A method and system for controlling air compressor frequency conversion and energy saving based on data analysis

Abstract

The present invention discloses a variable frequency energy-saving control method and system for air compressors based on data analysis, which specifically relates to the technical field of air compressor control. In view of the frequency jitter and motor instability problems that permanent magnet variable frequency screw air compressors are prone to in high-frequency gas fluctuation scenarios, the method collects exhaust pressure, gas flow, motor current, inverter output frequency and ambient temperature data in real time, uses a data analysis model to perform trend prediction, constructs a multi-dimensional operating characteristic curve, accurately identifies the gas fluctuation pattern, and makes a predictive judgment before the frequency fluctuation is about to exceed the limit. The method dynamically adjusts the inverter control strategy according to the prediction result, buffers the frequency response rate in advance, and automatically triggers the energy-saving mode when the load change trend is abnormal, and optimizes the speed control in real time. The method effectively improves the stability and response accuracy of the air compressor operation, significantly reduces energy consumption, and extends the service life of the equipment. The method is suitable for the intelligent energy-saving operation needs in high-beat, high-precision manufacturing scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of air compressor control, and in particular to a frequency conversion energy-saving control method and system for an air compressor based on data analysis. Background Art

[0002] With the continuous advancement of industrial automation, air compressors, as key power equipment, are widely used in industries such as manufacturing, metallurgy, chemicals, and electronics. Among various types of air compressors, permanent magnet variable-frequency screw air compressors are becoming a mainstream product due to their high efficiency, energy saving, and low noise levels. Compared to traditional power-frequency drive methods, variable-frequency control can dynamically adjust the speed based on actual air consumption, significantly reducing energy consumption and improving operational efficiency.

[0003] The existing technology has the following shortcomings:

[0004] In some manufacturing workshops where high-precision pneumatic equipment is concentrated, such as the SMT patch line of an electronics manufacturing company, due to the fast production cycle and drastic changes in air consumption, the permanent magnet variable frequency screw air compressor experiences frequency jitter during real-time response. That is, the inverter frequency fluctuates violently in a short period of time, causing unstable motor operation. Long-term operation will accelerate bearing wear and cause the system to alarm and shut down. Summary of the Invention

[0005] The purpose of the present invention is to provide an air compressor variable frequency energy-saving control method and system based on data analysis to solve the shortcomings of the background technology.

[0006] In order to achieve the above-mentioned object, the present invention provides the following technical solution: a variable frequency energy-saving control method for an air compressor based on data analysis, comprising:

[0007] Collect real-time operating data of the air compressor during operation, including exhaust pressure, air flow, motor current, inverter output frequency and ambient temperature;

[0008] Performing dynamic trend prediction on the real-time operating data through a data analysis model, constructing a multi-dimensional operating condition characteristic curve, identifying the gas consumption fluctuation pattern based on the characteristic curve, and performing predictive judgment before the frequency fluctuation amplitude exceeds a set threshold;

[0009] The inverter control strategy is adjusted according to the prediction results, the frequency conversion response rate is buffered in advance, and when an abnormal load change trend is detected, the adaptive energy-saving mode is triggered and the compressor operating speed is adjusted in real time.

[0010] Preferably, the output pressure of the compressed air is monitored in real time according to the pressure sensor installed at the exhaust port of the compressor, and a mass flow meter or vortex flow meter is installed on the output pipe or main pipe of the compressor to obtain the actual flow data of the gas system. The instantaneous current value of the motor when running is obtained through the current sensing unit built into the inverter or the Hall current sensor installed externally, and the actual operating frequency value output by the inverter to the main motor is directly read, and the temperature sensor arranged at the air inlet of the compressor or in the machine room monitors the working environment temperature.

[0011] Preferably, a random forest regression model is used to perform dynamic trend prediction on the multi-dimensional real-time operation data collected by the air compressor:

[0012] The raw operating data collected from the air compressor system, including exhaust pressure, air flow, motor current, inverter output frequency, and ambient temperature, is constructed as an input feature vector set. Samples are extracted from the historical operating data using a sliding window method. Each sample contains the characteristic parameters of the current and previous moments, and the value of the target parameter in the next time period.

[0013] Construct training set D = {(X t ,Y t+Δt )}, used for supervised learning, where X t is the input feature vector at time t, Y t+Δt is the target value at time Δt in the future;

[0014] Use the random forest algorithm to build multiple decision trees. Each tree is trained independently on different training subsets and feature subsets. The training process includes:

[0015] Bootstrap sampling method is used to subsample the training data;

[0016] Select the best splitting features and splitting points at the nodes of each tree;

[0017] Construct a regression forest consisting of multiple trees, and the final prediction result is the average of the prediction results of all trees.

[0018] Preferably, during the operation of the air compressor system, the feature vector X at the current time point is collected in real time. t , input into the trained random forest model, and output the predicted value Y t+Δt , that is, predicting the changing trend of key system parameters within a future time window;

[0019] Multiple prediction parameters are combined and plotted into a multi-dimensional time series curve to form an operating condition trend map. The horizontal axis is time and the vertical axis is the value of different prediction variables. A set of vector data is generated at each time point to form an operating condition status trajectory.

[0020] Preferably, the frequency sequence of the inverter output frequency F={f1, f2, ..., f m}; where f m Represents the predicted frequency of the mth time step, where m is the number of steps in the prediction time window; calculates the maximum rising slope of the continuous rising segment in the frequency sequence, and extracts the steepest falling slope of the continuous falling segment in the sequence.

[0021] Preferably, the maximum uplink rate and the steepest descent slope are normalized so that they are both between [0, 1], and the average of the normalized maximum uplink rate and the steepest descent slope is calculated to obtain the comprehensive fluctuation intensity assessment coefficient.

[0022] Preferably, the obtained comprehensive fluctuation intensity evaluation coefficient is compared with a predetermined threshold. If the comprehensive fluctuation intensity evaluation coefficient is greater than the predetermined threshold, it is determined that the frequency instability zone is about to be entered. At this time, the inverter control strategy needs to be adjusted to buffer the frequency conversion response rate in advance.

[0023] Preferably, the comprehensive fluctuation intensity assessment coefficient, the load change rate, and the current energy consumption per unit gas volume are used as input items of the fuzzy logic;

[0024] The inverter response buffer factor, target operating frequency adjustment factor, and energy-saving mode switching signal are used as output items of the fuzzy logic;

[0025] The continuous values ​​of input variables are converted into fuzzy linguistic variables through membership functions;

[0026] According to the established rule base, the input fuzzy quantity is pattern matched;

[0027] The inference results are converted into specific control outputs. For the energy-saving mode switching signal, whether it is correct is directly determined based on the activation degree of the fuzzy output;

[0028] The final processing results are transmitted to the inverter control unit and the compressor main control system to perform frequency adjustment, response buffering and energy-saving mode switching operations to form a closed-loop control.

[0029] The present invention also provides an air compressor variable frequency energy-saving control system based on data analysis, which includes a data acquisition module, a prediction and analysis module, and a control and adjustment module;

[0030] Data acquisition module: collects real-time operating data of the air compressor during operation, including exhaust pressure, air flow, motor current, inverter output frequency and ambient temperature;

[0031] Prediction and Analysis Module: This module uses a data analysis model to perform dynamic trend prediction on the real-time operating data, constructs a multi-dimensional operating condition characteristic curve, identifies the gas consumption fluctuation pattern based on the characteristic curve, and performs predictive judgment before the frequency fluctuation amplitude exceeds a set threshold;

[0032] Control adjustment module: Adjusts the inverter control strategy based on the prediction results, buffers the frequency conversion response rate in advance, and triggers the adaptive energy-saving mode when an abnormal load change trend is detected, adjusting the compressor operating speed in real time.

[0033] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0034] 1. This invention introduces a data analysis model based on random forest regression, combines multi-parameter real-time data acquisition with the construction of multi-dimensional operating characteristic curves, and achieves dynamic trend prediction and intelligent control of the air compressor's operating status. Compared with traditional methods that rely on fixed logic or PID control, this method can identify gas fluctuation patterns in advance, make predictive judgments before frequency fluctuations are about to exceed the limit, and promptly adjust the inverter response rate, significantly suppressing frequency jitter, reducing the risk of motor impact and system failure, and effectively extending the equipment's service life.

[0035] 2. This invention further incorporates fuzzy logic control technology, incorporating key indicators such as comprehensive fluctuation intensity, load change rate, and specific energy consumption as inputs. This enables adaptive adjustment of the variable frequency control strategy and intelligent switching of energy-saving modes. This dynamically optimizes the compressor operating speed based on actual operating conditions, improving the system's energy efficiency and operational stability. This approach is particularly suitable for modern manufacturing plants with frequent gas load fluctuations and high-speed cycles. The overall solution offers high real-time performance, adaptability, and significant energy savings, promising promising engineering applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0037] Figure 1 Flow chart of the method of the present invention.

[0038] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0040] Example 1, please refer to Figure 1 As shown, the air compressor variable frequency energy-saving control method based on data analysis described in this embodiment includes:

[0041] Collect real-time operating data of the air compressor during operation, including exhaust pressure, air flow, motor current, inverter output frequency and ambient temperature;

[0042] Performing dynamic trend prediction on the real-time operating data through a data analysis model, constructing a multi-dimensional operating condition characteristic curve, identifying the gas consumption fluctuation pattern based on the characteristic curve, and performing predictive judgment before the frequency fluctuation amplitude exceeds a set threshold;

[0043] The inverter control strategy is adjusted according to the prediction results, the frequency conversion response rate is buffered in advance, and when an abnormal load change trend is detected, the adaptive energy-saving mode is triggered and the compressor operating speed is adjusted in real time.

[0044] Real-time collection of key operating parameters of permanent magnet variable frequency screw air compressors, including the following:

[0045] A high-precision pressure sensor (such as a pressure transmitter) is installed at the compressor's exhaust port to monitor the compressed air output pressure in real time. This parameter reflects the current system's required air source pressure and is an important basis for adjusting the inverter's output frequency. The sampling frequency can be set between 100 and 500 milliseconds, adjusted based on actual response requirements.

[0046] Install a mass flowmeter or vortex flowmeter on the compressor's output or main pipeline to obtain real-time flow data from the gas system. This data is used to determine load changes at the gas user end and, combined with historical data, to predict short-term gas consumption trends, providing a reference for variable frequency control.

[0047] The VFD's built-in current sensing unit or an external Hall effect current sensor captures the instantaneous current value of the motor during operation. Motor current is a key indicator for evaluating load changes and determining system efficiency. It also serves as an early warning for potential problems such as overloads and mechanical failures.

[0048] Directly read the actual operating frequency output from the inverter to the main motor, reflecting changes in compressor speed. This parameter is dynamically correlated with exhaust pressure and air flow, making it a key control variable in the entire energy-saving control model.

[0049] Temperature sensors are installed at the compressor air inlet or in the machine room to monitor the operating environment. Ambient temperature directly affects compressor efficiency and motor heating. The system can adjust operating modes (such as automatic speed limit and enhanced heat dissipation) based on temperature changes to ensure safe and efficient equipment operation.

[0050] All of the above sensor data are connected to the data acquisition module through the PLC control system or industrial gateway and enter the central control unit for use in subsequent data analysis models for fusion calculation, working condition identification and predictive control.

[0051] The collected raw operating data (including exhaust pressure, air flow, motor current, inverter output frequency, ambient temperature, etc.) is first filtered, denoised and standardized to eliminate outliers and interference signals to ensure the accuracy and stability of subsequent analysis.

[0052] The system divides the data window according to the set time interval (such as 1 minute, 5 minutes, etc.), extracts the data features within each period, such as the average, maximum, minimum, standard deviation and other statistics, and calculates the correlation and coordinated change trend between the variables.

[0053] Introduce time series analysis (such as ARIMA model), machine learning algorithms (such as LSTM neural network, random forest regression) or industrial big data analysis methods to predict the trend of various operating parameters over time.

[0054] The present invention uses a random forest regression model to perform dynamic trend prediction on multi-dimensional real-time operating data collected by air compressors. The specific steps are as follows:

[0055] The original operating data collected from the air compressor system includes but is not limited to the following parameters:

[0056] Exhaust pressure (P), air flow (Q), motor current (I), inverter output frequency (F) and ambient temperature (T); in addition, timestamps and historical trend data (such as the mean, standard deviation, slope, etc. within the previous n minutes) can be introduced as auxiliary features. The above parameters are constructed as the input feature vector set X = {x1, x2, ..., x n}, the corresponding prediction target is the changing trend of key parameters (such as pressure and frequency) within a future time window.

[0057] Extract samples from historical running data in a sliding window manner. Each sample contains:

[0058] Feature parameters at the current and previous moments (as input);

[0059] The value of the target parameter within the next time period (e.g., 30 seconds or 1 minute in the future) (as output);

[0060] Construct training set D = {(X t ,Y t+Δt )}, used for supervised learning, where X t is the input feature vector at time t, Y t+Δt is the target value (such as frequency, pressure) at the future Δt time;

[0061] Use the random forest algorithm to build multiple decision trees, each of which is trained independently on different training subsets and feature subsets to enhance generalization ability. The training process includes:

[0062] Bootstrap sampling method is used to subsample the training data;

[0063] Select the best splitting features and splitting points at the nodes of each tree;

[0064] Construct a regression forest consisting of multiple trees, and the final prediction result is the average of the prediction results of all trees.

[0065] During the operation of the air compressor system, the feature vector X at the current time point is collected in real time. t , input into the trained random forest model, and output the predicted value Y t+Δt , that is, predicting the changing trend of key system parameters within a future time window.

[0066] Combine multiple prediction parameters (such as pressure, frequency, and current changes over the next 30 seconds) and plot them into a multidimensional time series curve, creating a working condition trend map. The horizontal axis represents time (t), and the vertical axis represents the values ​​of the different prediction variables (such as P(t), F(t), and I(t)). A set of vector data is generated at each time point, forming a working condition trajectory.

[0067] Multiple parameters output by real-time predictions are continuously monitored in the form of sliding time windows to generate a sequence of dynamic characteristic curves. For example, within each 30-second sliding window, the changing trend curves of each parameter are recorded and the data is continuously refreshed.

[0068] Based on historical operating data, several typical gas consumption fluctuation patterns are pre-defined, including:

[0069] Steady-state mode: flow and frequency change slightly, and the compressor maintains constant speed operation;

[0070] Light load periodic fluctuation: The flow rate rises and falls periodically, with slight frequency jitter;

[0071] Rapid load fluctuations: flow rate suddenly rises or falls, with obvious frequency response;

[0072] Abnormal fluctuation / sudden change: The frequency fluctuates sharply for a short period of time, posing a potential risk of failure.

[0073] Using machine learning models such as K-means clustering or support vector machine (SVM), the above curves are extracted for features, and the current characteristic curve is classified into the closest historical operating condition mode to achieve automatic identification.

[0074] The inverter output frequency sequence in the future prediction period is obtained through the trained random forest regression model: F = {f1,f2,...,f m}; where f m Indicates the prediction frequency of the mth time step, where m is the number of steps in the prediction time window (e.g., 30 points are sampled in 30 seconds).

[0075] Calculate the maximum slope of the continuous rising segment in the frequency sequence, reflecting the intensity of the upward fluctuation of the frequency in a short period of time. It is defined as: Among them, S up Indicates the maximum uplink rate, indicating a sharp increase in frequency. i , t j Indicates two different sampling time points;

[0076] Similarly, the steepest slope of the consecutive descending segments in the sequence is extracted, defined as: S down It is the steepest descent slope. This value is a negative number. The larger its absolute value is, the more rapid the frequency drop is, which means the risk of frequency undershoot is higher.

[0077] The maximum upward rate and the steepest downward slope are normalized so that they are both between [0,1]. The average of the normalized maximum upward rate and the steepest downward slope is calculated to obtain the comprehensive fluctuation intensity assessment coefficient.

[0078] The obtained comprehensive fluctuation intensity assessment coefficient is compared with the predetermined threshold. If the comprehensive fluctuation intensity assessment coefficient is greater than the predetermined threshold, it is determined that the frequency instability zone is about to be entered. At this time, the inverter control strategy needs to be adjusted to buffer the frequency conversion response rate in advance.

[0079] The comprehensive fluctuation intensity assessment coefficient, load change rate and current unit gas energy consumption are used as input items of fuzzy logic;

[0080] The comprehensive fluctuation intensity assessment coefficient reflects the severity of the change in compressor frequency in a short period of time and is an important priori signal for determining whether the system is facing frequency shock.

[0081] The load change rate is calculated by calculating the first-order derivative of the air flow in real time. It represents the rate of load change per unit time. A positive value indicates an increase in load, a negative value indicates a decrease in load, and a zero or near-zero value indicates a stable system load. This parameter reflects the dynamics and fluctuation frequency of the system's operating conditions.

[0082] Energy consumption per unit of air volume is calculated by dividing the current compressor power by the output air volume, reflecting the compressor's current energy efficiency level. A high value indicates that the system is operating outside its optimal efficiency range and is an important basis for initiating energy-saving strategies.

[0083] The inverter response buffer factor, target operating frequency adjustment factor, and energy-saving mode switching signal are used as output items of the fuzzy logic;

[0084] The inverter response buffer factor (α) adjusts the inverter's acceleration and deceleration ramp rate, or how quickly the inverter responds to changes. A high α indicates a need for frequency response buffering, and the controller automatically slows down the inverter's frequency change rate to avoid mechanical shock or system instability caused by an overly rapid response.

[0085] The target operating frequency adjustment factor (β) is used to modify the compressor's target operating frequency to dynamically align with actual gas demand and the optimal energy efficiency point. When the system load is forecast to decrease, β is adjusted negatively, reducing the compressor frequency appropriately. Conversely, if the load is forecast to increase, β is adjusted positively, increasing the frequency in advance.

[0086] The energy-saving mode switch signal is a Boolean logic output that determines whether to immediately switch to energy-saving operation. When system load changes slowly, energy consumption is high, or fluctuates dramatically but does not require a rapid response, the system automatically enters energy-saving mode. This can include reducing operating frequency, initiating intermittent compression, or extending downtime.

[0087] The fuzzy controller implements the decision-making process through the following reasoning steps:

[0088] The continuous values ​​of the input variables are converted into fuzzy linguistic variables through membership functions. For example, the comprehensive fluctuation intensity can be fuzzified into "low," "medium," "high," and "very high"; the load change rate can be fuzzified into "rapid decline," "slow change," and "rapid increase"; and the energy consumption per unit gas volume can be fuzzified into "high consumption," "medium consumption," and "low consumption."

[0089] The system performs pattern matching on fuzzy inputs based on an established rule base. For example, if the system experiences high fluctuation intensity, rapid load increases, or moderate unit energy consumption, the controller will determine that the system is about to face a dynamic load shock and has not yet reached efficient operation. Therefore, it should moderately buffer the response, increase the target frequency, and temporarily suspend energy-saving mode.

[0090] For example, when the "fluctuation intensity is medium", "the load changes smoothly", and "the energy consumption is high", the controller will infer that the current system is running redundantly, which can slow down the frequency conversion response speed, lower the operating frequency, and immediately enter the energy-saving mode to reduce energy consumption.

[0091] The inference results are converted into specific control outputs. For α and β, the center of gravity method is used for numerical defuzzification, and the output is a specific buffer factor and frequency adjustment amount (for example, α = 0.7 means the output change rate is limited to 70%; β = –2 means the target frequency is reduced by 2Hz). For the energy-saving mode switching signal, the correctness is directly determined based on the activation level of the fuzzy output.

[0092] The final processing results are transmitted to the inverter control unit and the compressor main control system to perform operations such as frequency adjustment, response buffering and energy-saving mode switching to form a closed-loop control.

[0093] Example 2, please refer to Figure 2 As shown, the air compressor variable frequency energy-saving control system based on data analysis described in this embodiment includes a data acquisition module, a prediction and analysis module, and a control and adjustment module;

[0094] Data acquisition module: collects real-time operating data of the air compressor during operation, including exhaust pressure, air flow, motor current, inverter output frequency and ambient temperature;

[0095] Prediction and Analysis Module: This module uses a data analysis model to perform dynamic trend prediction on the real-time operating data, constructs a multi-dimensional operating condition characteristic curve, identifies the gas consumption fluctuation pattern based on the characteristic curve, and performs predictive judgment before the frequency fluctuation amplitude exceeds a set threshold;

[0096] Control adjustment module: Adjusts the inverter control strategy based on the prediction results, buffers the frequency conversion response rate in advance, and triggers the adaptive energy-saving mode when an abnormal load change trend is detected, adjusting the compressor operating speed in real time.

[0097] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0098] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0099] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0100] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A variable frequency energy-saving control method for air compressors based on data analysis, characterized by: include: Collect real-time operating data of the air compressor during operation, including exhaust pressure, air flow, motor current, inverter output frequency and ambient temperature; Performing dynamic trend prediction on the real-time operating data through a data analysis model, constructing a multi-dimensional operating condition characteristic curve, identifying the gas consumption fluctuation pattern based on the characteristic curve, and performing predictive judgment before the frequency fluctuation amplitude exceeds a set threshold; Specifically, it uses a random forest regression model to perform dynamic trend prediction on multi-dimensional real-time operating data collected by air compressors; Adjust the inverter control strategy based on the prediction results, buffer the inverter response rate in advance, and trigger the adaptive energy-saving mode when abnormal load change trends are detected, adjusting the compressor operating speed in real time; Specifically, the trained random forest regression model is used to obtain the inverter output frequency sequence F={f1,f2,...,f m }; where f m Represents the predicted frequency of the mth time step, where m is the number of steps in the prediction time window; calculates the maximum rising slope of the continuous rising segment in the frequency sequence, and extracts the steepest falling slope of the continuous falling segment in the sequence; Normalize the maximum rising slope and the steepest falling slope so that they are both between [0,1]. Calculate the average of the normalized maximum rising slope and the steepest falling slope to obtain the comprehensive volatility intensity assessment coefficient. The obtained comprehensive fluctuation intensity assessment coefficient is compared with a predetermined threshold. If the comprehensive fluctuation intensity assessment coefficient is greater than the predetermined threshold, it is determined that the frequency is about to enter the unstable region. At this time, the inverter control strategy needs to be adjusted to buffer the frequency conversion response rate in advance. The comprehensive fluctuation intensity assessment coefficient, load change rate and current unit gas energy consumption are used as input items of fuzzy logic; The inverter response buffer factor, target operating frequency adjustment factor, and energy-saving mode switching signal are used as output items of the fuzzy logic; The inverter response buffer factor α is used to adjust the inverter's acceleration and deceleration slopes. When α is high, it means that the frequency response needs to be buffered, and the controller automatically reduces the inverter's frequency change rate.

2. The air compressor variable frequency energy-saving control method based on data analysis according to claim 1 is characterized in that: The output pressure of the compressed air is monitored in real time by the pressure sensor installed at the exhaust port of the compressor. A mass flow meter or vortex flow meter is installed on the output pipe or main pipe of the compressor to obtain the actual flow data of the gas system. The instantaneous current value of the motor when running is obtained through the current sensing unit built into the inverter or the external Hall current sensor. The actual operating frequency value output by the inverter to the main motor is directly read, and the temperature sensor installed at the air inlet of the compressor or in the machine room monitors the working environment temperature.

3. The air compressor variable frequency energy-saving control method based on data analysis according to claim 2 is characterized in that: A random forest regression model is used to perform dynamic trend prediction on the multi-dimensional real-time operating data collected by air compressors: The raw operating data collected from the air compressor system, including exhaust pressure, air flow, motor current, inverter output frequency, and ambient temperature, is constructed as an input feature vector set. Samples are extracted from the historical operating data using a sliding window method. Each sample contains the characteristic parameters of the current and previous moments, and the value of the target parameter in the next time period. Construct training set D = {(X t ,Y t+Δt )}, used for supervised learning, where X t is the input feature vector at time t, Y t+Δt is the target value at time Δt in the future; Use the random forest algorithm to build multiple decision trees. Each tree is trained independently on different training subsets and feature subsets. The training process includes: Bootstrap sampling method is used to subsample the training data; Select the best splitting features and splitting points at the nodes of each tree; Construct a regression forest consisting of multiple trees, and the final prediction result is the average of the prediction results of all trees.

4. The air compressor variable frequency energy-saving control method based on data analysis according to claim 3 is characterized in that: During the operation of the air compressor system, the feature vector at the current time point is collected in real time, input into the trained random forest regression model, and the predicted value is output, that is, the change trend of the key system parameters in the future time window is predicted; Multiple prediction parameters are combined and plotted into a multi-dimensional time series curve to form an operating condition trend map. The horizontal axis is time and the vertical axis is the value of different prediction variables. A set of vector data is generated at each time point to form an operating condition status trajectory.

5. The air compressor variable frequency energy-saving control method based on data analysis according to claim 1 is characterized in that: The comprehensive fluctuation intensity assessment coefficient, load change rate and current unit gas energy consumption are used as input items of fuzzy logic; The inverter response buffer factor, target operating frequency adjustment factor, and energy-saving mode switching signal are used as output items of the fuzzy logic; The continuous values ​​of input variables are converted into fuzzy linguistic variables through membership functions; According to the established rule base, the input fuzzy quantity is pattern matched; The inference results are converted into specific control outputs. For the energy-saving mode switching signal, whether it is correct is directly determined based on the activation degree of the fuzzy output; The final processing results are transmitted to the inverter control unit and the compressor main control system to perform frequency adjustment, response buffering and energy-saving mode switching operations to form a closed-loop control.

6. A data analysis-based air compressor variable frequency energy-saving control system, used to implement the data analysis-based air compressor variable frequency energy-saving control method according to any one of claims 1 to 5, characterized in that: Including data acquisition module, prediction analysis module and control adjustment module; Data acquisition module: collects real-time operating data of the air compressor during operation, including exhaust pressure, air flow, motor current, inverter output frequency and ambient temperature; Prediction and Analysis Module: This module uses a data analysis model to perform dynamic trend prediction on the real-time operating data, constructs a multi-dimensional operating condition characteristic curve, identifies the gas consumption fluctuation pattern based on the characteristic curve, and performs predictive judgment before the frequency fluctuation amplitude exceeds a set threshold; Control adjustment module: Adjusts the inverter control strategy based on the prediction results, buffers the frequency conversion response rate in advance, and triggers the adaptive energy-saving mode when an abnormal load change trend is detected, adjusting the compressor operating speed in real time.

Images