Compressor intelligent control method and system based on dynamic pressure relief and storage medium

Abstract

The invention provides a compressor intelligent control method and system based on dynamic pressure relief and a storage medium, and the method comprises the steps: firstly, capturing the multi-physical field coupling characteristics of a compressor in a shutdown state in real time by deploying a pressure, temperature, vibration and current four-dimensional sensing network; secondly, based on a preset pressure entropy model, fusing the pressure fluctuation intensity, the temperature anomaly index, the high-frequency vibration factor and the current attenuation coefficient to quantitatively evaluate a pressure entropy value, and triggering a three-stage pressure relief mode based on the pressure entropy value; then, based on the deviation between the cavity pressure and the target pressure, pressure relief parameters are dynamically adjusted, and stable pressure transition is achieved; and finally, collecting full-link data of pressure relief operation, and dynamically optimizing pressure entropy model parameters based on reinforcement learning, so that the system continuously adapts to equipment aging and working condition changes. Through dynamic closed-loop adjustment, pressure relief energy consumption waste and equipment loss are reduced, and the stability of the pressure relief process is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of refrigerators, more particularly, to a compressor intelligent control method and system based on dynamic pressure relief and a storage medium. BACKGROUND

[0002] In the field of compressor control, pressure relief operation is a key link to ensure the safe start of equipment. The traditional compressor pressure relief control generally adopts a fixed time pressure relief mechanism, that is, the pressure relief operation is performed according to a preset fixed time. When the pressure in the cavity has naturally decreased to a safe range after the compressor is stopped, the fixed time pressure relief operation will still be forced to start, resulting in invalid energy consumption. Moreover, there are problems of insufficient pressure relief and excessive pressure relief. When the fixed time is not enough to release high pressure, the compressor starts with load, causing current impact and accelerating the aging of the motor winding; when the pressure relief is prolonged in the low pressure state, it causes the lubricating oil to flow back, causing dry friction of the bearing and reducing the service life of the compressor.

[0003] At present, the existing technology has a pressure relief time control based on pressure feedback, but it relies on a single pressure sensor and cannot capture the coupling effect of multiple physical fields such as temperature, vibration and current; and it usually uses fixed pressure relief parameters, which cannot adapt to the actual working state of the compressor. Therefore, there is an urgent need for an intelligent control technology based on dynamic pressure relief. SUMMARY

[0004] In view of the above problems, the purpose of the present application is to provide a compressor intelligent control method and system based on dynamic pressure relief and a storage medium, to build a complete state portrait of the compressor by deploying a four-dimensional sensor network of pressure, temperature, vibration and current; to fuse pressure dynamic characteristics, temperature characteristics and mechanical state quantitative risk assessment; to implement graded pressure relief based on risk level, to continuously adjust the pressure relief parameters combined with the pressure drop rate, to realize smooth transition of pressure; and to continuously optimize the model parameters based on operation data, to adapt to the changes in the whole life cycle of the equipment.

[0005] The first aspect of the present application provides a compressor intelligent control method based on dynamic pressure relief, which comprises:

[0006] A plurality of heterogeneous data is collected by a preset sensor array;

[0007] According to the plurality of heterogeneous data, a feature operating parameter is obtained based on a preset cleaning and feature extraction algorithm;

[0008] According to the feature operating parameter, a pressure entropy value is obtained based on a preset pressure entropy model;

[0009] According to the pressure entropy value, a pressure relief mode is determined based on a preset graded threshold pressure relief strategy;

[0010] Based on a preset pressure relief valve parameter table, set the pressure relief parameters according to the pressure relief mode;

[0011] After performing the pressure relief operation, the cavity pressure is monitored in real time;

[0012] Dynamically adjusting the pressure relief parameter based on the deviation between the cavity pressure and a preset target pressure;

[0013] When it is determined based on the cavity pressure that the cavity pressure is in a preset stable state, the compressor is started and pressure relief operation data is recorded;

[0014] The pressure relief operation data is used as a training set, and the weights of the pressure entropy model are updated according to a preset self-training cycle.

[0015] In this solution, the multi-source heterogeneous data is collected through a preset sensor array, specifically:

[0016] Pressure sensors are deployed at the compressor suction chamber, discharge chamber and oil separator to synchronously collect pressure data and obtain a pressure change curve.

[0017] The infrared temperature sensor array is used to monitor the surface temperature of the compressor cylinder in real time and obtain a temperature distribution map;

[0018] The vibration curve of the compressor when it is stopped is captured by a three-axis vibration sensor;

[0019] Detect the residual current curve of the compressor through the current Hall sensor;

[0020] The pressure change curve, temperature distribution diagram, vibration curve and residual current curve are combined with timestamps to integrate into multi-source heterogeneous data.

[0021] In this solution, the preset cleaning and feature extraction algorithm obtains characteristic operation parameters based on the multi-source heterogeneous data, specifically:

[0022] According to the pressure change curve, filtering is performed based on a preset sliding window, and the pressure change rate and standard deviation in each window are calculated to obtain a pressure feature vector;

[0023] According to the temperature distribution diagram, the number, area and temperature value of the local overheating area are extracted to obtain a temperature feature vector;

[0024] Processing the vibration curve based on a preset wavelet packet decomposition to obtain a high-frequency vibration feature;

[0025] Analyzing the residual current curve based on the slope to obtain a current attenuation coefficient;

[0026] Integrate the pressure feature vector, temperature feature vector, high-frequency vibration feature and current attenuation coefficient to obtain a characteristic operating parameter.

[0027] In this scheme, the pressure entropy value is obtained based on the preset pressure entropy model according to the characteristic operating parameter, and specifically includes:

[0028] Obtain a first pressure weight and a second pressure weight.

[0029] According to the temperature feature vector, a pressure compensation coefficient is determined for adjusting the first pressure weight and the second pressure weight.

[0030] Calculate the product of the adjusted first pressure weight and the pressure change rate of the pressure feature vector to obtain a pressure change factor.

[0031] Calculate the product of the adjusted second pressure weight and the pressure standard deviation of the pressure feature vector to obtain a pressure standard deviation factor.

[0032] According to the high-frequency vibration feature, a correction coefficient is obtained based on a preset correction coefficient mapping relationship.

[0033] According to the pressure change factor, the pressure standard deviation factor and the correction coefficient, a pressure entropy value is obtained.

[0034] If the current attenuation coefficient exceeds a preset attenuation threshold, the pressure entropy value is positively compensated.

[0035] In this scheme, the pressure relief mode is determined according to the pressure entropy value based on the preset hierarchical threshold pressure relief strategy, and specifically includes:

[0036] If the pressure entropy value is lower than a preset first pressure entropy threshold, it is determined as a zero pressure relief mode, and the pressure relief time and the pressure relief opening degree are set as minimum values.

[0037] If the pressure entropy value is between the preset first pressure entropy threshold and a preset second pressure entropy threshold, it is determined as a short-time pressure relief mode, the pressure relief opening degree is adjusted according to the pressure relief entropy value, and the pressure relief operation is performed according to a preset first pressure relief time.

[0038] If the pressure entropy value is higher than the preset second pressure entropy threshold, it is determined as a forced pressure relief mode, the pressure relief parameters are set based on a preset three-stage pressure relief strategy, and the pressure relief operation is performed.

[0039] In this scheme, the pressure relief parameters are dynamically adjusted based on the deviation of the cavity pressure from the preset target pressure, and specifically includes:

[0040] When it is determined as a forced pressure relief mode, a pressure drop rate is calculated according to the cavity pressure.

[0041] If the pressure drop rate is greater than a preset upper limit of the drop rate, then the pressure relief opening degree is decreased step by step by a preset step size;

[0042] If the pressure drop rate is less than a preset lower limit of the drop rate, then the pressure relief opening degree is increased step by step by a preset step size;

[0043] According to the deviation of the cavity pressure from a preset target pressure and the pressure drop rate, a predicted pressure relief time is obtained;

[0044] If the predicted pressure relief time exceeds a set pressure relief time threshold, then the pressure relief opening degree is increased and the upper limit of the drop rate is adjusted upward.

[0045] The second aspect of the present application provides a compressor intelligent control system based on dynamic pressure relief, comprising a compressor intelligent control method program based on dynamic pressure relief, which realizes the following steps when executed by the processor:

[0046] Through a preset sensor array, multi-source heterogeneous data is collected;

[0047] Based on a preset cleaning and feature extraction algorithm, feature operation parameters are obtained according to the multi-source heterogeneous data;

[0048] Based on a preset pressure entropy model, pressure entropy values are obtained according to the feature operation parameters;

[0049] Based on a preset hierarchical threshold pressure relief strategy, a pressure relief mode is determined according to the pressure entropy values;

[0050] Based on a preset pressure relief valve parameter table, pressure relief parameters are set according to the pressure relief mode;

[0051] After performing the pressure relief operation, the cavity pressure is monitored in real time;

[0052] Based on the deviation of the cavity pressure from a preset target pressure, the pressure relief parameters are dynamically adjusted;

[0053] According to the cavity pressure, when the cavity pressure is in a preset stable state, the compressor is started and pressure relief operation data is recorded;

[0054] The pressure relief operation data is used as a training set, and the weight values of the pressure entropy model are updated according to a preset self-training period.

[0055] In this scheme, the multi-source heterogeneous data is collected through a preset sensor array, specifically:

[0056] Through pressure sensors deployed at the compressor suction cavity, exhaust cavity and oil separator, pressure data is synchronously collected to obtain a pressure change curve;

[0057] Through the infrared temperature sensor array, the compressor cylinder surface temperature is monitored in real time, and a temperature distribution map is obtained;

[0058] Through the three-axis vibration sensor, the vibration curve of the compressor in the shutdown state is captured;

[0059] Through the current Hall sensor, the residual current curve of the compressor is detected;

[0060] The pressure change curve, the temperature distribution map, the vibration curve and the residual current curve are combined with the time stamp, and are integrated into multi-source heterogeneous data.

[0061] In the scheme, the feature operation parameter is obtained according to the multi-source heterogeneous data based on the preset cleaning and feature extraction algorithm, and specifically:

[0062] According to the pressure change curve, the preset sliding window is used for filtering processing, the pressure change rate and the standard deviation in each window are calculated, and a pressure feature vector is obtained;

[0063] According to the temperature distribution map, the number, area and temperature value of the local overheating area are extracted, and a temperature feature vector is obtained;

[0064] The vibration curve is processed based on the preset wavelet packet decomposition, and a high-frequency vibration feature is obtained;

[0065] The residual current curve is analyzed based on the slope, and a current attenuation coefficient is obtained;

[0066] The pressure feature vector, the temperature feature vector, the high-frequency vibration feature and the current attenuation coefficient are integrated, and the feature operation parameter is obtained.

[0067] The third aspect of the application provides a computer readable storage medium, the computer readable storage medium comprises a compressor intelligent control method program based on dynamic pressure relief, when the compressor intelligent control method program based on dynamic pressure relief is executed by a processor, the steps of the compressor intelligent control method based on dynamic pressure relief are realized.

[0068] The present invention provides a compressor intelligent control method, system and storage medium based on dynamic pressure relief. First, by deploying a four-dimensional sensing network of pressure, temperature, vibration and current, the multi-physical field coupling characteristics of the compressor in the shutdown state are captured in real time; secondly, based on a preset pressure entropy model, the pressure fluctuation intensity, temperature anomaly index, high-frequency vibration factor and current attenuation coefficient are integrated to quantitatively evaluate the pressure entropy value, and a three-level pressure relief mode is triggered based on the pressure entropy value; then, based on the deviation between the cavity pressure and the target pressure, the pressure relief parameters are dynamically adjusted to achieve a smooth pressure transition; finally, the full-link data of the pressure relief operation is collected, and the pressure entropy model parameters are dynamically optimized based on reinforcement learning, so that the system can continuously adapt to equipment aging and working condition changes; the present invention reduces the energy waste and equipment loss of pressure relief through dynamic closed-loop adjustment, and improves the stability of the pressure relief process. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope.

[0070] Figure 1 A flow chart showing a compressor intelligent control method based on dynamic pressure relief according to the present invention is shown;

[0071] Figure 2 A flowchart for integrating multi-source heterogeneous data provided by an embodiment of the present invention is shown;

[0072] Figure 3 A flowchart of extracting characteristic operating parameters provided by an embodiment of the present invention is shown;

[0073] Figure 4 A block diagram of a compressor intelligent control system based on dynamic pressure relief according to the present invention is shown. DETAILED DESCRIPTION

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0075] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0076] The terms "first", "second", and similar terms used in the embodiments of the application do not necessarily mean any order, number, or importance, but are only used to distinguish different components. The terms "one", "a", or "the" and the like do not mean a quantity limitation, but mean the presence of at least one. Similarly, the terms "include" or "contain" and the like mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects.

[0077] The terms "connect" or "connected" and the like are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The steps before or after the method of the embodiments of the application do not necessarily proceed in order. On the contrary, various steps can be processed in reverse order or simultaneously. Meanwhile, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0078] In addition, the functional modules in each embodiment of the application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0079] Figure 1 A flowchart of an intelligent control method for a compressor based on dynamic pressure relief is shown.

[0080] As shown in Figure 1 The first aspect of the application discloses an intelligent control method for a compressor based on dynamic pressure relief, which comprises:

[0081] S102, acquiring multi-source heterogeneous data through a preset sensor array;

[0082] S104, obtaining feature operation parameters based on a preset cleaning and feature extraction algorithm according to the multi-source heterogeneous data;

[0083] S106, obtaining a pressure entropy value based on a preset pressure entropy model according to the feature operation parameters;

[0084] S108, determining a pressure relief mode based on a preset hierarchical threshold pressure relief strategy according to the pressure entropy value;

[0085] S110, setting pressure relief parameters according to the pressure relief mode based on a preset pressure relief valve parameter table;

[0086] S112, after performing the pressure relief operation, monitoring the cavity pressure in real time;

[0087] S114, dynamically adjusting the pressure relief parameter based on the deviation between the cavity pressure and a preset target pressure;

[0088] S116, when it is determined based on the cavity pressure that the cavity pressure is in a preset stable state, starting the compressor and recording pressure relief operation data;

[0089] S118: Using the pressure relief operation data as a training set, and updating the weights of the pressure entropy model according to a preset self-training cycle.

[0090] It should be noted that in this embodiment, after system startup, a distributed sensor array first synchronously collects heterogeneous data streams, including compressor cavity pressure fluctuation signals, cylinder surface temperature distribution, mechanical vibration spectrum, and motor system residual current. This raw data is then subjected to denoising using sliding window filtering and wavelet packet decomposition algorithms. Key characteristic parameters, such as the extreme pressure change rate, local overheating characteristics, high-frequency vibration energy ratio, and current decay time constant, are extracted. These characteristic parameters are then integrated into a pre-set pressure entropy model for calculation, outputting a pressure entropy value representing the system's risk level. Based on the threshold range within which this entropy value falls, the system automatically selects zero pressure relief, short-term pressure relief, or forced pressure relief mode and invokes the corresponding pressure relief parameter combination. During the pressure relief execution phase, the electronic pressure relief valve initiates pressure relief according to a preset opening, while simultaneously monitoring the cavity pressure curve in real time. If the actual pressure drop rate deviates from the target range, the system dynamically optimizes the pressure relief process through a step-by-step opening adjustment mechanism. Once the pressure value remains stable within the safe range and the mechanical vibration energy falls within the permitted range, the compressor enters the safe startup procedure. Data from the entire process is encrypted and recorded and transmitted to a cloud-based knowledge base. The system regularly updates the characteristic weight coefficients of the pressure entropy model based on a reinforcement learning algorithm, enabling continuous evolution of the control strategy. This embodiment implements a closed-loop process, significantly reducing the frequency of ineffective pressure relief operations through multi-dimensional state perception and adaptive decision-making mechanisms, thereby improving energy efficiency while ensuring equipment safety.

[0091] Figure 2 A flowchart for integrating multi-source heterogeneous data provided by an embodiment of the present invention is shown.

[0092] According to an embodiment of the present invention, Figure 2 As shown, the multi-source heterogeneous data is collected through the preset sensor array, specifically:

[0093] S202, synchronously collect pressure data through pressure sensors arranged at the suction cavity, the exhaust cavity and the oil separator of the compressor, to obtain a pressure change curve;

[0094] S204, monitor the surface temperature of the cylinder body of the compressor in real time through an infrared temperature sensor array, to obtain a temperature distribution map;

[0095] S206, capture a vibration curve of the compressor in a shutdown state through a three-axis vibration sensor;

[0096] S208, detect a residual current curve of the compressor through a current Hall sensor;

[0097] S210, integrate the pressure change curve, the temperature distribution map, the vibration curve and the residual current curve into multi-source heterogeneous data in combination with a time stamp.

[0098] It should be noted that the embodiment adopts four types of sensors to cover the mechanical, thermal and electromagnetic core system states. High-density sensor networks are arranged at key nodes of the compressor, including three groups of high-precision pressure sensors embedded in the inner walls of the suction cavity, the exhaust cavity and the oil separator, to capture pressure transient fluctuations at a millisecond-level sampling frequency and generate a pressure-time change curve; an infrared temperature sensor array arranged around the cylinder body adopts a scanning temperature measurement, and a surface temperature distribution thermal map is collected and refreshed once according to a preset period; a three-axis vibration sensor installed on the base of the compressor continuously collects wideband mechanical vibration signals, and generates a vibration energy spectrum through fast Fourier transform; a current Hall sensor connected in series in the power supply circuit records the residual current decay trajectory of the electromagnetic system after power-off. All sensor data are added with a time stamp, and spatiotemporal alignment and data encapsulation are performed by an edge computing unit, to construct a state matrix of four-dimensional physical fields including pressure, temperature, vibration and current. The multi-source heterogeneous sensing architecture adopted in the embodiment eliminates single-point monitoring blind spots and provides comprehensive and accurate underlying data support for subsequent feature extraction.

[0099] Figure 3 A feature operation parameter extraction flowchart provided by the embodiment of the application is shown.

[0100] According to the embodiment of the application, as shown in Figure 3 the preset cleaning and feature extraction algorithm, the feature operation parameters are obtained according to the multi-source heterogeneous data, specifically as follows:

[0101] S302, according to the pressure change curve, filter processing is performed based on a preset sliding window, the pressure change rate and the standard deviation in each window are calculated, and a pressure feature vector is obtained;

[0102] S304, according to the temperature distribution map, the number, area and temperature value of a local overheating area are extracted, and a temperature feature vector is obtained;

[0103] S306, based on the preset wavelet packet decomposition processing, the vibration curve is obtained High frequency vibration characteristics;

[0104] S308, based on the slope analysis, the residual current curve is obtained Current attenuation coefficient;

[0105] S310, integration pressure feature vector, temperature feature vector, high frequency vibration characteristics and current attenuation coefficient, get characteristic operation parameters.

[0106] It should be noted that the embodiment of the sensor measurement data is extracted, and the characteristic data is obtained. First, the pressure change curve is processed by sliding window, the absolute value of the pressure change rate and the statistical standard deviation are calculated in each time window, and the feature vector representing the pressure dynamic characteristics is output. Secondly, the temperature distribution map is positioned by image recognition algorithm Local overheating area, extract its number coordinate, projection area and highest temperature value form temperature feature set. Then, the vibration signal is separated by wavelet packet decomposition technology Different frequency components, the energy integral operation is carried out on the high frequency component of the set frequency band, and the mechanical impact strength is quantified. Finally, the residual current curve is fitted by least square method Attenuation equation, extract time constant as electromagnetic system state index. The pressure fluctuation intensity, temperature anomaly index, high frequency vibration factor and current attenuation coefficient are combined as structured feature vector. The process condenses the massive original data into the characteristic parameters with clear physical meaning through signal processing and pattern recognition technology, which significantly improves the subsequent decision efficiency.

[0107] According to the embodiment of the application, the pressure entropy model is obtained based on the preset pressure entropy model, and the pressure entropy value is obtained according to the characteristic operation parameters, specifically including:

[0108] Obtain the first pressure weight and the second pressure weight;

[0109] According to the temperature feature vector, determine the pressure compensation coefficient, used for adjusting the first pressure weight and the second pressure weight;

[0110] Calculate the product of the adjusted first pressure weight and the pressure change rate of the pressure feature vector, get Pressure change factor;

[0111] Calculate the product of the adjusted second pressure weight and the pressure standard deviation of the pressure feature vector, get Pressure standard deviation factor;

[0112] According to the high frequency vibration characteristics, the correction coefficient is obtained based on the preset correction coefficient mapping relationship;

[0113] According to the pressure change factor, pressure standard deviation factor and correction coefficient, the pressure entropy value is obtained;

[0114] If the current attenuation coefficient exceeds the preset attenuation threshold, the pressure entropy value is positively compensated.

[0115] It should be noted that in the embodiment, after the feature vector is input into the pressure entropy model, the system first adjusts the weight distribution coefficient of the pressure change rate and the pressure standard deviation according to the distribution of the superheated region in the temperature feature vector. The compensated weight coefficient is multiplied by the corresponding pressure feature value to generate the basic pressure entropy component. At the same time, according to the strength of the high-frequency vibration factor, the entropy value is mechanically corrected according to the preset mapping relationship. The vibration energy increases by a certain percentage, and the entropy value is correspondingly improved. If the current attenuation coefficient exceeds the safety threshold, an additional compensation mechanism is started to positively gain the entropy value. After all the correction items are superimposed, the non-dimensional pressure entropy value in the range [0, 1] is output through normalization processing. The model fuses thermal, mechanical, and electromagnetic multi-physical field features to construct a quantitative index that comprehensively reflects the system risk level, providing a scientific basis for pressure relief decision-making.

[0116] According to the embodiment of the present application, the pressure relief strategy based on the preset hierarchical threshold value determines the pressure relief mode according to the pressure entropy value, specifically including:

[0117] If the pressure entropy value is lower than the preset first pressure entropy threshold value, it is determined as zero pressure relief mode, and the pressure relief time and the pressure relief opening degree are set to the minimum value;

[0118] If the pressure entropy value is between the preset first pressure entropy threshold value and the preset second pressure entropy threshold value, it is determined as short-time pressure relief mode, the pressure relief opening degree is adjusted according to the pressure relief entropy value, and the pressure relief operation is performed according to the preset first pressure relief time;

[0119] If the pressure entropy value is higher than the preset second pressure entropy threshold value, it is determined as forced pressure relief mode, the pressure relief parameters are set based on the preset three-level pressure relief strategy, and the pressure relief operation is performed.

[0120] It should be noted that the embodiment provides a three-stage grading pressure relief strategy based on the pressure entropy value. When the entropy value continuously is lower than the first pressure entropy threshold value, it is determined that the system is in a low pressure stable state, and the pressure relief valve keeps the minimum opening degree to directly start the compressor. When the entropy value is between the first pressure entropy threshold value and the second pressure entropy threshold value, a short-time pressure relief mode is started, the opening degree of the pressure relief valve is linearly increased with the entropy value, and the pressure relief operation is completed within a fixed time. If the entropy value exceeds the second pressure entropy threshold value, a forced pressure relief mode is activated. In the forced pressure relief mode, a three-stage pressure relief process is adopted, in the first stage, the pressure relief valve is fully opened to achieve rapid pressure drop; when the cavity pressure drops to 150% of the critical value, the buffer pressure relief stage is entered, and the opening degree of the pressure relief valve decays according to a negative exponential curve; when the pressure approaches 120% of the safety threshold value, the fine-tuning pressure relief stage is entered, and the opening degree is finely controlled by using the pulse width modulation technology. The conversion of each stage needs to meet the preset pressure gradient condition to ensure that the pressure relief process is stable and controllable. The on-demand grading control strategy provided by the embodiment significantly reduces energy waste in low-risk working conditions.

[0121] According to the embodiment of the present application, the pressure relief parameter is dynamically adjusted based on the deviation of the cavity pressure from the preset target pressure, and specifically comprises:

[0122] When it is determined that the forced pressure relief mode, the pressure drop rate is calculated according to the cavity pressure;

[0123] If the pressure drop rate is greater than the preset upper limit of the drop rate, the pressure relief opening degree is decreased by a preset step size in a step-by-step manner;

[0124] If the pressure drop rate is less than the preset lower limit of the drop rate, the pressure relief opening degree is increased by a preset step size in a step-by-step manner;

[0125] The predicted pressure relief time is obtained according to the deviation of the cavity pressure from the preset target pressure and the pressure drop rate;

[0126] If the predicted pressure relief time exceeds the set pressure relief time threshold value, the pressure relief opening degree is increased and the upper limit of the drop rate is adjusted upward.

[0127] It should be noted that the embodiment provides a dynamic parameter adjustment pressure relief process. After the pressure relief is started, the system calculates the deviation of the current pressure drop rate from the preset target rate in real time. When the actual rate is lower than the target lower limit, the pressure relief valve opening degree is increased by a fixed step size in a step-by-step manner; otherwise, when the rate exceeds the upper limit, the opening degree is gradually reduced. At the same time, based on the current drop rate and the remaining pressure difference, the pressure relief time required to reach the safe pressure is predicted. If the predicted time exceeds the preset threshold value, the system simultaneously adjusts the upper limit of the pressure relief valve opening degree and relaxes the pressure drop rate permission range. After each opening degree adjustment, at least three control periods need to be maintained to observe the response effect, so as to avoid pressure oscillation caused by frequent actions. The dynamic parameter adjustment mechanism combines real-time feedback with forward-looking prediction, which ensures the efficiency of pressure relief while effectively preventing pressure out-of-control phenomenon.

[0128] It is worth mentioning that the update mechanism of the pressure entropy model is also included, specifically:

[0129] Record the key parameters of each pressure relief operation, including pressure entropy value, total pressure relief time, average opening degree, pressure drop curve and compressor starting current peak value;

[0130] Based on the preset pressure relief efficiency evaluation model, the pressure relief operation parameters are obtained to obtain the pressure relief efficiency;

[0131] If the deviation of the pressure relief efficiency from the theoretical pressure relief efficiency is greater than the preset efficiency threshold for three consecutive times, the model parameter optimization program is triggered;

[0132] Adjust the weight coefficients of each feature in the pressure entropy model through reinforcement learning algorithm.

[0133] It should be noted that the embodiment provides an update mechanism of a pressure entropy model. After each pressure relief operation is completed, the system automatically records the key parameters such as pressure entropy value, total pressure relief time, average opening degree, pressure drop curve shape and compressor starting current peak value. Based on these data, a pressure relief efficiency evaluation index is constructed. By comparing the deviation of the actual pressure relief time from the theoretical optimal time length, the operation efficiency is quantified. When the efficiency evaluation value of three consecutive operations is lower than a certain percentage of the historical best level, the parameter optimization program is triggered. Reinforcement learning algorithm is used to analyze operation data and adjust the weight coefficients of each feature parameter in the pressure entropy model. The updated model needs to be verified in a simulation environment for its control effect, and after confirming the performance improvement, it can be deployed to the actual system. The data-driven self-evolution mechanism provided in the embodiment enables the control system to continuously adapt to the changes in device aging characteristics.

[0134] It is worth mentioning that the pressure relief abnormality processing mechanism is also included, specifically:

[0135] When the pressure relief time exceeds the preset safety time limit, immediately close the pressure relief valve and cut off the compressor power supply;

[0136] Start the sensor data consistency self-check, control instruction transmission state self-check and mechanical structure evaluation in turn;

[0137] According to the self-check result, switch the standby sensor, enable the emergency pressure relief channel or generate a maintenance report.

[0138] It should be noted that the embodiment provides an abnormality processing implementation logic. When the pressure relief duration exceeds the preset safety time limit, the system immediately closes the pressure relief valve and cuts off the power supply of the compressor. Then a three-level diagnosis process is started: the first-level diagnosis verifies the consistency of the multi-sensor data, identifies the abnormal reading node; the second-level diagnosis traces the control instruction transmission path, verifies the response state of the actuator; the third-level diagnosis analyzes the vibration spectrum characteristics, and evaluates the mechanical structure integrity. According to the diagnosis result, the graded treatment is executed, if it is a sensor fault, the spare sensor module is switched to reinitialize the pressure relief process; if it is an actuator failure, an emergency pressure relief channel is enabled; when mechanical damage is detected, a three-dimensional damage report is generated and the device is locked. The whole process generates an encrypted audit log stored in a tamper-proof memory, providing a complete evidence chain for subsequent fault analysis. The embodiment significantly improves the fault tolerance of the system through multi-level diagnosis and redundancy design.

[0139] Figure 4 A block diagram of an intelligent compressor control system based on dynamic pressure relief is shown.

[0140] As shown in Figure 4 The second aspect of the application discloses an intelligent compressor control system based on dynamic pressure relief 4, comprising a memory 41 and a processor 42, the memory comprising an intelligent compressor control method program based on dynamic pressure relief, the intelligent compressor control method program based on dynamic pressure relief is executed by the processor to realize the following steps:

[0141] Through a preset sensor array, multi-source heterogeneous data is collected;

[0142] Based on the preset cleaning and feature extraction algorithm, the feature operating parameters are obtained according to the multi-source heterogeneous data;

[0143] Based on the preset pressure entropy model, the pressure entropy value is obtained according to the feature operating parameters;

[0144] Based on the preset hierarchical threshold pressure relief strategy, the pressure relief mode is determined according to the pressure entropy value;

[0145] Based on the preset pressure relief valve parameter table, the pressure relief parameters are set according to the pressure relief mode;

[0146] After performing the pressure relief operation, the cavity pressure is monitored in real time;

[0147] Based on the deviation of the cavity pressure and the preset target pressure, the pressure relief parameters are dynamically adjusted;

[0148] According to the cavity pressure, when the cavity pressure is in a preset stable state, the compressor is started and the pressure relief operation data is recorded;

[0149] The pressure relief operation data is taken as a training set, and weights of the pressure entropy model are updated according to a preset self-training period.

[0150] It should be noted that in the embodiment, after the system is started, firstly, the heterogeneous data streams such as the compressor cavity pressure fluctuation signal, the cylinder surface temperature field distribution, the mechanical vibration spectrum and the motor system residual current and the like are synchronously collected through the distributed sensor array. Then, the original data is denoised by using the sliding window filtering and wavelet packet decomposition algorithm, and the key characteristic parameters such as the pressure change rate extreme value, the local overheating area feature, the high-frequency vibration energy proportion and the current decay time constant and the like are extracted therefrom. These characteristic parameters are input into the preset pressure entropy model for fusion calculation, and the pressure entropy value representing the system risk level is output. According to the threshold interval where the entropy value is located, the system automatically selects the zero pressure relief, the short-time pressure relief or the forced pressure relief mode, and calls the corresponding pressure relief parameter combination. In the pressure relief execution stage, the electronic pressure relief valve starts pressure relief according to the preset opening degree, and simultaneously, the cavity pressure change curve is monitored in real time. When the actual pressure drop rate deviates from the target range, the system dynamically optimizes the pressure relief process through the step opening degree adjustment mechanism. When the pressure value is continuously stabilized in the safety interval and the mechanical vibration energy is reduced to the permissible range, the compressor enters the safe start program. The whole process data is encrypted and recorded and transmitted to the cloud knowledge base, and the system regularly updates the feature weight coefficients of the pressure entropy model based on the reinforcement learning algorithm, so that the control strategy is continuously evolved. The embodiment realizes a closed-loop process, significantly reduces the frequency of invalid pressure relief operation through the multi-dimensional state perception and adaptive decision mechanism, and improves the energy utilization efficiency under the premise of ensuring the safety of the equipment.

[0151] Figure 2 A multi-source heterogeneous data integration flowchart provided by an embodiment of the application is shown.

[0152] According to the embodiment of the application, as shown in Figure 2 The multi-source heterogeneous data is collected by a preset sensor array, specifically as follows.

[0153] Pressure data is synchronously collected by pressure sensors arranged at the compressor suction cavity, the exhaust cavity and the oil separator, and a pressure change curve is obtained;

[0154] The surface temperature of the compressor cylinder is monitored in real time by an infrared temperature sensor array, and a temperature distribution map is obtained;

[0155] The vibration curve of the compressor in the shutdown state is captured by a three-axis vibration sensor;

[0156] The residual current curve of the compressor is detected by a current Hall sensor;

[0157] The pressure change curve, the temperature distribution map, the vibration curve and the residual current curve are integrated into multi-source heterogeneous data in combination with a time stamp.

[0158] It should be noted that the embodiment adopts four types of sensors to cover the mechanical, thermal and electromagnetic core system states. High-density sensor networks are deployed at key nodes of the compressor, including three groups of high-precision pressure sensors embedded in the inner walls of the suction cavity, the exhaust cavity and the oil separator, respectively, to capture pressure transient fluctuations with millisecond-level sampling frequency and generate pressure-time change curves; the infrared temperature sensor array arranged around the cylinder block uses scanning temperature measurement to collect and refresh the surface temperature distribution thermal map according to the preset period; the three-axis vibration sensor installed on the compressor base continuously collects broadband mechanical vibration signals and generates vibration energy spectrum through fast Fourier transform; the current Hall sensor connected in series in the power supply circuit records the residual current decay trajectory of the electromagnetic system after power failure. All sensor data are time-stamped, and are spatio-temporally aligned and data-encapsulated by the edge computing unit to construct a state matrix containing four-dimensional physical fields of pressure, temperature, vibration and current. The multi-source heterogeneous sensing architecture adopted in the embodiment eliminates the single-point monitoring blind area and provides comprehensive and accurate underlying data support for subsequent feature extraction.

[0159] Figure 3 A feature operation parameter extraction flowchart provided by the embodiment of the application is shown.

[0160] According to the embodiment of the application, as shown in Figure 3 , the feature operation parameters are obtained based on the preset cleaning and feature extraction algorithm according to the multi-source heterogeneous data, specifically:

[0161] According to the pressure change curve, filtering processing is performed based on a preset sliding window, the pressure change rate and the standard deviation in each window are calculated, and a pressure feature vector is obtained;

[0162] According to the temperature distribution map, the number, area and temperature value of the local overheating area are extracted, and a temperature feature vector is obtained;

[0163] The vibration curve is processed based on a preset wavelet packet decomposition to obtain a high-frequency vibration feature;

[0164] The residual current curve is analyzed based on a slope to obtain a current decay coefficient;

[0165] The pressure feature vector, the temperature feature vector, the high-frequency vibration feature and the current decay coefficient are integrated to obtain the feature operation parameters.

[0166] It should be noted that the embodiment extracts features from sensor measurement data to obtain feature data. Firstly, the pressure change curve is processed by a sliding window, and the absolute value of the pressure change rate and the statistical standard deviation are calculated in each time window to output a feature vector representing the dynamic characteristics of the pressure. Secondly, the temperature distribution map is positioned by an image recognition algorithm to locate the local overheating area, and the number of coordinates, projected area and highest temperature value are extracted to form a temperature feature set. Then, the vibration signal is separated into different frequency components by wavelet packet decomposition technology, and the energy integral operation is performed on the high-frequency components of the set frequency band to quantify the mechanical impact strength. Finally, the residual current curve is fitted by the least square method to obtain the time constant as the state indicator of the electromagnetic system. The pressure fluctuation intensity, temperature anomaly index, high-frequency vibration factor and current decay coefficient are combined into a structured feature vector. This process condenses massive raw data into feature parameters with clear physical meaning through signal processing and pattern recognition technology, significantly improving the subsequent decision efficiency.

[0167] According to the embodiment of the present application, the pressure entropy value is obtained based on the preset pressure entropy model according to the feature operating parameter, specifically including:

[0168] The first pressure weight value and the second pressure weight value are obtained.

[0169] The pressure compensation coefficient is determined according to the temperature feature vector, which is used to adjust the first pressure weight value and the second pressure weight value.

[0170] The product of the adjusted first pressure weight value and the pressure change rate of the pressure feature vector is calculated to obtain a pressure change factor.

[0171] The product of the adjusted second pressure weight value and the pressure standard deviation of the pressure feature vector is calculated to obtain a pressure standard deviation factor.

[0172] The correction coefficient is obtained based on the preset correction coefficient mapping relationship according to the high-frequency vibration feature.

[0173] The pressure entropy value is obtained according to the pressure change factor, the pressure standard deviation factor and the correction coefficient.

[0174] If the current decay coefficient exceeds the preset decay threshold, the pressure entropy value is positively compensated.

[0175] It should be noted that in this embodiment, after the characteristic vector is input into the pressure entropy model, the system first dynamically adjusts the weight distribution coefficients of the pressure change rate and the pressure standard deviation according to the distribution of the overheating area in the temperature characteristic vector. The compensated weight coefficients are multiplied by the corresponding pressure characteristic values ​​to generate the basic pressure entropy components. At the same time, based on the intensity of the high-frequency vibration factor, the entropy value is mechanically corrected according to the preset mapping relationship. For every specific percentage increase in vibration energy, the entropy value increases the correction coefficient accordingly. If the current attenuation coefficient exceeds the safety threshold, the additional compensation mechanism is activated to perform a positive gain on the entropy value. After all the correction terms are superimposed, the dimensionless pressure entropy value in the range of [0,1] is output through normalization processing. This model constructs a quantitative indicator that comprehensively reflects the system risk level by integrating the characteristics of thermal, mechanical, and electromagnetic multiple physical fields, providing a scientific basis for pressure relief decisions.

[0176] According to an embodiment of the present invention, the pressure relief strategy based on the preset hierarchical threshold value determines the pressure relief mode according to the pressure entropy value, specifically including:

[0177] If the pressure entropy value is lower than the preset first pressure entropy threshold, it is determined to be in zero pressure relief mode, and the pressure relief time and pressure relief opening are both set to the minimum value;

[0178] If the pressure entropy value is between a preset first pressure entropy threshold and a preset second pressure entropy threshold, it is determined to be a short-time pressure relief mode, the pressure relief opening is adjusted according to the pressure relief entropy value, and the pressure relief operation is performed according to the preset first pressure relief time;

[0179] If the pressure entropy value is higher than the preset second pressure entropy threshold, it is determined to be a forced pressure relief mode, and based on the preset three-level pressure relief strategy, the pressure relief parameters are set and the pressure relief operation is performed.

[0180] It should be noted that this embodiment provides a three-stage pressure relief strategy based on pressure entropy. When the entropy value remains below the first pressure entropy threshold, the system is determined to be in a low-pressure stable state, and the pressure relief valve maintains its minimum opening, directly starting the compressor. When the entropy value is between the first and second pressure entropy thresholds, a short-term pressure relief mode is activated, in which the pressure relief valve opening increases linearly with the entropy value, and the pressure relief operation is completed within a fixed duration. If the entropy value exceeds the second pressure entropy threshold, a forced pressure relief mode is activated. The forced pressure relief mode utilizes a three-stage pressure relief process. In the first stage, the pressure relief valve is fully opened to achieve a rapid pressure drop. When the chamber pressure drops to 150% of the critical value, the buffer pressure relief stage begins, in which the pressure relief valve opening decays according to a negative exponential curve. When the pressure approaches 120% of the safety threshold, the fine-tuning pressure relief stage begins, using pulse width modulation technology to precisely control the opening. Each stage transition must meet preset pressure gradient conditions to ensure a smooth and controllable pressure relief process. The on-demand graded control strategy provided by this embodiment significantly reduces energy waste under low-risk operating conditions.

[0181] According to the embodiment of the present application, the dynamic adjustment of the pressure relief parameter based on the deviation of the cavity pressure from the preset target pressure specifically comprises:

[0182] When it is determined to be the forced pressure relief mode, the pressure drop rate is calculated according to the cavity pressure;

[0183] If the pressure drop rate is greater than the preset upper limit of the drop rate, the pressure relief opening degree is decreased step by step by a preset step;

[0184] If the pressure drop rate is less than the preset lower limit of the drop rate, the pressure relief opening degree is increased step by step by a preset step;

[0185] The predicted pressure relief time is obtained according to the deviation of the cavity pressure from the preset target pressure and the pressure drop rate;

[0186] If the predicted pressure relief time exceeds the set pressure relief time threshold, the pressure relief opening degree is increased and the upper limit of the drop rate is adjusted upward.

[0187] It should be noted that the embodiment provides a dynamic parameter adjustment pressure relief process. After the pressure relief is started, the system calculates the deviation of the current pressure drop rate from the preset target rate in real time. When the actual rate is lower than the target lower limit, the pressure relief valve opening degree is increased step by step by a fixed step; otherwise, when the rate exceeds the upper limit, the opening degree is gradually reduced. At the same time, based on the current drop rate and the remaining pressure difference, the pressure relief time required to reach the safe pressure is predicted. If the predicted time exceeds the preset threshold, the system simultaneously adjusts the upper limit of the pressure relief valve opening degree and relaxes the pressure drop rate permission range. After each opening degree adjustment, at least three control periods are maintained to observe the response effect, so as to avoid pressure oscillation caused by frequent actions. The dynamic parameter adjustment mechanism combines real-time feedback with forward-looking prediction, which ensures the pressure relief efficiency while effectively preventing pressure runaway.

[0188] It is worth mentioning that the updating mechanism of the pressure entropy model is also included, specifically comprising:

[0189] The key parameters of each pressure relief operation are recorded, including the pressure entropy value, the total pressure relief time, the average opening degree, the pressure drop curve, and the compressor starting current peak value;

[0190] Based on the preset pressure relief efficiency evaluation model, the pressure relief operation parameters are obtained to obtain the pressure relief efficiency;

[0191] If the deviation of the pressure relief efficiency from the theoretical pressure relief efficiency is greater than the preset efficiency threshold for three consecutive times, the model parameter optimization program is triggered;

[0192] The weight coefficients of each feature in the pressure entropy model are adjusted through the reinforcement learning algorithm.

[0193] It should be noted that the embodiment provides an updating mechanism of the pressure entropy model. After each pressure relief operation is completed, the system automatically records key parameters such as pressure entropy value, total pressure relief time, average opening degree, pressure drop curve shape and compressor starting current peak value. Based on these data, a pressure relief efficiency evaluation index is constructed, and the efficiency of this operation is quantified by comparing the deviation of the actual pressure relief time from the theoretical optimal time. When the efficiency evaluation value of three consecutive operations is lower than a specific percentage of the historical best level, the parameter optimization program is triggered. The reinforcement learning algorithm is used to analyze the operation data and adjust the weight coefficients of each feature parameter in the pressure entropy model. The updated model needs to be verified in the simulation environment for its control effect, and the performance is confirmed to be improved before it can be deployed to the actual system. The data-driven self-evolution mechanism provided in the embodiment enables the control system to continuously adapt to the changes in the characteristics of the aging equipment.

[0194] It is worth mentioning that it also includes a pressure relief abnormality processing mechanism, specifically:

[0195] When the pressure relief time exceeds the preset safety time limit, the pressure relief valve is immediately closed and the compressor power supply is cut off;

[0196] The sensor data consistency self-check, control instruction transmission state self-check and mechanical structure evaluation are started in turn;

[0197] According to the self-checking result, the standby sensor is switched, the emergency pressure relief channel is enabled or the maintenance report is generated.

[0198] It should be noted that the embodiment provides an abnormality processing implementation logic. When the pressure relief duration exceeds the preset safety time limit, the system immediately closes the pressure relief valve and cuts off the compressor power supply. Then a three-level diagnosis process is started: the first level diagnosis verifies the consistency of the multi-sensor data, identifies the abnormal reading node; the second level diagnosis traces the control instruction transmission path, verifies the response state of the actuator; the third level diagnosis analyzes the vibration spectrum characteristics, and evaluates the mechanical structure integrity. According to the diagnosis result, the graded treatment is executed, if it is a sensor failure, the standby sensor module is switched to reinitialize the pressure relief process; if it is an actuator failure, the emergency pressure relief channel is enabled; when mechanical damage is detected, a three-dimensional damage report is generated and the equipment is locked. The whole process generates an encrypted audit log stored in a tamper-proof memory, providing a complete evidence chain for subsequent fault analysis. The multi-level diagnosis and redundancy design significantly improve the fault tolerance capability of the system.

[0199] The third aspect of the present application provides a computer readable storage medium, the computer readable storage medium comprises a dynamic pressure relief based compressor intelligent control method program, when the dynamic pressure relief based compressor intelligent control method program is executed by a processor, the steps of the dynamic pressure relief based compressor intelligent control method according to any one of the above are realized.

[0200] In summary, the application provides a compressor intelligent control method and system based on dynamic pressure relief and a storage medium, first, by deploying a four-dimensional sensing network of pressure, temperature, vibration and current, the multi-physical field coupling characteristics in the shutdown state of the compressor are captured in real time, second, based on the preset pressure entropy model, the pressure entropy value is quantitatively evaluated by fusing the pressure fluctuation intensity, temperature anomaly index, high-frequency vibration factor and current attenuation coefficient, and the three-level pressure relief mode is triggered based on the pressure entropy value, then, based on the deviation of the cavity pressure and the target pressure, the pressure relief parameters are dynamically adjusted to realize the smooth transition of pressure, finally, the full-link data of the pressure relief operation is collected, the pressure entropy model parameters are dynamically optimized based on reinforcement learning, so that the system continuously adapts to equipment aging and working condition changes, and the application reduces the waste of pressure relief energy consumption and equipment loss through dynamic closed-loop regulation, and improves the stability of the pressure relief process.

[0201] If the functions are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the application or the part of the prior art that contributes essentially or the part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program code storage media.

[0202] The above only describes the preferred embodiments of the application and is not intended to limit the application. For those skilled in the art, the application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the application shall be included in the protection scope of the application.

Claims

1. A compressor intelligent control method based on dynamic pressure relief, characterized in that: The method comprises: Through the preset sensor array, multi-source heterogeneous data is collected; Based on a preset cleaning and feature extraction algorithm, characteristic operation parameters are obtained according to the multi-source heterogeneous data; Based on a preset pressure entropy model and according to the characteristic operating parameters, a pressure entropy value is obtained; Based on a preset hierarchical threshold pressure relief strategy, determining a pressure relief mode according to the pressure entropy value; Based on a preset pressure relief valve parameter table, set the pressure relief parameters according to the pressure relief mode; After performing the pressure relief operation, the cavity pressure is monitored in real time; Dynamically adjusting the pressure relief parameter based on the deviation between the cavity pressure and a preset target pressure; When it is determined based on the cavity pressure that the cavity pressure is in a preset stable state, the compressor is started and pressure relief operation data is recorded; The pressure relief operation data is used as a training set, and the weights of the pressure entropy model are updated according to a preset self-training cycle.

2. The intelligent control method for a compressor based on dynamic pressure relief according to claim 1, characterized in that: The multi-source heterogeneous data is collected through the preset sensor array, specifically: Pressure sensors are deployed at the compressor suction chamber, discharge chamber and oil separator to synchronously collect pressure data and obtain a pressure change curve. The infrared temperature sensor array is used to monitor the surface temperature of the compressor cylinder in real time and obtain a temperature distribution map; The vibration curve of the compressor when it is stopped is captured by a three-axis vibration sensor; Detect the residual current curve of the compressor through the current Hall sensor; The pressure change curve, temperature distribution diagram, vibration curve and residual current curve are combined with timestamps to integrate into multi-source heterogeneous data.

3. The intelligent control method for a compressor based on dynamic pressure relief according to claim 2, characterized in that: The preset cleaning and feature extraction algorithm is based on the multi-source heterogeneous data to obtain feature operation parameters, specifically: According to the pressure change curve, filtering is performed based on a preset sliding window, and the pressure change rate and standard deviation in each window are calculated to obtain a pressure feature vector; According to the temperature distribution diagram, the number, area and temperature value of the local overheating area are extracted to obtain a temperature feature vector; Processing the vibration curve based on a preset wavelet packet decomposition to obtain a high-frequency vibration feature; Analyzing the residual current curve based on the slope to obtain a current attenuation coefficient; The characteristic operating parameters are obtained by integrating the pressure characteristic vector, temperature characteristic vector, high-frequency vibration characteristics and current attenuation coefficient.

4. The intelligent control method for a compressor based on dynamic pressure relief according to claim 3, characterized in that: The pressure entropy value is obtained based on the preset pressure entropy model and the characteristic operating parameters, specifically including: Obtaining a first pressure weight and a second pressure weight; determining a pressure compensation coefficient according to the temperature characteristic vector, for adjusting the first pressure weight and the second pressure weight; Calculating the product of the adjusted first pressure weight and the pressure change rate of the pressure eigenvector to obtain a pressure change factor; Calculate the product of the adjusted second pressure weight and the pressure standard deviation of the pressure eigenvector to obtain a pressure standard deviation factor; Based on the preset correction coefficient mapping relationship, the correction coefficient is obtained according to the high-frequency vibration characteristics; Obtaining a pressure entropy value according to the pressure variation factor, the pressure standard deviation factor, and the correction coefficient; If the current attenuation coefficient exceeds the preset attenuation threshold, the pressure entropy value is positively compensated.

5. The intelligent control method for a compressor based on dynamic pressure relief according to claim 1, characterized in that: The pressure relief strategy based on the preset graded threshold value determines the pressure relief mode according to the pressure entropy value, specifically including: If the pressure entropy value is lower than the preset first pressure entropy threshold, it is determined to be in zero pressure relief mode, and the pressure relief time and pressure relief opening are both set to the minimum value; If the pressure entropy value is between a preset first pressure entropy threshold and a preset second pressure entropy threshold, it is determined to be a short-time pressure relief mode, the pressure relief opening is adjusted according to the pressure relief entropy value, and the pressure relief operation is performed according to the preset first pressure relief time; If the pressure entropy value is higher than the preset second pressure entropy threshold, it is determined to be a forced pressure relief mode, and based on the preset three-level pressure relief strategy, the pressure relief parameters are set and the pressure relief operation is performed.

6. The intelligent control method for a compressor based on dynamic pressure relief according to claim 1, characterized in that: The dynamically adjusting the pressure relief parameter based on the deviation between the cavity pressure and the preset target pressure specifically includes: When it is determined to be a forced pressure relief mode, the pressure drop rate is calculated according to the cavity pressure; If the pressure drop rate is greater than the preset drop rate upper limit, the pressure relief opening is reduced stepwise according to the preset step length; If the pressure drop rate is less than the preset lower limit of the drop rate, the pressure relief opening is increased stepwise according to the preset step length; Obtaining a predicted pressure relief time based on the deviation between the cavity pressure and the preset target pressure and the pressure drop rate; If the predicted pressure relief time exceeds the set pressure relief time threshold, the pressure relief opening is increased and the upper limit of the descent rate is adjusted upward.

7. A compressor intelligent control system based on dynamic pressure relief, characterized in that: The system includes a memory and a processor. The memory includes a compressor intelligent control method program based on dynamic pressure relief. When the compressor intelligent control method program based on dynamic pressure relief is executed by the processor, the following steps are implemented: Through the preset sensor array, multi-source heterogeneous data is collected; Based on a preset cleaning and feature extraction algorithm, characteristic operation parameters are obtained according to the multi-source heterogeneous data; Based on a preset pressure entropy model and according to the characteristic operating parameters, a pressure entropy value is obtained; Based on a preset hierarchical threshold pressure relief strategy, determining a pressure relief mode according to the pressure entropy value; Based on a preset pressure relief valve parameter table, set the pressure relief parameters according to the pressure relief mode; After performing the pressure relief operation, the cavity pressure is monitored in real time; Dynamically adjusting the pressure relief parameter based on the deviation between the cavity pressure and a preset target pressure; When it is determined based on the cavity pressure that the cavity pressure is in a preset stable state, the compressor is started and pressure relief operation data is recorded; The pressure relief operation data is used as a training set, and the weights of the pressure entropy model are updated according to a preset self-training cycle.

8. The intelligent control system for a compressor based on dynamic pressure relief according to claim 7, characterized in that: The multi-source heterogeneous data is collected through the preset sensor array, specifically: Pressure sensors are deployed at the compressor suction chamber, discharge chamber and oil separator to synchronously collect pressure data and obtain a pressure change curve. The infrared temperature sensor array is used to monitor the surface temperature of the compressor cylinder in real time and obtain a temperature distribution map; The vibration curve of the compressor when it is stopped is captured by a three-axis vibration sensor; Detect the residual current curve of the compressor through the current Hall sensor; The pressure change curve, temperature distribution diagram, vibration curve and residual current curve are combined with timestamps to integrate into multi-source heterogeneous data.

9. The intelligent control system for a compressor based on dynamic pressure relief according to claim 8, characterized in that: The preset cleaning and feature extraction algorithm is based on the multi-source heterogeneous data to obtain feature operation parameters, specifically: According to the pressure change curve, filtering is performed based on a preset sliding window, and the pressure change rate and standard deviation in each window are calculated to obtain a pressure feature vector; According to the temperature distribution diagram, the number, area and temperature value of the local overheating area are extracted to obtain a temperature feature vector; Processing the vibration curve based on a preset wavelet packet decomposition to obtain a high-frequency vibration feature; Analyzing the residual current curve based on the slope to obtain a current attenuation coefficient; The characteristic operating parameters are obtained by integrating the pressure characteristic vector, temperature characteristic vector, high-frequency vibration characteristics and current attenuation coefficient.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer-readable storage medium includes a compressor intelligent control method program based on dynamic pressure relief. When the compressor intelligent control method program based on dynamic pressure relief is executed by a processor, the steps of the compressor intelligent control method based on dynamic pressure relief as described in any one of claims 1 to 6 are implemented.

Images