Compressor liquid knock protection system and method based on multi-parameter fusion and time sequence prediction, electronic device and storage medium

Abstract

This application relates to a compressor liquid slugging protection system, method, electronic device, and storage medium based on multi-parameter fusion and time-series prediction. The compressor liquid slugging protection system based on multi-parameter fusion and time-series prediction includes: a data acquisition module, an intelligent computing module, an execution module, and a data iteration module. The data acquisition module collects multi-dimensional parameter data to form a multi-dimensional parameter sequence; the intelligent computing module inputs the multi-dimensional parameter sequence into a prediction model to calculate the probability of future liquid slugging risk and outputs an execution strategy based on the probability of future liquid slugging risk; the execution module runs the execution strategy and outputs intervention data; the data iteration module stores the intervention data and uploads the intervention data to the cloud. The solution provided by this application can comprehensively predict compressor liquid slugging based on multiple operating conditions, thereby improving the accuracy of protection.

Description

Technical Field

[0001] This invention relates to the field of compressor technology, and in particular to a compressor liquid slugging protection system, method, electronic device and storage medium based on multi-parameter fusion and timing prediction. Background Technology

[0002] Liquid slugging occurs when liquid refrigerant or lubricating oil is drawn into the cylinder of a compression system. Because the liquid is incompressible, this causes a sudden pressure change and is the primary cause of equipment failure.

[0003] In current technologies, the accuracy of liquid slugging protection for compressors is generally low, resulting in a high rate of compressor failure. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the prior art and provide a compressor liquid slugging protection system, method, electronic device and storage medium based on multi-parameter fusion and timing prediction, which can comprehensively predict compressor liquid slugging according to various operating conditions, thereby improving the accuracy of protection.

[0005] The objective of this invention is achieved through the following technical solution: The first aspect of this application provides a compressor liquid slugging protection system based on multi-parameter fusion and time-series prediction, comprising: a data acquisition module for acquiring multi-dimensional parameter data to form a multi-dimensional parameter sequence; an intelligent calculation module for inputting the multi-dimensional parameter sequence into a prediction model to calculate the future liquid slugging risk probability and outputting an execution strategy based on the future liquid slugging risk probability; an execution module for running the execution strategy and outputting intervention data; and a data iteration module for storing the intervention data and uploading the intervention data to the cloud.

[0006] The intelligent computing module includes a model building unit, a dynamic correction unit, and an intervention decision unit. The model building unit is used to build a prediction model and read the multidimensional parameter sequence to obtain the future liquid impact risk probability. The dynamic correction unit is used to create working condition correction factors and health correction factors to correct the future liquid impact risk probability and output the risk level. The intervention decision unit outputs the execution strategy according to the risk level.

[0007] The data acquisition module is also used to collect operating condition parameters, which are used to train the prediction model.

[0008] The execution module includes a main execution unit and an auxiliary execution unit, both of which are used to run the execution strategy and output the intervention data.

[0009] The second aspect of this application provides a compressor liquid slugging protection method based on multi-parameter fusion and time-series prediction, comprising: collecting multi-dimensional parameter data to form a multi-dimensional parameter sequence; inputting the multi-dimensional parameter sequence into a prediction model to calculate the future liquid slugging risk probability; outputting an execution strategy based on the future liquid slugging risk probability; running the execution strategy to output intervention data; storing the intervention data; and uploading the intervention data to the cloud.

[0010] The step of inputting the multidimensional parameter sequence into the prediction model to calculate the future liquid shock risk probability and outputting the execution strategy based on the future liquid shock risk probability includes: constructing a prediction model and using it to read the multidimensional parameter sequence to obtain the future liquid shock risk probability; creating a working condition correction factor and a health correction factor to correct the future liquid shock risk probability and outputting a risk level; and outputting the execution strategy based on the risk level.

[0011] The method further includes: collecting operating condition parameters, which are used to train the prediction model.

[0012] The method further includes: calculating the compressor health value based on the operating condition parameters.

[0013] A third aspect of this application provides an electronic device, comprising: Processor; and A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0014] A fourth aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0015] Compared with the prior art, the present invention has at least the following advantages: This application, through the acquisition of multi-dimensional parameter data and based on a predictive model, accurately predicts the future probability of liquid slugging in the compressor, and implements risk strategies to intervene in advance based on the future probability of liquid slugging, thereby reducing the probability of liquid slugging in the compressor and protecting the compressor. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below.

[0017] Figure 1 This is a functional block diagram of a compressor liquid slugging protection system based on multi-parameter fusion and timing prediction in one embodiment of the present invention; Figure 2This is a flowchart of a compressor liquid slugging protection method based on multi-parameter fusion and timing prediction according to an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0018] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0019] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0020] Unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0021] Liquid slugging occurs when liquid refrigerant or lubricating oil is drawn into the cylinder of a compression system. Because liquids are incompressible, this sudden pressure change is a primary cause of equipment failure. Current liquid slugging protection for compressors typically offers low accuracy, resulting in a high rate of compressor failure. To address the aforementioned issues, this application provides a compressor liquid slugging protection system, method, electronic device, and storage medium based on multi-parameter fusion and timing prediction. This system can comprehensively predict compressor liquid slugging based on various operating conditions, thereby improving the accuracy of protection.

[0022] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0023] Figure 1This is a functional block diagram of a compressor liquid slugging protection system based on multi-parameter fusion and timing prediction, as shown in an embodiment of this application.

[0024] See Figure 1 A compressor liquid slugging protection system based on multi-parameter fusion and time-series prediction includes: a data acquisition module 100, an intelligent computing module 200, an execution module 300, and a data iteration module 400. The data acquisition module 100 is used to collect multi-dimensional parameter data and form a multi-dimensional parameter sequence; the intelligent computing module 200 is used to input the multi-dimensional parameter sequence into a prediction model to calculate the probability of future liquid slugging risk and output an execution strategy based on the probability of future liquid slugging risk; the execution module 300 is used to run the execution strategy and output intervention data; the data iteration module 400 is used to store the intervention data and upload the intervention data to the cloud.

[0025] It should be noted that the data acquisition module 100 includes a high-precision sensor group, including but not limited to: an exhaust superheat sensor with an accuracy of ±0.3℃ and a sampling frequency of 20Hz; a compressor phase current sensor with a measurement range of 0-15A and a fluctuation capture accuracy of ±0.01A; a housing vibration acceleration sensor, located at the corresponding position on the roller with a range of 0-200m / s² and a response time ≤0.5ms; an intake / exhaust pressure sensor with an accuracy of ±0.005MPa; and a refrigerant flow sensor with a measurement range of 0-50L / min and an accuracy of ±1%. The exhaust superheat sensor is used to acquire the exhaust superheat (DHT), the compressor phase current sensor is used to acquire the current fluctuation value ΔI, the housing vibration acceleration sensor is used to acquire the vibration acceleration A, the intake / exhaust pressure sensor is used to acquire the pressure ratio Pcr, and the refrigerant flow sensor is used to acquire the refrigerant flow rate Q. Furthermore, the prediction model is an LSTM prediction model. The input is a multi-dimensional parameter sequence from the past 15 seconds, including exhaust superheat (DHT), current fluctuation (ΔI), vibration acceleration (A), pressure ratio (Pcr), and refrigerant flow rate (Q). The probability of liquid slugging within the next 5 seconds (0-100%) is then calculated. Based on this probability, a corresponding risk strategy is output. The execution module, based on the risk strategy, outputs intervention data after intervention, which is then stored by the data iteration module.

[0026] See Figure 1 In one embodiment, the execution module 300 includes a main execution unit and an auxiliary execution unit, both of which are used to run the execution strategy and output intervention data.

[0027] It should be noted that the main actuator includes an electronic expansion valve and a high-temperature gas bypass valve. The auxiliary actuators include a compressor inverter driver, a suction-side PTC heater, and a refrigerant pump controller. Furthermore, after the actuator intervention starts, parameter feedback is collected every 150ms, and the parameters of each actuator are dynamically adjusted via PID control until the risk is reduced to below 30%.

[0028] See Figure 1 In one embodiment, the intelligent computing module 200 includes a model building unit, a dynamic correction unit, and an intervention decision unit. The model building unit is used to build a prediction model and read multi-dimensional parameter sequences to obtain the probability of future liquid impact risk. The dynamic correction unit is used to create working condition correction factors and health correction factors to correct the probability of future liquid impact risk and output the risk level. The intervention decision unit outputs an execution strategy based on the risk level.

[0029] It should be noted that the model building unit is an LSTM prediction model, which obtains the future liquid slugging risk probability by reading the multi-dimensional parameter sequence over the past 15 seconds. The operating condition correction factor F = 0.7 + 0.03 * (ambient temperature - 5) * load rate, where the load rate refers to the real-time cooling load rate calculated from the return air temperature difference. The health correction factor H = 1.0 + 0.00012 * runtime. That is, the operating condition correction factor and the health correction factor are dynamically adjusted based on the actual operating conditions of the compressor, combined with the LSTM prediction model, to make the future liquid slugging risk probability more realistic and accurate. Finally, the intervention decision unit outputs the execution strategy based on the risk level. Specifically, when the risk level is between 60% and 85%, the electronic expansion valve closes by 3% increments, the high-temperature bypass valve closes, the compressor inverter driver remains unchanged, the suction-side PTC heater is turned off, and the refrigerant pump controller remains unchanged or enters a pre-switching state. When the risk level is greater than or equal to 85%, the electronic expansion valve is closed by 8% and dynamically fine-tuned, the high-temperature bypass valve is opened by 25%-40%, the compressor frequency converter driver is reduced by 3-8Hz, the suction end PTC heater is turned on, and the refrigerant pump controller is switched to auxiliary mode.

[0030] See Figure 1 In one embodiment, the data acquisition module 100 is also used to acquire operating condition parameters, which are used to train the prediction model.

[0031] It should be noted that operating condition parameters can be collected through devices such as integrated ambient temperature sensors, compressor runtime counters, and load rate detectors. These operating condition parameters can be used to train the prediction model, thereby improving the model's generalization and robustness.

[0032] In summary, this application, through the acquisition of multi-dimensional parameter data and based on a predictive model, accurately predicts the future probability of liquid slugging in the compressor, and implements risk strategies to intervene in advance based on the future probability of liquid slugging, thereby reducing the probability of liquid slugging in the compressor and protecting the compressor.

[0033] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a compressor liquid slugging protection system, electronic device, and corresponding embodiments based on multi-parameter fusion and timing prediction.

[0034] Figure 2 This is a flowchart illustrating the method of a compressor liquid slugging protection system based on multi-parameter fusion and timing prediction in an embodiment of this application.

[0035] See Figure 2 A compressor liquid slugging protection method based on multi-parameter fusion and time-series prediction includes... Step S101: Collect multidimensional parameter data to form a multidimensional parameter sequence; It should be noted that the multidimensional parameter sequence includes exhaust superheat DHT, current fluctuation value ΔI, vibration acceleration A, pressure ratio Pcr, and refrigerant flow rate Q.

[0036] Step S102: Input the multidimensional parameter sequence into the prediction model, calculate the probability of future liquid impact risk, and output the execution strategy based on the probability of future liquid impact risk. Step S103: Run the execution strategy and output intervention data; Step S104: Store the intervention data and upload it to the cloud.

[0037] It should be noted that the multidimensional parameter sequence is input into the prediction model to calculate the probability of liquid impact risk within the next 5 seconds, ranging from 0% to 100%. Then, based on the risk probability, the corresponding risk strategy is output. The execution module, based on the risk strategy, outputs and stores the intervention data after intervention.

[0038] In one embodiment, the multidimensional parameter sequence is input into the prediction model to calculate the future liquid shock risk probability. Based on the future liquid shock risk probability, the execution strategy is output, including: constructing a prediction model and using it to read the multidimensional parameter sequence to obtain the future liquid shock risk probability; creating a working condition correction factor and a health correction factor to correct the future liquid shock risk probability and outputting a risk level; and outputting an execution strategy based on the risk level.

[0039] It should be noted that the prediction model is an LSTM prediction model, which obtains the future liquid slugging risk probability by reading the multi-dimensional parameter sequence over the past 15 seconds. The operating condition correction factor F = 0.7 + 0.03 * (ambient temperature - 5) * load rate, where the load rate refers to the real-time cooling load rate calculated from the return air temperature difference. The health correction factor H = 1.0 + 0.00012 * runtime. That is, the operating condition correction factor and the health correction factor are dynamically adjusted based on the actual operating conditions of the compressor, combined with the LSTM prediction model, to make the future liquid slugging risk probability more realistic and accurate. Finally, an execution strategy is output based on the risk level. Specifically, when the risk level is between 60% and 85%, the electronic expansion valve closes by 3% increments, the high-temperature bypass valve closes, the compressor inverter driver remains unchanged, the suction-side PTC heater is turned off, and the refrigerant pump controller remains unchanged or enters a pre-switching state. When the risk level is greater than or equal to 85%, the electronic expansion valve is closed by 8% and dynamically fine-tuned, the high-temperature bypass valve is opened by 25%-40%, the compressor frequency converter driver is reduced by 3-8Hz, the suction end PTC heater is turned on, and the refrigerant pump controller is switched to auxiliary mode.

[0040] In one embodiment, the method further includes: collecting operating condition parameters, which are used to train the prediction model.

[0041] It is understandable that training the prediction model with operating condition parameters can improve the accuracy of the prediction model.

[0042] In one embodiment, the method further includes: calculating the compressor health value based on operating condition parameters.

[0043] It should be noted that the operating status parameters include data such as running time, cumulative number of interventions, and vibration baseline drift. Through calculation, the compressor health value can be obtained to remind the operator to perform timely maintenance.

[0044] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0045] Figure 3 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0046] See Figure 3 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0047] The processor 1020 can be a central processing unit (CPU), or it can be an integrated circuit composed of other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be any conventional processor that can run the Linux kernel.

[0048] Memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 1020 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0049] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to execute part or all of the methods described above.

[0050] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0051] Alternatively, this application may be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) storing executable code (or computer program or computer instruction code) thereon, which, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the steps of the methods described above according to this application.

[0052] The solution of this application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of each embodiment have different focuses; for parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. Those skilled in the art should also understand that the actions and modules involved in the specification are not necessarily essential to this application. Furthermore, it is understood that the steps in the method of this application embodiment can be adjusted, combined, and deleted according to actual needs, and the modules in the device of this application embodiment can be combined, divided, and deleted according to actual needs.

[0053] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A compressor liquid strike protection system based on multi-parameter fusion and timing prediction, characterized in that, include: The data acquisition module is used to collect multidimensional parameter data and form a multidimensional parameter sequence; The intelligent computing module is used to input the multidimensional parameter sequence into the prediction model, calculate the probability of future liquid impact risk, and output the execution strategy based on the probability of future liquid impact risk. The execution module is used to run the execution strategy and output intervention data; The data iteration module is used to store the intervention data and upload the intervention data to the cloud.

2. The multi-parameter fusion and timing prediction based compressor liquid strike protection system according to claim 1, wherein, The intelligent computing module includes a model building unit, a dynamic correction unit, and an intervention decision-making unit. The model building unit is used to build a prediction model and to read the multidimensional parameter sequence to obtain the probability of future liquid impact risk. The dynamic correction unit is used to create working condition correction factors and health correction factors to correct the probability of future liquid impact risk and output the risk level. The intervention decision-making unit outputs the execution strategy based on the risk level.

3. The multi-parameter fusion and timing prediction based compressor liquid strike protection system according to claim 1, wherein, The data acquisition module is also used to collect operating condition parameters, which are used to train the prediction model.

4. The compressor liquid slugging protection system based on multi-parameter fusion and timing prediction according to claim 1, characterized in that, The execution module includes a main execution unit and an auxiliary execution unit, both of which are used to run the execution strategy and output the intervention data.

5. A compressor liquid slugging protection method based on multi-parameter fusion and timing prediction, characterized in that, include: Collect multidimensional parameter data to form a multidimensional parameter sequence; The multidimensional parameter sequence is input into the prediction model to calculate the probability of future liquid impact risk, and the execution strategy is output based on the probability of future liquid impact risk. Run the execution strategy and output intervention data; The intervention data is stored and uploaded to the cloud.

6. The compressor liquid slugging protection system based on multi-parameter fusion and timing prediction according to claim 5, characterized in that, The step of inputting the multidimensional parameter sequence into the prediction model to calculate the future liquid impact risk probability, and outputting the execution strategy based on the future liquid impact risk probability, includes: A prediction model is constructed and used to read the multidimensional parameter sequence to obtain the probability of future liquid impact risk; Create working condition correction factors and health correction factors to correct the probability of future liquid impact risk and output the risk level; Based on the risk level, output the execution strategy.

7. The compressor liquid slugging protection system based on multi-parameter fusion and timing prediction according to claim 5, characterized in that, The method further includes: The operating condition parameters are collected and used to train the prediction model.

8. The compressor liquid slugging protection system based on multi-parameter fusion and timing prediction according to claim 7, characterized in that, The method further includes: Calculate the compressor health value based on the operating condition parameters.

9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 5-8.

10. A computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 5-8.

Images