AI-based compressed air energy supply system data control and processing method and device
Through the data management and processing methods of AI-based artificial intelligence agents and control sub-models, the problem of instability in pressure and flow in compressed air energy supply systems is solved, intelligent monitoring and control are realized, and enterprise energy efficiency and profit margin are improved.
Patent Information
- Application Number
- CN202411241537.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-09-05
AI Technical Summary
The existing technology lacks intelligent monitoring and regulation of compressed air energy supply systems, resulting in inconstant pressure on the pipeline network and unstable flow, reducing the optimization of enterprise energy efficiency and production costs.
Using AI-based artificial intelligence agents and data control processing methods of multiple control sub-models, monitoring the pressure and traffic data of the pipeline network, identifying abnormal data, calling the corresponding target control sub-model to generate task information, and controlling it based on the model prompt information Information generation realizes intelligent monitoring and control of compressed air energy supply system.
It realizes constant changes in pipeline pressure and stable operation of flow, improves enterprise energy efficiency and profit margins, and ensures the stable operation of compressed air energy supply system.
Smart Images

Figure CN118759859B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence data processing technology, and in particular to an AI-based compressed air energy supply system data control and processing method and device. Background Art
[0002] At present, many domestic manufacturing factories use compressed air energy supply systems. However, the existing technology lacks intelligent monitoring of the operation process of the compressed air energy supply system, and cannot detect problems in the compressed air energy supply system in a timely and accurate manner, nor can it be intelligently regulated, making it difficult to maintain a constant change in the pipeline pressure and to keep the flow stable. This greatly reduces the energy efficiency of the enterprise and restricts the further reduction of production costs. Summary of the invention
[0003] In order to solve the above technical problems or at least partially solve the above technical problems, an embodiment of the present invention provides an AI-based compressed air energy supply system data management and processing method and device, which realizes intelligent monitoring and control of the entire compressed air energy supply system to achieve constant changes in pipeline pressure and stable operation of flow, helping enterprises to improve energy efficiency while also increasing their profit margins.
[0004] An embodiment of the present invention provides an AI-based compressed air energy supply system data management and processing method, wherein the artificial intelligence control model combination includes an artificial intelligence agent and multiple control sub-models, and the method includes: the artificial intelligence agent determines whether there is abnormal data based on the pipeline pressure data and pipeline flow data of the compressed air energy supply system; if the abnormal data exists, the artificial intelligence agent determines at least one target control sub-model from the multiple control sub-models to process the problem corresponding to the abnormal data, and generates task information based on the problem processed by the target control sub-model; the target control sub-model receives the task information, understands the task information based on the model prompt information, and generates control information for the problem; wherein: the model prompt information is generated in advance based on the problem that the target control sub-model is responsible for solving.
[0005] An embodiment of the present invention also provides an AI-based compressed air energy supply system data management and processing device, wherein the artificial intelligence control model combination includes an artificial intelligence agent and multiple control sub-models, and the device includes: a determination module, used to determine whether there is abnormal data based on the pipeline pressure data and pipeline flow data of the compressed air energy supply system; a first generation module, used to determine at least one target control sub-model from the multiple control sub-models to handle the problem corresponding to the abnormal data if the abnormal data exists, and generate task information based on the problem handled by the target control sub-model; a second generation module, used to receive the task information, understand the task information based on the model prompt information, and generate control information for the problem; wherein: the model prompt information is generated in advance based on the problem that the target control sub-model is responsible for solving.
[0006] An embodiment of the present invention also provides an electronic device, comprising: one or more processors; a storage device for storing 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 AI-based compressed air energy supply system data management and processing method as described above.
[0007] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it implements the AI-based compressed air energy supply system data management and processing method as described above.
[0008] An embodiment of the present invention also provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, it implements the AI-based compressed air energy supply system data management and processing method as described above.
[0009] The technical solution provided by the embodiment of the present invention has at least the following advantages compared with the prior art: the AI-based compressed air energy supply system data management and processing method and device provided by the embodiment of the present invention realizes the intelligent monitoring and control of the entire compressed air energy supply system to achieve constant changes in pipeline pressure and stable operation of flow, which helps enterprises improve energy efficiency while also increasing their profit margins. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.
[0011] Figure 1It is a flow chart of a data control and processing method of a compressed air energy supply system based on AI in an embodiment of the present invention;
[0012] Figure 2 It is a flow chart of a data control and processing method of a compressed air energy supply system based on AI in another embodiment of the present invention;
[0013] Figure 3 A schematic structural diagram of a data control and processing device for a compressed air energy supply system based on AI in an embodiment of the present invention;
[0014] Figure 4 A schematic structural diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION
[0015] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.
[0016] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.
[0017] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.
[0018] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0019] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0020] refer to Figure 1As shown, an embodiment of the present invention provides a flow chart of a data management and processing method for a compressed air energy supply system based on AI, wherein the artificial intelligence control model combination includes an artificial intelligence agent and multiple control sub-models.
[0021] Here, the model in the AI control model combination refers to an AI model with a large number of parameters and powerful computing power, referred to as a large model. Large models contain a large number of parameters such as weights and biases, which enables them to learn and represent extremely complex patterns and knowledge; they have strong language understanding and generation capabilities, can accurately understand the input text, and generate coherent and logical natural language text responses.
[0022] Although large models are powerful, they may not be flexible enough when facing complex and changeable actual scenarios. Therefore, in the embodiment of the present invention, an artificial intelligence agent is deployed in the artificial intelligence control model. After receiving the pipeline pressure data and pipeline flow data of the compressed air energy supply system, the artificial intelligence agent can analyze the above data and make autonomous decisions on whether there are problems that need to be dealt with, and decompose the problems to generate several tasks, and arrange matching target control sub-models for different tasks to complete them together, thereby improving the efficiency and effectiveness of task execution.
[0023] Step S101, the artificial intelligence agent determines whether there is abnormal data based on the pipeline pressure data and pipeline flow data of the compressed air energy supply system.
[0024] According to the compressed air energy demand of the enterprise, the matching constant pressure of the pipeline network and the constant flow rate between each gas-consuming vehicle are pre-set to ensure the stable operation of the entire compressed air energy supply system. The artificial intelligence agent receives the pipeline pressure data and pipeline flow data of the compressed air energy supply system monitored in real time. When it is determined that the pipeline pressure data and / or pipeline flow data do not match the set value, the inconsistent pipeline pressure data and / or pipeline flow data are identified as abnormal data.
[0025] Once the abnormal data exists, step S102 is executed.
[0026] In step S102, the artificial intelligence agent determines at least one target control sub-model from the multiple control sub-models that processes the problem corresponding to the abnormal data, and generates task information according to the problem processed by the target control sub-model.
[0027] Here, the problem that each control sub-model is responsible for handling is determined based on the data set trained on the control sub-model. The training data sets include but are not limited to pressure regulation data sets for non-increase and decrease equipment, pressure regulation data sets for increase and decrease equipment, flow regulation data sets for non-increase and decrease equipment, and flow regulation data sets for increase and decrease equipment. The artificial intelligence agent determines whether it is a pressure regulation problem or a flow regulation problem based on the type of abnormal data, and then determines one or more target control sub-models to call based on the deviation between the abnormal data and the set value. Specifically, if the type of abnormal data belongs to a pressure regulation problem and a flow regulation problem, there are at least two target control sub-models, which handle the pressure regulation problem and the flow regulation problem respectively, and the two target control sub-models can handle the problem in parallel. If the type of abnormal data belongs to a pressure regulation problem or a flow regulation problem, the number of target control sub-models is determined according to the deviation between the abnormal data and the set value; if the deviation is not large, there is at least one target control sub-model, that is, the control sub-model trained based on the flow regulation data set of non-increase and decrease equipment or the pressure regulation data set of non-increase and decrease equipment can be called as the target control sub-model; if the deviation is large, there is at least one target control sub-model, that is, the control sub-model trained based on the flow regulation data set of non-increase and decrease equipment + the flow regulation data set of increase and decrease equipment is needed as the target control sub-model, or the control sub-model trained based on the pressure regulation data set of non-increase and decrease equipment + the control sub-model trained based on the pressure regulation data set of increase and decrease equipment is needed as the target control sub-model, and the two target control sub-models need to process the problem serially.
[0028] Furthermore, after determining the target control sub-model, the artificial intelligence agent generates task information according to the problem that each target control sub-model needs to deal with, and assigns it to the corresponding target control sub-model. Specifically, the task information includes the type of abnormal data (pipeline network pressure and / or pipeline network flow), the specific value of the abnormal data, and the target value to be adjusted (pipeline network pressure setting value and / or pipeline network flow setting value).
[0029] As optional implementation modes of the embodiments of the present invention, several types of abnormal data are introduced in detail below.
[0030] If the abnormal data is the pipeline network pressure data, the target control sub-model includes a pressure stabilization model and an intelligent start-stop model.
[0031] The task information is generated according to the problem processed by the target control sub-model, including: the artificial intelligence agent generates first task information for the pressure stabilization model based on the pressure setting value; in response to exceeding a preset adjustment time, the pipeline network pressure data is not equal to the pressure setting value and reaches an expected deviation from the setting value, the artificial intelligence agent generates second task information for the intelligent start-stop model based on the pressure setting value.
[0032] Specifically, the first task information includes the type of abnormal data (network pressure), network pressure data, and pressure setting value. When the first task information is sent to the pressure stabilization model, the pressure stabilization model adjusts the current air compressor posture in real time so that the network pressure is always in a narrow band operation to achieve constant pressure change and save energy and reduce consumption.
[0033] When the artificial intelligence agent sends the first task information to the pressure stabilization model for more than the preset adjustment time, the received network pressure value is still not equal to the pressure setting value and reaches the expected deviation from the setting value (if the deviation is small, the time can be extended to allow the pressure stabilization model to continue adjusting), indicating that the network management pressure cannot be adjusted by relying solely on the pressure stabilization model, so it is necessary to call the intelligent start-stop model.
[0034] The second task information includes the type of abnormal data (network management pressure), the latest real-time data of network management pressure, and the pressure setting value. When the second task information is sent to the intelligent start-stop model, the intelligent start-stop model starts or stops the optimal air compressor based on the latest real-time pressure data and the pressure setting value deviation to achieve the pressure setting value and save energy and reduce consumption.
[0035] Optionally, after the artificial intelligence agent sends the first task information to the pressure stabilization model, within the preset adjustment time, the received network pressure value is equal to the pressure setting value, indicating that the pressure stabilization model has achieved the adjustment of the network management pressure, and there is no need to call the intelligent start-stop model at this time.
[0036] If the abnormal data is the pipe network flow data, the target control sub-model includes a steady flow model.
[0037] The generating of task information according to the problem processed by the target control sub-model includes: the artificial intelligence agent generating third task information for the steady flow model based on the flow setting value.
[0038] Specifically, the third task information includes the type of abnormal data (network management flow), network management flow data, and flow setting value. When the third task information is sent to the steady flow model, the steady flow model adjusts and controls the steady flow unit in the compressed air energy supply system to stabilize the flow of each gas pipeline, in order to achieve stable operation of the main network flow. By calculating the difference between the branch pipeline flow and the total pipeline flow, the adjustment range of the air compressor unit is calculated, and the air compressor unit is adjusted to ensure the stable operation of the entire compressed air energy supply system.
[0039] Step S103, the target control sub-model receives the task information, understands the task information according to the model prompt information, and generates control information for the problem; wherein: the model prompt information is generated in advance based on the problem that the target control sub-model is responsible for solving.
[0040] In this step, the model prompt information can be understood as an instruction to control the target control sub-model to perform a task, and is used to guide the target control sub-model to perform its corresponding task. The target control sub-model will understand the received task information based on the model prompt information and generate corresponding control information text as a response.
[0041] Continuing from the above, the problem that each control sub-model is responsible for handling is determined based on the data set trained by the control sub-model, and its model prompt information is also obtained by summarizing the methods for solving such problems in the data set. Specifically, the model prompt information at least includes the target parameters and target devices that need to be adjusted when the abnormal data is higher than the set value; the target parameters and target devices that need to be adjusted when the abnormal data is lower than the set value. Furthermore, the specific values to which the target devices and target parameters need to be adjusted are calculated by the control sub-model based on the abnormal data in the task information.
[0042] Taking the steady flow model as an example, the corresponding model prompt information includes: when the flow rate is lower than the flow setting value, the branch pipeline regulating valve opening is adjusted to become larger, and the current actual flow rate of the main pipeline and the total value of the rated flow rate of the currently running air compressor unit are compared. If it is less than the rated flow rate, the centrifuge adjusts the guide vane valve opening to increase, and the frequency of the variable frequency screw machine is increased until the current flow rate meets the gas demand; when the flow rate is higher than the flow setting value, the branch pipeline regulating valve opening is adjusted to become smaller, and the centrifuge adjusts the guide vane valve opening to become smaller, and the frequency of the variable frequency screw machine is reduced until the current flow rate meets the gas demand.
[0043] Taking the pressure stabilization model as an example, the corresponding model prompt information includes: when the pressure is lower than the pressure setting value, the centrifuge adjusts the guide vane valve opening to increase, and the frequency of the variable frequency screw machine is increased; when the pressure is higher than the pressure setting value, the centrifuge adjusts the guide vane valve opening to decrease, and the frequency of the variable frequency screw machine is reduced; the specific data of the opening and frequency are determined according to the current pressure value and historical operating conditions.
[0044] Taking the intelligent start-stop model as an example, the corresponding model prompt information includes: when the pressure is lower than the pressure setting value and reaches the expected deviation, find the optimal air compressor to be started according to the current real-time flow and historical operation conditions, and start the air compressor; when the pressure is higher than the pressure setting value and reaches the expected deviation, when the opening of all centrifuge guide vane valves is adjusted to the minimum value and the actual pressure is still higher than the pressure setting value, calculate the most suitable air compressor to be stopped corresponding to the surplus flow according to the current flow deviation of the centrifuge (stop the screw machine first).
[0045] As some further optional implementations of the embodiments of the present invention, if the control information includes an air compressor to be started or stopped, the target control sub-model understands the task information according to the model prompt information and generates control information for the problem, including:
[0046] The target control sub-model understands the task information based on the model prompt information and determines whether it is necessary to call the air compressor database; the air compressor database includes the attribute feature information, historical operation data, and current operating status of all air compressors in the compressed air energy supply system; if it is necessary to call the air compressor database, the target air compressor is found from the air compressor database based on the model prompt information, and the control information including controlling the target air compressor is generated.
[0047] Specifically, the attribute characteristic information (model, production date, energy efficiency, etc.), historical operation data, current working status and other data of all air compressors in the compressed air energy supply system are obtained in advance, the above data are cleaned and preprocessed, and a vector index is constructed. The target control sub-model determines the parameter conditions (attribute characteristics, working conditions, etc.) corresponding to the target compressor based on the model prompt information and abnormal data, and searches for matching target air compressors in the air compressor database based on the parameter conditions, thereby improving the accuracy and search efficiency of the target air compressor.
[0048] After the control information is generated, it is sent to the compressed air energy supply system, so that the system can adjust the relevant equipment according to the control information to ensure that the pressure and flow reach the set value level.
[0049] The technical solution provided by the embodiment of the present invention realizes intelligent monitoring and control of the entire compressed air energy supply system to achieve constant changes in pipeline pressure and stable operation of flow, which helps enterprises improve energy efficiency while also increasing their profit margins.
[0050] As some other optional implementations of the embodiments of the present invention, in order to achieve refined control and management of the compressed air energy supply system, the model prompt information includes first-stage prompt information and second-stage prompt information.
[0051] The target control sub-model understands the task information based on the model prompt information and generates control information for the problem, including: the target control sub-model understands the task information and determines the abnormal data and the task setting value; the target control sub-model generates the first control information for the problem according to the first-stage prompt information and the abnormal data; in response to the problem not being resolved, the target control sub-model generates the second control information for the problem according to the second-stage prompt information and the abnormal data.
[0052] Here, the first stage prompt information is used to adjust the operating parameters of the equipment in the compressed air energy supply system, and the second stage prompt information is used to start or stop the equipment in the compressed air energy supply system. The target control submodel will understand the received task information according to the model prompt information of each stage and generate the corresponding control information text as a response.
[0053] Specifically, for the pressure stabilization model, the first prompt information includes: when the pressure is lower than the pressure setting value, the centrifuge adjusts the guide vane valve opening to increase, and the variable frequency screw machine frequency is increased; when the pressure is higher than the setting value, the centrifuge adjusts the guide vane valve opening to decrease, and the variable frequency screw machine frequency is reduced. The second prompt information includes: when the pressure is still lower than the pressure setting value, start an air compressor with the best current working condition; when the pressure is still higher than the pressure setting value, stop an air compressor with the best current working condition.
[0054] For the steady flow model, when the flow rate is lower than the flow setting value, the branch pipeline regulating valve opening is adjusted to be larger, and the current actual flow rate of the main pipeline is compared with the total value of the rated flow rate of the currently running air compressor unit. If it is less than the rated flow rate, the centrifuge adjusts the guide vane valve opening to increase, and the frequency of the variable frequency screw machine is increased; when the flow rate is higher than the flow setting value, the branch pipeline regulating valve opening is adjusted to be smaller, and the centrifuge adjusts the IGV to be smaller, and the frequency of the variable frequency screw machine is reduced. The second prompt information includes: if the flow rate is still lower than the flow setting value, start an air compressor with the best current working condition until the current flow rate reaches the gas requirement; if the flow rate is still higher than the flow setting value, stop an air compressor with the best current working condition until the current flow rate reaches the gas requirement.
[0055] As some optional implementation methods of the embodiments of the present invention, Figure 2 As shown, the artificial intelligence model combination also includes a data analysis model, and the method also includes:
[0056] Step S201, the data analysis model determines the type of analysis report to be generated based on the real-time operation data of the compressed air energy supply system; different analysis report types correspond to different report prompt information, and the report prompt information is used to characterize the information dimension of the report.
[0057] In this step, the analysis report types include energy efficiency analysis reports and air compressor evaluation reports. The prompt information of the energy efficiency analysis report includes information on the dimensions of generating energy efficiency levels, energy efficiency diagnosis problems, energy efficiency optimization suggestions, and air compressor use priorities. The prompt information of the air compressor evaluation report includes information on the dimensions of air compressor adjustment plans, air compressor replacement plans, and air compressor maintenance plans. The data analysis model obtains the real-time operating data of the compressed air energy supply system collected in real time, and determines whether the system has energy efficiency or air compressor related problems through the real-time operating data. If so, the type of report to be generated is determined.
[0058] Step S202: the data analysis model generates an analysis report according to the report prompt information and the real-time operation data.
[0059] The energy efficiency analysis report can analyze the energy efficiency comparison of the system in real time, making the energy-saving status of the compressed air energy supply system clear at a glance. Then analyze the current energy efficiency level. When it is lower than the standard value, display the current problem and propose solutions. Through the air compressor evaluation report, it is possible to identify faulty air compressors and provide reasonable and effective maintenance and repair plans, realize online status evaluation and diagnosis of individual equipment, accurately locate the source of faults, and realize preventive maintenance. Furthermore, the report can also compare whether the current air compressor group matches. If it does not match, adjust the air compressor combination in real time based on the current status of the air compressor.
[0060] Through the scheme of the embodiment of the present invention, the combination of artificial intelligence control models can be used to monitor and control the entire compressed air energy supply system in real time, ensure constant pressure and flow, thereby protecting the normal operation of the circuit, and quickly cut off the power supply when an abnormal situation occurs in the circuit (such as short circuit, open circuit, phase loss, etc.) to protect the circuit from further damage. When the pressure and flow are abnormal due to equipment failure, the system responds in seconds, automatically starts the backup equipment, ensures production safety, and notifies relevant personnel through the system, text messages, etc.
[0061] Furthermore, the compressed air energy supply system in the embodiment of the present invention has a variety of protection functions, such as overload, overcurrent, temperature overheating protection, arc exceeding the standard, etc. These functions help to improve the safety of electrical equipment. The protection units composed of the integrated circuit components of the system simplify the circuit structure and improve the control accuracy. In addition, the system usually adopts manual reset or automatic reset to make troubleshooting more convenient and quick. The priority of the air compressor operation can also be set according to the intelligent rotation model, so that the same type of equipment can be operated alternately to ensure that the system does not stop.
[0062] As some optional implementations of the embodiments of the present invention, during the training of the data analysis model, the running data prediction value is generated by exponentially weighted averaging of the previous L prediction values through an autoregressive sliding average model.
[0063] Specifically, the training data of the data analysis model includes the operation data of the compressed air energy supply system at various times. However, due to the existence of certain emergencies, the power supply surges or decreases, which affects the operation data at the corresponding time of these emergencies. Because the occurrence of emergencies has extremely strong randomness, chaos, dispersion, short cycle and other characteristics, considering the stability and robustness of the model (where stability refers to the characteristics of the model that are basically consistent on different data sets, and robustness refers to the model's ability to resist abnormal data and noise), it is necessary to eliminate the influence of accidental events, so the median and time series sliding average methods are used for data preprocessing. That is, using the time series data of the past period without emergencies (at least 30 days), the autoregressive sliding average model is used to generate the predicted value of the operation data by the exponential weighted average of the predicted values of the previous L times, so that a certain "inertia" is introduced into the prediction of the operation data. When the abnormal operation data caused by the emergency comes, the normal operation data prediction model cannot be easily changed, and the predicted value of the normal operation data can be better obtained.
[0064] The technical solution provided by the embodiment of the present invention realizes intelligent monitoring and control of the entire compressed air energy supply system to achieve constant changes in pipeline pressure and stable operation of flow, which helps enterprises improve energy efficiency while also increasing their profit margins.
[0065] In one embodiment, reference Figure 3 As shown in FIG. 1 , a schematic diagram of a data control and processing device for a compressed air energy supply system based on AI is provided. The device can be used to perform Figure 1-Figure 2 In any of the AI-based compressed air energy supply system data management and control processing methods shown, the artificial intelligence control model combination includes an artificial intelligence agent and multiple control sub-models, and the device includes: a determination module 310, a first generation module 320, and a second generation module 330; wherein,
[0066] A determination module 310 is used to determine whether abnormal data exists based on the pipeline pressure data and pipeline flow data of the compressed air energy supply system; a first generation module 320 is used to determine at least one target control sub-model from the multiple control sub-models to handle the problem corresponding to the abnormal data if the abnormal data exists, and generate task information according to the problem handled by the target control sub-model; a second generation module 330 is used to receive the task information, understand the task information based on the model prompt information, and generate control information for the problem; wherein: the model prompt information is generated in advance based on the problem that the target control sub-model is responsible for solving.
[0067] Optionally, if the abnormal data is the pipeline network pressure data, the target control sub-model includes a pressure stabilization model and an intelligent start-stop model; the first generation module 320 is used to generate first task information for the pressure stabilization model based on the pressure setting value; in response to exceeding a preset adjustment time, the pipeline network pressure data is not equal to the pressure setting value and reaches an expected deviation from the setting value, generating second task information for the intelligent start-stop model based on the pressure setting value.
[0068] Optionally, if the abnormal data is the pipe network flow data, the target control sub-model includes a steady flow model, and the first generating module 320 is used to generate third task information for the steady flow model based on the flow setting value.
[0069] Optionally, the model prompt information includes first-stage prompt information and second-stage prompt information; the second generation module 330 is used to understand the task information, determine the abnormal data and the task setting value; generate first control information for the problem according to the first-stage prompt information and the abnormal data; in response to the problem being unresolved, generate second control information for the problem according to the second-stage prompt information and the abnormal data.
[0070] Optionally, the second generation module 330 is used to understand the task information based on the model prompt information and determine whether it is necessary to call the air compressor database; the air compressor database includes the attribute characteristic information, historical operation data, and current operating status of all air compressors in the compressed air energy supply system; if it is necessary to call the air compressor database, the target air compressor is found from the air compressor database based on the model prompt information, and the control information including controlling the target air compressor is generated.
[0071] Optionally, the artificial intelligence model combination also includes a data analysis model, and the device also includes a third generation module, which is used to determine the type of analysis report to be generated based on the real-time operation data of the compressed air energy supply system; different analysis report types correspond to different report prompt information, and the report prompt information is used to characterize the information dimension of the report; an analysis report is generated according to the report prompt information and the real-time operation data.
[0072] Optionally, during the training of the data analysis model, the running data prediction value is generated by exponentially weighted averaging of the previous L prediction values through an autoregressive sliding average model.
[0073] It should be noted that the AI-based compressed air energy supply system data control and processing device provided in the embodiment of the present invention corresponds to the technical solution that can be used to execute the above-mentioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.
[0074] Figure 4 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. Figure 4 , which shows a schematic diagram of the structure of an electronic device 400 suitable for implementing the embodiment of the present invention. The electronic device 400 in the embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0075] like Figure 4 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes to implement the method of the embodiment of the present invention according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage device 408 to the random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.
[0076] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0077] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart, thereby realizing the AI-based compressed air energy supply system data management and control processing method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.
[0078] It should be noted that the computer-readable medium of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0079] In some embodiments, the terminals and servers may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with 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"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0080] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0081] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device: the artificial intelligence agent determines whether there is abnormal data based on the pipeline pressure data and pipeline flow data of the compressed air energy supply system; if the abnormal data exists, the artificial intelligence control model determines at least one target control sub-model from the multiple control sub-models to handle the problem corresponding to the abnormal data, and generates task information according to the problem handled by the target control sub-model; the target control sub-model receives the task information, understands the task information according to the model prompt information, and generates control information for the problem; wherein: the model prompt information is generated in advance based on the problem that the target control sub-model is responsible for solving.
[0082] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the method, device and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0083] The units involved in the embodiments of the present invention may be implemented by software or hardware, wherein the name of a unit does not limit the unit itself in some cases.
[0084] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0085] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) to form a technical solution.
Claims
1. A data control and processing method for a compressed air energy supply system based on AI, characterized in that: include: Determine whether there is abnormal data based on the pipeline network pressure data and pipeline network flow data of the compressed air energy supply system using an artificial intelligence agent; If the abnormal data exists and the abnormal data is the pipe network pressure data, the artificial intelligence agent is instructed to determine at least one target control sub-model for processing the problem corresponding to the abnormal data from a plurality of control sub-models, the target control sub-model comprising a pressure stabilization model and an intelligent start-stop model, and the artificial intelligence agent is instructed to generate first task information for the pressure stabilization model based on the pressure setting value; In response to exceeding a preset adjustment time, the pipe network pressure data is not equal to the pressure setting value and reaches a predicted deviation from the pressure setting value, the artificial intelligence agent generates second task information for the intelligent start-stop model based on the pressure setting value; Instructing the target control sub-model to receive the first task information and the second task information, understand the first task information and the second task information, and determine the abnormal data and the task setting value; Instructing the target control sub-model to generate first control information for the problem according to the first-stage prompt information and the abnormal data; In response to the problem not being solved, the target control sub-model generates second control information for the problem according to the second-stage prompt information and the abnormal data; wherein the first-stage prompt information and the second-stage prompt information are generated in advance based on the problem that the target control sub-model is responsible for solving; when the second control information includes an air compressor that is turned on or off, the target control sub-model is instructed to understand the task information according to the second-stage prompt information to determine whether it is necessary to call the air compressor database; the air compressor database includes attribute feature information, historical operating data and current operating status of all air compressors in the compressed air energy supply system; if it is necessary to call the air compressor database, the target air compressor is found from the air compressor database according to the second-stage prompt information, and the second control information including controlling the target air compressor is generated.
2. The AI-based compressed air energy supply system data management and processing method according to claim 1 is characterized in that: If the abnormal data is the pipe network flow data, the target control sub-model includes a steady flow model, and the generating of task information according to the problem processed by the target control sub-model includes: The artificial intelligence agent is enabled to generate third task information for the steady flow model based on the flow setting value.
3. The AI-based compressed air energy supply system data management and processing method according to claim 1 is characterized in that: Also includes: Analyzing the real-time operation data of the compressed air energy supply system through a data analysis model to determine the type of analysis report to be generated; Different analysis report types correspond to different report prompt information, and the report prompt information is used to characterize the information dimension of the report; The data analysis model is enabled to generate an analysis report according to the report prompt information and the real-time operation data.
4. The AI-based compressed air energy supply system data management and control processing method according to claim 3 is characterized in that: During the training process of the data analysis model, the running data prediction value is generated by exponentially weighted averaging of the previous L prediction values through an autoregressive sliding average model.
5. A data control and processing device for a compressed air energy supply system based on AI, characterized in that: include: A determination module, used to determine whether there is abnormal data based on the pipe network pressure data and pipe network flow data of the compressed air energy supply system using an artificial intelligence agent; A first generating module is used for, if the abnormal data exists and the abnormal data is the pipe network pressure data, causing the artificial intelligence agent to determine at least one target control sub-model for processing the problem corresponding to the abnormal data from a plurality of control sub-models, wherein the target control sub-model includes a pressure stabilization model and an intelligent start-stop model, and causing the artificial intelligence agent to generate first task information for the pressure stabilization model based on a pressure setting value; In response to exceeding a preset adjustment time, the pipe network pressure data is not equal to the pressure setting value and reaches a predicted deviation from the pressure setting value, the artificial intelligence agent generates second task information for the intelligent start-stop model based on the pressure setting value; A second generating module is used to enable the target control sub-model to receive the first task information and the second task information, understand the first task information and the second task information, and determine the abnormal data and the task setting value; Instructing the target control sub-model to generate first control information for the problem according to the first-stage prompt information and the abnormal data; In response to the problem not being solved, the target control sub-model generates second control information for the problem according to the second-stage prompt information and the abnormal data; wherein the first-stage prompt information and the second-stage prompt information are generated in advance based on the problem that the target control sub-model is responsible for solving; when the second control information includes an air compressor that is turned on or off, the target control sub-model is instructed to understand the task information according to the second-stage prompt information to determine whether it is necessary to call the air compressor database; the air compressor database includes attribute feature information, historical operating data and current operating status of all air compressors in the compressed air energy supply system; if it is necessary to call the air compressor database, the target air compressor is found from the air compressor database according to the second-stage prompt information, and the second control information including controlling the target air compressor is generated.
6. The AI-based compressed air energy supply system data control and processing device according to claim 5 is characterized in that: If the abnormal data is the pipeline flow data, the target control sub-model includes a steady flow model, and the first generation module is used to: enable the artificial intelligence agent to generate third task information for the steady flow model based on the flow setting value.
7. The AI-based compressed air energy supply system data control and processing device according to claim 6 is characterized in that: Also included is a third generation module for: Analyzing the real-time operation data of the compressed air energy supply system through a data analysis model to determine the type of analysis report to be generated; different types of analysis reports correspond to different report prompt information, and the report prompt information is used to characterize the information dimension of the report; Generate an analysis report based on the data analysis model according to the report prompt information and the real-time operation data.
Citation Information
Patent Citations
Cluster optimization control system for air compressor
CN104635684A
Intelligent diagnosis system for air compressor cluster
CN112529320A
Industrial control network abnormal flow detection method and device and electronic equipment
CN115348092A
Monitoring processing method and device of vacuum circuit breaker, electronic equipment and storage medium
CN116008799A
Integrated air compression station intelligent cloud control system and control method
CN117032120A
Cited By
Air compressor cluster-oriented AI energy-saving capacity trading platform construction method
CN122593013A
