Storage medium, oil refining and chemical equipment reliability evaluation method, device and equipment

Abstract

The application discloses a storage medium, a refining chemical equipment reliability evaluation method, a device and equipment, and the method comprises the following steps: based on the real-time state monitoring data of the equipment, a first reliability evaluation model based on wavelet information entropy is established; based on the historical maintenance data of the equipment, a second reliability evaluation model based on a Weibull distribution algorithm is established; according to the data samples of the first reliability parameter and the second reliability parameter, a device reliability evaluation model based on multi-source information fusion of an extreme learning machine is constructed, which is used for calculating the comprehensive dynamic reliability parameter of the refining chemical equipment. The application introduces the real-time state reliability of the equipment represented by the wavelet information entropy of the real-time state monitoring data of the equipment, corrects the traditional reliability evaluation model based on the Weibull distribution algorithm, constructs a reliability evaluation coupling model which comprehensively reflects the historical state and the real-time state of the equipment, and therefore the mechanical equipment reliability can be comprehensively and accurately evaluated.

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring, and in particular to storage media, methods, apparatus and equipment for reliability evaluation of oil refining and chemical equipment. Background Technology

[0002] Safe and reliable operation of equipment is the fundamental guarantee for the long-term operation of production facilities. Equipment reliability is the basis for scientific and accurate decision-making in enterprise equipment management, the guarantee for promoting the construction of an equipment integrity system, the foundation for the comprehensive implementation of preventive maintenance and the reduction of sudden failures, and the support for carrying out equipment risk assessment.

[0003] Existing reliability assessment methods can be broadly categorized into three main types: physical failure model-based methods, data-driven statistical failure models, and empirical model-based reliability assessment methods. In practical applications, due to the difficulty in obtaining physical models of the failure mechanisms of complex, high-reliability equipment, data-driven reliability assessment and fault prediction methods have become the mainstream research approach. These methods analyze equipment failure data to identify failure distribution types and then perform statistical inferences.

[0004] Currently, it is generally believed that the reliability distribution of most oil refining and chemical machinery and equipment follows the Weibull distribution. The Weibull distribution has good compatibility and strong fitting ability for various types of data, and can comprehensively describe the failure process and characteristics of oil refining and chemical equipment at different failure stages.

[0005] The inventors discovered through research that existing equipment reliability evaluation technologies still have at least the following shortcomings:

[0006] In engineering practice, equipment operating conditions and environments are highly variable. Reliability analysis theories and methods based on historical maintenance data fitting cannot adequately reflect the dynamic characteristics of equipment and fail to reflect the reliability change patterns reflected by real-time changes in equipment operating status. This results in a large deviation between reliability evaluation results and actual conditions, making it difficult to scientifically and accurately guide preventive maintenance of equipment.

[0007] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0008] The purpose of this invention is to effectively reduce the deviation between reliability evaluation results and reality, thereby accurately guiding preventive maintenance of equipment.

[0009] This invention provides a reliability evaluation method for oil refining and chemical equipment, comprising the following steps:

[0010] S11. Based on real-time status monitoring data in the real-time fault database of oil refining and chemical equipment, establish a first reliability evaluation model based on wavelet information entropy; the first reliability evaluation model is used to generate the first reliability parameters of oil refining and chemical equipment; the real-time status monitoring data includes the original waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables; the operating condition monitoring indicators include equipment status.

[0011] S12. Based on historical maintenance data in the historical fault database of oil refining and chemical equipment, establish a second reliability evaluation model based on the Weibull distribution algorithm; the second reliability evaluation model is used to generate the second reliability parameters of oil refining and chemical equipment.

[0012] S13. Based on the data samples of the first reliability parameter and the second reliability parameter, construct a device reliability evaluation model based on a multi-source information extreme learning machine; the device reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of the oil refining and chemical equipment.

[0013] Preferably, the present invention further includes, when evaluating the reliability of oil refining and chemical equipment:

[0014] Using the current raw waveform data from multiple monitoring points as input, the first reliability parameter value is obtained through the first reliability evaluation model;

[0015] Using the failure interval time data from multiple historical maintenance data as input, the second reliability parameter value is obtained through the second reliability evaluation model;

[0016] Using the first reliability parameter value and the second reliability parameter value as input, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

[0017] In another aspect of the present invention, a reliability evaluation device for oil refining and chemical equipment is also provided, comprising:

[0018] The first model unit is used to establish a first reliability evaluation model based on wavelet information entropy, based on real-time status monitoring data from the real-time fault database of oil refining and chemical equipment. The first reliability evaluation model is used to generate the first reliability parameters of the oil refining and chemical equipment. The real-time status monitoring data includes the original vibration waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables. The operating condition monitoring indicators include equipment status.

[0019] The second model unit is used to establish a second reliability evaluation model based on the Weibull distribution algorithm, using historical maintenance data from the historical fault database of oil refining and chemical equipment; the second reliability evaluation model is used to generate the second reliability parameters of oil refining and chemical equipment.

[0020] The evaluation model unit is used to construct a device reliability evaluation model based on a multi-source information extreme learning machine based on data samples of the first reliability parameter and the second reliability parameter; the device reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of the oil refining and chemical equipment.

[0021] Preferably, the present invention further includes an evaluation generation unit for performing the following when evaluating the reliability of oil refining and chemical equipment:

[0022] Using the current raw waveform data from multiple monitoring points as input, a first reliability parameter value is obtained through the first reliability evaluation model; using the fault interval time data from multiple historical maintenance data as input, a second reliability parameter value is obtained through the second reliability evaluation model; using the first reliability parameter value and the second reliability parameter value as input, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

[0023] In another aspect of the present invention, a storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the various steps of the device dynamic reliability evaluation method as described in any of the preceding claims.

[0024] In another aspect of this invention, a device dynamic reliability evaluation device is also provided; the device dynamic reliability evaluation device includes a computer program stored on a medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer performs the methods described in the above aspects and achieves the same technical effect.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] This invention addresses the problem that traditional reliability evaluation methods based on Weibull regression analysis of historical maintenance data cannot reflect the reliability change patterns reflected by real-time operating status changes of equipment, cannot accurately reflect the dynamic characteristics of equipment reliability changes over time, and have large deviations between reliability evaluation results and actual conditions, making it difficult to scientifically and accurately guide preventive maintenance of equipment.

[0027] This invention aims to correct the traditional reliability evaluation model based on the Weibull distribution algorithm by coupling a wavelet information entropy reliability evaluation model (i.e., the first reliability evaluation model) based on real-time raw waveform data with a reliability evaluation model based on Weibull regression analysis of historical maintenance data. It reflects the reliability change law reflected by the real-time operating status changes of the equipment and can accurately reflect the dynamic characteristics of the equipment's reliability changes over time. Thus, it can comprehensively and accurately evaluate the reliability of mechanical equipment and provide technical support for the scientific decision-making of preventive maintenance.

[0028] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description

[0029] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a flowchart illustrating the steps of the reliability evaluation method for oil refining and chemical equipment described in this invention;

[0031] Figure 2 This is a schematic diagram of the cumulative distribution function described in this invention;

[0032] Figure 3 This is a schematic diagram of the device reliability function described in this invention;

[0033] Figure 4 This is a schematic diagram of the operation process of the equipment reliability evaluation model in this invention;

[0034] Figure 5 This is a schematic diagram of the neural network structure of the equipment reliability evaluation model described in this invention;

[0035] Figure 6 This is a schematic diagram of the reliability evaluation device for oil refining and chemical equipment described in this invention;

[0036] Figure 7 This is a schematic diagram of the reliability evaluation equipment for oil refining and chemical equipment described in this invention. Detailed Implementation

[0037] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0038] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprises" shall be understood to include the stated elements or components without excluding other elements or other components.

[0039] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.

[0040] Example 1

[0041] To effectively reduce the discrepancy between reliability evaluation results and actual conditions, and thus accurately guide preventative maintenance of equipment, such as... Figure 1 As shown, this embodiment of the invention provides a reliability evaluation method for oil refining and chemical equipment, including the following steps:

[0042] S11. Based on real-time status monitoring data in the real-time fault database of oil refining and chemical equipment, establish a first reliability evaluation model based on wavelet information entropy; the first reliability evaluation model is used to generate the first reliability parameters of oil refining and chemical equipment; the real-time status monitoring data includes the original vibration waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables; the operating condition monitoring indicators include equipment status.

[0043] The inventors discovered through research that the reason why the traditional reliability evaluation model based on the Weibull distribution algorithm is not accurate enough when applied to the reliability evaluation of oil refining and chemical equipment is that the operating state of oil refining and chemical equipment has the characteristic of real-time change. These fluctuations in the operating state that can affect the reliability of oil refining and chemical equipment cannot be reflected in the reliability evaluation model based on the Weibull distribution algorithm, thus causing the deviation of the evaluation results.

[0044] The inventors further discovered that for oil refining and chemical equipment, as the operating condition deteriorates, the uncertainty of the system increases, resulting in more complex operating state information. Information entropy is a good measure of the degree of system uncertainty and can assess the complexity of random signals. A higher information entropy indicates that the system is in multiple states, the more severe the equipment performance degradation, and the higher the operational reliability, and vice versa. Therefore, in this embodiment of the invention, using the original waveform data of the current state of the oil refining and chemical equipment, an auxiliary reliability evaluation of the equipment is performed using a reliability evaluation model based on wavelet information entropy, and the first reliability parameter of the oil refining and chemical equipment is calculated.

[0045] The specific implementation methods for this step may include:

[0046] The vibration waveform data is decomposed into wavelet packets, and the normalized wavelet packet information entropy and its corresponding reliability are calculated to generate the first reliability parameters of the equipment, including:

[0047] The original waveform data was decomposed and reconstructed using second-generation wavelet packets in a 3-level (l=3) manner, resulting in 2 3 =8 decomposed frequency band signals, calculate the relative energy E of each decomposed frequency band. 3,I The normalized wavelet information entropy is calculated using formula (3);

[0048]

[0049] In the formula: 2 l This represents the total number of frequency bands in the wavelet packet decomposition. Let represent the relative energy of the l-th layer and the i-th frequency band after wavelet packet decomposition, and

[0050] Formula (4) available for calculating the first reliability parameter Re includes:

[0051] The first reliability parameter Re∈[0,1]:

[0052] R(e) = 1 - e; Formula (4).

[0053] In a specific instance, this step may include the following procedures:

[0054] Based on the pump and machine condition monitoring system and the large unit condition monitoring system, the original waveform data and fault characteristic parameters of typical rotating machinery such as centrifugal pumps, centrifugal compressors, centrifugal fans, flue gas turbines, axial flow compressors, and steam turbines are collected.

[0055] Establish a real-time fault database for mechanical equipment, which mainly includes key information such as enterprise, device, unit, equipment, component, monitoring point, monitoring point type (including vibration and displacement), raw waveform data, monitoring alarm value, operating parameters (including speed, power, temperature and flow rate, etc.), and equipment status (including start-up, shutdown and alarm), as shown in Table 1.

[0056] Table 1:

[0057]

[0058] By utilizing real-time raw waveform data and applying modern signal processing theory, a reliability evaluation model based on wavelet information entropy is established to evaluate the reliability of the equipment based on real-time status monitoring data and calculate the corresponding reliability parameters of the equipment.

[0059] The vibration signal is decomposed into wavelet packets, and the normalized wavelet packet information entropy and its corresponding reliability are calculated to evaluate the reliability of equipment operation. The vibration signal of mechanical equipment is decomposed and reconstructed in 3 layers (l=3) using second-generation wavelet packets to obtain 23=8 decomposed frequency band signals. The relative energy E3,I of each decomposed frequency band is calculated, and the normalized wavelet information entropy is calculated using formula (3).

[0060]

[0061] In the formula: 2 l This represents the total number of frequency bands in the wavelet packet decomposition. Let represent the relative energy of the l-th layer and the i-th frequency band after wavelet packet decomposition, and

[0062] Formula (4) available for calculating the first reliability parameter Re includes:

[0063] The first reliability parameter Re∈[0,1]:

[0064] R(e) = 1 - e; Formula (4).

[0065] S12. Based on historical maintenance data in the historical fault database of oil refining and chemical equipment, establish a second reliability evaluation model based on the Weibull distribution algorithm; the second reliability evaluation model is used to generate the second reliability parameters of oil refining and chemical equipment.

[0066] In practical applications, referring to Table 2, the historical maintenance data in this embodiment of the invention may specifically include: the fault time, downtime, maintenance start date, maintenance end date, maintenance time, fault mode, fault cause, maintenance type, maintenance content, and replaced components corresponding to the enterprise, device, unit, equipment, and parts.

[0067] Table 2:

[0068]

[0069] In this embodiment of the invention, the objects for collecting historical maintenance data may include centrifugal pumps, centrifugal compressors, centrifugal fans, flue gas turbines, axial flow compressors, and steam turbines, etc. The types of historical maintenance data may specifically include routine maintenance, minor repairs, medium repairs, and major overhauls due to shutdown.

[0070] Based on historical maintenance data and applying probability and statistics theory, a Weibull distribution reliability evaluation model can be established to evaluate the reliability of equipment based on historical maintenance data and calculate the corresponding reliability parameters of the equipment.

[0071] The Weibull distribution reliability evaluation model in this embodiment of the invention is based on historical failure time data and is used to evaluate the reliability of typical rotating machinery and components such as centrifugal pumps, centrifugal compressors, centrifugal fans, flue gas turbines, axial flow compressors, and steam turbines to determine reliability parameters such as failure model, failure cause, shape parameters, distribution scale parameters, mean time between failures (MTBF), and equipment availability.

[0072] The establishment of the second reliability evaluation model based on the Weibull distribution algorithm includes:

[0073] Based on the equipment and components corresponding to the failure time, a reliability evaluation is carried out to determine reliability parameters such as failure model, failure cause, shape parameter, distribution scale parameter, mean time between failures, and equipment availability.

[0074] The failure rate function of the two-parameter Weibull distribution model is shown in Equation (1):

[0075]

[0076] Its corresponding reliability function is shown in formula (2):

[0077]

[0078] In the formula, t is the failure time, which can be in days, hours, minutes or seconds, etc.; β is the shape parameter of the Weibull distribution; and η is the scale parameter of the Weibull distribution.

[0079] Taking the reliability evaluation of the overhead gas compressor of an atmospheric and vacuum distillation unit as an example:

[0080] Using the historical fault records of the cleaning equipment in Table 3, the historical fault-free operating time can be obtained.

[0081] Table 3:

[0082]

[0083]

[0084] Next, by organizing the interval probability table, we obtain, as follows: Figure 2 The cumulative distribution function is shown.

[0085] Then, the widely applicable Weibull model is selected for reliability function fitting; the values ​​of the shape parameter β and scale parameter θ of the two-parameter Weibull model are solved to obtain the following results: Figure 3 The device reliability function is shown.

[0086] S13. Based on the data samples of the first reliability parameter and the second reliability parameter, construct a device reliability evaluation model based on multi-source information fusion using extreme learning machine; the device reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of oil refining and chemical equipment.

[0087] In this embodiment of the invention, the formula in the equipment reliability evaluation model can be as shown in formula (5):

[0088]

[0089] In the formula: the inputs are the first reliability parameter and the second reliability parameter X. j The result value of the comprehensive dynamic reliability parameter output is Z'. j ;w j b represents the connection weights from the input layer to the hidden layer. i The threshold from the input layer to the hidden layer; β i The connection coefficients from the hidden layer to the output layer; w i ·x j For w i and x j The inner product.

[0090] Based on historical and real-time fault reliability evaluation data samples, an ELM (Extreme Learning Machine) neural network is applied to construct an equipment reliability evaluation model based on the coupled analysis of historical maintenance data and condition monitoring data, in order to calculate the comprehensive dynamic reliability parameter value of the oil refining and chemical equipment. In this embodiment, based on data samples of the first and second reliability parameters, an equipment reliability evaluation model based on a multi-source information extreme learning machine is constructed, which can then obtain the comprehensive dynamic reliability parameter value based on historical maintenance data and current condition monitoring data. This is equivalent to coupling the first and second reliability evaluation models, thereby achieving the purpose of correcting the traditional reliability evaluation model based on the Weibull distribution algorithm.

[0091] In a specific example, the first reliability evaluation model and the second reliability evaluation model were coupled; the operation process and neural network structure of the equipment reliability evaluation model can be found by referring to... Figure 4 and Figure 5 .

[0092] Furthermore, in this embodiment of the invention, the method may also include a step of evaluating the reliability of oil refining and chemical equipment using the above-described model, specifically including:

[0093] Using the current raw waveform data from multiple monitoring points as input, the first reliability parameter value is obtained through the first reliability evaluation model;

[0094] The second reliability parameter value is obtained through the second reliability evaluation model;

[0095] Using the first reliability parameter value and the second reliability parameter value as input, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

[0096] In summary, the embodiments of the present invention, by introducing wavelet information entropy reliability evaluation data based on real-time state raw waveform data, solve the problem that the traditional reliability evaluation method based on Weibull regression analysis of historical maintenance data cannot reflect the reliability change law reflected by the real-time operating status changes of the equipment, cannot accurately reflect the dynamic characteristics of the equipment's reliability changes over time, and the reliability evaluation results deviate significantly from the actual situation, making it difficult to scientifically and accurately guide the preventive maintenance of the equipment.

[0097] This invention, through coupling a wavelet information entropy reliability evaluation model based on real-time state raw waveform data (i.e., the first reliability evaluation model) with a reliability evaluation model based on Weibull regression analysis of historical maintenance data, aims to correct the traditional reliability evaluation model based on the Weibull distribution algorithm. It reflects the reliability change law reflected by the real-time operating state changes of the equipment, accurately reflects the dynamic characteristics of the equipment's reliability changing over time, and thus can comprehensively and accurately evaluate the reliability of mechanical equipment, providing technical support for scientific decision-making in preventive maintenance.

[0098] Example 2

[0099] Corresponding to the method embodiment, another aspect of the present invention also provides a reliability evaluation device for oil refining and chemical equipment. Figure 6 The present invention provides a schematic diagram of the structure of a reliability evaluation device for oil refining and chemical equipment, wherein the reliability evaluation device for oil refining and chemical equipment is a... Figure 1 The device corresponding to the reliability evaluation method for oil refining and chemical equipment described in the corresponding embodiment is implemented through a virtual device. Figure 1 The reliability evaluation method for oil refining and chemical equipment in the corresponding embodiments allows each virtual module constituting the reliability evaluation device for the oil refining and chemical equipment to be executed by electronic devices, such as network devices, terminal devices, or servers. Specifically, the reliability evaluation device for oil refining and chemical equipment in the embodiments of the present invention includes:

[0100] The first model unit 01 establishes a first reliability evaluation model based on wavelet information entropy using real-time status monitoring data from a real-time fault database of refining and chemical equipment. The first reliability evaluation model is used to generate first reliability parameters for the refining and chemical equipment. The real-time status monitoring data includes the original vibration waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables. The operating condition monitoring indicators include equipment status.

[0101] The second model unit 02 establishes a second reliability evaluation model based on the Weibull distribution algorithm using historical maintenance data from a historical fault database of refining and chemical equipment; the second reliability evaluation model is used to generate the second reliability parameters of the refining and chemical equipment.

[0102] The evaluation model unit 03 constructs a multi-source information fusion equipment reliability evaluation model based on extreme learning machine according to the data samples of the first reliability parameter and the second reliability parameter; the equipment reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of oil refining and chemical equipment.

[0103] Preferably, the present invention further includes an evaluation generation unit (not shown in the figure) for performing the following when evaluating the reliability of oil refining and chemical equipment:

[0104] Using the current raw waveform data from multiple monitoring points as input, a first reliability parameter value is obtained through the first reliability evaluation model; using the fault interval time data from multiple historical maintenance data as input, a second reliability parameter value is obtained through the second reliability evaluation model; using the first reliability parameter value and the second reliability parameter value as input, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

[0105] It should be noted that the specific implementation method and technical effects of the equipment dynamic reliability evaluation system in the embodiments of the present invention can be referred to Figure 1 The corresponding dynamic reliability evaluation methods for equipment will not be elaborated here.

[0106] Example 3

[0107] Corresponding to the method embodiments, this invention also provides a device for dynamic reliability evaluation, such as a terminal or server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these.

[0108] An example diagram of the hardware structure block diagram of the device dynamic reliability evaluation device provided in this embodiment of the invention is shown below. Figure 7 As shown, it may include:

[0109] Processor 1, communication interface 2, memory 3, and communication bus 4;

[0110] The processor 1, communication interface 2, and memory 3 communicate with each other via communication bus 4.

[0111] Optionally, communication interface 2 can be an interface of a communication module, such as the interface of a GSM module;

[0112] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0113] Memory 3 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0114] Specifically, processor 1 is used to execute the computer program stored in memory 3 to perform the following steps:

[0115] S11. Based on real-time status monitoring data in the real-time fault database of oil refining and chemical equipment, establish a first reliability evaluation model based on wavelet information entropy; the first reliability evaluation model is used to generate the first reliability parameters of oil refining and chemical equipment; the real-time status monitoring data includes the original vibration waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables; the operating condition monitoring indicators include equipment status.

[0116] S12. Based on historical maintenance data in the historical fault database of oil refining and chemical equipment, establish a second reliability evaluation model based on the Weibull distribution algorithm; the second reliability evaluation model is used to generate the second reliability parameters of oil refining and chemical equipment.

[0117] S13. Based on the data samples of the first reliability parameter and the second reliability parameter, construct a device reliability evaluation model based on multi-source information fusion using extreme learning machine; the device reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of oil refining and chemical equipment.

[0118] Preferably, the present invention further includes, when evaluating the reliability of oil refining and chemical equipment:

[0119] Using the current raw waveform data from multiple monitoring points as input, the first reliability parameter value is obtained through the first reliability evaluation model;

[0120] Using the failure interval time data from multiple historical maintenance data as input, the second reliability parameter value is obtained through the second reliability evaluation model;

[0121] Using the first reliability parameter value and the second reliability parameter value as input, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

[0122] The above-described product can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the device dynamic reliability evaluation method provided in the embodiments of the present invention.

[0123] Example 4

[0124] In this embodiment of the invention, a storage medium is also provided, which can store a program suitable for execution by a processor, the program being used for:

[0125] S11. Based on real-time status monitoring data in the real-time fault database of oil refining and chemical equipment, establish a first reliability evaluation model based on wavelet information entropy; the first reliability evaluation model is used to generate the first reliability parameters of oil refining and chemical equipment; the real-time status monitoring data includes the original vibration waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables; the operating condition monitoring indicators include equipment status.

[0126] S12. Based on historical maintenance data in the historical fault database of oil refining and chemical equipment, establish a second reliability evaluation model based on the Weibull distribution algorithm; the second reliability evaluation model is used to generate the second reliability parameters of oil refining and chemical equipment.

[0127] S13. Based on the data samples of the first reliability parameter and the second reliability parameter, construct a device reliability evaluation model based on multi-source information fusion using extreme learning machine; the device reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of oil refining and chemical equipment.

[0128] Preferably, the present invention further includes, when evaluating the reliability of oil refining and chemical equipment:

[0129] Using the current raw vibration waveform data from multiple monitoring points as input, the first reliability parameter value is obtained through the first reliability evaluation model;

[0130] Using the failure interval time data from multiple historical maintenance data as input, the second reliability parameter value is obtained through the second reliability evaluation model;

[0131] Using the first reliability parameter value and the second reliability parameter value as input, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

[0132] Optionally, the refined and extended functions of the program can be found in the description above.

[0133] The above-described product can execute the methods provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in other embodiments of the present invention.

[0134] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0135] 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. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0136] 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.

[0137] 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.

[0138] It should be understood that in the embodiments of this application, the claims, various embodiments, and features can be combined with each other to solve the aforementioned technical problems.

[0139] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a 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 described in 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.

[0140] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A reliability evaluation method for oil refining and chemical equipment, characterized in that, Including the following steps: S11. Based on real-time status monitoring data in the real-time fault database of oil refining and chemical equipment, establish a first reliability evaluation model based on wavelet information entropy; the first reliability evaluation model is used to generate the first reliability parameters of oil refining and chemical equipment; the real-time status monitoring data includes the original waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables; the operating condition monitoring indicators include equipment status. S12. Based on historical maintenance data in the historical fault database of oil refining and chemical equipment, establish a second reliability evaluation model based on the Weibull distribution algorithm; the second reliability evaluation model is used to generate the second reliability parameters of oil refining and chemical equipment. S13. Based on the data samples of the first reliability parameter and the second reliability parameter, construct a multi-source information fusion equipment reliability evaluation model based on Extreme Learning Machine (ELM); the equipment reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of oil refining and chemical equipment.

2. The reliability evaluation method for oil refining and chemical equipment according to claim 1, characterized in that, This also includes evaluating the reliability of oil refining and chemical equipment: Using the current raw waveform data from multiple monitoring points as input, the first reliability parameter value is obtained through the first reliability evaluation model; Using the failure interval time data from multiple historical maintenance data as input, the second reliability parameter value is obtained through the second reliability evaluation model; Using the first reliability parameter value and the second reliability parameter value as inputs, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

3. The reliability evaluation method for oil refining and chemical equipment according to claim 1 or 2, characterized in that, The historical maintenance data includes: For enterprises, units, equipment, and components, the following information is provided: failure time, downtime, maintenance start date, maintenance end date, maintenance time, failure mode, failure cause, maintenance type, maintenance content, and replaced components. The real-time status monitoring data includes: The monitoring points, monitoring point types, original waveform data of the monitoring points, monitoring alarm values, operating parameters, and equipment status corresponding to enterprises, devices, units, equipment, and components.

4. The reliability evaluation method for oil refining and chemical equipment according to claim 3, characterized in that, The first reliability evaluation model generates the first reliability parameter of the device by performing wavelet packet decomposition on the original waveform data, calculating the normalized wavelet packet information entropy and its corresponding reliability.

5. The reliability evaluation method for oil refining and chemical equipment according to claim 4, characterized in that, The historical maintenance data collection targets include: Centrifugal pumps, centrifugal compressors, centrifugal fans, flue gas turbines, axial flow compressors, and steam turbines.

6. The reliability evaluation method for oil refining and chemical equipment according to claim 5, characterized in that, Historical maintenance data includes the following types: Routine maintenance, minor repairs, medium repairs, and major repairs during shutdown.

7. The reliability evaluation method for oil refining and chemical equipment according to claim 6, characterized in that, The establishment of the second reliability evaluation model based on the Weibull distribution algorithm includes: Based on the equipment and components corresponding to the failure time, a reliability evaluation is carried out to determine reliability parameters such as failure model, failure cause, shape parameter, distribution scale parameter, mean time between failures, and equipment availability. The failure rate function of the two-parameter Weibull distribution model is shown in Equation (1): Its corresponding reliability function is shown in formula (2): In the formula, t is the failure time; β is the shape parameter of the Weibull distribution; and η is the scale parameter of the Weibull distribution.

8. The reliability evaluation method for oil refining and chemical equipment according to claim 7, characterized in that, The step of performing wavelet packet decomposition on the original waveform data, calculating the normalized wavelet packet information entropy and its corresponding reliability, and generating the first reliability parameter of the device includes: The original waveform data was decomposed and reconstructed using second-generation wavelet packets in a 3-level (l=3) manner, resulting in 2 3 =8 decomposed frequency band signals, calculate the relative energy E of each decomposed frequency band. 3,I The normalized wavelet information entropy is calculated using formula (3); In the formula: 2 l The total number of frequency bands for wavelet packet decomposition Let represent the relative energy of the l-th layer and the i-th frequency band after wavelet packet decomposition, and Formula (4) available for calculating the first reliability parameter Re includes: The first reliability parameter Re∈[0,1]: R(e) = 1 - e; Formula (4).

9. The reliability evaluation method for oil refining and chemical equipment according to claim 8, characterized in that, Formula (5) in the equipment reliability evaluation model includes: In the formula: the inputs are the first reliability parameter and the second reliability parameter X. j The result value of the comprehensive dynamic reliability parameter output is Z'. j ;w j b represents the connection weights from the input layer to the hidden layer. i The threshold from the input layer to the hidden layer; β i w represents the connection coefficients from the hidden layer to the output layer. i ·x j For w i and x j The inner product.

10. A reliability evaluation device for oil refining and chemical equipment, characterized in that, include: The first model unit is used to establish a first reliability evaluation model based on wavelet information entropy, using real-time status monitoring data from the real-time fault database of oil refining and chemical equipment. The first reliability evaluation model is used to generate the first reliability parameters of the oil refining and chemical equipment; the real-time status monitoring data includes the original waveform data corresponding to each monitoring point as independent variables, and the operating condition monitoring indicators as dependent variables; the operating condition monitoring indicators include the equipment status. The second model unit is used to establish a second reliability evaluation model based on the Weibull distribution algorithm, using historical maintenance data from the historical fault database of oil refining and chemical equipment; the second reliability evaluation model is used to generate the second reliability parameters of oil refining and chemical equipment. The evaluation model unit is used to construct a device reliability evaluation model based on multi-source information fusion using extreme learning machine, based on data samples of the first reliability parameter and the second reliability parameter; the device reliability evaluation model is used to calculate the comprehensive dynamic reliability parameters of the oil refining and chemical equipment.

11. The reliability evaluation device for oil refining and chemical equipment according to claim 10, characterized in that, It also includes an evaluation generation unit, used to perform evaluations of the reliability of refining and chemical equipment: Using the current raw waveform data from multiple monitoring points as input, the first reliability parameter value is obtained through the first reliability evaluation model; Using the failure interval time data from multiple historical maintenance data as input, the second reliability parameter value is obtained through the second reliability evaluation model; Using the first reliability parameter value and the second reliability parameter value as inputs, the current comprehensive dynamic reliability parameter value of the oil refining and chemical equipment is obtained through the equipment reliability evaluation model.

12. A reliability evaluation device for oil refining and chemical equipment, characterized in that, include: Memory, used to store computer programs; A processor is used to call and execute the computer program to implement the steps of the reliability evaluation method for oil refining and chemical equipment as described in any one of claims 1-9.

13. A storage medium, characterized in that, Includes a software program adapted by a processor to perform the steps of the reliability evaluation method for oil refining and chemical equipment as described in any one of claims 1-9.

Images