Failure probability prediction method and system for safety instrument system of petroleum refining device

Abstract

The invention belongs to the technical field of safety engineering in petrochemical production, and discloses a failure probability prediction method and system for a safety instrument system of a petroleum refining device. Compared with a traditional multiple regression method, the KPCA and GAM combination can effectively process high-dimensional and nonlinear data problems, and a stable modeling result is provided in a complex system. The KPCA extracts a key principal component score matrix through nonlinear dimensionality reduction of input data, so that features which contribute to the failure probability most in the data are reserved; and the GAM flexibly models a nonlinear relationship between the score of the principal component and the failure probability by using a smooth function, so that high-precision prediction is realized. According to the method, a data-driven model based on empirical data is combined with a traditional statistical model, so that factors which have the greatest influence on the SIS failure probability can be effectively identified, the failure probability of newly accessed SIS equipment can be predicted, potential failure behaviors of old equipment are preventively reinforced, and the safety of a petroleum refining production process is further ensured.

Description

Technical Field

[0001] The invention belongs to the technical field of safety engineering in petrochemical production, and in particular relates to a failure probability prediction method and system for a safety instrument system of a petroleum refining device. Background Art

[0002] In petrochemical production, the Safety Instrumented System (SIS) is used to execute predetermined protective measures in extremely dangerous situations, such as closing valves, stopping equipment operation, or initiating emergency shutdown procedures. Its purpose is to protect personnel, equipment, and the environment from potential dangers, and it is the last line of defense to ensure the safety of petrochemical production and personnel. Once the SIS equipment fails, it will cause major safety accidents such as explosions, fires, or leaks of harmful chemicals, causing huge economic losses to petrochemical production. Therefore, predicting the failure probability of SIS equipment in oil refining units and replacing or reinforcing equipment in a timely manner are important means to ensure the safe operation of the unit.

[0003] The international functional safety standard IEC 61508 divides SIS equipment failures into four categories: detectable dangerous failures (Dangerous Detected, DD), undetectable dangerous failures (Dangerous Undetected, DU), safe failures, and non-component / no-impact failures. Among them, DD failures and DU failures are dangerous failure types that are critical to the safe operation of equipment. The difference is that DD failures are detectable and can be discovered through automatic diagnostic procedures after they occur, and quickly switched to backup SIS equipment, so their impact is relatively small; while DU failures are latent and are usually only exposed when executing control instructions, shutdown tests, or occasional inspections. Since DU failures cannot be detected immediately and must wait until the next regular test to return to normal, they pose the greatest threat to the safe operation of SIS equipment. Therefore, how to accurately predict the probability of DU failures of newly connected SIS equipment has become a key issue in the design and risk management of oil refining safety instrumentation systems.

[0004] Among the existing failure probability prediction methods, traditional statistical models have been widely used. For example, patent CN117708703A uses BP neural network to predict the failure probability of electronic detonators, obtains key data through multi-stage detection, and trains the neural network after establishing a sample library. However, this method relies on a complex network structure, the training process is computationally intensive and lacks interpretability, and it is difficult to identify the role of specific influencing factors. Another method, patent CN114065674B, predicts the failure probability of CMOS devices based on a linear regression model, and quantifies the importance of different influencing factors by assigning weight values. However, this method assumes that there is a linear relationship between variables, it is difficult to capture complex nonlinear characteristics, and it is also highly dependent on data quality. At the same time, most statistical models rely on multiple groups of equipment data and assume that items in the same group of equipment have similar functions and the same failure rate, but their designs (such as measurement principles), locations and environments are different, so such assumptions are flawed. Even if the operating environment is the same, the failure rates of similar devices are different. For example, the failure mode "failure to open (FTO)" of the same valve is affected by the temperature of the medium flowing through the valve, and its failure probability is often in dynamic change. Many factors in petrochemical production have a certain impact on the failure probability of SIS equipment. Among them, the factors that have the greatest impact on the failure probability are called important influencing factors. In addition, existing methods are difficult to provide accurate predictions when dealing with high-dimensional and nonlinear factors with complex relationships.

[0005] Through the above analysis, the problems and defects of the prior art are as follows:

[0006] Most statistical models assume that the same group of devices have similar functions and the same failure rate, but in reality, the design (such as measurement principle), installation location and operating environment of the equipment are often different. This assumption makes it difficult to accurately reflect the differences between devices. In addition, traditional models are not adaptable enough to dynamic changes in operating conditions. For example, the failure mode of valves, "failure to open (FTO)", will affect the failure probability due to medium temperature fluctuations, but existing methods are difficult to capture real-time changes. More importantly, many models assume that the relationship between variables is linear, lack the ability to model complex nonlinear relationships, and have a high reliance on high-quality data and lack clear explanations, which is not conducive to optimizing equipment design and operating conditions. Summary of the invention

[0007] In view of the problems existing in the prior art, the present invention provides a failure probability prediction method and system for a safety instrument system of a petroleum refining device.

[0008] The present invention is implemented as follows: a failure probability prediction method for a safety instrument system of a petroleum refining device comprises:

[0009] Step 1: Data collection and preprocessing: Demarcate the boundaries of the safety instrument system, collect equipment information and historical failure data of the safety instrument system of the oil refining unit to determine the failure mode and cause, and perform classification and preprocessing;

[0010] Step 2: Data dimensionality reduction and failure probability modeling. KPCA is used to reduce the dimensionality of high-dimensional data and extract key features. KPCA maps complex data to a low-dimensional principal component space and generates a principal component score matrix to capture the nonlinear correlation between DU failure and influencing factors. On this basis, GAM is combined to describe the relationship between the principal component score and the DU failure probability, and a failure probability prediction model is established.

[0011] Step 3, failure probability prediction, is used to import the probability distribution, correlation and important influencing factors of DU failure nodes obtained by kernel principal component analysis after data dimensionality reduction and failure probability modeling, and then use GAM to model to predict the failure probability of newly connected equipment in the safety instrumented system, verify and interpret the prediction results, evaluate the accuracy and reliability of the failure probability, and calculate the failure probability of SIS equipment in the newly connected facilities according to the failure rate prediction formula.

[0012] Further, the data collection and preprocessing includes:

[0013] Data collection: Data sources for collection include equipment maintenance records, safety standards and specifications, process and instrumentation diagrams, control command configurations, safety analysis reports, manufacturer specifications, safety ratings and standards. The above data sources are crucial for analyzing failure component data and influencing component data. The selected equipment must be accompanied by sufficient data to obtain the required statistical confidence, and the time scale must be greater than a complete equipment life cycle.

[0014] Data review and classification: Review historical failure data based on failure causes, failure modes, and detection methods to avoid invalid data that affects the overall results; classify the reviewed historical failure data into failure component data and impact component data, where failure component data includes failure causes, failure time, failure mode, and failure probability, and impact component data includes equipment attributes, environmental attributes, and maintenance activities; where the impact component data type mainly includes equipment attributes, operating environment, and maintenance activities, and equipment attributes are used to describe equipment information related to manufacturer data and design characteristics;

[0015] Data preprocessing: In order to ensure that there is no invalid impact on the overall results, data preprocessing is required to eliminate some invalid data; for example, repeated failures caused by specific problems can be removed. In addition, the classification type of the equipment needs to be determined in advance based on expert advice so that appropriate data grouping can be performed in the analysis. In some cases, there will be missing data, which can be filled by making reasonable assumptions. If no information is provided about the flow medium inside the valve, it can be assumed that valves installed in the same specific system share the same medium.

[0016] Furthermore, the data dimension reduction and failure probability modeling are carried out:

[0017] DU failure component data includes key factors affecting failure, such as failure causes and failure modes; influencing component data mainly involves equipment attributes, environmental factors, and maintenance activities; high-dimensional data is reduced in dimension through kernel principal component analysis (KPCA) to extract key features; then a low-dimensional principal component score matrix can be generated; this matrix not only reveals the correlation between DU failure component data and influencing component data, but also provides simplified and accurate input features for subsequent failure probability modeling based on generalized additive model (GAM);

[0018] Specifically, the influencing factors can be defined as a set of explanatory variables, expressed as X = [X1, X2, ... X n ] T Assuming that there are m equipment samples used to describe the various influencing factors and the DU failure status, and using '1' and '0' to represent the detection of DU failure, where the number '1' represents the detection of DU failure, and '0' represents the non-detection, the high-dimensional space matrix X is mapped to the low-dimensional principal component space to obtain the score matrix Z = [Z1, Z2…Z k ], the process is as follows: Use kernel principal component analysis (KPCA) to calculate the kernel matrix:

[0019]

[0020] Among them, the kernel matrix K(x i ,x j ) Calculate the sample x i and x j Similarity in high-dimensional space, δ is the kernel parameter, then the kernel matrix K is centered to remove the mean effect and obtain the centralized kernel matrix:

[0021]

[0022] Among them, 1 is a full The matrix is ​​used to realize data centering in the kernel space, and the centered kernel matrix Perform eigenvalue decomposition and obtain the eigenvalue λ i and the eigenvector υ i :

[0023]

[0024] Eigenvalue λ i Represents the weight of each principal component, the eigenvector υ i Then describes the direction of the principal component. In the high-dimensional kernel space, each sample is projected onto the kernel principal component to obtain the principal component score matrix Z:

[0025]

[0026] Here, Z i is the score of the i-th sample on the principal component, which is used for subsequent failure probability modeling.

[0027] Combined with the principal component score matrix Z obtained in the above steps, the generalized additive model GAM is used to build a failure probability prediction model;

[0028] Specifically, the response variable Y = [Y1, Y2, ... Y m ] T Represents the predicted target variable, which is the failure probability of DU in this case. GAM is used to model the effect of each principal component on the failure probability Y. The basic form of the GAM model is as follows:

[0029]

[0030] Among them, α is the intercept term, f j (Z j ) is the score Z for the jth principal component j The smoothing function of GAM is used to capture the relationship between the principal component and the failure probability. ε is the error term. The smoothing function f of GAM j (Z j ) can be further expressed as a spline basis expansion form:

[0031]

[0032] Among them, B m (Z j ) is the spline basis function, β j,m is the parameter to be estimated, the principal component Z j Contribution to the failure probability. Further, in order to optimize the GAM model and determine the best parameters for each smoothing function, the following loss function can be constructed and minimized:

[0033]

[0034] Among them, the first Represents the sum of squares of prediction errors, which is used to minimize the model prediction deviation. The second term is a smoothing regularization term, which is used to control the complexity of the smoothing function and prevent overfitting. λ is a regularization parameter, which controls the smoothness. By optimizing the loss function, the optimal smoothing parameter β can be found. j,m and regularization parameter λ, thus obtaining a more stable and accurate GAM model.

[0035] Furthermore, the failure probability prediction is:

[0036] The DU failure rate Y DU According to different failure modes, they are divided into i groups and the failure rate Y under different failure modes is calculated respectively. DU,i , which are grouped as follows:

[0037] Y DU =Y DU,1 +Y DU,2 …+Y DU,i

[0038] According to the kernel principal component analysis (KPCA) in step 2, the input high-dimensional data is reduced in dimension to obtain the score matrix Z of each sample in the kernel principal component space; based on the principal component scores, the generalized additive model (GAM) is used to model the failure probability of each failure mode. For each failure mode i, the GAM modeling formula is:

[0039]

[0040] Finally, the failure probabilities of all failure modes are combined to obtain the overall failure probability of the new device; as shown below:

[0041]

[0042] Another object of the present invention is to provide a failure probability prediction system for a safety instrument system of a petroleum refining device, comprising:

[0043] Data acquisition and preprocessing module, used to divide the boundaries of the safety instrument system, collect equipment information and historical failure data of the safety instrument system of the oil refining unit, determine the failure mode and cause, and perform classification and preprocessing;

[0044] The data dimension reduction and failure probability modeling module is used to reduce the dimension of high-dimensional data through KPCA and extract key features. KPCA maps complex data to a low-dimensional principal component space and generates a principal component score matrix to capture the nonlinear correlation between DU failure and influencing factors. On this basis, GAM is combined to describe the relationship between the principal component score and the DU failure probability, and a failure probability prediction model is established.

[0045] The failure probability prediction module is used to import the probability distribution, correlation and important influencing factors of DU failure nodes obtained by kernel principal component analysis after data dimension reduction and failure probability modeling, and then use GAM to model to predict the failure probability of newly connected equipment in the safety instrument system, verify and interpret the prediction results, evaluate the accuracy and reliability of the failure probability, and calculate the failure probability of SIS equipment in the newly connected facilities according to the failure rate prediction formula.

[0046] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the failure probability prediction method for the safety instrument system of a petroleum refining device.

[0047] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the failure probability prediction method for a safety instrument system of a petroleum refining device.

[0048] Another object of the present invention is to provide an information data processing terminal, which is used to implement the failure probability prediction system for the safety instrument system of the petroleum refining device.

[0049] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0050] First, the present invention provides a failure rate prediction method for the safety instrument system of a petroleum refining unit. In view of the shortcomings of the prior art in processing nonlinear data and high-dimensional variables, the method combines the nonlinear dimensionality reduction capability of KPCA and the flexible modeling and interpretation capability of GAM to achieve accurate prediction of the DU probability of SIS equipment. The method uses KPCA to extract the nonlinear principal components of failure data, which fundamentally solves the limitations of traditional PCA in processing high-dimensional and nonlinear data, and can more comprehensively capture the complex characteristics of DU failure modes. At the same time, the nonlinear relationship between the principal component score and the failure probability is modeled by GAM, and an explanatory analysis of the influence of the principal component is provided while performing failure prediction, providing a scientific basis for the identification of important influencing factors and the optimization of the prediction model. The results show that the method has significant accuracy and reliability in the prediction of failure probability, solves the problem of insufficient processing capability of traditional statistical models for nonlinear data, and shows strong adaptability in the failure prediction of newly connected equipment. The specific description is as follows:

[0051] The present invention adopts a data-driven method, that is, the kernel principal component analysis (KPCA) method and the generalized additive model (GAM) are used to complete the identification of important influencing factors and the prediction of SIS equipment failure probability. Among them, KPCA is a technology for simplifying data sets. It maps data to a high-dimensional space through a nonlinear kernel function, captures the nonlinear structure of the data in this space, and thus performs dimensionality reduction processing, while retaining the features that contribute the most to the variance and capturing important influencing factors. GAM aims to establish a nonlinear model to capture the nonlinear relationship between the principal component score and the target variable through a smoothing function. Compared with the traditional multiple regression method, GAM can adaptively adjust the influence of each principal component without explicit linear assumptions, thereby accurately predicting the relationship between the independent variable and the dependent variable. GAM uses the principal component scores obtained by KPCA for modeling, finds the maximum influence of the principal component on the failure probability, and finally transforms the original high-dimensional data set into a feature space that can capture the main nonlinear relationship. The present invention combines a data-driven model based on empirical data with a traditional statistical model, which can effectively identify the factors that have the greatest impact on the failure probability of SIS, predict the failure probability of newly connected SIS equipment, and preventively reinforce the potential failure behavior of old equipment, thereby ensuring the safety of the petroleum refining production process.

[0052] Second, the expected benefits and commercial value after the transformation of the technical solution of the present invention are as follows: The failure probability prediction method based on KPCA+GAM proposed in the present invention significantly improves the equipment safety and operating efficiency in industrial scenarios such as petroleum refining units by accurately predicting the DU failure probability of SIS equipment. This improvement directly reduces the equipment maintenance costs, unplanned downtime costs, and economic losses caused by safety accidents, and improves overall operational efficiency. In addition, the core algorithm of this technology is universal and can be extended to fields such as electricity, aviation, and medical care to achieve accurate prediction of failures of other equipment in complex systems, and has broad commercialization potential. In particular, with the increasing attention paid to the safety of high-reliability industrial equipment in China, this method has significant market promotion prospects and economic value.

[0053] The technical solution of the present invention fills the technical gap in the industry at home and abroad: traditional failure probability prediction methods are mostly based on linear statistical models (such as PLSR), which have obvious limitations when processing high-dimensional and nonlinear data, especially for the prediction of DU modes in complex industrial systems. There is a lack of reliable and accurate solutions. The present invention combines the nonlinear dimensionality reduction capability of KPCA and the flexible modeling capability of GAM to propose a new failure probability prediction framework, which fundamentally solves the problem that traditional methods are difficult to capture complex nonlinear modes, and fills the technical gap in the accurate prediction of nonlinear DU failure modes in complex industrial scenarios. It has important scientific value and practical significance.

[0054] Third, in the safety instrument system (SIS) of petroleum refining units, the complexity of the equipment and the diversity of operating conditions make failure prediction face huge challenges. Traditional failure prediction methods mainly rely on simple statistical models or expert experience, which cannot fully capture the nonlinear relationship between equipment failure modes and multidimensional influencing factors. In addition, the existing methods have limited processing capabilities for high-dimensional data and it is difficult to extract key features, resulting in insufficient prediction accuracy and difficulty in meeting the needs of real-time warning and accurate prediction of equipment failure in actual industrial scenarios. This deficiency directly affects the safety and reliability of refining units and increases maintenance costs and safety risks.

[0055] In view of the deficiencies in the prior art, the present invention proposes a failure probability prediction method based on kernel principal component analysis (KPCA) and generalized additive model (GAM). KPCA is used to reduce the dimensionality of high-dimensional data, extract key features related to failure modes, and use the GAM model to describe the nonlinear relationship between principal component scores and failure probabilities, effectively solving the problem that traditional methods cannot handle complex nonlinear associations. At the same time, the present invention can dynamically analyze failure modes and predict the failure probability of newly connected equipment in real time, providing a reliable basis for equipment operation status monitoring and maintenance strategy optimization.

[0056] The present invention has achieved a number of technological advances in industrial applications: (1) Through data dimension reduction and nonlinear modeling, the accuracy and robustness of failure prediction have been significantly improved; (2) A dynamic prediction method for failure probability that can adapt to different equipment characteristics has been established to meet the diverse industrial scenario requirements of petroleum refining equipment; (3) The introduction of intelligent modeling technology has achieved automatic processing of high-dimensional complex data and extraction of key features, reducing dependence on expert experience and improving prediction efficiency and real-time performance. These technological advances have significantly improved the early warning capability of the SIS system and reduced the safety risks caused by equipment failure.

[0057] The present invention provides an efficient and reliable failure prediction tool for the safety management of petroleum refining equipment. Its advanced modeling method and data processing capabilities not only optimize the equipment operation and maintenance process, but also reduce the risk of downtime caused by equipment failure, and improve the overall safety and economic benefits of the system. At the same time, the present invention provides a general technical framework for the intelligent monitoring of industrial equipment, which can be widely used in the field of safety management of other complex industrial systems. It has important industrial value and promotion prospects, and provides important support for the digital transformation and intelligent upgrading of the petrochemical industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 The present invention provides a flowchart of a failure probability prediction method for a safety instrument system of a petroleum refining device.

[0059] Figure 2 The present invention provides a block diagram of a failure probability prediction system for a safety instrument system of a petroleum refining device.

[0060] Figure 3 The present invention provides a method for predicting the failure probability of a safety instrument system for a petroleum refining device and an overall flow chart of the system;

[0061] Figure 4 It is a schematic diagram of data collection and preprocessing provided by an embodiment of the present invention;

[0062] Figure 5 It is a schematic diagram of data dimensionality reduction and failure probability modeling provided by an embodiment of the present invention;

[0063] Figure 6 is a schematic diagram of failure probability prediction provided by an embodiment of the present invention;

[0064] Figure 7 It is a brief schematic diagram of the process of evaluating the explanatory power of the model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0066] like Figure 1 As shown, a failure probability prediction method for a safety instrument system of a petroleum refining device provided by an embodiment of the present invention comprises the following steps:

[0067] S101, data collection and preprocessing, dividing the boundaries of the safety instrument system, collecting equipment information and historical failure data of the safety instrument system of the oil refining unit to determine the failure mode and cause, and classify and preprocess;

[0068] S102, data dimensionality reduction and failure probability modeling, KPCA is used to reduce the dimensionality of high-dimensional data and extract key features; KPCA maps complex data to a low-dimensional principal component space and generates a principal component score matrix to capture the nonlinear correlation between DU failure and influencing factors; on this basis, GAM is combined to describe the relationship between the principal component score and the DU failure probability, and a failure probability prediction model is established;

[0069] S103, failure probability prediction, after data dimension reduction and failure probability modeling, the probability distribution, correlation and important influencing factors of DU failure nodes obtained by kernel principal component analysis are imported, and then GAM is used for modeling to predict the failure probability of newly connected equipment in the safety instrument system, and the prediction results are verified and interpreted, the accuracy and reliability of the failure probability are evaluated, and the failure probability of SIS equipment in the newly connected facilities is calculated according to the failure rate prediction formula.

[0070] This method first divides the boundaries of the safety instrument system (SIS) of the petroleum refining unit and clarifies the equipment and subsystems included in the system. By collecting the operating information, historical failure records and equipment attribute data of the relevant equipment, common failure modes and their causes are identified. The collected raw data is classified and sorted, missing values ​​are filled, outliers are eliminated, and multi-source data is uniformly formatted. The goal of data preprocessing is to generate high-quality, standardized input data to lay the foundation for subsequent dimensionality reduction and modeling.

[0071] Since the failure data of SIS equipment usually has complex characteristics such as high dimension, multivariate, and nonlinearity, it is difficult to extract key features through direct modeling. This method uses kernel principal component analysis (KPCA) to reduce the dimension of high-dimensional data and map the complex nonlinear relationship into a low-dimensional principal component space. The principal component score matrix generated by KPCA can effectively capture the nonlinear correlation between failure modes and influencing factors. On this basis, the generalized additive model (GAM) is used to model the relationship between the principal component score and the DU failure probability, and a failure probability prediction model is constructed. GAM approximates complex relationships through flexible nonlinear functions, so that the model can accurately describe the dynamic relationship between failure probability and influencing factors.

[0072] After completing data dimension reduction and modeling, the principal component score matrix generated by KPCA, the probability distribution of DU failure nodes, and correlation information are imported, and the failure probability of newly connected devices is predicted using the GAM model. During the prediction process, the model calculates the DU failure probability of the device based on the historical data and current operating status of the device and generates a prediction result. At the same time, the results of the model output are verified and interpreted, and the accuracy and reliability of the prediction are evaluated by comparing with known failure data, and the mechanism of action of the main influencing factors is analyzed.

[0073] According to the predicted failure probability and the failure rate prediction formula, the specific failure probability values ​​of key SIS devices in the newly connected equipment are calculated. The prediction results can be used to identify equipment with high failure risks in advance, support the optimization of preventive maintenance strategies for SIS systems, and improve the overall operational safety and reliability of the system. Through feedback and iteration of the prediction process, the parameter settings of KPCA and GAM are further optimized to enhance the generalization ability of the model, so that it can adapt to more diverse industrial scenario requirements and provide reliable technical guarantees for the safe operation of petroleum refining units.

[0074] The data collection and preprocessing provided by the embodiment of the present invention include:

[0075] Data collection: Data sources for collection include equipment maintenance records, safety standards and specifications, process and instrumentation diagrams, control command configurations, safety analysis reports, manufacturer specifications, safety ratings and standards. The above data sources are crucial for analyzing failure component data and influencing component data. The selected equipment must be accompanied by sufficient data to obtain the required statistical confidence, and the time scale must be greater than a complete equipment life cycle.

[0076] Data review and classification: Review historical failure data based on failure causes, failure modes, and detection methods to avoid invalid data that affects the overall results; classify the reviewed historical failure data into failure component data and impact component data, where failure component data includes failure causes, failure time, failure mode, and failure probability, and impact component data includes equipment attributes, environmental attributes, and maintenance activities; where the impact component data type mainly includes equipment attributes, operating environment, and maintenance activities, and equipment attributes are used to describe equipment information related to manufacturer data and design characteristics;

[0077] Data preprocessing: In order to ensure that there is no invalid impact on the overall results, data preprocessing is required to eliminate some invalid data; for example, repeated failures caused by specific problems can be removed. In addition, the classification type of the equipment needs to be determined in advance based on expert advice so that appropriate data grouping can be performed in the analysis. In some cases, there will be missing data, which can be filled by making reasonable assumptions. If no information is provided about the flow medium inside the valve, it can be assumed that valves installed in the same specific system share the same medium.

[0078] Data dimensionality reduction and failure probability modeling provided by the embodiment of the present invention:

[0079] DU failure component data includes key factors affecting failure, such as failure causes and failure modes; influencing component data mainly involves equipment attributes, environmental factors, and maintenance activities; high-dimensional data is reduced in dimension through kernel principal component analysis (KPCA) to extract key features; then a low-dimensional principal component score matrix can be generated; this matrix not only reveals the correlation between DU failure component data and influencing component data, but also provides simplified and accurate input features for subsequent failure probability modeling based on generalized additive model (GAM);

[0080] Specifically, the influencing factors can be defined as a set of explanatory variables, expressed as X = [X1, X2, ... X n ] T Assuming that there are m equipment samples used to describe the various influencing factors and the DU failure status, and using '1' and '0' to represent the detection of DU failure, where the number '1' represents the detection of DU failure, and '0' represents the non-detection, the high-dimensional space matrix X is mapped to the low-dimensional principal component space to obtain the score matrix Z = [Z1, Z2…Z k ], the process is as follows: Use kernel principal component analysis (KPCA) to calculate the kernel matrix:

[0081]

[0082] Among them, the kernel matrix K(x i ,x j ) Calculate the sample x i and x j Similarity in high-dimensional space, δ is the kernel parameter, then the kernel matrix K is centered to remove the mean effect and obtain the centralized kernel matrix:

[0083]

[0084] Among them, 1 is a full The matrix is ​​used to realize data centering in the kernel space, and the centered kernel matrix Perform eigenvalue decomposition and obtain the eigenvalue λ i and the eigenvector υ i :

[0085]

[0086] Eigenvalue λ i Represents the weight of each principal component, the eigenvector υ i Then describes the direction of the principal component. In the high-dimensional kernel space, each sample is projected onto the kernel principal component to obtain the principal component score matrix Z:

[0087]

[0088] Here, Zi is the score of the i-th sample on the principal component, which is used for subsequent failure probability modeling.

[0089] Combined with the principal component score matrix Z obtained in the above steps, the generalized additive model GAM is used to build a failure probability prediction model;

[0090] Specifically, the response variable Y = [Y1, Y2, ... Y m ] T Represents the predicted target variable, which is the failure probability of DU in this case. GAM is used to model the effect of each principal component on the failure probability Y. The basic form of the GAM model is as follows:

[0091]

[0092] Among them, α is the intercept term, f j (Z j ) is the score Z for the jth principal component j The smoothing function of GAM is used to capture the relationship between the principal component and the failure probability. ε is the error term. The smoothing function f of GAM j (Z j ) can be further expressed as a spline basis expansion form:

[0093]

[0094] Among them, B m (Z j ) is the spline basis function, β j,m is the parameter to be estimated, the principal component Z j Contribution to the failure probability. Further, in order to optimize the GAM model and determine the best parameters for each smoothing function, the following loss function can be constructed and minimized:

[0095]

[0096] Among them, the first Represents the sum of squares of prediction errors, which is used to minimize the model prediction deviation. The second term is a smoothing regularization term, which is used to control the complexity of the smoothing function and prevent overfitting. λ is a regularization parameter, which controls the smoothness. By optimizing the loss function, the optimal smoothing parameter β can be found. j,m and regularization parameter λ, thus obtaining a more stable and accurate GAM model.

[0097] Failure probability prediction provided by the embodiment of the present invention:

[0098] The DU failure rate Y DU According to different failure modes, they are divided into i groups and the failure rate Y under different failure modes is calculated respectively. DU,i, which are grouped as follows:

[0099] Y DU =Y DU,1 +Y DU,2 …+Y DU,i

[0100] According to the kernel principal component analysis (KPCA) in step 2, the input high-dimensional data is reduced in dimension to obtain the score matrix Z of each sample in the kernel principal component space; based on the principal component scores, the generalized additive model (GAM) is used to model the failure probability of each failure mode. For each failure mode i, the GAM modeling formula is:

[0101]

[0102] Finally, the failure probabilities of all failure modes are combined to obtain the overall failure probability of the new device; as shown below:

[0103]

[0104] like Figure 2 As shown, a failure probability prediction system for a safety instrument system of a petroleum refining device provided by an embodiment of the present invention includes:

[0105] Data acquisition and preprocessing module, used to divide the boundaries of the safety instrument system, collect equipment information and historical failure data of the safety instrument system of the oil refining unit, determine the failure mode and cause, and perform classification and preprocessing;

[0106] The data dimension reduction and failure probability modeling module is used to reduce the dimension of high-dimensional data through KPCA and extract key features. KPCA maps complex data to a low-dimensional principal component space and generates a principal component score matrix to capture the nonlinear correlation between DU failure and influencing factors. On this basis, GAM is combined to describe the relationship between the principal component score and the DU failure probability, and a failure probability prediction model is established.

[0107] The failure probability prediction module is used to import the probability distribution, correlation and important influencing factors of DU failure nodes obtained by kernel principal component analysis after data dimension reduction and failure probability modeling, and then use GAM to model to predict the failure probability of newly connected equipment in the safety instrument system, verify and interpret the prediction results, evaluate the accuracy and reliability of the failure probability, and calculate the failure probability of SIS equipment in the newly connected facilities according to the failure rate prediction formula.

[0108] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the failure probability prediction method for the safety instrument system of a petroleum refining device.

[0109] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the failure probability prediction method for a safety instrument system of a petroleum refining device.

[0110] Another object of the present invention is to provide an information data processing terminal, which is used to implement the failure probability prediction system for the safety instrument system of the petroleum refining device.

[0111] The present invention is specifically implemented:

[0112] The data-driven models KPCA and GAM mentioned in the present invention can reduce the dimension of the collected multi-dimensional data information and analyze the correlation between each piece of information, which can more accurately predict the failure rate of the SIS equipment of the new facility, so that developers can build a system that meets the safety integrity level requirements when there is a need. In addition, since the present invention is a general model, it can not only be used for the failure rate prediction of the oil refining safety instrument system, but also for the failure rate prediction of other equipment.

[0113] The technical scheme and effects of the present invention will be described in detail below, in conjunction with the accompanying drawings, taking the shut-off valve in the safety instrument system (SIS) as a specific example. Among them, the SIS control strategy is "three-choose-one", that is, three SIS loops jointly control one shut-off valve, and when the sensor acquisition data of any of the SIS loops exceeds the safety threshold, the shut-off valve will act immediately. It should be noted that in order to prevent SIS from malfunctioning, some manufacturers adopt a "three-choose-two" strategy when configuring the system configuration, that is, the actuator will only act when the sensor acquisition data of at least two SIS loops exceeds the safety threshold. Although the failure probability of SIS equipment obtained under different control strategies is different, it can be processed by data normalization, so it does not affect the feasibility of the method proposed in this patent for predicting the failure probability of SIS. Figure 3 The overall failure rate prediction process is shown, and its contents are as follows:

[0114] Step 1: Collect and process data of existing comparable equipment for the specific equipment to be predicted. Figure 4 A schematic diagram of the data processing system is shown, which includes:

[0115] Obtain historical failure data of SIS equipment from fault notifications and maintenance records, including failure component data and influencing component data. Failure component data includes failure cause, failure time, failure mode and failure probability, which are derived from safety standards, control instructions and configurations, safety manuals and safety analysis reports, and manufacturer specifications; influencing component data includes equipment attributes, environmental attributes and maintenance activities, which are derived from maintenance notifications, process and instrumentation diagrams, safety ratings and related standards. In addition, when collecting historical failure data, it is necessary to discuss with technical consultants and process engineers to obtain a more comprehensive understanding and record them. The collected data needs to be preprocessed, including data cleaning, missing data filling, and normalization of failure probabilities under different control strategies. First, data cleaning is performed to remove duplicate, invalid or inconsistent data and unify the data format. Then, missing data is filled by expert experience method, interpolation method and other methods. Next, failure probability normalization is performed according to different control strategies and working conditions. For example, the failure probability of a certain SIS device under high load is 0.08 and under low load is 0.03. In order to make a unified comparison, it can be normalized to a standard working condition (such as average load) to obtain a new failure probability for subsequent analysis. Commonly used normalization methods include maximum-minimum normalization or Z-score normalization. Finally, the collected SIS device failure history data is sorted and recorded to ensure that the failure mode, failure cause, failure probability and its influencing components of each device are archived in detail. Taking the shut-off valve as an example: the DU failure mode of the shut-off valve mainly includes three types: fail to close (FTC), leakage in closed position (LCP) and delayed operation (LCP). After the data of these three types of failure modes are recorded in detail, they will be helpful for subsequent safety assessment, maintenance optimization and system upgrade decisions. The failure record examples are shown in Table 1:

[0116] Table 1 Example of failure component data

[0117]

[0118]

[0119] (2) In order to avoid invalid effects on the overall results, repeated failure data caused by some specific problems should be deleted when preprocessing the data; in addition, the equipment classification type needs to be determined in advance according to expert advice to ensure the accuracy and reliability of subsequent analysis; examples of equipment attributes, environmental attributes and maintenance activities of shut-off valves are shown in Table 2, Table 3, and Table 4. Since equipment attributes have been shown to be very important in explaining the differences in the empirical reliability performance of SIS equipment, the main focus is on equipment attributes when collecting data;

[0120] Table 2 Example of equipment properties of shut-off valves

[0121]

[0122]

[0123] Table 3 Examples of environmental properties of shut-off valves

[0124]

[0125] Table 4 Examples of maintenance activities for shut-off valves

[0126]

[0127] Step 2: Use the data-driven module to reduce the data dimension and build the failure probability model. Figure 5 The derivation process of data dimension reduction and failure probability modeling is demonstrated, including:

[0128] In the analysis, each of the above influencing factors is defined as an explanatory variable, and its symbol is represented by X = [X1, X2, ... X n ] T , where X is a column vector containing the values ​​of various influencing factors; the shut-off valve is regarded as a device sample, which is used to describe the situation in which various influencing factors are related to the DU failure state. In this scenario, '1' represents the detection of DU failure and '0' represents the non-detection of DU failure. These data are distributed in the variable space and are used to build a model to explore the relationship between the influencing factors and the DU failure state.

[0129] KPCA is used to determine the overall correlation between DU failure and different influencing factors; here, the Gaussian kernel function is used to calculate the kernel matrix K, and the kernel matrix is ​​obtained as follows:

[0130]

[0131] Among them, δ is the kernel parameter (), and then the kernel matrix K is centered to obtain the centered kernel matrix:

[0132]

[0133] Then, the centered kernel matrix Perform eigenvalue decomposition and obtain the eigenvalue λ i and the eigenvector υ i , through the projection operation, we can get the principal component score matrix Z:

[0134]

[0135] Eigenvalue λ i The size reflects the amount of information contained in the principal component, that is, it is related to the score of each influencing factor. The larger the eigenvalue, the higher the score and the more information it carries, that is, the greater the impact. By selecting the principal component with a larger eigenvalue, the data dimension can be reduced and the most influential information for failure probability modeling can be retained.

[0136] GAM modeling is used to further analyze the nonlinear relationship between the principal component Z and the DU failure probability Y. The basic form of the GAM model is:

[0137]

[0138] f j (Z j ) is a smooth function for the jth principal component, by fitting f j (Z j ) can explain the nonlinear contribution of principal components to failure probability and identify important influencing factors;

[0139] Finally, various evaluation indicators can be used to evaluate the performance and goodness of fit of the GAM model, such as root mean square error (RMSE) and coefficient of determination (R 2 ), where the root mean square error (RMSE) is used to measure the deviation between the predicted value and the actual value, and its formula is as follows:

[0140]

[0141] Where n is the number of samples, y i is the actual value, is the predicted value. If the calculated RMSE is smaller, the prediction error of the model is smaller and the prediction accuracy of the model is higher. When RMSE is 0, it means that the model prediction is completely consistent with the actual value.

[0142] Coefficient of determination (R 2 ) is used to evaluate the explanatory power of the model, that is, the degree of fit of the model to the data. The formula is as follows:

[0143]

[0144] in, is the residual sum of squares of the model (SS_res), is the total sum of squares (SS_tot), is the mean of the actual values, R 2 The value range of R is [0,1]. The closer to 1, the better the model fit is, and the closer to 0, the worse the model fit is. 2 =1 means that the model can perfectly explain the variation of the data, while R 2 = 0 means that the model cannot explain any data changes. Since this step is mainly to evaluate whether the established model meets the requirements, after considering the advantages and disadvantages of both, R is used in the present example. 2 To evaluate the accuracy and explanatory power of model prediction, the brief flowchart is as follows Figure 7 shown.

[0145] Step 3: Combine the results obtained from the data-driven module and the safety integrity level (SIL) requirements to predict the case failure rate. The steps are as follows: Figure 6 As shown, its contents include:

[0146] DU failures are subdivided into the three failure modes discussed: DOP, FTC, and LCP. For the data of each failure mode, KPCA and GAM are used to calculate the failure rate of each mode. Make predictions:

[0147]

[0148] Table 5 below lists examples of DU failures and corresponding failure rates for each failure mode of the shut-off valve, where OTH represents other or unknown failure mode;

[0149] Table 5 Failure distribution and corresponding failure rate examples

[0150]

[0151] As described in the above steps, when collecting data, the main focus is on equipment attributes; the principal component score matrix extracted by KPCA and the modeling results of GAM can be used to evaluate the contribution of different principal components to the failure rate. The GAM model directly generates the predicted value of each failure mode by capturing the nonlinear relationship between the principal component and the failure probability. The formula is as follows:

[0152]

[0153] The above formula takes into account the operation conditions under different DU failure modes, that is, extracting data from different DU failure modes to predict the failure rates of different failure modes and then integrating them, which helps to accurately identify the characteristics of each mode, avoid data mixing, and improve prediction accuracy; at the same time, it reduces the complexity of the model and the risk of data overfitting; in addition, this method enhances the adaptability and flexibility of the model, and can select appropriate variables and modeling strategies for different modes, which is convenient for decomposing the total failure rate and clarifying the contribution of each mode, providing a clearer basis for failure management and optimization decisions, thereby formulating more focused and effective improvement measures to meet the needs of complex industrial scenarios.

[0154] Embodiment 1:

[0155] Failure prediction of safety instrument systems in petrochemical plants

[0156] In a large petrochemical plant, the safety instrument system (SIS) is used to control and monitor the operating status of key equipment to ensure safe and stable production. Because the equipment is in a harsh environment of high temperature and high pressure for a long time, some equipment has frequent failure problems, which can lead to major safety accidents. In order to reduce the occurrence of these failure events, the plant adopts the above failure probability prediction method.

[0157] Step 1: Data collection and preprocessing

[0158] The factory collected a large amount of data including equipment maintenance records, historical failure data, and safety standards and specifications, and preprocessed these data to eliminate invalid and redundant data to ensure the integrity and accuracy of the model input data.

[0159] Step 2: Data dimensionality reduction and failure probability model building

[0160] The pre-processed high-dimensional data is reduced in dimension by kernel principal component analysis (KPCA) to extract key features that affect the failure probability (such as principal component scores). Subsequently, a generalized additive model (GAM) is used to build a failure probability prediction model to capture the nonlinear relationship in the data, describe the association between the principal component characteristics and the failure probability, and provide a basis for quantitative modeling of equipment failure risk.

[0161] Step 3: Failure probability prediction

[0162] Based on the modeling results, the factory predicted the failure probability of newly connected key equipment (such as emergency shut-off valves and pressure controllers) under different operating conditions. By continuously verifying and adjusting the model, the failure risk of these devices under different operating conditions was predicted, and preventive maintenance was carried out accordingly, greatly reducing the occurrence rate of equipment failures.

[0163] Embodiment 2:

[0164] Failure Probability Prediction in Natural Gas Pipeline Safety Monitoring System

[0165] In a natural gas transmission pipeline system, the safety instrument system is used to monitor the pressure, flow and temperature of the pipeline in real time to ensure the safety of natural gas transmission. In order to prevent major safety accidents caused by pipeline failures (such as ruptures, leaks, etc.), the gas transmission company deployed this failure probability prediction method to improve the reliability of the equipment.

[0166] Step 1: Data collection and preprocessing

[0167] The pipeline company collected historical operating data and sensor data from gas transmission equipment, including pressure change records, temperature sensor data, flow data, maintenance records, and fault history, and classified and preprocessed these data to remove noise data and duplicate records.

[0168] Step 2: Data dimensionality reduction and failure probability model building

[0169] KPCA is used to reduce the dimension of the pre-processed high-dimensional data and extract the main features that affect pipeline failure (such as the service life of the pipeline, the corrosiveness of the transported medium, the pressure fluctuation amplitude, etc.). Subsequently, GAM is used to establish a failure probability prediction model to capture the nonlinear relationship between characteristic data and failure probability, providing a key basis for the accurate prediction of pipeline failure.

[0170] Step 3: Failure probability prediction

[0171] Based on the established prediction model, the gas transmission company accurately predicted the probability of pipeline failure under different pressure fluctuations and temperature conditions. Under different pressure fluctuations and temperature conditions, the model accurately predicted the failure risk of the pipeline. By optimizing the pipeline maintenance plan and repairing high-risk pipeline sections in advance, the risk of pipeline leakage and rupture accidents was greatly reduced.

[0172] These two embodiments demonstrate how to use the failure probability prediction method in the fields of petrochemicals and natural gas pipelines to prevent safety accidents and improve system reliability and safety.

[0173] 2. Relevant evidence of the technical effects obtained by the embodiments of the present invention.

[0174] KPCA's dimensionality reduction effect: KPCA can extract the main features from high-dimensional nonlinear data, reduce the dimensionality of complex input data to a low-dimensional principal component score matrix, and eliminate redundant data while retaining key information. This dimensionality reduction effect improves the computational efficiency of subsequent modeling and reduces the risk of overfitting.

[0175] GAM's nonlinear modeling capability: GAM can use smooth functions to capture the nonlinear relationship between principal components and failure probability, avoiding errors caused by linear assumptions.

[0176] Effect of mode-based prediction: DU failure is subdivided into multiple failure modes and modeled separately to avoid the impact of data congestion on prediction accuracy and reduce modeling complexity.

[0177] Nonlinear feature extraction: KPCA’s nonlinear dimensionality reduction capability can capture DU failure characteristics more accurately.

[0178] Flexibility and adaptability: The modeling flexibility of GAM significantly improves the accuracy of failure probability prediction.

[0179] Highly targeted: Sub-mode modeling provides a clearer basis for failure management and optimization.

[0180] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0181] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A failure probability prediction method for a safety instrument system of a petroleum refining device, characterized in that: The method comprises the following steps: Step 1, data collection and preprocessing: divide the safety instrument system boundary, collect equipment information and historical failure data, determine the failure mode and cause, classify and preprocess the data; Step 2: Data dimensionality reduction and failure probability modeling: KPCA is used to reduce the dimensionality of high-dimensional data, extract key features, and generate a principal component score matrix. On this basis, GAM is used to describe the relationship between the principal component score and the DU failure probability, and a failure probability prediction model is established. Step 3, failure probability prediction: Based on the KPCA and GAM analysis results, predict the failure probability of the newly connected equipment, and calculate the failure probability according to the failure rate prediction formula.

2. The failure probability prediction method for a safety instrument system of a petroleum refining device according to claim 1 is characterized in that: The data collection and preprocessing include data from equipment maintenance records, safety standards and specifications, process and instrumentation diagrams, control instruction configurations, safety analysis reports and manufacturer specifications, etc., and the time scale is greater than a complete equipment life cycle.

3. The failure probability prediction method for a safety instrument system of a petroleum refining device according to claim 1 is characterized in that: The data dimensionality reduction and failure probability modeling identify the nonlinear correlation of failure component data through KPCA, and calculate the principal component score matrix through the kernel matrix, so as to screen out low-dimensional features that have a significant impact on the equipment.

4. The failure probability prediction method for a safety instrument system of a petroleum refining device according to claim 1 is characterized in that: GAM analyzes the nonlinear relationship between the failure probability of safety instrumented system equipment and the principal component characteristics, and captures the quantitative contribution of each principal component to the failure probability through a smoothing function.

5. The failure probability prediction method for a safety instrument system of a petroleum refining device according to claim 1 is characterized in that: Based on the prediction results of different failure modes, the failure probability of each mode is integrated to calculate the overall failure probability of the equipment, and the accuracy and reliability of the prediction are improved through verification and adjustment.

6. A failure probability prediction system for a safety instrument system of a petroleum refining device implementing the failure probability prediction method for a safety instrument system of a petroleum refining device as claimed in any one of claims 1 to 5, characterized in that: The failure probability prediction system for the safety instrument system of the petroleum refining device includes: Data acquisition and preprocessing module, used to divide the boundaries of the safety instrument system, collect equipment information and historical failure data of the safety instrument system of the oil refining unit, determine the failure mode and cause, and perform classification and preprocessing; The data dimension reduction and failure probability modeling module reduces the dimension of high-dimensional data through KPCA and extracts key features. KPCA maps complex data to a low-dimensional principal component space and generates a principal component score matrix to capture the nonlinear correlation between DU failure and influencing factors. On this basis, GAM is combined to describe the relationship between the principal component score and the DU failure probability, and a failure probability prediction model is established. The failure probability prediction module is used to import the probability distribution, correlation and important influencing factors of DU failure nodes obtained by kernel principal component analysis after data dimension reduction and failure probability modeling, and then use GAM to model to predict the failure probability of newly connected equipment in the safety instrument system, verify and interpret the prediction results, evaluate the accuracy and reliability of the failure probability, and calculate the failure probability of SIS equipment in the newly connected facilities according to the failure rate prediction formula.

7. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the failure probability prediction method for a safety instrument system of a petroleum refining device as claimed in any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the failure probability prediction method for a safety instrument system of a petroleum refining device as claimed in any one of claims 1 to 4.

9. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the failure probability prediction system for the safety instrument system of the petroleum refining device as described in claim 5.

Images