[0048] S101, obtaining the current start-stop state of the air compressor unit and the air consumption demand by the start-stop scheduling agent.

[0049] In this step, the current start-stop state of the air compressor unit can include: running, stopping and standby. The running state means that the air compressor unit is working normally and providing compressed air for the system; the stopping state means that the air compressor unit is in a stopped state and does not produce compressed air; in the standby state, the air compressor unit is not running, but can be started and put into use at any time according to the air consumption demand.

[0050] The air consumption demand of the air compressor unit refers to the actual air consumption demand of the user during the current system operation. The air consumption demand is a dynamic value that can be affected by many factors. For example, in different industrial production scenarios, the demand for compressed air varies greatly at different stages of the production process. When the production line is running at high speed and a large number of pneumatic devices are working together, the air consumption demand will increase significantly; when the production equipment is partially shut down for maintenance or in a low-load running state, the air consumption demand will decrease accordingly.

[0051] S102, determining the optimal start-stop state corresponding to the air compressor unit based on the current start-stop state of the air compressor unit and the air consumption demand by the start-stop scheduling agent.

[0052] In this step, the start-stop scheduling intelligent agent takes the large model as the intelligent center to realize the optimal scheduling of the air compressor unit according to the gas demand.

[0053] S103, intelligently control the air compressor unit based on the optimal start-stop state of the air compressor unit by the pressure control intelligent agent.

[0054] In this step, the pressure control intelligent agent can perform start-stop control through "flow-pressure" cooperation, and the priority of the pressure threshold is higher than that of the flow. When the instruction of the pressure control intelligent agent conflicts with the recommended state (i.e., the optimal start-stop state) of the start-stop scheduling intelligent agent, the pressure control instruction has a higher priority and can interrupt the execution of the scheduling instruction to ensure the safe and stable operation of the system. At the same time, the pressure control intelligent agent feeds back the corrected state to the start-stop scheduling intelligent agent so that it can adjust in subsequent scheduling.

[0055] The multi-agent air compressor intelligent control method proposed in the embodiments of the present application obtains the current start-stop state and gas demand of the air compressor unit through the start-stop scheduling intelligent agent; determines the optimal start-stop state of the air compressor unit based on the current start-stop state and gas demand of the air compressor unit through the start-stop scheduling intelligent agent; and intelligently controls the air compressor unit based on the optimal start-stop state of the air compressor unit through the pressure control intelligent agent. That is, in the technical solution of the present application, the air compressor unit can be intelligently controlled through the collaborative division and driving of multiple intelligent agents. In the prior art, only a single algorithm is used for driving, the model training and scheduling control are decoupled, and the pressure control lags behind the actual demand, resulting in low air compressor control efficiency. Therefore, compared with the prior art, the multi-agent air compressor intelligent control method, device, equipment and storage medium proposed in the embodiments of the present application can drive multiple intelligent agents collaboratively, and the intelligent agent driving tasks are realized through division, so that the air compressor control efficiency can be effectively improved; and the technical solution of the embodiments of the present application is simple and convenient to popularize, and has a wider application range.

[0056] Figure 2 The flowchart of the multi-agent air compressor intelligent control method provided for another embodiment of the present application. Based on the above technical solution, further optimization and expansion can be performed, and can be combined with the above various optional embodiments. As shown in Figure 2 The multi-agent air compressor intelligent control method can include the following steps:

[0057] S201, identify the gas demand intention of the gas demand through the start-stop scheduling intelligent agent to determine whether the current gas demand of the air compressor unit meets the preset gas supply condition.

[0058] In this step, the large model in the start-stop scheduling intelligent agent can receive the current start-stop state S of the air compression unit and the gas demand Q, perform intention recognition on the gas demand, and determine whether the current gas demand exceeds the gas supply capacity of the current unit combination (i.e., the preset gas supply condition). According to the result of intention recognition, the large model determines whether the start-stop scheduling of the unit is needed. If the gas demand does not exceed the current combination gas supply capacity, the current start-stop state is directly output as the recommended state; if it exceeds, the subsequent scheduling process is triggered.

[0059] S202, if the current gas demand of the air compression unit meets the preset gas supply condition, the current start-stop state of the air compression unit is determined as the optimal start-stop state corresponding to the air compression unit through the start-stop scheduling intelligent agent.

[0060] S203, if the current gas demand of the air compression unit does not meet the preset gas supply condition, the current running data of the air compression unit is collected through the data sensor; the power consumption prediction model corresponding to the air compression unit is determined based on the current running data of the air compression unit through the prediction intelligent agent, and the power consumption prediction model is used to determine the power consumption data under different gas production capacities according to the running data of the air compression unit.

[0061] In this step, the prediction intelligent agent uses the large model as the intelligent center to schedule all nodes, realizing the automatic process from data input to model training and selection. After collecting the current running data of the air compression unit through the data sensor, the current running data can be optimized. The large model receives EXCEL or CSV format data and parses the key fields therein, including the instantaneous gas production data, instantaneous power data, running state data (start, stop, etc.) of all air compressors at different time points (minute granularity), and the rated gas production and other rated parameters. First screening and load rate calculation: according to the parsed data, the load rate of each air compressor is calculated; if there is no load rate data in the data, the load rate is obtained by dividing the instantaneous gas production by the rated gas production. Second screening- abnormal value and missing value processing: abnormal value detection: the large model uses Z-score method to detect abnormal values of instantaneous gas production and instantaneous power data. Z-score method judges whether the data is an abnormal value by calculating the deviation of the data point from the mean value; abnormal value processing: for the detected abnormal values, the large model uses linear interpolation method, etc. to process according to the effective data before and after the time point, to ensure the continuity and accuracy of the data; missing value processing: similarly, for the missing data, the large model uses linear interpolation, etc. to complete. Third screening-steady state interval marking: the large model analyzes the data through a sliding window (window size T hours) from the time dimension; the standard deviation of the load rate in the window is calculated, and if the unit running state in the interval does not change, it is determined that the time period is a steady state interval and is marked; then the steady state data is grouped and extracted according to the unit.

[0062] Model automatic training and selection: algorithm calling: the large model autonomously and dynamically calls the built-in machine learning algorithm library, including linear regression (LR), support vector machine (SVM), random forest, gradient boosting tree (GBDT), etc., to fit and train the instantaneous gas production and instantaneous power data of each air compressor. Cross-validation and evaluation: the k-fold cross-validation method is used to evaluate the trained model, and the large model calculates the root mean square error (RMSE) and the mean absolute percentage error (MAPE) of each model. Optimal model selection: the large model autonomously selects the optimal prediction model for each air compressor according to the values of RMSE and MAPE, which can most accurately reflect the power consumption of the air compressor under different gas production.

[0063] S204, calling the optimization solver through the start-stop scheduling agent, and inputting the power consumption prediction model corresponding to the air compressor unit, the gas demand and the current start-stop state into the optimization solver through the start-stop scheduling agent to obtain the optimal start-stop state corresponding to the air compressor unit.

[0064] In this step, the large model in the start-stop scheduling agent calls the optimization solver through function call, and passes the current start-stop state S, gas demand Q and power consumption prediction model of each unit as input to the solver. The optimization model is established to minimize the air-to-electricity ratio of the air compressor unit, that is: ; while satisfying the constraint condition that the gas production is greater than or equal to the gas demand Q, the start-stop state is represented by 0-1 variable. The optimization solver selects a suitable solving algorithm according to the number of air compressor units; when the number of units is less than or equal to 5, the branch and bound method can be used to solve the exact solution; when the number of units is greater than 5, the improved particle swarm algorithm can be used to solve the approximate solution to improve the solving speed. The solver calculates the optimal start-stop state and returns it to the large model, which outputs the state as the recommended start-stop state of the air compressor unit.

[0065] The air compressor intelligent control method of multiple agents proposed in the embodiments of the present application identifies the gas demand through the start-stop scheduling agent, and identifies the gas supply condition according to the gas demand. If the current gas demand of the air compressor unit meets the preset gas supply condition, the current start-stop state of the air compressor unit is determined as the optimal start-stop state corresponding to the air compressor unit through the start-stop scheduling agent; if the current gas demand of the air compressor unit does not meet the preset gas supply condition, the optimization solver is called through the start-stop scheduling agent, and the power consumption prediction model corresponding to the air compressor unit, the gas demand and the current start-stop state are input into the optimization solver through the start-stop scheduling agent to obtain the optimal start-stop state corresponding to the air compressor unit, so as to accurately determine the optimal start-stop state corresponding to the air compressor unit.

[0066] Figure 3A flowchart of a multi-agent intelligent control method of an air compressor is provided for another embodiment of the present application. Based on the above technical solutions, further optimization and expansion can be performed, and the above-mentioned optional embodiments can be combined. As shown in Figure 3 The multi-agent intelligent control method of the air compressor can include the following steps:

[0067] S301, collecting a mother pipe pressure value through a pressure sensor.

[0068] In this step, the pressure sensor transmits the mother pipe pressure P to the pressure control agent in real time. The pressure control agent obtains the current recommended state of the start-stop scheduling agent and continuously judges whether the pressure P is within the preset reasonable interval .

[0069] S302, if the mother pipe pressure value is higher than the preset upper threshold, determining a first control instruction with a higher execution priority than the optimal start-stop state corresponding to the air compressor set through the pressure control agent; and sending the first control instruction to the execution mechanism through the pressure control agent.

[0070] In this step, when the pressure P is higher than the upper threshold , the pressure control agent immediately triggers the unloading logic, sends an unloading instruction (i.e., the first control instruction) to the execution mechanism, which is higher than the recommended state of the start-stop scheduling agent, so that the execution mechanism intelligently controls the air compressor set based on the first control instruction to reduce the gas production to restore the pressure to the reasonable interval.

[0071] S303, if the mother pipe pressure value is lower than the preset lower threshold, determining a second control instruction with a higher execution priority than the optimal start-stop state corresponding to the air compressor set through the pressure control agent; and sending the second control instruction to the execution mechanism through the pressure control agent.

[0072] In this step, when the pressure P is lower than the lower threshold , the pressure control agent triggers the loading logic, sends a loading instruction (i.e., the second control instruction) to the execution mechanism, which is higher than the recommended state, so that the execution mechanism intelligently controls the air compressor set based on the second control instruction to increase the gas production.

[0073] S304, if the mother pipe pressure value is not higher than the preset upper threshold and not lower than the preset lower threshold, generating a third control instruction based on the optimal start-stop state corresponding to the air compressor set through the pressure control agent; and sending the third control instruction to the execution mechanism through the pressure control agent.

[0074] In this step, if the pressure P is within the reasonable interval, the pressure control agent follows the recommended state of the start-stop scheduling agent The adjustment instruction (i.e., the third control instruction) is sent to the actuator, so that the actuator controls the air compressor unit intelligently based on the third control instruction.

[0075] The air compressor intelligent control method of the multi-agent proposed in the embodiment of the application sends the mother pipe pressure value collected by the pressure sensor to the pressure control sensor, so that the pressure control sensor effectively determines the execution control instruction of the air compressor unit matched with the mother pipe pressure value by comparing the range of the mother pipe pressure value, and sends the control instruction to the actuator to make the actuator perform intelligent control on the air compressor unit.

[0076] Preferably, the air compressor intelligent control method of the multi-agent further comprises:

[0077] The execution state feedback information sent by the actuator is received by the pressure control agent, and the execution state feedback information is sent by the pressure control agent to the start-stop scheduling agent; and the current start-stop state of the air compressor unit is updated by the start-stop scheduling agent based on the execution state feedback information.

[0078] In this step, the actuator executes the instruction and feeds back the execution state to the pressure control agent. The pressure control agent corrects the state according to the feedback result and sends the corrected state to the start-stop scheduling agent, so that the start-stop scheduling agent corrects in the subsequent scheduling.

[0079] In summary, the prediction agent, the pressure control agent and the start-stop scheduling agent in the embodiment work cooperatively through the data bus and the function call mechanism, and realize joint management and control of the air compressor unit. Data interaction: the prediction agent sends the power-flow model of each unit to the start-stop scheduling agent and the pressure control agent through the data bus, providing data support for their decision-making; the start-stop scheduling agent sends the optimal start-stop state to the data bus, and the pressure control agent sends the real-time pressure P and the corrected state to the data bus as well. Model iteration: the sensor layer collects the gas production, power, pressure and other operation data of the air compressor unit in real time and transmits them to the prediction agent; the prediction agent updates the model once according to the newly collected data to ensure the accuracy and real-time performance of the model. Scheduling and control: the start-stop scheduling agent scans the gas demand once, calculates the optimal start-stop state according to the prediction model and the gas demand. The pressure control agent monitors the pressure once in a while (fine granularity), and when the pressure is abnormal, the loading or unloading operation of the unit is performed preferentially.

[0080] The embodiment defines a steady-state operation interval quantization standard (continuous T-hour unit state unchanged) through an automatic multi-level data screening mechanism to solve the problem of noise in the input data of the traditional model. Through a dynamic algorithm optimization strategy, the optimal prediction model is automatically selected based on the double indicators of RMSE and MAPE, rather than a fixed algorithm, which is suitable for different unit characteristics. Through a gas-to-power ratio oriented scheduling target, an operational optimization model is established to minimize the gas-to-power ratio, which is different from the traditional total power minimization and is closer to the essence of energy saving. Through a pressure priority control logic, the loading / unloading rules triggered by the pressure threshold are clear, and the priority is higher than the flow scheduling, filling the gap in the safety control of the prior art. Through a multi-agent collaborative architecture, three information interaction interfaces (data bus, function call mechanism) of the intelligent agent are defined to realize a "prediction-scheduling-control" closed loop, rather than a single module running independently. Automatic data screening removes non-steady-state noise, improves the signal-to-noise ratio of the model input data, reduces the RMSE compared with the traditional method, reduces the energy consumption calculation error during scheduling, and avoids "false start and stop". The traditional total power minimization may select "high-power unit low load" (high gas-to-power ratio), and the embodiment directly optimizes the gas-to-power ratio to reduce energy consumption under the same gas consumption. The pressure overrun response time is dynamically changed, the pressure fluctuation amplitude is dynamically changed, the number of equipment start-stop is reduced, and the equipment life is prolonged. The prediction model is automatically iterated, the scheduling algorithm is dynamically adapted, and the pressure control is real-time corrected, without manual intervention, to adapt to long-period continuous working conditions and solve the "parameter rigidity" problem of the traditional system.

[0081] In addition, the embodiment can also integrate the prediction, scheduling and control functions into one module, and use a unified algorithm (such as reinforcement learning) for end-to-end optimization, thereby reducing the module interaction delay. A preset "gas consumption-unit combination" mapping table (such as Start No. 1 unit, Start No. 1 and No. 2 units), instead of operational optimization solution, with fast response speed (table lookup operation) and simple implementation. The pressure is maintained by adjusting the motor speed (variable frequency control), reducing the start-stop frequency and reducing the start-stop loss.

[0082] Figure 4 A structure diagram of the multi-agent air compressor intelligent control device provided by the embodiment of the application is shown in FIG. 1. Figure 4 As shown in FIG. 1, the multi-agent air compressor intelligent control device includes an acquisition module 401, a determination module 402 and a control module 403.

[0083] The acquisition module 401 is configured to acquire the current start-stop state and gas consumption demand of the air compressor unit through the start-stop scheduling agent.

[0084] The determination module 402 is configured to determine the optimal start-stop state corresponding to the air compressor unit based on the current start-stop state and gas consumption demand of the air compressor unit through the start-stop scheduling agent.

[0085] The control module 403 is used to intelligently control the air compressor unit based on the optimal start-stop state of the air compressor unit through the pressure control agent.

[0086] The aforementioned multi-agent intelligent control device for air compressors can execute the methods provided in any embodiment of this application, and possesses the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the multi-agent intelligent control method for air compressors provided in any embodiment of this application.

[0087] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement embodiments of the present invention is shown. For example... Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0088] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0089] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as multi-agent intelligent control methods for air compressors.

[0090] In some embodiments, the multi-agent air compressor intelligent control method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the multi-agent air compressor intelligent control method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the multi-agent air compressor intelligent control method by other any suitable means, e.g., by way of firmware.

[0091] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0092] Computer programs used to implement the methods of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0093] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0094] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device 10 having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device 10. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0095] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), blockchain network, and the Internet.

[0096] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0097] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0098] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A multi-agent intelligent control method for an air compressor, characterized in that, The method includes: The current start / stop status and air consumption demand of the air compressor unit are obtained through the start / stop scheduling intelligent agent. The start / stop scheduling agent determines the optimal start / stop state of the air compressor unit based on the current start / stop state and the air consumption demand. The pressure control agent intelligently controls the air compressor unit based on the optimal start-stop state of the air compressor unit.

2. The method according to claim 1, characterized in that, The step of determining the optimal start / stop state of the air compressor unit through the start / stop scheduling agent based on the current start / stop state of the air compressor unit and the air consumption demand includes: The start / stop scheduling intelligent agent identifies the gas consumption intention of the gas demand to determine whether the current gas consumption of the air compressor unit meets the preset gas supply conditions. If the current air consumption of the air compressor unit meets the preset air supply conditions, then the start-stop scheduling intelligent agent determines the current start-stop state of the air compressor unit as the optimal start-stop state corresponding to the air compressor unit.

3. The method according to claim 2, characterized in that, The method further includes: If the current air consumption of the air compressor unit does not meet the preset air supply conditions, the current operating data of the air compressor unit is collected through a data sensor. The predictive agent determines the power consumption prediction model corresponding to the air compressor unit based on the current operating data of the air compressor unit. The power consumption prediction model is used to determine the power consumption data under different gas production rates based on the operating data of the air compressor unit. The start-stop scheduling agent invokes the optimization solver, and the start-stop scheduling agent inputs the power consumption prediction model corresponding to the air compressor unit, the air consumption demand, and the current start-stop state into the optimization solver to obtain the optimal start-stop state corresponding to the air compressor unit.

4. The method according to claim 1, characterized in that, The intelligent control of the air compressor unit by the pressure control agent based on the optimal start-stop state of the air compressor unit includes: The pressure value of the main pipe is collected by a pressure sensor; If the main pipe pressure value is higher than the preset upper threshold, the pressure control agent determines and executes the first control command with a priority higher than the optimal start-stop state corresponding to the air compressor unit. The pressure control agent sends the first control command to the actuator, so that the actuator can intelligently control the air compressor unit based on the first control command.

5. The method according to claim 4, characterized in that, The method further includes: If the main pipe pressure value is lower than the preset lower threshold, the pressure control agent determines to execute a second control command with a higher priority than the optimal start-stop state corresponding to the air compressor unit. The pressure control agent sends the second control command to the actuator, so that the actuator can intelligently control the air compressor unit based on the second control command.

6. The method according to claim 5, characterized in that, The method further includes: If the main pipe pressure value is not higher than the preset upper threshold and not lower than the preset lower threshold, then the pressure control agent generates a third control command based on the optimal start-stop state of the air compressor unit. The pressure control agent sends the third control command to the actuator, so that the actuator can intelligently control the air compressor unit based on the third control command.

7. The method according to claim 6, characterized in that, The method further includes: The pressure control agent receives execution status feedback information sent by the actuator and sends the execution status feedback information to the start / stop scheduling agent. The start / stop scheduling agent updates the current start / stop status of the air compressor unit based on the execution status feedback information.

8. A multi-agent intelligent control device for an air compressor, characterized in that, The device includes: The acquisition module is used to obtain the current start / stop status and air consumption demand of the air compressor unit through the start / stop scheduling intelligent agent; The determination module is used to determine the optimal start-stop state of the air compressor unit based on the current start-stop state of the air compressor unit and the air consumption demand through the start-stop scheduling intelligent agent; The control module is used to intelligently control the air compressor unit based on the optimal start-stop state of the air compressor unit through a pressure control agent.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the multi-agent intelligent control method for air compressors as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the multi-agent intelligent control method for air compressors as described in any one of claims 1 to 7.

Images