Compressor running state recognition method and device, medium and equipment
The Hidden Markov State Model established by the EM algorithm solves the problems of low efficiency in abnormal handling and high false alarm rate in compressor operation status identification, realizes more efficient compressor health management, and reduces the false alarm rate caused by parameter fluctuations.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PETROCHINA CO LTD
- Filing Date
- 2024-11-20
- Publication Date
- 2026-05-22
AI Technical Summary
Existing technologies have low efficiency in identifying and handling abnormal compressor operating conditions, are prone to false alarms, and are severely affected by parameter fluctuations, resulting in low efficiency in handling abnormalities.
The Hidden Markov State Model is established using the EM algorithm. By defining the compressor operating state as a two-dimensional state space, the load state and health state are identified and labeled. An operating state space transition model is established to obtain a health state assessment, and the health indicators are redefined as a continuous expression.
It improves the efficiency of compressor anomaly handling, reduces false alarm rate, alleviates the analytical burden on staff, and enables more accurate identification of compressor degradation processes under different load conditions.
Smart Images
Figure CN122071981A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of compressor technology, and in particular to a method, apparatus, medium and equipment for identifying the operating status of a compressor. Background Technology
[0002] A compressor is a driven fluid machine that elevates low-pressure gas to high-pressure gas; it is the heart of a refrigeration system. As a key piece of equipment in large-scale industrial production sites, compressors are crucial for providing the critical compression medium required for production, ensuring the continuity and stability of the production process. In the continuous operation management of compressors in production sites, real-time monitoring and analysis are inefficient, and monitoring effectiveness relies heavily on expert experience. Researching a compressor operating status identification method based on a data analysis model can achieve automatic 24-hour assessment of the compressor's operating status, real-time monitoring of various operating parameters, and identification of potential abnormal operating states by observing the long-term transition of the compressor's operating status. This reduces false alarms caused by parameter fluctuations, thereby preventing serious malfunctions. This research can significantly reduce the manpower required for compressor monitoring and improve operational management efficiency. Identifying the compressor's operating status and health status is an important aspect of compressor health management.
[0003] Currently, the continuous operation management of compressors in the production site generally adopts the working mode of "real-time monitoring by the Internet of Things + on-site inspection and handling".
[0004] However, changes in compressor operating load cause parameter fluctuations that interfere with compressor health status assessment, resulting in low efficiency in handling anomalies and a heavy workload for staff analyzing false abnormal parameter fluctuations in the compressor. Sudden fluctuations in random parameters such as process and environment can cause abnormal interference in compressor status identification, easily leading to false alarms. Summary of the Invention
[0005] The main objective of this invention is to provide a method, device, medium, and equipment for identifying the operating status of a compressor, aiming to solve the technical problems of low efficiency in handling anomalies and the tendency to generate false alarms in the prior art.
[0006] To achieve the above objectives, the present invention provides a method for identifying the operating status of a compressor, the method comprising the following steps: S10, defining the compressor operating status as a dual state space, wherein the dual state spaces are the compressor load state space and the compressor health state space; S20, identifying the compressor load state and labeling the health state; S30, establishing an operating state space transition model; S40, performing parameter estimation based on the EM algorithm, and obtaining the parameter calculation results of the operating state space transition model; S50, Obtain the compressor health status assessment from the operating state space transfer model, and redefine the compressor health indicators as a continuous expression; S60, Obtain the real-time load status, health classification status, and health index of the compressor, and prompt the operation and management personnel to perform corresponding compressor health management operations.
[0007] In one possible embodiment, after step S10, the following steps are further included: S110, using the compressor intake flow rate as the load classification parameter, the load state space of the compressor is defined as low load, lower load, medium load, higher load and high load state space; S120, based on the state classification idea of quantitatively describing the health state of the compressor, the health index of the compressor health state space is defined as the state value of [0,1].
[0008] In one possible embodiment, step S20 includes: S210, identifying the compressor load status by classifying the distribution of compressor intake airflow; and S220, labeling the health status of historical samples by human experts.
[0009] In one possible embodiment, step S30 includes: S310, establishing a hidden Markov state model based on the following formula:
[0010] in, This represents the hidden Markov state model; N = N1 * N2 is the finite number of operating states of the compressor, which is equal to the product of the number of load states N1 and the number of healthy states N2; M is the number of compressor state monitoring parameters. , where represents the initial state probability distribution.
[0011] In one possible embodiment, step S40 includes: S410, estimating parameters using the EM algorithm based on historical data samples from state space identification and data annotation; S420, obtaining the parameter calculation results of the running state space transition model based on the following formula:
[0012]
[0013]
[0014] in, The state is The probability of state q = The probability of , and the sum of the probabilities of all states is 1; The state at the initial moment The probability of; Let θ be the state at a certain time t. ip The probability of; For state θ ip The average number of all transitions to each state; Indicates from state θ ip Transition to state θ jp The probability of; For state θ ip Transition to state θ jp The average number of times; Indicates that in state θ ij Status monitoring value V appears k The probability of; The compressor's state parameter is V k Under the condition of being in state θ ij The average number of times; The compressor is in state θ ij The average number of times.
[0015] In one possible embodiment, step S50 includes: S510, calculating the state parameter monitoring sequence of the compressor at a certain time t based on real-time data, where the compressor is in state θ. ip probability S520, combining the health indicator distribution definition of compressor health status classification, redefines the continuous expression of health indicators based on the following formula;
[0016] Among them, H t Indicates health indicators; a p Definition of the distribution of health indicators representing different health states; This indicates that the state parameter monitoring sequence is in state θ at a certain time t. ip The probability of N1 is given by N1; N2 represents the number of compressor load states; N2 represents the number of compressor health states.
[0017] In one possible embodiment, step S60 includes: S610, obtaining the real-time load status, health classification status, and health index of the compressor based on the compressor status results and health quantification results identified by the multi-state space transition model; S620, prompting the operation and management personnel to perform corresponding compressor health management operations based on the classification criteria of the health index.
[0018] Furthermore, to achieve the above objectives, this application embodiment also provides a compressor operating status identification device, which includes: a space definition module, used to define the compressor operating status as a dual state space, the dual state spaces being a compressor load state space and a health state space; and an identification and labeling module, used to identify the compressor load state and label its health state. The model building module is used to build a state space transition model; the calculation module is used to perform parameter estimation based on the EM algorithm and obtain the parameter calculation results of the state space transition model; the expression form definition module is used to obtain the compressor health status assessment of the state space transition model and redefine the compressor health indicators as a continuous expression form; the prompting module is used to obtain the real-time load status, health level status and health index of the compressor and prompt the operation and management personnel to perform corresponding compressor health management operations.
[0019] In addition, to achieve the above objectives, embodiments of this application also provide a computer-readable storage medium including instructions that, when run on a computer, cause the computer to execute the compressor operating status identification method of any embodiment of this application.
[0020] Furthermore, to achieve the above objectives, embodiments of this application also provide a computing device, which includes at least one processor, a memory, and an input / output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the compressor operating status identification method of any embodiment of this application.
[0021] This application provides a compressor operating status identification method. It uses the EM algorithm for parameter estimation to obtain the parameter calculation results of the operating state space transition model. By obtaining the compressor health status assessment from the operating state space transition model, and redefining the compressor's health indicators as a continuous expression, it refines the trend curve of health indicator decline during compressor degradation. Based on the operating status, health status, and health indicator information provided in the analysis results, the workload of staff analyzing false abnormal parameter fluctuations in the compressor can be reduced, improving the efficiency of anomaly handling. By defining the compressor operating status as a dual-state space, the degradation process of the compressor under different load switching conditions can be identified, significantly reducing the false alarm rate of compressor health status anomaly identification and reducing false alarms caused by compressor load switching and parameter fluctuations. Attached Figure Description
[0022] Figure 1 A flowchart illustrating a compressor operating status identification method provided in one or more embodiments of this application; Figure 2Structural block diagram of a compressor operating status identification device provided in one or more embodiments of this application; Figure 3 A compressor operating status development trajectory diagram provided for one or more embodiments of this application; Figure 4 The compressor equipment health degradation curve provided for one or more embodiments of this application; Figure 5 A business process diagram for health early warning management provided in one or more embodiments of this application; Figure 6 Example diagram of input parameters for identifying the operating status and health status of a compressor provided in one or more embodiments of this application; Figure 7 Example diagrams illustrating the identification of the operating status and health status of a compressor provided in one or more embodiments of this application; Figure 8 This is a schematic diagram of the structure of a medium provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application.
[0023] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0024] It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of the application. Rather, these embodiments are provided to make the disclosure more thorough and complete, and to fully convey the scope of the disclosure to those skilled in the art.
[0025] Those skilled in the art will understand that the embodiments of this application can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this application can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.
[0026] This application provides a method for identifying the operating status of a compressor, which can be executed by a computer, such as... Figure 1 As shown, the method may include the following steps: Step S10: Define the compressor operating state as a dual state space, namely the compressor load state space and the health state space.
[0027] In an exemplary embodiment, after step S10, the following steps may also be included: S110, using the compressor intake flow rate as the load classification parameter, defines the compressor's load state space as low load, lower load, medium load, higher load, and high load state spaces, specifically as follows: Figure 3 As shown; S120, based on the state classification approach for quantitatively describing the compressor's health status, referenced Figure 4 The health index of the compressor's health state space is defined as the state value of [0,1].
[0028] Specifically, the health status of a compressor undergoes a degradation process, during which its performance and failure rate change. Based on the quantitative description of compressor health status through state grading, the compressor's health index is defined as a state value of [0,1], such as... Figure 4 As shown, the compressor goes through four states, H1 to H4, from healthy to faulty. As equipment performance deteriorates and the failure rate increases, the health index gradually decreases.
[0029] The compressor's health status is divided into four levels, as detailed below: (1) Health: The compressor has a good production capacity, a very low failure rate, and its health indicators are generally above 0.9.
[0030] (2) Sub-health: The compressor has good production capacity, the failure rate is within a controllable range, and the health indicators are generally between 0.8 and 0.9.
[0031] (3) Deterioration: Occasional abnormalities occur during the compressor production process, resulting in unqualified production capacity and a high failure rate. Maintenance is required as needed, and health indicators are generally between 0.6 and 0.8.
[0032] (4) Faults: The compressor cannot operate, the production capacity is unqualified, the failure rate is very high, maintenance is required, and the health indicators are generally below 0.6.
[0033] State space identification and labeling are divided into load state identification and health state labeling, with the aim of forming the historical dataset required for the state identification model. Load state identification is mainly achieved by classifying the distribution of compressor intake airflow. Based on the calculation of recent historical flow data distribution characteristics, the labeling rules for each load state level are as shown in Table 1: Table 1
[0034] Step S20: Identify the compressor load status and label its health status.
[0035] In an exemplary embodiment, step S20 may specifically include the following steps: S210 identifies the compressor load status by classifying the distribution of compressor intake airflow. S220 involves human experts labeling the health status of historical samples.
[0036] Among them, "human experts" refers to personnel with more than 10 years of experience in health status labeling of compressors or other large machinery. The final labeled data sample is V = (V1,V2,...,Vn, load state, health state), where Vi is the compressor's status parameter signal, including temperature, pressure, flow rate, liquid level, speed, power, vibration, and noise, etc. The set of measurement points varies depending on the compressor model.
[0037] Step S30: Establish the running state space transition model.
[0038] In an exemplary embodiment, step S30 may specifically include the following steps: S310, a hidden Markov state model is established based on the following formula: (1) in, This represents the hidden Markov state model; N = N1 * N2 is the finite number of operating states of the compressor, which is equal to the product of the number of load states N1 and the number of healthy states N2; M is the number of compressor state monitoring parameters. , where represents the initial state probability distribution.
[0039] In this exemplary embodiment, the operating state space transition model adopts the Hidden Markov State Model. The operating state of the compressor evolves over time, and the transition from one operating state to another is called state transition.
[0040] Furthermore, a Hidden Markov Model (HMM) is a statistical model used to describe a Markov process with hidden, unknown parameters. The challenge lies in determining these hidden parameters from the observable parameters. These parameters are then used for further analysis, such as pattern recognition and, in this embodiment, state recognition.
[0041] Step S40: Perform parameter estimation based on the EM algorithm to obtain the parameter calculation results of the running state space transition model.
[0042] In an exemplary embodiment, step S40 may specifically include the following steps: S410 uses the EM algorithm for parameter estimation based on historical data samples with state space identification and data annotation. S420, the parameter calculation results of the running state space transition model are obtained based on the following formula: (2) (3) (4) in, The state is The probability of state q = The probability of , and the sum of the probabilities of all states is 1; The state at the initial moment The probability of; Let θ be the state at a certain time t. ip The probability of; For state θ ip The average number of all transitions to each state; Indicates from state θ ip Transition to state θ jp The probability of; For state θ ip Transition to state θ jp The average number of times; Indicates that in state θ ij Status monitoring value V appears k The probability of; The compressor's state parameter is V k Under the condition of being in state θ ij The average number of times; The compressor is in state θ ij The average number of times.
[0043] Step S50: Obtain the compressor health status assessment of the operating state space transition model, and redefine the compressor health index as a continuous expression.
[0044] In an exemplary embodiment, step S50 may include the following steps: S510, based on real-time data, calculates the compressor's state parameter monitoring sequence, which is in state θ at a certain time t. ip probability : S520, combining the distribution definition of health indicators for compressor health status grading, redefines the continuous expression of health indicators based on the following formula; (5) Among them, H t Indicates health indicators; ap Definition of the distribution of health indicators representing different health states; This indicates that the state parameter monitoring sequence is in state θ at a certain time t. ip The probability of N1 is given by N1; N2 represents the number of compressor load states; N2 represents the number of compressor health states.
[0045] Specifically, a p Generally, the average of the upper and lower thresholds defined by the health index is taken, where a1 is the healthy state, a2 is the sub-healthy state, a3 is the deteriorated state, and a4 is the healthy state.
[0046] a1=(1+0.9) / 2=0.95, a2=(0.9+0.8) / 2=0.85, a3=(0.8+0.6) / 2=0.7, a4=(0.6+0) / 2=0.3.
[0047] S60 acquires the real-time load status, health classification status, and health indicators of the compressor, and prompts the operation and management personnel to perform corresponding compressor health management operations.
[0048] In an exemplary embodiment, step S60 may include the following steps: S610, based on the compressor state results and health quantification results identified by the multi-state space transition model, obtains the real-time load status, health classification status and health index of the compressor; S620, based on the classification criteria of health indicators, prompts operation and management personnel to perform corresponding compressor health management operations.
[0049] Specifically, when the health score is >0.9, the health rating is healthy, indicating that the compressor has good production capacity and a very low failure rate; When the health level is between 0.8 and 0.9, the health grade is sub-healthy, indicating that the compressor has good production capacity and the failure rate is within a controllable range, and generally no additional operation is required. When the health level is between 0.6 and 0.8, the health grade is sub-healthy or deteriorated, indicating that the compressor is in the process of deterioration, the compressor production process is prone to abnormalities, the production capacity is unqualified, the failure rate is high, and maintenance is required as appropriate. When the health level is below 0.6, the health grade is deterioration or failure, indicating that the compressor cannot operate, the production capacity is unqualified, the failure rate is high, and maintenance and repair are required.
[0050] The specific business process of compressor health early warning management is as follows: Figure 5 As shown.
[0051] In one or more embodiments of this method, parameter estimation is performed using the EM algorithm to obtain the parameter calculation results of the operating state space transition model; the compressor health status assessment is obtained from the operating state space transition model, and the compressor health indicators are redefined as a continuous expression, refining the trend curve of health indicator decline during compressor degradation. Based on the operating status, health status, and health indicator information provided in the analysis results, the workload of staff analyzing false abnormal parameter fluctuations in the compressor can be reduced, and the efficiency of anomaly handling can be improved; by defining the compressor operating status as a dual state space, the degradation process of the compressor under different load switching conditions can be identified, significantly reducing the false alarm rate of compressor health status anomaly identification and reducing false alarms caused by compressor load switching and parameter fluctuations.
[0052] The following is a specific application scenario: A certain work area has 12 large screw compressor units. After the units compress the gas, the gas temperature rises. An aftercooler is installed at the outlet to lower the temperature of the compressed gas. The gas then enters the outlet scrubber for washing and dehydration, separating the liquid droplets in the compressed process gas to ensure that its liquid content meets the requirements of subsequent processes.
[0053] The data from the past year (May 2023 to April 2024) of 12 large screw compressors in the sealed station of this work area were used for verification. A total of 23 operating parameters of the compressors were used, as shown in Table 2.
[0054] Table 2
[0055] Figure 6 Example diagram of input parameters for identifying the operating status and health status of a compressor provided in one or more embodiments of this application; Figure 7 Example diagrams illustrating the identification of the operating and health status of a compressor provided in one or more embodiments of this application.
[0056] Using the method described in the above embodiments, the time-varying results of the probability of each stage of the compressor's health state are calculated. Figure 7 It can be seen that in a certain failure, the probability of its health status gradually changes from healthy to sub-healthy, deteriorates to failure, and the health indicators continue to decline and deteriorate.
[0057] The data from 12 large screw compressors in the sealed station of this work area over the past year (May 2023 to April 2024) were used for verification. Referring to Table 3, the compressor operating health status identification result was calculated and output once per hour, with a total of 56,280 identification results. A total of 152 real compressor abnormalities were effectively identified (out of an actual total of 189), with an accuracy rate of 80.4%. There were 17 false alarms (0.2 times / unit / month), with a false alarm rate of 11.1%.
[0058] Table 3
[0059] Based on the above embodiments, refer to Figure 2 Another embodiment of this application also provides a compressor operating status identification device, which may include the following modules: The space definition module 210 is used to define the compressor operating state as a dual state space, wherein the dual state spaces are the compressor load state space and the health state space. The identification and labeling module 220 is used to identify the compressor load status and label its health status. Model building module 230 is used to build a runtime state space transition model; The calculation module 240 is used to perform parameter estimation based on the EM algorithm and obtain the parameter calculation results of the running state space transition model; The expression form definition module 250 is used to obtain the compressor health status assessment of the operating state space transition model and redefine the compressor health indicators as a continuous expression form. The prompting module 260 is used to obtain the real-time load status, health classification status and health index of the compressor, and prompt the operation and management personnel to perform corresponding compressor health management operations.
[0060] Based on the above embodiments, this application also provides a computer-readable storage medium, see reference. Figure 8 The computer-readable storage medium shown is an optical disc 50, on which a computer program (i.e., a program product) is stored. When the computer program is executed by a processor, it implements the steps described in the above method implementation, such as defining the compressor operating state as a two-dimensional state space, namely the compressor load state space and the compressor health state space; identifying the compressor load state and labeling the health state; establishing an operating state space transition model; performing parameter estimation based on the EM algorithm and obtaining the parameter calculation results of the operating state space transition model; obtaining the compressor health state assessment of the operating state space transition model and redefining the compressor health indicators as a continuous expression; obtaining the compressor's real-time load state, health classification state, and health index, and prompting the operation and management personnel to perform corresponding compressor health management operations. The specific implementation methods of each step will not be repeated here.
[0061] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.
[0062] Furthermore, based on the above embodiments, this application also provides a computing device. Figure 9 A block diagram is shown of an exemplary computing device 60 suitable for implementing embodiments of the present application. The computing device 60 may be a computer system or a server. Figure 9 The computing device 60 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0063] like Figure 9 As shown, the components of computing device 60 may include, but are not limited to: one or more processors or processing units 601, system memory 602, and bus 603 connecting different system components (including system memory 602 and processing unit 601).
[0064] The computing device 60 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 60, including volatile and non-volatile media, removable and non-removable media.
[0065] System memory 602 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 6021 and / or cache memory 6022. Computing device 60 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 6023 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 9 (Not shown in the image, usually referred to as "hard drive"). Although not shown in... Figure 9 The diagram illustrates that a disk drive for reading and writing to removable non-volatile disks (e.g., "floppy disks") and an optical disk drive for reading and writing to removable non-volatile optical disks (e.g., CD-ROMs, DVD-ROMs, or other optical media) can be provided. In these cases, each drive can be connected to a bus 603 connecting different system components via one or more data media interfaces. The system memory 602 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.
[0066] A program / utility 6025 having a set (at least one) of program modules 6024 may be stored, for example, in system memory 602, and such program modules 6024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment. Program modules 6024 typically perform the functions and / or methods described in the embodiments of this application.
[0067] The computing device 60 can also communicate with one or more external devices 604 (such as a keyboard, pointing device, display, etc.). This communication can be performed via input / output (I / O) interface 605. Furthermore, the computing device 60 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 606. Figure 9 As shown, network adapter 606 communicates with other modules of computing device 60 (such as processing unit 601, etc.) via bus 603, which connects different system components. It should be understood that, although... Figure 9 Other hardware and / or software modules may be used in conjunction with computing device 60, as not shown in the diagram.
[0068] The processing unit 601 executes various functional applications and data processing by running programs stored in the system memory 602. For example, it defines the compressor operating state as a dual-state space, namely the compressor load state space and the compressor health state space; identifies the compressor load state and labels the health state; establishes an operating state space transition model; performs parameter estimation based on the EM algorithm and obtains the parameter calculation results of the operating state space transition model; obtains the compressor health state assessment of the operating state space transition model and redefines the compressor health indicators as a continuous expression; obtains the compressor's real-time load state, health classification state, and health index, and prompts the operation management personnel to perform corresponding compressor health management operations. The specific implementation methods of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the compressor operating state identification device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of a unit / module described above can be further divided into multiple units / modules for specificity.
[0069] In the description of this application, it should be noted that the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0070] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0071] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0072] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0073] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0074] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0075] Finally, it should be noted that the above embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the technical scope disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.
[0076] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.
Claims
1. A method for identifying the operating status of a compressor, characterized in that, The method includes the following steps: S10, The compressor operating state is defined as a dual state space, namely the compressor load state space and the health state space. S20, identify the compressor load status and label its health status; S30, Establish the running state space transition model; S40, Perform parameter estimation based on the EM algorithm to obtain the parameter calculation results of the running state space transition model; S50, Obtain the compressor health status assessment of the operating state space transition model, and redefine the compressor health index as a continuous expression. S60 acquires the real-time load status, health classification status, and health indicators of the compressor, and prompts the operation and management personnel to perform corresponding compressor health management operations.
2. The compressor operating status identification method according to claim 1, characterized in that, Following step S10, the following steps are also included: S110, using the compressor intake flow rate as the load classification parameter, the load state space of the compressor is defined as low load, lower load, medium load, higher load and high load state space; S120, based on the state classification approach of quantitatively describing the health status of the compressor, defines the health index of the compressor's health status space as the state value of [0,1].
3. The compressor operating status identification method according to claim 1, characterized in that, Step S20 includes: S210, identifying the compressor load state by classifying the distribution of compressor intake airflow; S220 involves human experts labeling the health status of historical samples.
4. The compressor operating status identification method according to claim 1, characterized in that, Step S30 includes: S310, a hidden Markov state model is established based on the following formula: in, This represents the hidden Markov state model; N = N1 * N2 is the finite number of operating states of the compressor, which is equal to the product of the number of load states N1 and the number of healthy states N2; M is the number of compressor state monitoring parameters. , where represents the initial state probability distribution.
5. The compressor operating status identification method according to claim 1, characterized in that, Step S40 includes: S410 uses the EM algorithm for parameter estimation based on historical data samples with state space identification and data annotation. S420, the parameter calculation results of the running state space transition model are obtained based on the following formula: in, The state is The probability of state q = The probability of , and the sum of the probabilities of all states is 1; The initial state is The probability of; Let θ be the state at a certain time t. ip The probability of; For state θ ip The average number of all transitions to each state; Indicates from state θ ip Transition to state θ jp The probability of; For state θ ip Transition to state θ jp The average number of times; Indicates that in state θ ij Status monitoring value V appears k The probability of; The compressor's state parameter is V k Under the condition of being in state θ ij The average number of times; The compressor is in state θ ij The average number of times.
6. The compressor operating status identification method according to claim 1, characterized in that, Step S50 includes: S510, based on real-time data, calculates the compressor's state parameter monitoring sequence, which is in state θ at a certain time t. ip probability : S520, combining the distribution definition of health indicators for compressor health status grading, redefines the continuous expression of health indicators based on the following formula; Among them, H t Indicates health indicators; a p Definition of the distribution of health indicators representing different health states; This indicates that the state parameter monitoring sequence is in state θ at a certain time t. ip The probability of N1 is given by N1; N2 represents the number of compressor load states; N2 represents the number of compressor health states.
7. The compressor operating status identification method according to claim 1, characterized in that, Step S60 includes: S610, based on the compressor state results and health quantification results identified by the multi-state space transition model, obtains the real-time load status, health classification status and health index of the compressor; S620, based on the classification criteria of health indicators, prompts operation and management personnel to perform corresponding compressor health management operations.
8. A compressor operating status identification device, characterized in that, include: The space definition module is used to define the compressor operating state as a dual state space, namely the compressor load state space and the health state space. The identification and labeling module is used to identify the compressor load status and label its health status. The model building module is used to build the runtime state space transition model. The calculation module is used to perform parameter estimation based on the EM algorithm and obtain the parameter calculation results of the running state space transition model; The expression form definition module is used to obtain the compressor health status assessment of the operating state space transition model and redefine the compressor health indicators as a continuous expression form; The prompting module is used to obtain the real-time load status, health classification status, and health indicators of the compressor, and to prompt the operation and management personnel to perform corresponding compressor health management operations.
9. A computer-readable storage medium, characterized in that, It includes instructions that, when run on a computer, cause the computer to perform the compressor operating status identification method according to any one of claims 1 to 7.
10. A computing device, characterized in that, The computing device includes: At least one processor, memory, and input / output unit; The memory is used to store computer programs, and the processor is used to call the computer programs stored in the memory to execute the compressor operating status identification method according to any one of claims 1 to 7.