Intelligent air compressor abnormity monitoring system and method

Abstract

The embodiment of the invention provides an intelligent air compressor abnormity monitoring system. The intelligent air compressor abnormity monitoring system comprises pressure sensing equipment, electric quantity monitoring equipment, a sound monitoring device, an image monitoring device and a processor. The processor comprises an edge processor, remote equipment and a control center; the edge processor is configured to determine air supply abnormal data for one air compressor through an abnormal model based on the pressure feature data, the air compressor power consumption data, the sound data and the image data, and the abnormal model is a machine learning model; the far-end device is configured to periodically train the anomaly model based on the update period; and the control center is configured to periodically transmit the model parameters of the abnormal model trained by the far-end equipment to the edge processor based on the updating period.

Description

DIVISION

[0001] This application is a divisional application of the Chinese application with the application number 202411870116.0 and the application title "Intelligent air compressor control system and method based on deep learning and optimization algorithm", which has an application date of December 18, 2024. TECHNICAL FIELD

[0002] The present specification relates to the field of intelligent control, in particular to an intelligent air compressor abnormality monitoring system and method. BACKGROUND

[0003] In modern industry, air compressors are widely used in pneumatic tools, mechanical equipment and other aspects of the production line as gas supply equipment. With the increasing demand for energy saving and emission reduction, the energy consumption of air compressors has attracted widespread attention.

[0004] Traditional air compressor control methods, such as proportional-integral-differential (PID) controllers, are widely used in air compressor control due to their simple structure and easy implementation. However, PID controllers cannot adapt to complex nonlinear working conditions and dynamic changes, and cannot achieve optimal control of air compressor energy consumption.

[0005] Therefore, it is desirable to provide an intelligent air compressor control system and method based on deep learning and optimization algorithm, which can achieve flexible control of air compressors under various working conditions, thereby reducing energy consumption and improving production efficiency. SUMMARY

[0006] The one or more embodiments of the specification provide an intelligent air compressor abnormality monitoring system, comprising a pressure sensing device, an electric quantity monitoring device, a sound monitoring device, an image monitoring device and a processor; the pressure sensing device is connected with a gas supply pipeline, the gas supply pipeline is connected with at least one of an air compressor, a gas using device and a gas using production line, and the pressure sensing device is configured to obtain pressure characteristic data; the pressure characteristic data comprises gas supply pressure data and / or gas using pressure data; the electric quantity monitoring device is configured to obtain air compressor power consumption data; the sound monitoring device and the image monitoring device are arranged in the gas using production line, the sound monitoring device is configured to obtain sound data, and the image monitoring device is configured to obtain image data; the processor comprises an edge processor, a remote device and a control center; the edge processor is configured to: for one air compressor, based on the pressure characteristic data, the air compressor power consumption data, the sound data and the image data, determining the gas supply abnormality data through an abnormality model, and the abnormality model is a machine learning model; the remote device is configured to periodically train the abnormality model based on an update cycle; and the control center is configured to periodically transmit model parameters of the abnormality model trained by the remote device to the edge processor based on the update cycle.

[0007] One of the embodiments of the specification provides an intelligent air compressor abnormality monitoring method, which is executed by a processor of an intelligent air compressor abnormality monitoring system, comprising: obtaining pressure characteristic data through a pressure sensing device, the pressure characteristic data comprising gas supply pressure data and / or gas using pressure data; obtaining air compressor power consumption data through an electric quantity monitoring device; obtaining sound data through a sound monitoring device; obtaining image data through an image monitoring device; for one air compressor, determining gas supply abnormality data through an abnormality model based on the pressure characteristic data, the air compressor power consumption data, the sound data and the image data, and the abnormality model is a machine learning model; and periodically training the abnormality model based on an update cycle.

[0008] Beneficial effects: the intelligent air compressor control system and method based on deep learning and optimization algorithm can determine the running parameters of the air compressor through the air compression model, can solve the optimal strategy through the reinforcement learning method, can reduce the energy consumption of the air compressor while ensuring the stability of the gas supply, can ensure that the gas supply pressure and the gas supply amount meet the production requirements, and can improve the product quality. The running parameters of the air compressor can be periodically determined based on the adjustment cycle, the control strategy can be adjusted in real time based on the current working condition, and stable control of the air compressor under various working conditions can be realized. BRIEF DESCRIPTION OF DRAWINGS

[0009] The present specification will be further described in the manner of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. The embodiments are not restrictive, and in the embodiments, the same reference numbers denote the same structures, in which: Figure 1 is an exemplary block diagram of an intelligent air compressor control system based on deep learning and optimization algorithm according to some embodiments of the present specification; Figure 2 is an exemplary flow chart of an intelligent air compressor control method based on deep learning and optimization algorithm according to some embodiments of the present specification; Figure 3 is an exemplary schematic diagram of an air compression model according to some embodiments of the present specification; Figure 4 is an exemplary schematic diagram of determining operating parameters of an air compressor and / or cooling parameters of a cooling device according to some embodiments of the present specification; Figure 5 is an exemplary schematic diagram of generating alarm information according to some embodiments of the present specification. DETAILED DESCRIPTION

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can also be applied to other similar scenarios without creative labor on the basis of these drawings. Unless it is clear from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structure or operation.

[0011] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0012] As shown in the specification and claims, unless the context clearly indicates otherwise, "one", "a", "an", and / or "the" do not refer to the singular, but can also include the plural. Generally, the terms "comprise" and "include" only indicate the inclusion of the steps and elements explicitly identified, and these steps and elements do not constitute an exclusive list, and the method or device can also include other steps or elements.

[0013] Flowcharts are used in the specification to illustrate the operations of systems in accordance with embodiments of the specification. It should be understood that the operations in the figures need not necessarily be performed in the order shown. Rather, various steps can be handled in reverse order or simultaneously. Additionally, other operations can be added or removed from the processes.

[0014] Figure 1 is an exemplary block diagram of an intelligent air compressor control system based on deep learning and optimization algorithm according to some embodiments of the specification.

[0015] In some embodiments, as shown in Figure 1 An intelligent air compressor control system based on deep learning and optimization algorithm 100 includes a pressure sensing device 110, a power monitoring device 120, a temperature sensing device 130, and a processor 140.

[0016] The pressure sensing device 110 refers to a device that can sense a pressure signal and convert the pressure signal into an electrical signal. The pressure sensing device 110 includes an analog air pressure sensor, a digital air pressure sensor, etc.

[0017] In some embodiments, the pressure sensing device 110 is configured to obtain pressure feature data.

[0018] In some embodiments, the pressure sensing device 110 is connected to a gas supply pipeline, and the gas supply pipeline is connected to at least one of an air compressor, a gas using device, and a gas using production line.

[0019] The gas supply pipeline is a passage for gas transportation. The gas supply pipeline includes a gas pipeline, a control valve, a filter, etc. The input end of the gas supply pipeline is an air compressor, and the output end is a gas using device or a gas using production line.

[0020] The air compressor is a device for compressing gas. For example, the air compressor includes a positive displacement compressor, a piston compressor, a rotary compressor, etc.

[0021] In some embodiments, the air compressor sucks in low-pressure air from an air inlet and discharges high-pressure air from an air outlet. The air in the gas supply pipeline flows from a high-pressure place to a low-pressure place under the action of pressure. That is, the high-pressure air discharged by the air compressor flows to the gas using device or the gas using production line through the gas supply pipeline.

[0022] In some embodiments, the gas supply pipeline is mechanically connected to the air compressor. For example, threaded connection, flange connection, etc.

[0023] The gas using device refers to a device that needs to use high-pressure gas. For example, a pick, a pneumatic rock drill, a riveter, etc.

[0024] The gas-consuming line refers to a production line that needs to use high-pressure gas. For example, in the food or pharmaceutical industry, high-pressure gas needs to be used to stir the slurry, and in the chemical industry, the synthesis and polymerization of some gases are facilitated by increasing the pressure through an air compressor.

[0025] In some embodiments, multiple pressure sensing devices 110 can be arranged at different positions of the gas supply pipeline. For example, the pressure sensing device 110 arranged at the input end of the gas supply pipeline is configured to obtain gas supply pressure data, and the pressure sensing device 110 arranged at the output end of the gas supply pipeline is configured to obtain gas consumption pressure data.

[0026] The power monitoring device 120 is a device for monitoring the power consumption of the power-consuming device. The power monitoring device 120 includes an electronic power meter, a multifunctional power meter, etc.

[0027] In some embodiments, the power monitoring device 120 is arranged in the current loop where the air compressor is located, and is configured to obtain air compressor power consumption data.

[0028] The temperature sensing device 130 refers to a device that can sense a temperature signal and convert the temperature signal into an electrical signal. The temperature sensing device 130 includes a resistance sensor, a thermocouple sensor, etc.

[0029] In some embodiments, the temperature sensing device 130 is arranged on the air compressor and is configured to obtain air compressor temperature data.

[0030] The processor 140 can process data and / or information related to the intelligent air compressor control system 100 based on deep learning and optimization algorithms. The processor 140 can execute program instructions based on these data, information and / or processing results to perform one or more functions described in this application.

[0031] In some embodiments, the processor 140 can include one or more sub-processing devices (e.g., single-core processing devices or multi-core multi-core processing devices). For example only, the processor can include one or any combination of a central processing unit (CPU), a digital signal processor (DSP), an embedded processor, etc.

[0032] In some embodiments, the processor 140 is configured to periodically determine the operating parameters of the air compressor based on an adjustment period. In one adjustment period, the processor is configured to determine the operating parameters of the air compressor based on the pressure characteristic data, the air compressor power consumption data and the air compressor temperature data through the air compression model for one air compressor.

[0033] In some embodiments, as Figure 1As shown, processor 140 includes edge processor 141, remote device 142, multiple service databases 143, and control center 144.

[0034] Edge processor 141 refers to a processor located closer to the location where data is generated. In some embodiments, edge processor 141 is located in an air consumption production line and is configured to: for an air compressor, determine the operating parameters of the air compressor and / or the cooling parameters of the cooling equipment based on pressure characteristic data, air compressor power consumption data, air compressor temperature data, and intake air temperature, using an air compressor model; and send an update request to the control center in response to the air compressor operating parameters and / or the cooling parameters of the cooling equipment meeting update conditions within a preset time period.

[0035] Remote device 142 refers to a device located at a distance from the data generation location. In some embodiments, remote device 142 is located at a distance that communicates with the gas production line and is configured to periodically train the compressed air model based on an update cycle.

[0036] Service database 143 is used to store data and / or information related to the intelligent air compressor control system 100 based on deep learning and optimization algorithms. In some embodiments, multiple service databases are located in edge processor 141 and / or remote device 142 and are configured to store at least one of pressure characteristic data, air compressor power consumption data, and air compressor temperature data.

[0037] In some embodiments, data may be stored in multiple service databases 143 according to preset rules. For example, each service database 143 is configured to store storage pressure characteristic data, air compressor power consumption data, and air compressor temperature data generated by the most recent gas-consuming production line. Alternatively, each service database 143 may be configured to store storage pressure characteristic data, air compressor power consumption data, and air compressor temperature data generated by multiple gas-consuming production lines.

[0038] Control center 144 refers to a device used for data transmission and instruction execution. In some embodiments, control center 144 is configured to periodically transmit model parameters trained by a remote device to an edge processor based on an update cycle.

[0039] In some embodiments, such as Figure 1 As shown, the intelligent air compressor control system 100 based on deep learning and optimization algorithms also includes a cooling device 150, an environmental monitoring device 160, a sound monitoring device 170, and an image monitoring device 180.

[0040] Cooling equipment 150 is a device used to achieve the function of cooling. For example, cooling equipment 150 includes air-cooled coolers, water-cooled coolers, and double-cooled coolers.

[0041] In some embodiments, the cooling device 150 is disposed on the air compressor and is configured to reduce the temperature of the air compressor.

[0042] The environmental monitoring device 160 is a device for monitoring the working environment of the air compressor.

[0043] In some embodiments, the environmental monitoring device 160 is configured to obtain the suction air temperature, and at this time, the environmental monitoring device 160 can be a temperature sensor disposed at the air inlet of the air compressor.

[0044] The sound monitoring device 170 is a device for collecting sound data. For example, the sound monitoring device 170 is an audio collector or the like.

[0045] In some embodiments, the sound monitoring device 170 is disposed on the gas using production line and is configured to collect sound data on the gas using production line.

[0046] The image monitoring device 180 is a device for collecting image data. For example, the image monitoring device 180 includes a camera, a video camera, or the like.

[0047] In some embodiments, the image monitoring device 180 is disposed on the gas using production line and is configured to collect image data on the gas using production line.

[0048] In some embodiments of the present specification, various parameters during the operation of the air compressor are collected by various monitoring devices, and the operating parameters of the air compressor are adjusted based on the various parameters, which can integrate data from different sensors, realize efficient use and deep analysis of information.

[0049] It should be understood that, Figure 1 The system and its modules shown can be implemented in various ways.

[0050] It should be noted that the above description of the intelligent air compressor control system 100 based on deep learning and optimization algorithm and its modules is for convenience of description, and cannot limit the present specification to the scope of the embodiments. It can be understood that, for those skilled in the art, after understanding the principle of the system, various modules can be combined or connected to form a subsystem with other modules without departing from the principle. In some embodiments, Figure 1 The pressure sensing device 110, the power monitoring device 120, the temperature sensing device 130, and the processor 140 disclosed in the present specification can be different modules in a system, or can be a module to realize the functions of two or more modules described above. For example, each module can share a storage module, and each module can have its own storage module. Variations such as this are within the scope of protection of the present specification.

[0051] Figure 2is an exemplary flowchart of a deep learning and optimization algorithm based intelligent air compressor control method according to some embodiments shown in the specification. As shown in Figure 2 Flow 200 includes the following steps. In some embodiments, flow 200 can be performed by a processor (e.g., processor 140).

[0052] Step 210, acquiring pressure feature data by a pressure sensing device.

[0053] The pressure feature data refers to data related to the pressure at each position in the air supply pipeline. The pressure feature data includes air supply pressure data and / or air use pressure data.

[0054] The air supply pressure data refers to the pressure at the connection between the air compressor and the air supply pipeline. In some embodiments, the processor can determine the pressure sensing data collected by the pressure sensing device closest to the air compressor in the air supply pipeline as the air supply pressure data corresponding to the air compressor.

[0055] The air use pressure data refers to the pressure at the connection between the air use device or air use production line and the air supply pipeline. In some embodiments, the processor can determine the pressure sensing data collected by the pressure sensing device closest to the air use device or air use production line in the air supply pipeline as the air use pressure data corresponding to the air use device or air use production line.

[0056] For more information about the air supply pipeline, air compressor, pressure sensing device, air use device, and air use production line, see Figure 1 and related descriptions.

[0057] Step 220, acquiring air compressor power consumption data by a power monitoring device.

[0058] The air compressor power consumption data refers to data related to the power consumption of the air compressor. For example, the air compressor power consumption data includes the power consumption of the air compressor, etc.

[0059] In some embodiments, the processor can collect the power consumption of the air compressor by the power monitoring device, and determine the power consumption of the air compressor as the air compressor power consumption data.

[0060] For more information about the power monitoring device, see Figure 1 and related descriptions.

[0061] Step 230, acquiring air compressor temperature data by a temperature sensing device.

[0062] The air compressor temperature data refers to the temperature of the air compressor. In some embodiments, the processor can collect the temperature of the air compressor by the temperature sensing device arranged on the air compressor, thereby obtaining the air compressor temperature data.

[0063] For more information about the temperature sensing device, seeFigure 1 and related descriptions.

[0064] At step 240, based on the adjustment period, the operation parameters of the air compressor are periodically determined according to the pressure characteristic data, the air compressor power consumption data and the air compressor temperature data by the air compression model.

[0065] The adjustment period refers to the period in which the processor adjusts the operation parameters of the air compressor. In some embodiments, the adjustment period is a preset value of the system.

[0066] In some embodiments, the processor determines the adjustment period corresponding to the air compressor of the gas-using production line based on the production plan of the gas-using production line.

[0067] The production plan of the gas-using production line refers to the plan of producing products on the gas-using production line. The production plan of the gas-using production line at least includes the expected output of the products. The more the expected output of the products, the shorter the corresponding adjustment period. The production plan of the gas-using production line can be determined based on the obtained user input.

[0068] The operation parameters refer to parameters related to the operation of the air compressor. For example, the operation parameters include the valve opening degree, the motor power of the air compressor, the start-stop of the compressor, etc.

[0069] In some embodiments, within one adjustment period, for one air compressor, the processor determines the operation parameters of the air compressor based on the pressure characteristic data, the air compressor power consumption data and the air compressor temperature data by the air compression model.

[0070] The air compression model is a model used to determine the operation parameters of the air compressor. In some embodiments, the air compression model is a reinforcement learning (RL) model.

[0071] Figure 3 is an exemplary schematic diagram of an air compression model according to some embodiments of the present specification. In some embodiments, as shown in Figure 3 , the input of the air compression model 320 includes the working state information 310, and the output of the air compression model 320 includes the optimal parameters 330. The air compression model 320 includes a working module 321 and an optimal action determination module 322.

[0072] The working state information 310 refers to information related to the working state of the air compressor. The working state information 310 includes the pressure characteristic sequence, the power consumption sequence and the temperature sequence corresponding to the air compressor. Among them, the pressure characteristic sequence is a sequence obtained by arranging the pressure characteristic data at multiple time points in chronological order, the power consumption sequence is a sequence obtained by arranging the air compressor power consumption data at multiple time points in chronological order, and the temperature sequence is a sequence obtained by arranging the air compressor temperature data at multiple time points in chronological order.

[0073] In some embodiments, before constructing the working state information 310, the processor can perform cleaning and normalization on the collected data to improve the quality and availability of the data, thereby improving the efficiency of the model processing. The data cleaning includes one or more of data deduplication, missing value processing, outlier processing, etc. The normalization method includes but is not limited to the minimum maximum normalization or Zscore standardization method, etc.

[0074] The optimal parameter 330 is the preferred operating parameter of the air compressor in the next adjustment period.

[0075] In some embodiments, when determining the optimal parameter 330 based on the air compression model 320, the working state information 310 can be input into the air compression model 320. In the model, the working state information 310 is input into the working module 321, and the working module 321 outputs a set of optional actions. The working state information 310 and the set of optional actions are input into the optimal action determination module 322, and the optimal action determination module 322 outputs the optimal optional action 323. The operating parameter of the air compressor corresponding to the optimal optional action 323 output by the optimal action determination module 322 is determined as the optimal parameter 330, which is output as the output of the air compression model 320.

[0076] The working module 321 can determine the set of optional actions of the air compressor based on the working state information of the current adjustment period.

[0077] The set of optional actions refers to the set of actions that the air compressor can perform under a certain working state. The actions that the air compressor can perform include adjusting the valve opening, adjusting the motor power, etc. The set of optional actions of the air compressor can be different under different working states. For example, when the valve opening reaches the maximum, the set of optional actions of the air compressor does not include increasing the valve opening.

[0078] The optimal action determination module 322 can be used to determine the reward value of each optional action in the set of optional actions based on the working state information. The reward value can be used to evaluate the impact of the air compressor adjusting the operating parameter according to the optional action on the product production.

[0079] In some embodiments, in the trained air compression model 320, the optimal action determination module 322 stores the reward values corresponding to the air compressor performing each optional action under various working state information, wherein the reward value corresponding to performing an optional action under a working state information can be determined based on a set formula.

[0080] For example, the reward value is related to the energy efficiency coefficient and the motor power after the air compressor performs the corresponding action, and the optimal action determination module 322 can determine the reward value based on a first incentive function.

[0081] Exemplarily, the first excitation function can be represented by the following formula (1).

[0082] (1) wherein, is the energy efficiency coefficient of the air compressor after the action is performed, is the motor power of the air compressor after the action is performed, is the reward value corresponding to the action performed.

[0083] The energy efficiency coefficient of the air compressor reflects the energy utilization rate of the air compressor. The greater the energy efficiency coefficient, the lower the energy consumption (such as the lower the power consumption) of the air compressor. In some embodiments, the energy efficiency coefficient of the air compressor is positively correlated with the supply air pressure data and negatively correlated with the air compressor power consumption data.

[0084] In the actual application of the air compression model, after the optimal action determination module 322 obtains the working state information and the set of optional actions, the reward value corresponding to each optional action under the working state information can be determined.

[0085] The optimal action determination module 322 can determine the optional action with the highest reward value as the optimal optional action 323 and output it.

[0086] In some embodiments, the optimal action determination module 322 can be a machine learning model, which can be implemented in various ways, such as a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), etc.

[0087] In some embodiments, the air compression model can be trained based on a reinforcement learning method, such as a Deep Q-Learning Network (DQN), a Double Deep Q-Learning Network (DDQN), etc. The first training sample can be the historical working state information of the sample air compressor, and the first label is the optimal optional action corresponding to the historical working state information of the sample air compressor. The first training sample can be obtained based on historical data. The first label can be obtained by a reinforcement learning method, for example, the first label can be the optimal optional action with the highest reward value determined based on formula (1).

[0088] For example only, the processor can construct a training data set based on the historical working state information of the sample air compressor at a first historical time point and the running parameters of the air compressor after performing a corresponding action at a second historical time point, and train the air compression model based on the training data set and in combination with a reinforcement learning method. Based on the training data set and the actual running state of the sample air compressor at the second historical time point, the initial air compression model can determine the reward value corresponding to the execution of each action of the air compressor under various working state information based on an incentive function such as formula (1), and the processor can further update the parameters of the working module and the optimal action determination module of the initial air compression model based on the reward value and a loss function until a training stop condition is met. The training stop condition can include meeting the number of iterations of training.

[0089] In some embodiments, before constructing the training data set, the processor can perform cleaning and normalization processing on the collected historical data to improve the quality and availability of the data, thereby improving the model training effect.

[0090] In some embodiments, as shown in Figure 1 The training of the air compression model is performed by the remote device. After the air compression model is initially trained, the edge processor determines the running parameters of the air compressor based on the pressure feature data, the air compressor power consumption data, and the air compressor temperature data through the air compression model.

[0091] During the use of the air compression model, the remote device periodically trains the air compression model based on an update period, and the control center periodically transmits the model parameters trained by the remote device to the edge processor based on the update period.

[0092] In some embodiments, the update period is a system default value, for example, the update period is one week.

[0093] In some embodiments, the update period is related to the data amount of production data of the gas-using production line. The larger the data amount of the production data, the shorter the update period.

[0094] Production data refers to data related to the production of products. The production data includes pressure feature data, air compressor power consumption data, and air compressor temperature data.

[0095] In some embodiments, the processor can determine the data amount of the production data based on the memory usage of the service database. The more memory usage of the service database, the larger the data amount of the production data.

[0096] The larger the data amount of the production data, the greater the production amount of the gas-using production line, and the more variable the situation of the gas-using production line. In order to meet the accuracy requirements in the production process, it is necessary to shorten the update period of the model to improve the accuracy of the model.

[0097] For more information about the remote device, the edge processor, the service database and the control center, see Figure 1 and the related description.

[0098] In some embodiments, in response to the running parameters of the air compressor and / or the cooling parameters of the cooling device satisfying a first update condition within a preset period, the edge processor sends a first update request to the control center. The preset period can be a system default value.

[0099] The first update condition is used to determine whether the control center transmits the trained model parameters to the edge processor.

[0100] In some embodiments, the first update condition is that the fluctuation of the running parameters of the air compressor is greater than a first fluctuation threshold, or the fluctuation of the cooling parameters of the cooling device is greater than a second fluctuation threshold within the preset period. The first fluctuation threshold and the second fluctuation threshold can be set based on experience.

[0101] For more information about the cooling parameters of the cooling device, see Figure 4 and the related description.

[0102] In some embodiments, the processor calculates the coefficient of variation of each running parameter of the air compressor within the preset period, and determines the mean of the coefficients of variation of the plurality of running parameters as the fluctuation value of the running parameters of the air compressor within the preset period. Wherein, the processor can obtain a plurality of values of a running parameter within the preset period, and then determine the standard deviation and the mean of the values of the running parameter within the preset period, and then take the ratio of the standard deviation and the mean of the running parameter as the coefficient of variation of the running parameter. The processor can determine the fluctuation value of the cooling parameters of the cooling device in the same way.

[0103] In some embodiments, the first fluctuation threshold and the second fluctuation threshold are related to the update cycle and the product type produced by the gas-using production line. The shorter the update cycle, the lower the first fluctuation threshold and the second fluctuation threshold; the higher the quality requirement of the product produced by the gas-using production line, the lower the first fluctuation threshold and the second fluctuation threshold.

[0104] When the first update condition is met, the product quality fluctuates greatly, which may be caused by the fact that the model parameters are no longer applicable. By sending the first update request, the model parameters can be actively updated to improve the product quality.

[0105] The first update request refers to a request for the control center to transmit the trained model parameters to the edge processor. In response to receiving the first update request, the control center transmits the trained model parameters to the edge processor.

[0106] Remote devices have long response times and require significant computing resources, while edge processors have short response times and fewer computing resources. Since model training takes a long time and requires substantial computing resources, choosing remote devices for model training and edge processors for model application satisfies both the rapid response requirements of the gas production line and the accuracy requirements of model training. By integrating data from different sensors, efficient information utilization and in-depth analysis can be achieved.

[0107] In some embodiments, within an adjustment cycle, the processor can simultaneously determine the operating parameters of multiple air compressors based on pressure characteristic data, power consumption data, and temperature data of multiple air compressors, using the air compressor model 320. At this time, the operating status information 310 includes a sequence combination of the operating status information of the multiple air compressors, and the optimal parameters 330 includes a sequence combination of the optimal operating parameters of the multiple air compressors.

[0108] For example, working status information 310 can be represented as .in, For the first Pressure characteristic sequence of an air compressor For the first Power consumption sequence of an air compressor For the first The temperature sequence of the air compressor. The optimal parameter 330 can be expressed as: ,in, Indicates the first The optimal operating parameters for each air compressor.

[0109] In some embodiments, within an adjustment cycle, for an air compressor, the processor determines the operating parameters of the air compressor and / or the cooling parameters of the cooling equipment based on pressure characteristic data, air compressor power consumption data, air compressor temperature data, and intake air temperature, using an air compressor model. See more details. Figure 4 And related explanations.

[0110] Some embodiments in this specification determine the operating parameters of the air compressor through an air compressor model. The optimal strategy can be solved using reinforcement learning methods, ensuring stable air supply while reducing the air compressor's energy consumption, guaranteeing that the air supply pressure and volume meet production needs, and improving product quality. By periodically determining the air compressor's operating parameters based on an adjustment cycle, the control strategy can be adjusted in real time based on the current operating conditions, achieving stable control of the air compressor under various operating conditions.

[0111] It should be noted that the above description of the flow 200 is merely for example and illustration, and does not limit the scope of the present specification. Various modifications and changes can be made to the flow 200 by those skilled in the art under the guidance of the present specification. However, these modifications and changes still fall within the scope of the present specification. For example, steps 210-230 can be performed simultaneously.

[0112] Figure 4 is an exemplary schematic diagram of determining the operation parameter of the air compressor and / or the cooling parameter of the cooling device according to some embodiments of the present specification.

[0113] In some embodiments, as shown in Figure 4 , for an air compressor, the processor determines the operation parameter 421 of the air compressor and / or the cooling parameter 422 of the cooling device based on the pressure characteristic data 411, the air compressor power consumption data 412, the air compressor temperature data 413, and the intake air temperature 414 through the air compressor model 320 in one adjustment cycle.

[0114] For more information about the air compressor and the cooling device, see Figure 1 and the related description. For more information about the adjustment cycle, the pressure characteristic data, the air compressor power consumption data, the air compressor temperature data, the air compressor model, and the operation parameter of the air compressor, see Figure 2 and the related description.

[0115] The intake air temperature 414 refers to the temperature of the air sucked by the air compressor. In some embodiments, the processor obtains the intake air temperature 414 through the environment monitoring device. For more information about the environment monitoring device, see Figure 1 and the related description.

[0116] The cooling parameter of the cooling device refers to the parameter related to the refrigeration of the cooling device. The cooling parameter of the cooling device at least includes the power of the cooling device.

[0117] In some embodiments, as shown in Figure 4 , the air compressor model 320 can also be used to determine the cooling parameter 422 of the cooling device while determining the operation parameter 421 of the air compressor. At this time, the input (i.e., the working state information 310 in Figure 3 ) of the air compressor model 320 also includes the intake air temperature 414, and the output (i.e., the optimal parameter 330 in Figure 3 ) of the air compressor model 320 also includes the preferred cooling parameter of the cooling device in the next adjustment cycle.

[0118] In some embodiments, when the air compression model 320 is used to determine the operation parameter 421 of the air compressor and the cooling parameter 422 of the cooling device simultaneously, the optimal action determination module 322 can determine the reward value of the optional action based on a second excitation function. In some embodiments, the second excitation function is related to the operation parameter of the air compressor, the cooling parameter of the cooling device, the energy efficiency coefficient of the air compressor, and the energy efficiency coefficient of the cooling device. Exemplarily, the second excitation function can be represented by the following formula (2).

[0119] (2) wherein, is the energy efficiency coefficient of the air compressor after the optional action is performed on the air compressor, is the motor power of the air compressor after the optional action is performed on the air compressor, is the energy efficiency coefficient of the cooling device after the optional action is performed on the cooling device, is the power of the cooling device after the optional action is performed on the cooling device, is the score corresponding to the optional action performed on the air compressor and the cooling device (i.e., the reward value of the optional action), , is the weight. For more information about the energy efficiency coefficient of the air compressor, see Figure 3 and the related description.

[0120] In some embodiments, , can be set based on actual needs. The higher the requirement for the working efficiency of the air compressor, the larger the weight, the smaller the weight.

[0121] In some embodiments of the present specification, the score corresponding to each combination of the candidate operation parameter and the candidate cooling parameter is calculated by the second excitation function, and the operation parameter of the air compressor and the cooling parameter of the cooling device are determined based on the score. The optimal solution can be found among the combinations of the candidate operation parameter and the candidate cooling parameter, so as to ensure the stable operation of the air compressor, improve the safety of the air compressor, and reduce the energy consumption of the air compressor and the cooling device.

[0122] For more information about the application and training of the air compression model 320, see the related description of step 240.

[0123] In some embodiments, the input (i.e., the working state information 310 in Figure 3 ) of the air compression model 320 further includes supply abnormality data. The supply abnormality data refers to data related to air compressor supply abnormality. For more information about the supply abnormality data, see Figure 4 and the related description.

[0124] In some embodiments of the present specification, the operation parameters of the air compressors and the cooling parameters of the cooling devices are determined based on the abnormal gas supply data, and the obtained operation parameters and cooling parameters are safer and more reliable, and the risk of failure of the air compressors can be reduced.

[0125] In some embodiments, in one adjustment cycle, the processor can simultaneously determine the operation parameters of the plurality of air compressors and the cooling parameters of the plurality of cooling devices based on the pressure characteristic data, the power consumption data, the temperature data of the air compressors and the suction air temperature of the plurality of air compressors through the air compression model 320. At this time, the working state information 310 includes a sequence combination of the working state information of the plurality of air compressors, and the optimal parameters 330 include a sequence combination of the optimal operation parameters of the plurality of air compressors and the optimal cooling parameters of the plurality of cooling devices.

[0126] For example, the working state information 310 can be represented as , wherein is the pressure characteristic sequence of the i th air compressor, is the power consumption sequence of the i th air compressor, is the temperature sequence of the i th air compressor, is the suction air temperature of the i th air compressor. The optimal parameters 330 can be represented as , wherein represents the optimal operation parameter corresponding to the i th air compressor, represents the optimal cooling parameter corresponding to the j th cooling device. Some embodiments of the present specification consider the influence of the ambient temperature on product production, determine the operation parameters of the air compressors and the cooling parameters of the cooling devices through the air compression model, and can ensure that the gas supply amount of the air compressors and the ambient temperature meet the production requirements, and improve the product quality. is an example schematic diagram of generating alarm information according to some embodiments of the present specification. In some embodiments, as shown in

[0127] , the processor determines the abnormal gas supply data 530 based on the pressure characteristic data 411 and the power consumption data 412 of the air compressors; and in response to the abnormal gas supply data 530 meeting the early warning condition, generates alarm information and sends the alarm information to the alarm component.

[0128] For more information about the pressure characteristic data and the power consumption data of the air compressors, see Figure 5 the related description.

[0129] In some embodiments, as shown in Figure 5 , the processor determines the abnormal gas supply data 530 based on the pressure characteristic data 411 and the power consumption data 412 of the air compressors; and in response to the abnormal gas supply data 530 meeting the early warning condition, generates alarm information and sends the alarm information to the alarm component.

[0130] For more information about the pressure characteristic data and the power consumption data of the air compressors, see Figure 2 the related description.

[0131] ​​Air supply anomaly data 530 refers to data related to abnormal air supply from the air compressor. For example, air supply anomaly data 530 includes the location of the anomaly and the air compressor temperature at the time of the anomaly. Air supply anomalies include, but are not limited to, the difference between the air supply pressure data and the air consumption pressure data exceeding a preset threshold, and the fluctuation value of the air supply volume at multiple time points exceeding a preset fluctuation threshold.

[0132] In some embodiments, the processor constructs a reference vector based on the pressure characteristic data and air compressor power consumption data during gas supply anomalies in historical data, and determines the abnormal location and air compressor temperature at the time of the anomaly as the labels corresponding to the reference vector, and constructs a reference vector library based on multiple reference vectors and labels.

[0133] The processor constructs a target vector based on current pressure characteristic data and air compressor power consumption data. It then matches this target vector against a reference vector library to obtain the reference vector with the highest similarity. The label corresponding to this reference vector is then identified as the current abnormal air supply data. The similarity can be determined based on vector distance, which includes, but is not limited to, cosine distance.

[0134] In some embodiments, when constructing the reference vector library, the processor can also perform clustering optimization on the reference vectors. For example, the reference vectors recorded in the reference vector library are the reference vectors corresponding to the cluster centers of each cluster, to obtain more concise and representative reference vectors. Clustering methods include, but are not limited to, the K-Means clustering algorithm and the DBSCAN clustering algorithm.

[0135] In some embodiments, for an air compressor, the processor determines air supply anomaly data 530 based on pressure characteristic data 411, air compressor power consumption data 412, sound data 511 and image data 512, through anomaly model 520.

[0136] Anomaly model 520 is a model used to determine gas supply anomaly data 530. In some embodiments, anomaly model 520 is a machine learning model, such as a deep neural network (DNN) model.

[0137] The inputs to the anomaly model 520 include pressure characteristic data 411, air compressor power consumption data 412, sound data 511, and image data 512. The output of the anomaly model 520 is air supply anomaly data 530.

[0138] Sound data 511 refers to data related to sound on the gas production line. In some embodiments, the processor collects sound data 511 via a sound monitoring device.

[0139] The image data 512 refers to data related to images of the gas production line. In some embodiments, the processor collects the image data 512 through the image monitoring device.

[0140] For more information about the gas production line, see Figure 2 and related descriptions. For more information about the sound monitoring device and the image monitoring device, see Figure 1 and related descriptions.

[0141] In some embodiments, the processor trains the anomaly model 520 based on a plurality of second training samples with second labels. For example, the processor can input the plurality of second training samples into an initial anomaly model, construct a loss function based on the output of the initial anomaly model and the second labels, iteratively update the parameters of the initial anomaly model based on the loss function, and end the iteration when a completion condition of iteration is met to obtain the trained anomaly model. The method of iterative update includes but is not limited to gradient descent method, and the completion condition of iteration can be convergence of the loss function or the number of iterations reaching a threshold.

[0142] The second training sample includes sample pressure feature data, sample air compressor power consumption data, sample sound data, and sample image data. The second label is the actual gas supply anomaly data of the sample air compressor corresponding to the second training sample. The second training sample and the second label can be constructed based on historical data.

[0143] In some embodiments, the remote device 142 is configured to periodically train the anomaly model based on an update period. The control center 144 is configured to periodically transmit the model parameters of the trained anomaly model of the remote device 142 to the edge processor 141 based on the update period. The edge processor 141 is configured to determine the gas supply anomaly data by the anomaly model based on the data in the service database 143, and in response to the gas supply anomaly data in a preset time period meeting a second update condition, send a second update request to the control center 144.

[0144] For more information about the remote device, the edge processor, the service database, and the control center, see Figure 1 and related descriptions. For more information about the update period, see Figure 3 and related descriptions.

[0145] The second update condition is used to determine whether the control center transmits the model parameters of the trained anomaly model to the edge processor.

[0146] In some embodiments, the second update condition is that the difference between the number of alarms and the actual number of faults in a preset time period is greater than a preset number threshold. For more information about the alarm, see below.

[0147] In some embodiments, after receiving the alarm information, the maintenance personnel can check the air compressor to determine whether the air compressor has failed, and then obtain the actual number of failures.

[0148] In some embodiments, the preset number threshold can be determined based on the amount of resources (manpower, material resources) for handling failures. The greater the amount of resources, the greater the preset number threshold.

[0149] The second update request refers to a request for the control center to transmit the model parameters of the trained anomaly model to the edge processor. In response to receiving the second update request, the control center transmits the model parameters of the trained anomaly model to the edge processor.

[0150] Some embodiments of the present specification can quickly and accurately evaluate the condition of the air compressor in the mode of training the anomaly model by the remote device and performing calculation by the edge processor, effectively ensuring the safety of the production process.

[0151] Some embodiments of the present specification can more comprehensively analyze the state of the air compressor and more easily find anomalies in the air compressor by evaluating the working state of the air compressor through the anomaly model based on data in multiple modalities such as images and audio.

[0152] The early warning condition is used to determine whether the air compressor has failed. In some embodiments, the early warning condition includes any one of the anomaly position being a preset risk position, the air compressor temperature being greater than a temperature threshold, and the like. The temperature threshold can be set based on experience.

[0153] The preset risk position refers to a critical position that is set by the user in advance according to the importance of each link in the production process. For example, the preset position is the air outlet of the air compressor.

[0154] The alarm information refers to information related to the alarm of the alarm component. For example, the alarm information includes the air compressor that has failed, the failure site, the severity, and the like. In some embodiments, the processor determines the anomaly position as the failure site, and determines the severity based on the air compressor temperature. The higher the air compressor temperature, the greater the severity.

[0155] In some embodiments, after receiving the alarm information, the alarm component alarms the user. The form of the alarm can be one or more of a text prompt, a sound prompt, a voice prompt, a vibration, a flashing light, and the like.

[0156] Some embodiments of the present specification monitor the product production process in real time, and when the data is abnormal, the alarm component installed in the gas production line alarms, which can timely remind the maintenance personnel to perform maintenance when the equipment is abnormal, thereby ensuring the safe production of the product.

[0157] One or more embodiments of the present specification provide an intelligent air compressor control device based on deep learning and optimization algorithm, characterized in that the device comprises at least one processor and at least one memory; the at least one memory is used to store computer instructions; and the at least one processor is used to execute at least part of the computer instructions to realize the method as described above.

[0158] One or more embodiments of the present specification provide a computer readable storage medium, characterized in that the storage medium stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer executes the method as described above.

[0159] The above has described the basic concept, and it is obvious that the above detailed disclosure is only used as an example and does not limit the present specification for those skilled in the art. Although it is not explicitly stated here, those skilled in the art can make various modifications, improvements and corrections to the present specification. Such modifications, improvements and corrections are suggested in the present specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present specification.

[0160] At the same time, the present specification uses specific words to describe the embodiments of the present specification. As "one embodiment", "an embodiment", and / or "some embodiments" means a certain feature, structure or characteristic related to at least one embodiment of the present specification. Therefore, it should be emphasized and noted that the "an embodiment" or "one embodiment" or "one alternative embodiment" mentioned in different places in the present specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present specification can be properly combined.

[0161] In addition, unless the claim explicitly states, the order of the processing elements and sequences described in the present specification, the use of numerals and letters, or the use of other names, is not intended to limit the order of the processes and methods of the present specification. Although some currently considered useful embodiments of the invention are discussed in the above disclosure through various examples, it should be understood that such details are only for the purpose of illustration, and the additional claims are not limited to the disclosed embodiments, on the contrary, the claims are intended to cover all modifications and equivalent combinations that meet the spirit and scope of the embodiments of the present specification. For example, although the system components described above can be realized by hardware devices, they can also be realized only by software solutions, such as installing the described system on existing servers or mobile devices.

[0162] For simplicity and to facilitate understanding of one or more embodiments, a description of an embodiment sometimes refers to a plurality of features in a single embodiment, drawing, or description of an embodiment. However, this method of disclosure is not to be interpreted as meaning that the claimed embodiment requires more features than are explicitly recited in the claims. In fact, claims that do not specifically claim a combination of features are intended to cover the various possible combinations of features as would be understood by a person of ordinary skill in the art.

[0163] Some embodiments use numerical values to describe components, quantities of attributes. It should be understood that such numerical values used in the description of embodiments are, in some examples, modified by the adjectives "about," "approximately," or "substantially." Unless otherwise stated, "about," "approximately," or "substantially" indicate that the described numerical value allows for a variation of ±20%. Accordingly, numerical values used in the specification and claims of some embodiments are approximations that can vary depending on the desired characteristics of the individual embodiments. In some embodiments, numerical values used in the specification and claims are approximations that can vary depending on the desired characteristics of the individual embodiments. In some embodiments, numerical values should be considered in the context of the number of significant digits used in the number and the accepted bits of precision of the number. Although the numerical ranges and parameters setting forth the broadest scope of some embodiments of the specification are approximations, the numerical values set forth in the specific examples are reported as precisely as reasonably possible. The application is not limited to the specific numerical values set forth in the examples.

[0164] Each patent, patent application, patent publication, and other material cited in this specification is hereby incorporated by reference in its entirety. In the event of inconsistencies between the disclosure of this specification and the materials incorporated by reference, the disclosure of this specification shall prevail. In the event of inconsistencies between the disclosure of this specification and the claims, the claims shall prevail. In the event of inconsistencies between the disclosure of this specification and the materials incorporated by reference (whether attached hereto or subsequently added), the disclosure of this specification shall prevail. In the event of inconsistencies between the disclosure of this specification and the description, definitions, and / or terminology used in the materials incorporated by reference, the description, definitions, and / or terminology used in this specification shall prevail.

[0165] Finally, it should be understood that the embodiments described herein are merely exemplary of the principles of the embodiments described herein. Other variations having essentially the same structure and function are within the scope of the embodiments described herein. Accordingly, the embodiments described herein are not limited to the specific embodiments described herein, but rather, are intended to cover any and all alternatives, modifications, equivalents, and / or adaptations resulting from the application of the principles of the embodiments described herein.

Claims

1. An intelligent air compressor anomaly monitoring system, characterized in that, This includes pressure sensing devices, power monitoring devices, sound monitoring devices, image monitoring devices, and processors; The pressure sensing device is connected to the air supply line, which is connected to at least one of an air compressor, an air-consuming device, and an air-consuming production line. The pressure sensing device is configured to acquire pressure characteristic data, which includes air supply pressure data and / or air consumption pressure data. The power monitoring device is configured to acquire power consumption data of the air compressor; the sound monitoring device and the image monitoring device are installed in the gas production line, the sound monitoring device is configured to acquire sound data, and the image monitoring device is configured to acquire image data; The processor includes an edge processor, a remote device, and a control center; The edge processor is configured to: for one of the air compressors, determine the abnormal air supply data based on the pressure characteristic data, the air compressor power consumption data, the sound data, and the image data, using an anomaly model, wherein the anomaly model is a machine learning model; The remote device is configured to periodically train the anomaly model based on an update cycle; The control center is configured to periodically transmit the model parameters of the anomaly model trained by the remote device to the edge processor based on the update cycle.

2. The system as described in claim 1, characterized in that, The system also includes a temperature sensing device, which is installed on the air compressor and configured to acquire air compressor temperature data. The edge processor is further configured to periodically determine the operating parameters of the air compressor based on an adjustment cycle; Within one of the aforementioned adjustment cycles For an air compressor, based on the pressure characteristic data, the power consumption data, and the temperature data, the operating parameters of the air compressor are determined through an air compressor model, wherein the air compressor model is a reinforcement learning model.

3. The system as described in claim 2, characterized in that, The system also includes cooling equipment and an environmental monitoring device, the environmental monitoring device being configured to acquire the intake air temperature, the intake air temperature being the air temperature of the air intake of the air compressor; During one of the adjustment cycles, the edge processor is further configured to: For one of the air compressors, based on the pressure characteristic data, the power consumption data of the air compressor, the temperature data of the air compressor, and the intake air temperature, the operating parameters of the air compressor and / or the cooling parameters of the cooling equipment are determined through the air compressor model.

4. The system as described in claim 3, characterized in that, The input to the compressed air model also includes abnormal air supply data.

5. The system as described in claim 3, characterized in that, The excitation function of the air compressor model is related to the operating parameters, the cooling parameters, the energy efficiency coefficient of the air compressor, and the energy efficiency coefficient of the cooling equipment.

6. The system as described in claim 3, characterized in that, The processor also includes multiple service databases; The plurality of service databases are located in the edge processor and / or the remote device, and the plurality of service databases are configured to store at least one of the pressure characteristic data, the air compressor power consumption data, and the air compressor temperature data; The remote device is located at a remote end that communicates with the gas production line, and is further configured to periodically train the air compression model based on an update cycle; the control center is further configured to periodically transmit the model parameters trained by the remote device to the edge processor based on the update cycle. The edge processor is disposed in the gas production line and is further configured as follows: For one of the air compressors, based on the pressure characteristic data, the power consumption data of the air compressor, the temperature data of the air compressor, and the intake air temperature, the operating parameters of the air compressor and / or the cooling parameters of the cooling equipment are determined through the air compressor model. In response to the fact that the operating parameters of the air compressor and / or the cooling parameters of the cooling equipment meet the first update condition within a preset time period, a first update request is sent to the control center.

7. The system as described in claim 6, characterized in that, The update cycle is related to the amount of production data of the gas-consuming production line, which includes the gas supply pressure data, the gas consumption pressure data, the air compressor power consumption data, and the air compressor temperature data.

8. The system as described in claim 1, characterized in that, The system also includes an alarm component, which is installed in the gas production line and configured to trigger an alarm based on alarm information. The edge processor is further configured to: In response to the gas supply anomaly data meeting the early warning conditions, an alarm message is generated and sent to the alarm component.

9. The system as described in claim 8, characterized in that, The edge processor is further configured to send a second update request to the control center in response to the gas supply anomaly data within a preset time period meeting the second update condition.

10. A method for monitoring abnormalities in an intelligent air compressor, executed by a processor of the intelligent air compressor abnormality monitoring system as described in claim 1, comprising: Pressure characteristic data is acquired through pressure sensing devices, including gas supply pressure data and / or gas consumption pressure data. The power consumption data of the air compressor is obtained through power monitoring equipment; Acquire sound data through a sound monitoring device; Image data is acquired through an image monitoring device; For one of the air compressors, based on the pressure characteristic data, the air compressor power consumption data, the sound data, and the image data, the abnormal air supply data is determined through an anomaly model, wherein the anomaly model is a machine learning model; The anomaly model is periodically trained based on the update cycle.

Images