Three-phase separator fault diagnosis method and device

Abstract

The present invention provides a three-phase separator fault diagnosis method and device. The method comprises: obtaining current three-phase separator monitoring parameters; inputting the current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result. The present invention can improve the efficiency and accuracy of fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of three-phase separator fault diagnosis, and in particular to a three-phase separator fault diagnosis method and device. Background Art

[0002] Horizontal three-phase separator systems are crucial components of the modern oil and gas storage and transportation industry. Failures can not only cause severe economic losses but can also lead to catastrophic consequences. Therefore, fault diagnosis plays a key role in improving the safety and reliability of separator systems and reducing operating and maintenance costs.

[0003] The application of Bayesian networks (BNs) in fault diagnosis is of great significance. BNs integrate the information required for fault diagnosis into a network structure, representing different variables and states as nodes. By observing known variables and states, Bayes' theorem can be used to calculate the probability distribution of unknown variables and states, thereby enabling fault diagnosis. Furthermore, BNs excel at handling uncertainty. Therefore, they are widely considered one of the most effective theoretical models for fault diagnosis in complex systems.

[0004] Currently, BN still has the following shortcomings in fault diagnosis:

[0005] (1) Fault symptom acquisition. For small systems, expert experience can provide relatively accurate fault symptoms. However, with the development of technology, systems tend to be more complex, and existing expert knowledge may not be able to efficiently provide accurate fault symptoms;

[0006] (2) Probability acquisition. Expert experience is highly subjective, resulting in low accuracy of the obtained probability. Secondly, collecting expert experience requires interviewing a certain number of experts, which increases work costs. At the same time, as the system becomes more complex, experts are unable to provide accurate prior probabilities. Summary of the Invention

[0007] The main purpose of the embodiments of the present invention is to provide a three-phase separator fault diagnosis method and device to improve the efficiency and accuracy of fault diagnosis.

[0008] To achieve the above objectives, an embodiment of the present invention provides a three-phase separator fault diagnosis method, comprising:

[0009] Get the current three-phase separator monitoring parameters;

[0010] The current three-phase separator monitoring parameters are input into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result.

[0011] In one embodiment, the step of creating the Bayesian fault diagnosis model includes:

[0012] The three-phase separator discretization data set is obtained according to the three-phase separator state change results, historical three-phase separator monitoring parameters and separator simulation model;

[0013] Obtaining virtual expert node probability data according to the abnormal operating conditions and the separator simulation model;

[0014] The Bayesian fault diagnosis model is created according to a Bayesian network framework, the three-phase separator discretization data set and the virtual expert node probability data.

[0015] In one embodiment, obtaining a three-phase separator discretized data set according to a three-phase separator state change result, historical three-phase separator monitoring parameters, and a separator simulation model includes:

[0016] Inputting the three-phase separator state change result and the historical three-phase separator monitoring parameters into a separator simulation model to obtain first fault symptom data;

[0017] The three-phase separator discretization data set is obtained according to the first fault symptom data and the three-phase separator state change result.

[0018] In one embodiment, obtaining virtual expert node probability data according to the abnormal operating condition and the separator simulation model includes:

[0019] Inputting the abnormal operating condition into the separator simulation model to obtain second fault symptom data;

[0020] The virtual expert node probability data is obtained according to the second fault symptom data.

[0021] In one embodiment, obtaining the virtual expert node probability data according to the second fault symptom data includes:

[0022] Performing virtual expert calculation on the second fault symptom data to obtain basic probability data of Bayesian network nodes;

[0023] The virtual expert node probability data is obtained according to the basic probability data and the maximum noise model.

[0024] In one embodiment, it further includes:

[0025] The Bayesian network framework is constructed based on the abnormal operating condition and fault symptom data; the fault symptom data includes the first fault symptom data and the second fault symptom data.

[0026] In one embodiment, it further includes:

[0027] A sequential Monte Carlo simulation is performed according to the abnormal operating conditions, the three-phase separator parameters and the life distribution type of the three-phase separator to obtain the state change result of the three-phase separator.

[0028] In one embodiment, the Bayesian network framework includes a state layer, a fault layer, and a fault symptom layer;

[0029] Creating the Bayesian fault diagnosis model according to the Bayesian network framework, the three-phase separator discretization data set and the virtual expert node probability data includes:

[0030] Obtaining state layer probability data according to the three-phase separator discretization data set and the state layer, and determining fault layer probability data according to the three-phase separator discretization data set and the fault layer;

[0031] Obtaining a virtual expert node probability corresponding to the missing condition probability from the virtual expert node probability data, and determining fault symptom layer probability data according to the corresponding virtual expert node probability, the three-phase separator discretization data set, and the fault symptom layer;

[0032] The Bayesian fault diagnosis model is created according to the fault layer probability data and the fault symptom layer probability data.

[0033] An embodiment of the present invention further provides a three-phase separator fault diagnosis device, comprising:

[0034] An acquisition module is used to obtain the current monitoring parameters of the three-phase separator;

[0035] The fault diagnosis module is used to input the current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert calculation to obtain a fault diagnosis result.

[0036] In one embodiment, it further includes:

[0037] A discretized data set module is used to obtain a three-phase separator discretized data set based on the three-phase separator state change results, historical three-phase separator monitoring parameters and separator simulation model;

[0038] A virtual expert node probability data module is used to obtain virtual expert node probability data according to abnormal working conditions and the separator simulation model;

[0039] The Bayesian fault diagnosis model creation module is used to create the Bayesian fault diagnosis model according to the Bayesian network framework, the three-phase separator discretization data set and the virtual expert node probability data.

[0040] In one embodiment, the discretization data set module includes:

[0041] A first fault symptom data unit is configured to input the three-phase separator state change result and the historical three-phase separator monitoring parameters into a separator simulation model to obtain first fault symptom data;

[0042] The three-phase separator discretization data set unit is configured to obtain the three-phase separator discretization data set according to the first fault symptom data and the three-phase separator state change result.

[0043] In one embodiment, the virtual expert node probability data module includes:

[0044] a second fault symptom data unit, configured to input an abnormal operating condition into the separator simulation model to obtain second fault symptom data;

[0045] The virtual expert node probability data unit is configured to obtain the virtual expert node probability data according to the second fault symptom data.

[0046] In one embodiment, the virtual expert node probability data unit includes:

[0047] a basic probability data subunit, configured to perform virtual expert calculation on the second fault symptom data to obtain basic probability data of Bayesian network nodes;

[0048] The virtual expert node probability data subunit is configured to obtain the virtual expert node probability data according to the basic probability data and a maximum noise model.

[0049] In one embodiment, it further includes:

[0050] A Bayesian network framework module is used to build the Bayesian network framework based on the abnormal working condition and fault symptom data; the fault symptom data includes the first fault symptom data and the second fault symptom data.

[0051] In one embodiment, it further includes:

[0052] The three-phase separator state change result module is used to perform sequential Monte Carlo simulation according to the abnormal operating conditions, three-phase separator parameters and three-phase separator life distribution type to obtain the three-phase separator state change result.

[0053] In one embodiment, the Bayesian network framework includes a state layer, a fault layer, and a fault symptom layer;

[0054] The Bayesian fault diagnosis model creation module includes:

[0055] a fault state layer probability data unit, configured to obtain state layer probability data according to the three-phase separator discretization data set and the state layer, and determine fault layer probability data according to the three-phase separator discretization data set and the fault layer;

[0056] a fault symptom layer probability data unit, configured to obtain a virtual expert node probability corresponding to a missing condition probability from the virtual expert node probability data, and determine the fault symptom layer probability data according to the corresponding virtual expert node probability, the three-phase separator discretization data set, and the fault symptom layer;

[0057] The Bayesian fault diagnosis model unit is used to create the Bayesian fault diagnosis model according to the fault layer probability data and the fault symptom layer probability data.

[0058] An embodiment of the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the three-phase separator fault diagnosis method are implemented.

[0059] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the three-phase separator fault diagnosis method are implemented.

[0060] An embodiment of the present invention further provides a computer program product, comprising a computer program / instruction, which implements the steps of the three-phase separator fault diagnosis method when executed by a processor.

[0061] The three-phase separator fault diagnosis method and device of the embodiment of the present invention inputs the acquired current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert calculation to obtain a fault diagnosis result, which can improve the efficiency and accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 is a flow chart of a three-phase separator fault diagnosis method according to an embodiment of the present invention;

[0064] Figure 2 is a flow chart of a three-phase separator fault diagnosis method according to another embodiment of the present invention;

[0065] Figure 3 is a flow chart of creating the Bayesian fault diagnosis model in an embodiment of the present invention;

[0066] Figure 4 This is a flow chart of S201 in an embodiment of the present invention;

[0067] Figure 5 This is a flow chart of S202 in an embodiment of the present invention;

[0068] Figure 6 This is a flow chart of S402 in an embodiment of the present invention;

[0069] Figure 7 This is a flow chart of S203 in an embodiment of the present invention;

[0070] Figure 8 is a schematic diagram of state changes in an embodiment of the present invention;

[0071] Figure 9 This is a workflow diagram of a virtual expert system according to an embodiment of the present invention;

[0072] Figure 10 Schematic diagram of a simulation model of a horizontal three-phase separator system according to an embodiment of the present invention;

[0073] Figure 11 Schematic diagram of the structure of the Bayesian network in an embodiment of the present invention;

[0074] Figure 12 Schematic diagram of creating a Bayesian fault diagnosis model in an embodiment of the present invention;

[0075] Figure 13 is a schematic diagram of a fault diagnosis result of a water valve blockage according to an embodiment of the present invention;

[0076] Figure 14 is a structural block diagram of a three-phase separator fault diagnosis device according to an embodiment of the present invention;

[0077] Figure 15 This is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. DETAILED DESCRIPTION

[0078] 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.

[0079] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0080] The acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.

[0081] The terms involved in the present invention are explained as follows:

[0082] Bayesian network: A graphical model for modeling probabilistic relationships. Based on Bayes' theorem and concepts from graph theory, it is used to represent dependencies between variables and use probabilistic reasoning to infer the state of unknown variables.

[0083] Horizontal three-phase separator system: A device system used to separate oil-gas mixtures into three phases: oil, gas, and water. It is commonly used in oil fields, natural gas processing plants, and refineries.

[0084] The present invention combines random processes, virtual experts, and BN to primarily address the difficulty in collecting fault symptoms and obtaining probabilities for a horizontal three-phase separator system. The present invention is described in detail below with reference to the accompanying drawings.

[0085] Figure 1 4 is a flow chart of a three-phase separator fault diagnosis method according to an embodiment of the present invention. Figure 2 FIG. 1 is a flow chart of a three-phase separator fault diagnosis method according to another embodiment of the present invention. Figure 1-Figure 2 As shown, the three-phase separator fault diagnosis method includes:

[0086] S101: Obtain current three-phase separator monitoring parameters.

[0087] S102: Inputting the current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result.

[0088] In specific implementation, the monitoring parameters obtained from the field can be input into the network to calculate the posterior probability of each faulty node, and the cause of the system failure can be diagnosed based on the posterior probability.

[0089] Figure 13 FIG. 1 is a schematic diagram of the fault diagnosis result of water valve blockage in an embodiment of the present invention. Figure 13As shown in the figure, when the separator water valve is blocked, the flow rate behind the water valve will suddenly decrease. The flow rate at the separator inlet will also show a downward trend. As the valve blockage causes the internal pressure of the separator to gradually increase, the liquid levels inside the separator will gradually show an upward trend over time. At the same time, in order to reduce the internal pressure of the separator, the opening of each valve will show an upward trend under the control of PID. Therefore, the flow rate behind the oil valve and gas valve will suddenly increase. Enter these monitoring parameters into BN, and the diagnosis results are as follows: Figure 11 As shown in the figure, the probability of water valve blockage is 100%, while the probability of other faults is basically 0%. At this time, the probability of the separator being abnormal is 99.9%. Therefore, the diagnosis result can be considered correct.

[0090] Figure 1 The execution subject of the three-phase separator fault diagnosis method shown is a computer. Figure 1 As can be seen from the process shown, the three-phase separator fault diagnosis method and device of the embodiment of the present invention inputs the acquired current three-phase separator monitoring parameters into the Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert calculation to obtain the fault diagnosis results, which can improve the efficiency and accuracy of fault diagnosis.

[0091] Figure 3 This is a flow chart of creating the Bayesian fault diagnosis model in an embodiment of the present invention. Figure 3 As shown, the steps of creating the Bayesian fault diagnosis model include:

[0092] S201: Obtain a three-phase separator discretization data set according to the three-phase separator state change result, historical three-phase separator monitoring parameters and the separator simulation model.

[0093] Before executing S201, the following steps are also included:

[0094] A sequential Monte Carlo simulation is performed according to the abnormal operating conditions, the three-phase separator parameters and the life distribution type of the three-phase separator to obtain the state change result of the three-phase separator.

[0095] In specific implementation, the state space simulation of the horizontal three-phase separator system can be performed: for the horizontal three-phase separator and its accessories, based on the random process theory, considering the failure and maintenance of each unit, the system state transition rate matrix is constructed, and the SMC (Sequential Monte-Carlo) algorithm is used to simulate the state transition of the separator system.

[0096] This paper uses a combination of the SMC algorithm and the principle of equal ignorance in a random process to simulate the state transitions of a separator system over a period of time. The principle of equal ignorance is a method often used to determine prior distributions. Its essence is that when there is no understanding of an event or it is difficult to determine its pros and cons, a uniform distribution can be used to determine the prior distribution.

[0097] Table 1

[0098]

[0099] Table 2

[0100]

[0101] Table 1 shows the lifespan distribution and parameters of each device in the three-phase separator. Table 2 shows the meaning of the labels on each device. Figure 8 This is a schematic diagram of the state change in the embodiment of the present invention. First, the distribution and related parameters of the life of each device in the separator system are determined, as shown in Table 1. As shown in Table 1, the three-phase separator parameters include failure rate and maintenance rate. Then, the state transition simulation of the separator unit, valve unit and actuator unit is carried out using SMC simulation. The simulation time is 50 years. The results are shown in Figure 1. Figure 8 The labels have different meanings for different devices in the system, as shown in Table 2.

[0102] Figure 4 This is a flow chart of S201 in an embodiment of the present invention. Figure 4 As shown, S201 includes:

[0103] S301: Inputting the three-phase separator state change result and the historical three-phase separator monitoring parameters into a separator simulation model to obtain first fault symptom data.

[0104] S302: Obtain the three-phase separator discretization data set according to the first fault symptom data and the three-phase separator state change result.

[0105] S202: Obtaining virtual expert node probability data according to the abnormal operating condition and the separator simulation model.

[0106] Figure 5 This is a flow chart of S202 in an embodiment of the present invention. Figure 5 As shown, S202 includes:

[0107] S401: Inputting abnormal operating conditions into the separator simulation model to obtain second fault symptom data.

[0108] Table 3

[0109]

[0110]

[0111] Figure 9 It is a workflow diagram of the virtual expert system in an embodiment of the present invention. Figure 10 Schematic diagram of a simulation model of a horizontal three-phase separator system in an embodiment of the present invention. Figure 10 The parameters in are the monitoring parameters of the system in fault diagnosis. Table 3 is a schematic table of fault symptom data. Figure 9 、 Figure 10 As shown in Table 3, a field-based horizontal three-phase separator system was investigated. A simulation model of the separator system was constructed using a computer language. The SMC simulation results were input into a virtual expert system, where the simulation model generated a dataset for each fault condition. By comparing the faulty operating conditions with the normal operating conditions, fault symptoms were identified and described using expert semantics. To mitigate the risk of randomness in the virtual expert's results, the model's basic parameters were varied multiple times, allowing for multiple fault symptom statistics.

[0112] S402: Obtain the virtual expert node probability data according to the second fault symptom data.

[0113] Figure 6 This is a flow chart of S402 in an embodiment of the present invention. Figure 6 As shown, S402 includes:

[0114] S501: Perform virtual expert calculation on the second fault symptom data to obtain basic probability data of Bayesian network nodes.

[0115] S502: Obtain the virtual expert node probability data according to the basic probability data and the maximum noise model.

[0116] In one embodiment, the specific method of obtaining the virtual expert node probability data is as follows:

[0117] Expert semantics is used to describe the fault symptoms, and algorithms such as Fuzzy-Set theory and Noisy-MAX are introduced to calculate the probability table of each node in the fault symptom layer.

[0118] Taking the outlet water flow node of a separator system with a blocked water valve as an example, the valve blockage fault was first input into the virtual expert system and the results were compared with normal operating conditions. It was found that when a valve is blocked, the flow rate downstream of the valve decreases. This process, analogous to the process of asking questions of an expert, was defined as the process of asking questions of the virtual expert. To eliminate randomness in the simulation model, the abnormal operating condition was simulated by varying the degree of valve blockage multiple times. It was found that the flow rate downstream of the valve consistently decreased.

[0119] Table 4

[0120]

[0121]

[0122] Table 4 shows the basic probability data for Bayesian network nodes. As shown in Table 4, when a water valve in the separator system is clogged, the probability of the flow rate downstream of the valve decreasing is very high. However, the probability of other phenomena occurring is very low. Fuzzy-Set theory can then be used to calculate the basic probabilities of the outlet water flow node state when the valve is clogged. Similarly, basic probabilities for the outlet water flow node state under other fault conditions can be calculated. Finally, using the Noisy-MAX formula, the virtual expert node probability data can be obtained.

[0123] S203: Creating the Bayesian fault diagnosis model according to the Bayesian network framework, the three-phase separator discretization data set and the virtual expert node probability data.

[0124] Before executing S203 , the method further includes: building the Bayesian network framework according to the abnormal working condition and fault symptom data, wherein the fault symptom data includes the first fault symptom data and the second fault symptom data.

[0125] Figure 11 Schematic diagram of the Bayesian network structure in the embodiment of the present invention. Figure 11 As shown, a three-layer BN network is built, and the Bayesian network framework includes a system status layer, a fault layer, and a fault symptom layer.

[0126] Figure 7 This is a flow chart of S203 in an embodiment of the present invention. Figure 7 As shown, S203 includes:

[0127] S601: Obtain state layer probability data according to the three-phase separator discretization data set and the state layer, and determine fault layer probability data according to the three-phase separator discretization data set and the fault layer.

[0128] Table 5

[0129]

[0130] Table 5 shows the probability data of the state layer and the probability data of the fault layer. As shown in Table 5, for the nodes in the system state layer and the fault layer, the SMC algorithm is used to calculate the prior probability of the nodes.

[0131] S602: Obtain a virtual expert node probability corresponding to the missing condition probability from the virtual expert node probability data, and determine fault symptom layer probability data according to the corresponding virtual expert node probability, the three-phase separator discretization data set, and the fault symptom layer.

[0132] S603: Creating the Bayesian fault diagnosis model according to the fault layer probability data and the fault symptom layer probability data.

[0133] Figure 12 Schematic diagram of creating a Bayesian fault diagnosis model in an embodiment of the present invention. Figure 12 As shown in the figure, the prior probabilities of state and fault layer nodes are calculated using Bayesian estimation based on the SMC simulation results and the statistical fault symptom dataset. However, the SMC algorithm cannot simulate the simultaneous occurrence of multiple operating conditions, resulting in an inaccurate table of fault symptom layer node probabilities (Symptom Layer Node Probability Table). To address this issue, the SVEPF (SMC and Virtual Experts Probability Fusion) algorithm was proposed.

[0134] The operating condition combinations of the node probability table in the fault symptom layer are traversed. If the combination can be obtained by SMC simulation, the probability of the combination is obtained from the data set formed by SMC and fault symptoms. If the combination cannot be obtained by SMC simulation, the probability of the combination is supplemented by the probability table provided by the virtual expert, thus completing the construction of the BN fault symptom layer node probability table (the overall probability table of the symptom layer nodes).

[0135] The specific process of the embodiment of the present invention is as follows:

[0136] 1. Perform a sequential Monte Carlo simulation based on the abnormal operating conditions, three-phase separator parameters, and three-phase separator life distribution type to obtain the state change results of the three-phase separator.

[0137] 2. Inputting the three-phase separator state change result and the historical three-phase separator monitoring parameters into a separator simulation model to obtain first fault symptom data.

[0138] 3. Obtain the three-phase separator discretization data set according to the first fault symptom data and the three-phase separator state change result.

[0139] 4. Input the abnormal operating condition into the separator simulation model to obtain second fault symptom data.

[0140] 5. Perform virtual expert calculation on the second fault symptom data to obtain basic probability data of Bayesian network nodes.

[0141] 6. Obtain the virtual expert node probability data according to the basic probability data and the maximum noise model.

[0142] 7. Build the Bayesian network framework based on the abnormal operating condition and fault symptom data; the fault symptom data includes the first fault symptom data and the second fault symptom data. The Bayesian network framework includes a state layer, a fault layer, and a fault symptom layer.

[0143] 8. Obtain state layer probability data based on the three-phase separator discretization data set and the state layer, and determine fault layer probability data based on the three-phase separator discretization data set and the fault layer.

[0144] 9. Obtain a virtual expert node probability corresponding to the missing condition probability from the virtual expert node probability data, and determine fault symptom layer probability data based on the corresponding virtual expert node probability, the three-phase separator discretization data set, and the fault symptom layer.

[0145] 10. Create the Bayesian fault diagnosis model based on the fault layer probability data and the fault symptom layer probability data.

[0146] 11. Obtain current monitoring parameters of the three-phase separator. Input the current monitoring parameters of the three-phase separator into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result.

[0147] In summary, the three-phase separator fault diagnosis method of the embodiment of the present invention makes up for the problem of missing on-site probability and difficulty in collecting fault symptoms in BN fault diagnosis of horizontal three-phase separator systems, and uses virtual experts instead of real experts to improve work efficiency.

[0148] Based on the same inventive concept, an embodiment of the present invention further provides a three-phase separator fault diagnosis device. Since the principle of solving the problem by the device is similar to that of the three-phase separator fault diagnosis method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0149] Figure 14 FIG. 1 is a structural block diagram of a three-phase separator fault diagnosis device according to an embodiment of the present invention. Figure 14 As shown, the three-phase separator fault diagnosis device includes:

[0150] An acquisition module is used to obtain the current monitoring parameters of the three-phase separator;

[0151] The fault diagnosis module is used to input the current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert calculation to obtain a fault diagnosis result.

[0152] In one embodiment, it further includes:

[0153] A discretized data set module is used to obtain a three-phase separator discretized data set based on the three-phase separator state change results, historical three-phase separator monitoring parameters and separator simulation model;

[0154] A virtual expert node probability data module is used to obtain virtual expert node probability data according to abnormal working conditions and the separator simulation model;

[0155] The Bayesian fault diagnosis model creation module is used to create the Bayesian fault diagnosis model according to the Bayesian network framework, the three-phase separator discretization data set and the virtual expert node probability data.

[0156] In one embodiment, the discretization data set module includes:

[0157] A first fault symptom data unit is configured to input the three-phase separator state change result and the historical three-phase separator monitoring parameters into a separator simulation model to obtain first fault symptom data;

[0158] The three-phase separator discretization data set unit is configured to obtain the three-phase separator discretization data set according to the first fault symptom data and the three-phase separator state change result.

[0159] In one embodiment, the virtual expert node probability data module includes:

[0160] a second fault symptom data unit, configured to input an abnormal operating condition into the separator simulation model to obtain second fault symptom data;

[0161] The virtual expert node probability data unit is configured to obtain the virtual expert node probability data according to the second fault symptom data.

[0162] In one embodiment, the virtual expert node probability data unit includes:

[0163] a basic probability data subunit, configured to perform virtual expert calculation on the second fault symptom data to obtain basic probability data of Bayesian network nodes;

[0164] The virtual expert node probability data subunit is configured to obtain the virtual expert node probability data according to the basic probability data and a maximum noise model.

[0165] In one embodiment, it further includes:

[0166] A Bayesian network framework module is used to build the Bayesian network framework based on the abnormal working condition and fault symptom data; the fault symptom data includes the first fault symptom data and the second fault symptom data.

[0167] In one embodiment, it further includes:

[0168] The three-phase separator state change result module is used to perform sequential Monte Carlo simulation according to the abnormal operating conditions, three-phase separator parameters and three-phase separator life distribution type to obtain the three-phase separator state change result.

[0169] In one embodiment, the Bayesian network framework includes a state layer, a fault layer, and a fault symptom layer;

[0170] The Bayesian fault diagnosis model creation module includes:

[0171] a fault state layer probability data unit, configured to obtain state layer probability data according to the three-phase separator discretization data set and the state layer, and determine fault layer probability data according to the three-phase separator discretization data set and the fault layer;

[0172] a fault symptom layer probability data unit, configured to obtain a virtual expert node probability corresponding to a missing condition probability from the virtual expert node probability data, and determine the fault symptom layer probability data according to the corresponding virtual expert node probability, the three-phase separator discretization data set, and the fault symptom layer;

[0173] The Bayesian fault diagnosis model unit is used to create the Bayesian fault diagnosis model according to the fault layer probability data and the fault symptom layer probability data.

[0174] In summary, the three-phase separator fault diagnosis device of the embodiment of the present invention inputs the acquired current three-phase separator monitoring parameters into the Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert calculation to obtain the fault diagnosis results, which can improve the efficiency and accuracy of fault diagnosis.

[0175] Figure 15 Schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 15 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that the Figure 15 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0176] In one embodiment, the three-phase separator fault diagnosis method function may be integrated into the central processing unit 9100. The central processing unit 9100 may be configured to perform the following control:

[0177] Get the current three-phase separator monitoring parameters;

[0178] The current three-phase separator monitoring parameters are input into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result.

[0179] From the above description, it can be seen that the three-phase separator fault diagnosis method provided in this application inputs the acquired current three-phase separator monitoring parameters into the Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert calculation to obtain the fault diagnosis results, which can improve the efficiency and accuracy of fault diagnosis.

[0180] In another embodiment, the three-phase separator fault diagnosis device can be configured separately from the central processing unit 9100. For example, the three-phase separator fault diagnosis device can be configured as a chip connected to the central processing unit 9100, and the functions of the three-phase separator fault diagnosis method can be realized through the control of the central processing unit.

[0181] like Figure 15 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Figure 15 In addition, the electronic device 9600 may also include all components shown in Figure 15 For components not shown, reference may be made to the prior art.

[0182] like Figure 15 As shown, the central processing unit 9100 is sometimes also referred to as a controller or operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0183] Memory 9140 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and also store programs that execute the relevant information. The CPU 9100 can execute the programs stored in memory 9140 to implement information storage or processing.

[0184] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 may be, for example, a keypad or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0185] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), or a SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is provided with more data. Examples of such memory are sometimes referred to as EPROMs. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer 9141 (sometimes referred to as a buffer memory). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 by the central processing unit 9100.

[0186] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various driver programs for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0187] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in a conventional mobile communication terminal.

[0188] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing common telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 9130 is also coupled to the central processing unit 9100, enabling local recording via the microphone 9132 and playback of stored audio via the speaker 9131.

[0189] An embodiment of the present invention further provides a computer-readable storage medium capable of implementing all steps of the three-phase separator fault diagnosis method in the above embodiment, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all steps of the three-phase separator fault diagnosis method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0190] Get the current three-phase separator monitoring parameters;

[0191] The current three-phase separator monitoring parameters are input into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result.

[0192] In summary, the computer-readable storage medium of the embodiment of the present invention inputs the acquired current three-phase separator monitoring parameters into the Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert calculation to obtain a fault diagnosis result, which can improve the efficiency and accuracy of fault diagnosis.

[0193] An embodiment of the present invention further provides a computer program product capable of implementing all steps of the three-phase separator fault diagnosis method in the above embodiment, where the execution subject is a server or a client. The computer program product includes a computer program / instruction. When the computer program / instruction is executed by a processor, all steps of the three-phase separator fault diagnosis method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0194] Get the current three-phase separator monitoring parameters;

[0195] The current three-phase separator monitoring parameters are input into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result.

[0196] In summary, the computer program product of the embodiment of the present invention inputs the acquired current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result, which can improve the efficiency and accuracy of fault diagnosis.

[0197] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the hardware + program embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0198] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0199] Although the present application provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative work. The order of steps listed in the embodiments is only one way of executing the steps among many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, in a parallel processor or multi-threaded processing environment).

[0200] Although the present specification embodiment provides the method operation steps as described in the embodiment or flow chart, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way in the order of execution of many steps and does not represent a unique execution order. When the device or terminal product in practice is executed, it can be performed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (such as a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "comprise", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or equipment including a series of elements not only include those elements, but also include other elements not clearly listed, or also include elements inherent to such process, method, product or equipment. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or equipment including the elements.

[0201] For the convenience of description, the above devices are described in terms of functions divided into various modules. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0202] Those skilled in the art will also appreciate that, in addition to implementing the controller in pure computer-readable program code, it is entirely possible to implement the same functionality by logically programming the method steps in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, and the like. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered structures within the hardware component. Alternatively, the devices for implementing various functions can be considered both software modules implementing the method and structures within the hardware component.

[0203] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0204] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0205] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0206] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0207] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0208] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media 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 memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0209] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0210] The various embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0211] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from the other embodiments. In particular, since the system embodiments are generally similar to the method embodiments, the description is relatively simple. For relevant parts, reference can be made to the description of the method embodiments. Throughout this specification, reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the embodiments in this specification. In this specification, the schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and integrate the different embodiments or examples, and features of different embodiments or examples, described in this specification, without conflict.

[0212] The above description is merely an example of the embodiments of this specification and is not intended to limit the embodiments of this specification. For those skilled in the art, various modifications and variations of the embodiments of this specification are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A three-phase separator fault diagnosis method, characterized in that: include: Get the current three-phase separator monitoring parameters; Inputting the current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result; The steps of creating the Bayesian fault diagnosis model include: The three-phase separator discretization data set is obtained according to the three-phase separator state change results, historical three-phase separator monitoring parameters and separator simulation model; Obtaining virtual expert node probability data according to the abnormal operating conditions and the separator simulation model; Creating the Bayesian fault diagnosis model based on a Bayesian network framework, the three-phase separator discretization data set, and the virtual expert node probability data; The Bayesian network framework includes a state layer, a fault layer and a fault symptom layer; Creating the Bayesian fault diagnosis model according to the Bayesian network framework, the three-phase separator discretization data set and the virtual expert node probability data includes: Obtaining state layer probability data according to the three-phase separator discretization data set and the state layer, and determining fault layer probability data according to the three-phase separator discretization data set and the fault layer; Obtaining a virtual expert node probability corresponding to the missing condition probability from the virtual expert node probability data, and determining fault symptom layer probability data according to the corresponding virtual expert node probability, the three-phase separator discretization data set, and the fault symptom layer; The Bayesian fault diagnosis model is created according to the fault layer probability data and the fault symptom layer probability data.

2. The three-phase separator fault diagnosis method according to claim 1, characterized in that: The three-phase separator discretization data set obtained based on the three-phase separator state change results, historical three-phase separator monitoring parameters and separator simulation model includes: Inputting the three-phase separator state change result and the historical three-phase separator monitoring parameters into a separator simulation model to obtain first fault symptom data; The three-phase separator discretization data set is obtained according to the first fault symptom data and the three-phase separator state change result.

3. The three-phase separator fault diagnosis method according to claim 2, characterized in that: The virtual expert node probability data obtained according to the abnormal working conditions and the separator simulation model include: Inputting the abnormal operating condition into the separator simulation model to obtain second fault symptom data; The virtual expert node probability data is obtained according to the second fault symptom data.

4. The three-phase separator fault diagnosis method according to claim 3, characterized in that: Obtaining the virtual expert node probability data according to the second fault symptom data includes: Performing virtual expert calculation on the second fault symptom data to obtain basic probability data of Bayesian network nodes; The virtual expert node probability data is obtained according to the basic probability data and the maximum noise model.

5. The three-phase separator fault diagnosis method according to claim 3, characterized in that: Also includes: Building the Bayesian network framework based on the abnormal operating condition and fault symptom data; The fault symptom data includes the first fault symptom data and the second fault symptom data.

6. The three-phase separator fault diagnosis method according to claim 1, characterized in that: Also includes: A sequential Monte Carlo simulation is performed according to the abnormal operating conditions, the three-phase separator parameters and the life distribution type of the three-phase separator to obtain the state change result of the three-phase separator.

7. A three-phase separator fault diagnosis device, characterized in that: include: An acquisition module is used to obtain the current monitoring parameters of the three-phase separator; a fault diagnosis module, configured to input the current three-phase separator monitoring parameters into a Bayesian fault diagnosis model created based on sequential Monte Carlo simulation and virtual expert computing to obtain a fault diagnosis result; A discretized data set module is used to obtain a three-phase separator discretized data set based on the three-phase separator state change results, historical three-phase separator monitoring parameters and separator simulation model; A virtual expert node probability data module is used to obtain virtual expert node probability data according to abnormal working conditions and the separator simulation model; A Bayesian fault diagnosis model creation module, configured to create the Bayesian fault diagnosis model based on a Bayesian network framework, the three-phase separator discretization data set, and the virtual expert node probability data; The Bayesian network framework includes a state layer, a fault layer and a fault symptom layer; The Bayesian fault diagnosis model creation module includes: a fault state layer probability data unit, configured to obtain state layer probability data according to the three-phase separator discretization data set and the state layer, and determine fault layer probability data according to the three-phase separator discretization data set and the fault layer; a fault symptom layer probability data unit, configured to obtain a virtual expert node probability corresponding to a missing condition probability from the virtual expert node probability data, and determine the fault symptom layer probability data according to the corresponding virtual expert node probability, the three-phase separator discretization data set, and the fault symptom layer; The Bayesian fault diagnosis model unit is used to create the Bayesian fault diagnosis model according to the fault layer probability data and the fault symptom layer probability data.

8. The three-phase separator fault diagnosis device according to claim 7, characterized in that: The discretization data set module includes: A first fault symptom data unit is configured to input the three-phase separator state change result and the historical three-phase separator monitoring parameters into a separator simulation model to obtain first fault symptom data; The three-phase separator discretization data set unit is configured to obtain the three-phase separator discretization data set according to the first fault symptom data and the three-phase separator state change result.

9. The three-phase separator fault diagnosis device according to claim 8, characterized in that: The virtual expert node probability data module includes: a second fault symptom data unit, configured to input an abnormal operating condition into the separator simulation model to obtain second fault symptom data; The virtual expert node probability data unit is configured to obtain the virtual expert node probability data according to the second fault symptom data.

10. The three-phase separator fault diagnosis device according to claim 9, characterized in that: The virtual expert node probability data unit includes: a basic probability data subunit, configured to perform virtual expert calculation on the second fault symptom data to obtain basic probability data of Bayesian network nodes; The virtual expert node probability data subunit is configured to obtain the virtual expert node probability data according to the basic probability data and a maximum noise model.

11. The three-phase separator fault diagnosis device according to claim 9, characterized in that: Also includes: A Bayesian network framework module, configured to construct the Bayesian network framework based on the abnormal operating condition and fault symptom data; The fault symptom data includes the first fault symptom data and the second fault symptom data.

12. The three-phase separator fault diagnosis device according to claim 7, characterized in that: Also includes: The three-phase separator state change result module is used to perform sequential Monte Carlo simulation according to the abnormal operating conditions, three-phase separator parameters and three-phase separator life distribution type to obtain the three-phase separator state change result.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the three-phase separator fault diagnosis method according to any one of claims 1 to 6 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the three-phase separator fault diagnosis method according to any one of claims 1 to 6 are implemented.

15. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the three-phase separator fault diagnosis method according to any one of claims 1 to 6 are implemented.

Images